Commit 17d9f311eca13a42bf950198a358be1420d19c5f
Committed by
David S. Miller
1 parent
90d3ac15e5
Exists in
master
and in
4 other branches
SCHED_TTWU_QUEUE is not longer needed since sparc32 now implements IPI
Signed-off-by: Daniel Hellstrom <daniel@gaisler.com> Reported-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Showing 2 changed files with 1 additions and 6 deletions Inline Diff
init/Kconfig
1 | config ARCH | 1 | config ARCH |
2 | string | 2 | string |
3 | option env="ARCH" | 3 | option env="ARCH" |
4 | 4 | ||
5 | config KERNELVERSION | 5 | config KERNELVERSION |
6 | string | 6 | string |
7 | option env="KERNELVERSION" | 7 | option env="KERNELVERSION" |
8 | 8 | ||
9 | config DEFCONFIG_LIST | 9 | config DEFCONFIG_LIST |
10 | string | 10 | string |
11 | depends on !UML | 11 | depends on !UML |
12 | option defconfig_list | 12 | option defconfig_list |
13 | default "/lib/modules/$UNAME_RELEASE/.config" | 13 | default "/lib/modules/$UNAME_RELEASE/.config" |
14 | default "/etc/kernel-config" | 14 | default "/etc/kernel-config" |
15 | default "/boot/config-$UNAME_RELEASE" | 15 | default "/boot/config-$UNAME_RELEASE" |
16 | default "$ARCH_DEFCONFIG" | 16 | default "$ARCH_DEFCONFIG" |
17 | default "arch/$ARCH/defconfig" | 17 | default "arch/$ARCH/defconfig" |
18 | 18 | ||
19 | config CONSTRUCTORS | 19 | config CONSTRUCTORS |
20 | bool | 20 | bool |
21 | depends on !UML | 21 | depends on !UML |
22 | default y | 22 | default y |
23 | 23 | ||
24 | config HAVE_IRQ_WORK | 24 | config HAVE_IRQ_WORK |
25 | bool | 25 | bool |
26 | 26 | ||
27 | config IRQ_WORK | 27 | config IRQ_WORK |
28 | bool | 28 | bool |
29 | depends on HAVE_IRQ_WORK | 29 | depends on HAVE_IRQ_WORK |
30 | 30 | ||
31 | menu "General setup" | 31 | menu "General setup" |
32 | 32 | ||
33 | config EXPERIMENTAL | 33 | config EXPERIMENTAL |
34 | bool "Prompt for development and/or incomplete code/drivers" | 34 | bool "Prompt for development and/or incomplete code/drivers" |
35 | ---help--- | 35 | ---help--- |
36 | Some of the various things that Linux supports (such as network | 36 | Some of the various things that Linux supports (such as network |
37 | drivers, file systems, network protocols, etc.) can be in a state | 37 | drivers, file systems, network protocols, etc.) can be in a state |
38 | of development where the functionality, stability, or the level of | 38 | of development where the functionality, stability, or the level of |
39 | testing is not yet high enough for general use. This is usually | 39 | testing is not yet high enough for general use. This is usually |
40 | known as the "alpha-test" phase among developers. If a feature is | 40 | known as the "alpha-test" phase among developers. If a feature is |
41 | currently in alpha-test, then the developers usually discourage | 41 | currently in alpha-test, then the developers usually discourage |
42 | uninformed widespread use of this feature by the general public to | 42 | uninformed widespread use of this feature by the general public to |
43 | avoid "Why doesn't this work?" type mail messages. However, active | 43 | avoid "Why doesn't this work?" type mail messages. However, active |
44 | testing and use of these systems is welcomed. Just be aware that it | 44 | testing and use of these systems is welcomed. Just be aware that it |
45 | may not meet the normal level of reliability or it may fail to work | 45 | may not meet the normal level of reliability or it may fail to work |
46 | in some special cases. Detailed bug reports from people familiar | 46 | in some special cases. Detailed bug reports from people familiar |
47 | with the kernel internals are usually welcomed by the developers | 47 | with the kernel internals are usually welcomed by the developers |
48 | (before submitting bug reports, please read the documents | 48 | (before submitting bug reports, please read the documents |
49 | <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>, | 49 | <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>, |
50 | <file:Documentation/BUG-HUNTING>, and | 50 | <file:Documentation/BUG-HUNTING>, and |
51 | <file:Documentation/oops-tracing.txt> in the kernel source). | 51 | <file:Documentation/oops-tracing.txt> in the kernel source). |
52 | 52 | ||
53 | This option will also make obsoleted drivers available. These are | 53 | This option will also make obsoleted drivers available. These are |
54 | drivers that have been replaced by something else, and/or are | 54 | drivers that have been replaced by something else, and/or are |
55 | scheduled to be removed in a future kernel release. | 55 | scheduled to be removed in a future kernel release. |
56 | 56 | ||
57 | Unless you intend to help test and develop a feature or driver that | 57 | Unless you intend to help test and develop a feature or driver that |
58 | falls into this category, or you have a situation that requires | 58 | falls into this category, or you have a situation that requires |
59 | using these features, you should probably say N here, which will | 59 | using these features, you should probably say N here, which will |
60 | cause the configurator to present you with fewer choices. If | 60 | cause the configurator to present you with fewer choices. If |
61 | you say Y here, you will be offered the choice of using features or | 61 | you say Y here, you will be offered the choice of using features or |
62 | drivers that are currently considered to be in the alpha-test phase. | 62 | drivers that are currently considered to be in the alpha-test phase. |
63 | 63 | ||
64 | config BROKEN | 64 | config BROKEN |
65 | bool | 65 | bool |
66 | 66 | ||
67 | config BROKEN_ON_SMP | 67 | config BROKEN_ON_SMP |
68 | bool | 68 | bool |
69 | depends on BROKEN || !SMP | 69 | depends on BROKEN || !SMP |
70 | default y | 70 | default y |
71 | 71 | ||
72 | config INIT_ENV_ARG_LIMIT | 72 | config INIT_ENV_ARG_LIMIT |
73 | int | 73 | int |
74 | default 32 if !UML | 74 | default 32 if !UML |
75 | default 128 if UML | 75 | default 128 if UML |
76 | help | 76 | help |
77 | Maximum of each of the number of arguments and environment | 77 | Maximum of each of the number of arguments and environment |
78 | variables passed to init from the kernel command line. | 78 | variables passed to init from the kernel command line. |
79 | 79 | ||
80 | 80 | ||
81 | config CROSS_COMPILE | 81 | config CROSS_COMPILE |
82 | string "Cross-compiler tool prefix" | 82 | string "Cross-compiler tool prefix" |
83 | help | 83 | help |
84 | Same as running 'make CROSS_COMPILE=prefix-' but stored for | 84 | Same as running 'make CROSS_COMPILE=prefix-' but stored for |
85 | default make runs in this kernel build directory. You don't | 85 | default make runs in this kernel build directory. You don't |
86 | need to set this unless you want the configured kernel build | 86 | need to set this unless you want the configured kernel build |
87 | directory to select the cross-compiler automatically. | 87 | directory to select the cross-compiler automatically. |
88 | 88 | ||
89 | config LOCALVERSION | 89 | config LOCALVERSION |
90 | string "Local version - append to kernel release" | 90 | string "Local version - append to kernel release" |
91 | help | 91 | help |
92 | Append an extra string to the end of your kernel version. | 92 | Append an extra string to the end of your kernel version. |
93 | This will show up when you type uname, for example. | 93 | This will show up when you type uname, for example. |
94 | The string you set here will be appended after the contents of | 94 | The string you set here will be appended after the contents of |
95 | any files with a filename matching localversion* in your | 95 | any files with a filename matching localversion* in your |
96 | object and source tree, in that order. Your total string can | 96 | object and source tree, in that order. Your total string can |
97 | be a maximum of 64 characters. | 97 | be a maximum of 64 characters. |
98 | 98 | ||
99 | config LOCALVERSION_AUTO | 99 | config LOCALVERSION_AUTO |
100 | bool "Automatically append version information to the version string" | 100 | bool "Automatically append version information to the version string" |
101 | default y | 101 | default y |
102 | help | 102 | help |
103 | This will try to automatically determine if the current tree is a | 103 | This will try to automatically determine if the current tree is a |
104 | release tree by looking for git tags that belong to the current | 104 | release tree by looking for git tags that belong to the current |
105 | top of tree revision. | 105 | top of tree revision. |
106 | 106 | ||
107 | A string of the format -gxxxxxxxx will be added to the localversion | 107 | A string of the format -gxxxxxxxx will be added to the localversion |
108 | if a git-based tree is found. The string generated by this will be | 108 | if a git-based tree is found. The string generated by this will be |
109 | appended after any matching localversion* files, and after the value | 109 | appended after any matching localversion* files, and after the value |
110 | set in CONFIG_LOCALVERSION. | 110 | set in CONFIG_LOCALVERSION. |
111 | 111 | ||
112 | (The actual string used here is the first eight characters produced | 112 | (The actual string used here is the first eight characters produced |
113 | by running the command: | 113 | by running the command: |
114 | 114 | ||
115 | $ git rev-parse --verify HEAD | 115 | $ git rev-parse --verify HEAD |
116 | 116 | ||
117 | which is done within the script "scripts/setlocalversion".) | 117 | which is done within the script "scripts/setlocalversion".) |
118 | 118 | ||
119 | config HAVE_KERNEL_GZIP | 119 | config HAVE_KERNEL_GZIP |
120 | bool | 120 | bool |
121 | 121 | ||
122 | config HAVE_KERNEL_BZIP2 | 122 | config HAVE_KERNEL_BZIP2 |
123 | bool | 123 | bool |
124 | 124 | ||
125 | config HAVE_KERNEL_LZMA | 125 | config HAVE_KERNEL_LZMA |
126 | bool | 126 | bool |
127 | 127 | ||
128 | config HAVE_KERNEL_XZ | 128 | config HAVE_KERNEL_XZ |
129 | bool | 129 | bool |
130 | 130 | ||
131 | config HAVE_KERNEL_LZO | 131 | config HAVE_KERNEL_LZO |
132 | bool | 132 | bool |
133 | 133 | ||
134 | choice | 134 | choice |
135 | prompt "Kernel compression mode" | 135 | prompt "Kernel compression mode" |
136 | default KERNEL_GZIP | 136 | default KERNEL_GZIP |
137 | depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO | 137 | depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO |
138 | help | 138 | help |
139 | The linux kernel is a kind of self-extracting executable. | 139 | The linux kernel is a kind of self-extracting executable. |
140 | Several compression algorithms are available, which differ | 140 | Several compression algorithms are available, which differ |
141 | in efficiency, compression and decompression speed. | 141 | in efficiency, compression and decompression speed. |
142 | Compression speed is only relevant when building a kernel. | 142 | Compression speed is only relevant when building a kernel. |
143 | Decompression speed is relevant at each boot. | 143 | Decompression speed is relevant at each boot. |
144 | 144 | ||
145 | If you have any problems with bzip2 or lzma compressed | 145 | If you have any problems with bzip2 or lzma compressed |
146 | kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older | 146 | kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older |
147 | version of this functionality (bzip2 only), for 2.4, was | 147 | version of this functionality (bzip2 only), for 2.4, was |
148 | supplied by Christian Ludwig) | 148 | supplied by Christian Ludwig) |
149 | 149 | ||
150 | High compression options are mostly useful for users, who | 150 | High compression options are mostly useful for users, who |
151 | are low on disk space (embedded systems), but for whom ram | 151 | are low on disk space (embedded systems), but for whom ram |
152 | size matters less. | 152 | size matters less. |
153 | 153 | ||
154 | If in doubt, select 'gzip' | 154 | If in doubt, select 'gzip' |
155 | 155 | ||
156 | config KERNEL_GZIP | 156 | config KERNEL_GZIP |
157 | bool "Gzip" | 157 | bool "Gzip" |
158 | depends on HAVE_KERNEL_GZIP | 158 | depends on HAVE_KERNEL_GZIP |
159 | help | 159 | help |
160 | The old and tried gzip compression. It provides a good balance | 160 | The old and tried gzip compression. It provides a good balance |
161 | between compression ratio and decompression speed. | 161 | between compression ratio and decompression speed. |
162 | 162 | ||
163 | config KERNEL_BZIP2 | 163 | config KERNEL_BZIP2 |
164 | bool "Bzip2" | 164 | bool "Bzip2" |
165 | depends on HAVE_KERNEL_BZIP2 | 165 | depends on HAVE_KERNEL_BZIP2 |
166 | help | 166 | help |
167 | Its compression ratio and speed is intermediate. | 167 | Its compression ratio and speed is intermediate. |
168 | Decompression speed is slowest among the three. The kernel | 168 | Decompression speed is slowest among the three. The kernel |
169 | size is about 10% smaller with bzip2, in comparison to gzip. | 169 | size is about 10% smaller with bzip2, in comparison to gzip. |
170 | Bzip2 uses a large amount of memory. For modern kernels you | 170 | Bzip2 uses a large amount of memory. For modern kernels you |
171 | will need at least 8MB RAM or more for booting. | 171 | will need at least 8MB RAM or more for booting. |
172 | 172 | ||
173 | config KERNEL_LZMA | 173 | config KERNEL_LZMA |
174 | bool "LZMA" | 174 | bool "LZMA" |
175 | depends on HAVE_KERNEL_LZMA | 175 | depends on HAVE_KERNEL_LZMA |
176 | help | 176 | help |
177 | The most recent compression algorithm. | 177 | The most recent compression algorithm. |
178 | Its ratio is best, decompression speed is between the other | 178 | Its ratio is best, decompression speed is between the other |
179 | two. Compression is slowest. The kernel size is about 33% | 179 | two. Compression is slowest. The kernel size is about 33% |
180 | smaller with LZMA in comparison to gzip. | 180 | smaller with LZMA in comparison to gzip. |
181 | 181 | ||
182 | config KERNEL_XZ | 182 | config KERNEL_XZ |
183 | bool "XZ" | 183 | bool "XZ" |
184 | depends on HAVE_KERNEL_XZ | 184 | depends on HAVE_KERNEL_XZ |
185 | help | 185 | help |
186 | XZ uses the LZMA2 algorithm and instruction set specific | 186 | XZ uses the LZMA2 algorithm and instruction set specific |
187 | BCJ filters which can improve compression ratio of executable | 187 | BCJ filters which can improve compression ratio of executable |
188 | code. The size of the kernel is about 30% smaller with XZ in | 188 | code. The size of the kernel is about 30% smaller with XZ in |
189 | comparison to gzip. On architectures for which there is a BCJ | 189 | comparison to gzip. On architectures for which there is a BCJ |
190 | filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ | 190 | filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ |
191 | will create a few percent smaller kernel than plain LZMA. | 191 | will create a few percent smaller kernel than plain LZMA. |
192 | 192 | ||
193 | The speed is about the same as with LZMA: The decompression | 193 | The speed is about the same as with LZMA: The decompression |
194 | speed of XZ is better than that of bzip2 but worse than gzip | 194 | speed of XZ is better than that of bzip2 but worse than gzip |
195 | and LZO. Compression is slow. | 195 | and LZO. Compression is slow. |
196 | 196 | ||
197 | config KERNEL_LZO | 197 | config KERNEL_LZO |
198 | bool "LZO" | 198 | bool "LZO" |
199 | depends on HAVE_KERNEL_LZO | 199 | depends on HAVE_KERNEL_LZO |
200 | help | 200 | help |
201 | Its compression ratio is the poorest among the 4. The kernel | 201 | Its compression ratio is the poorest among the 4. The kernel |
202 | size is about 10% bigger than gzip; however its speed | 202 | size is about 10% bigger than gzip; however its speed |
203 | (both compression and decompression) is the fastest. | 203 | (both compression and decompression) is the fastest. |
204 | 204 | ||
205 | endchoice | 205 | endchoice |
206 | 206 | ||
207 | config SWAP | 207 | config SWAP |
208 | bool "Support for paging of anonymous memory (swap)" | 208 | bool "Support for paging of anonymous memory (swap)" |
209 | depends on MMU && BLOCK | 209 | depends on MMU && BLOCK |
210 | default y | 210 | default y |
211 | help | 211 | help |
212 | This option allows you to choose whether you want to have support | 212 | This option allows you to choose whether you want to have support |
213 | for so called swap devices or swap files in your kernel that are | 213 | for so called swap devices or swap files in your kernel that are |
214 | used to provide more virtual memory than the actual RAM present | 214 | used to provide more virtual memory than the actual RAM present |
215 | in your computer. If unsure say Y. | 215 | in your computer. If unsure say Y. |
216 | 216 | ||
217 | config SYSVIPC | 217 | config SYSVIPC |
218 | bool "System V IPC" | 218 | bool "System V IPC" |
219 | ---help--- | 219 | ---help--- |
220 | Inter Process Communication is a suite of library functions and | 220 | Inter Process Communication is a suite of library functions and |
221 | system calls which let processes (running programs) synchronize and | 221 | system calls which let processes (running programs) synchronize and |
222 | exchange information. It is generally considered to be a good thing, | 222 | exchange information. It is generally considered to be a good thing, |
223 | and some programs won't run unless you say Y here. In particular, if | 223 | and some programs won't run unless you say Y here. In particular, if |
224 | you want to run the DOS emulator dosemu under Linux (read the | 224 | you want to run the DOS emulator dosemu under Linux (read the |
225 | DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>), | 225 | DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>), |
226 | you'll need to say Y here. | 226 | you'll need to say Y here. |
227 | 227 | ||
228 | You can find documentation about IPC with "info ipc" and also in | 228 | You can find documentation about IPC with "info ipc" and also in |
229 | section 6.4 of the Linux Programmer's Guide, available from | 229 | section 6.4 of the Linux Programmer's Guide, available from |
230 | <http://www.tldp.org/guides.html>. | 230 | <http://www.tldp.org/guides.html>. |
231 | 231 | ||
232 | config SYSVIPC_SYSCTL | 232 | config SYSVIPC_SYSCTL |
233 | bool | 233 | bool |
234 | depends on SYSVIPC | 234 | depends on SYSVIPC |
235 | depends on SYSCTL | 235 | depends on SYSCTL |
236 | default y | 236 | default y |
237 | 237 | ||
238 | config POSIX_MQUEUE | 238 | config POSIX_MQUEUE |
239 | bool "POSIX Message Queues" | 239 | bool "POSIX Message Queues" |
240 | depends on NET && EXPERIMENTAL | 240 | depends on NET && EXPERIMENTAL |
241 | ---help--- | 241 | ---help--- |
242 | POSIX variant of message queues is a part of IPC. In POSIX message | 242 | POSIX variant of message queues is a part of IPC. In POSIX message |
243 | queues every message has a priority which decides about succession | 243 | queues every message has a priority which decides about succession |
244 | of receiving it by a process. If you want to compile and run | 244 | of receiving it by a process. If you want to compile and run |
245 | programs written e.g. for Solaris with use of its POSIX message | 245 | programs written e.g. for Solaris with use of its POSIX message |
246 | queues (functions mq_*) say Y here. | 246 | queues (functions mq_*) say Y here. |
247 | 247 | ||
248 | POSIX message queues are visible as a filesystem called 'mqueue' | 248 | POSIX message queues are visible as a filesystem called 'mqueue' |
249 | and can be mounted somewhere if you want to do filesystem | 249 | and can be mounted somewhere if you want to do filesystem |
250 | operations on message queues. | 250 | operations on message queues. |
251 | 251 | ||
252 | If unsure, say Y. | 252 | If unsure, say Y. |
253 | 253 | ||
254 | config POSIX_MQUEUE_SYSCTL | 254 | config POSIX_MQUEUE_SYSCTL |
255 | bool | 255 | bool |
256 | depends on POSIX_MQUEUE | 256 | depends on POSIX_MQUEUE |
257 | depends on SYSCTL | 257 | depends on SYSCTL |
258 | default y | 258 | default y |
259 | 259 | ||
260 | config BSD_PROCESS_ACCT | 260 | config BSD_PROCESS_ACCT |
261 | bool "BSD Process Accounting" | 261 | bool "BSD Process Accounting" |
262 | help | 262 | help |
263 | If you say Y here, a user level program will be able to instruct the | 263 | If you say Y here, a user level program will be able to instruct the |
264 | kernel (via a special system call) to write process accounting | 264 | kernel (via a special system call) to write process accounting |
265 | information to a file: whenever a process exits, information about | 265 | information to a file: whenever a process exits, information about |
266 | that process will be appended to the file by the kernel. The | 266 | that process will be appended to the file by the kernel. The |
267 | information includes things such as creation time, owning user, | 267 | information includes things such as creation time, owning user, |
268 | command name, memory usage, controlling terminal etc. (the complete | 268 | command name, memory usage, controlling terminal etc. (the complete |
269 | list is in the struct acct in <file:include/linux/acct.h>). It is | 269 | list is in the struct acct in <file:include/linux/acct.h>). It is |
270 | up to the user level program to do useful things with this | 270 | up to the user level program to do useful things with this |
271 | information. This is generally a good idea, so say Y. | 271 | information. This is generally a good idea, so say Y. |
272 | 272 | ||
273 | config BSD_PROCESS_ACCT_V3 | 273 | config BSD_PROCESS_ACCT_V3 |
274 | bool "BSD Process Accounting version 3 file format" | 274 | bool "BSD Process Accounting version 3 file format" |
275 | depends on BSD_PROCESS_ACCT | 275 | depends on BSD_PROCESS_ACCT |
276 | default n | 276 | default n |
277 | help | 277 | help |
278 | If you say Y here, the process accounting information is written | 278 | If you say Y here, the process accounting information is written |
279 | in a new file format that also logs the process IDs of each | 279 | in a new file format that also logs the process IDs of each |
280 | process and it's parent. Note that this file format is incompatible | 280 | process and it's parent. Note that this file format is incompatible |
281 | with previous v0/v1/v2 file formats, so you will need updated tools | 281 | with previous v0/v1/v2 file formats, so you will need updated tools |
282 | for processing it. A preliminary version of these tools is available | 282 | for processing it. A preliminary version of these tools is available |
283 | at <http://www.gnu.org/software/acct/>. | 283 | at <http://www.gnu.org/software/acct/>. |
284 | 284 | ||
285 | config FHANDLE | 285 | config FHANDLE |
286 | bool "open by fhandle syscalls" | 286 | bool "open by fhandle syscalls" |
287 | select EXPORTFS | 287 | select EXPORTFS |
288 | help | 288 | help |
289 | If you say Y here, a user level program will be able to map | 289 | If you say Y here, a user level program will be able to map |
290 | file names to handle and then later use the handle for | 290 | file names to handle and then later use the handle for |
291 | different file system operations. This is useful in implementing | 291 | different file system operations. This is useful in implementing |
292 | userspace file servers, which now track files using handles instead | 292 | userspace file servers, which now track files using handles instead |
293 | of names. The handle would remain the same even if file names | 293 | of names. The handle would remain the same even if file names |
294 | get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2) | 294 | get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2) |
295 | syscalls. | 295 | syscalls. |
296 | 296 | ||
297 | config TASKSTATS | 297 | config TASKSTATS |
298 | bool "Export task/process statistics through netlink (EXPERIMENTAL)" | 298 | bool "Export task/process statistics through netlink (EXPERIMENTAL)" |
299 | depends on NET | 299 | depends on NET |
300 | default n | 300 | default n |
301 | help | 301 | help |
302 | Export selected statistics for tasks/processes through the | 302 | Export selected statistics for tasks/processes through the |
303 | generic netlink interface. Unlike BSD process accounting, the | 303 | generic netlink interface. Unlike BSD process accounting, the |
304 | statistics are available during the lifetime of tasks/processes as | 304 | statistics are available during the lifetime of tasks/processes as |
305 | responses to commands. Like BSD accounting, they are sent to user | 305 | responses to commands. Like BSD accounting, they are sent to user |
306 | space on task exit. | 306 | space on task exit. |
307 | 307 | ||
308 | Say N if unsure. | 308 | Say N if unsure. |
309 | 309 | ||
310 | config TASK_DELAY_ACCT | 310 | config TASK_DELAY_ACCT |
311 | bool "Enable per-task delay accounting (EXPERIMENTAL)" | 311 | bool "Enable per-task delay accounting (EXPERIMENTAL)" |
312 | depends on TASKSTATS | 312 | depends on TASKSTATS |
313 | help | 313 | help |
314 | Collect information on time spent by a task waiting for system | 314 | Collect information on time spent by a task waiting for system |
315 | resources like cpu, synchronous block I/O completion and swapping | 315 | resources like cpu, synchronous block I/O completion and swapping |
316 | in pages. Such statistics can help in setting a task's priorities | 316 | in pages. Such statistics can help in setting a task's priorities |
317 | relative to other tasks for cpu, io, rss limits etc. | 317 | relative to other tasks for cpu, io, rss limits etc. |
318 | 318 | ||
319 | Say N if unsure. | 319 | Say N if unsure. |
320 | 320 | ||
321 | config TASK_XACCT | 321 | config TASK_XACCT |
322 | bool "Enable extended accounting over taskstats (EXPERIMENTAL)" | 322 | bool "Enable extended accounting over taskstats (EXPERIMENTAL)" |
323 | depends on TASKSTATS | 323 | depends on TASKSTATS |
324 | help | 324 | help |
325 | Collect extended task accounting data and send the data | 325 | Collect extended task accounting data and send the data |
326 | to userland for processing over the taskstats interface. | 326 | to userland for processing over the taskstats interface. |
327 | 327 | ||
328 | Say N if unsure. | 328 | Say N if unsure. |
329 | 329 | ||
330 | config TASK_IO_ACCOUNTING | 330 | config TASK_IO_ACCOUNTING |
331 | bool "Enable per-task storage I/O accounting (EXPERIMENTAL)" | 331 | bool "Enable per-task storage I/O accounting (EXPERIMENTAL)" |
332 | depends on TASK_XACCT | 332 | depends on TASK_XACCT |
333 | help | 333 | help |
334 | Collect information on the number of bytes of storage I/O which this | 334 | Collect information on the number of bytes of storage I/O which this |
335 | task has caused. | 335 | task has caused. |
336 | 336 | ||
337 | Say N if unsure. | 337 | Say N if unsure. |
338 | 338 | ||
339 | config AUDIT | 339 | config AUDIT |
340 | bool "Auditing support" | 340 | bool "Auditing support" |
341 | depends on NET | 341 | depends on NET |
342 | help | 342 | help |
343 | Enable auditing infrastructure that can be used with another | 343 | Enable auditing infrastructure that can be used with another |
344 | kernel subsystem, such as SELinux (which requires this for | 344 | kernel subsystem, such as SELinux (which requires this for |
345 | logging of avc messages output). Does not do system-call | 345 | logging of avc messages output). Does not do system-call |
346 | auditing without CONFIG_AUDITSYSCALL. | 346 | auditing without CONFIG_AUDITSYSCALL. |
347 | 347 | ||
348 | config AUDITSYSCALL | 348 | config AUDITSYSCALL |
349 | bool "Enable system-call auditing support" | 349 | bool "Enable system-call auditing support" |
350 | depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH) | 350 | depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH) |
351 | default y if SECURITY_SELINUX | 351 | default y if SECURITY_SELINUX |
352 | help | 352 | help |
353 | Enable low-overhead system-call auditing infrastructure that | 353 | Enable low-overhead system-call auditing infrastructure that |
354 | can be used independently or with another kernel subsystem, | 354 | can be used independently or with another kernel subsystem, |
355 | such as SELinux. | 355 | such as SELinux. |
356 | 356 | ||
357 | config AUDIT_WATCH | 357 | config AUDIT_WATCH |
358 | def_bool y | 358 | def_bool y |
359 | depends on AUDITSYSCALL | 359 | depends on AUDITSYSCALL |
360 | select FSNOTIFY | 360 | select FSNOTIFY |
361 | 361 | ||
362 | config AUDIT_TREE | 362 | config AUDIT_TREE |
363 | def_bool y | 363 | def_bool y |
364 | depends on AUDITSYSCALL | 364 | depends on AUDITSYSCALL |
365 | select FSNOTIFY | 365 | select FSNOTIFY |
366 | 366 | ||
367 | source "kernel/irq/Kconfig" | 367 | source "kernel/irq/Kconfig" |
368 | 368 | ||
369 | menu "RCU Subsystem" | 369 | menu "RCU Subsystem" |
370 | 370 | ||
371 | choice | 371 | choice |
372 | prompt "RCU Implementation" | 372 | prompt "RCU Implementation" |
373 | default TREE_RCU | 373 | default TREE_RCU |
374 | 374 | ||
375 | config TREE_RCU | 375 | config TREE_RCU |
376 | bool "Tree-based hierarchical RCU" | 376 | bool "Tree-based hierarchical RCU" |
377 | depends on !PREEMPT && SMP | 377 | depends on !PREEMPT && SMP |
378 | help | 378 | help |
379 | This option selects the RCU implementation that is | 379 | This option selects the RCU implementation that is |
380 | designed for very large SMP system with hundreds or | 380 | designed for very large SMP system with hundreds or |
381 | thousands of CPUs. It also scales down nicely to | 381 | thousands of CPUs. It also scales down nicely to |
382 | smaller systems. | 382 | smaller systems. |
383 | 383 | ||
384 | config TREE_PREEMPT_RCU | 384 | config TREE_PREEMPT_RCU |
385 | bool "Preemptible tree-based hierarchical RCU" | 385 | bool "Preemptible tree-based hierarchical RCU" |
386 | depends on PREEMPT | 386 | depends on PREEMPT |
387 | help | 387 | help |
388 | This option selects the RCU implementation that is | 388 | This option selects the RCU implementation that is |
389 | designed for very large SMP systems with hundreds or | 389 | designed for very large SMP systems with hundreds or |
390 | thousands of CPUs, but for which real-time response | 390 | thousands of CPUs, but for which real-time response |
391 | is also required. It also scales down nicely to | 391 | is also required. It also scales down nicely to |
392 | smaller systems. | 392 | smaller systems. |
393 | 393 | ||
394 | config TINY_RCU | 394 | config TINY_RCU |
395 | bool "UP-only small-memory-footprint RCU" | 395 | bool "UP-only small-memory-footprint RCU" |
396 | depends on !SMP | 396 | depends on !SMP |
397 | help | 397 | help |
398 | This option selects the RCU implementation that is | 398 | This option selects the RCU implementation that is |
399 | designed for UP systems from which real-time response | 399 | designed for UP systems from which real-time response |
400 | is not required. This option greatly reduces the | 400 | is not required. This option greatly reduces the |
401 | memory footprint of RCU. | 401 | memory footprint of RCU. |
402 | 402 | ||
403 | config TINY_PREEMPT_RCU | 403 | config TINY_PREEMPT_RCU |
404 | bool "Preemptible UP-only small-memory-footprint RCU" | 404 | bool "Preemptible UP-only small-memory-footprint RCU" |
405 | depends on !SMP && PREEMPT | 405 | depends on !SMP && PREEMPT |
406 | help | 406 | help |
407 | This option selects the RCU implementation that is designed | 407 | This option selects the RCU implementation that is designed |
408 | for real-time UP systems. This option greatly reduces the | 408 | for real-time UP systems. This option greatly reduces the |
409 | memory footprint of RCU. | 409 | memory footprint of RCU. |
410 | 410 | ||
411 | endchoice | 411 | endchoice |
412 | 412 | ||
413 | config PREEMPT_RCU | 413 | config PREEMPT_RCU |
414 | def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU ) | 414 | def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU ) |
415 | help | 415 | help |
416 | This option enables preemptible-RCU code that is common between | 416 | This option enables preemptible-RCU code that is common between |
417 | the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. | 417 | the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. |
418 | 418 | ||
419 | config RCU_TRACE | 419 | config RCU_TRACE |
420 | bool "Enable tracing for RCU" | 420 | bool "Enable tracing for RCU" |
421 | help | 421 | help |
422 | This option provides tracing in RCU which presents stats | 422 | This option provides tracing in RCU which presents stats |
423 | in debugfs for debugging RCU implementation. | 423 | in debugfs for debugging RCU implementation. |
424 | 424 | ||
425 | Say Y here if you want to enable RCU tracing | 425 | Say Y here if you want to enable RCU tracing |
426 | Say N if you are unsure. | 426 | Say N if you are unsure. |
427 | 427 | ||
428 | config RCU_FANOUT | 428 | config RCU_FANOUT |
429 | int "Tree-based hierarchical RCU fanout value" | 429 | int "Tree-based hierarchical RCU fanout value" |
430 | range 2 64 if 64BIT | 430 | range 2 64 if 64BIT |
431 | range 2 32 if !64BIT | 431 | range 2 32 if !64BIT |
432 | depends on TREE_RCU || TREE_PREEMPT_RCU | 432 | depends on TREE_RCU || TREE_PREEMPT_RCU |
433 | default 64 if 64BIT | 433 | default 64 if 64BIT |
434 | default 32 if !64BIT | 434 | default 32 if !64BIT |
435 | help | 435 | help |
436 | This option controls the fanout of hierarchical implementations | 436 | This option controls the fanout of hierarchical implementations |
437 | of RCU, allowing RCU to work efficiently on machines with | 437 | of RCU, allowing RCU to work efficiently on machines with |
438 | large numbers of CPUs. This value must be at least the fourth | 438 | large numbers of CPUs. This value must be at least the fourth |
439 | root of NR_CPUS, which allows NR_CPUS to be insanely large. | 439 | root of NR_CPUS, which allows NR_CPUS to be insanely large. |
440 | The default value of RCU_FANOUT should be used for production | 440 | The default value of RCU_FANOUT should be used for production |
441 | systems, but if you are stress-testing the RCU implementation | 441 | systems, but if you are stress-testing the RCU implementation |
442 | itself, small RCU_FANOUT values allow you to test large-system | 442 | itself, small RCU_FANOUT values allow you to test large-system |
443 | code paths on small(er) systems. | 443 | code paths on small(er) systems. |
444 | 444 | ||
445 | Select a specific number if testing RCU itself. | 445 | Select a specific number if testing RCU itself. |
446 | Take the default if unsure. | 446 | Take the default if unsure. |
447 | 447 | ||
448 | config RCU_FANOUT_EXACT | 448 | config RCU_FANOUT_EXACT |
449 | bool "Disable tree-based hierarchical RCU auto-balancing" | 449 | bool "Disable tree-based hierarchical RCU auto-balancing" |
450 | depends on TREE_RCU || TREE_PREEMPT_RCU | 450 | depends on TREE_RCU || TREE_PREEMPT_RCU |
451 | default n | 451 | default n |
452 | help | 452 | help |
453 | This option forces use of the exact RCU_FANOUT value specified, | 453 | This option forces use of the exact RCU_FANOUT value specified, |
454 | regardless of imbalances in the hierarchy. This is useful for | 454 | regardless of imbalances in the hierarchy. This is useful for |
455 | testing RCU itself, and might one day be useful on systems with | 455 | testing RCU itself, and might one day be useful on systems with |
456 | strong NUMA behavior. | 456 | strong NUMA behavior. |
457 | 457 | ||
458 | Without RCU_FANOUT_EXACT, the code will balance the hierarchy. | 458 | Without RCU_FANOUT_EXACT, the code will balance the hierarchy. |
459 | 459 | ||
460 | Say N if unsure. | 460 | Say N if unsure. |
461 | 461 | ||
462 | config RCU_FAST_NO_HZ | 462 | config RCU_FAST_NO_HZ |
463 | bool "Accelerate last non-dyntick-idle CPU's grace periods" | 463 | bool "Accelerate last non-dyntick-idle CPU's grace periods" |
464 | depends on TREE_RCU && NO_HZ && SMP | 464 | depends on TREE_RCU && NO_HZ && SMP |
465 | default n | 465 | default n |
466 | help | 466 | help |
467 | This option causes RCU to attempt to accelerate grace periods | 467 | This option causes RCU to attempt to accelerate grace periods |
468 | in order to allow the final CPU to enter dynticks-idle state | 468 | in order to allow the final CPU to enter dynticks-idle state |
469 | more quickly. On the other hand, this option increases the | 469 | more quickly. On the other hand, this option increases the |
470 | overhead of the dynticks-idle checking, particularly on systems | 470 | overhead of the dynticks-idle checking, particularly on systems |
471 | with large numbers of CPUs. | 471 | with large numbers of CPUs. |
472 | 472 | ||
473 | Say Y if energy efficiency is critically important, particularly | 473 | Say Y if energy efficiency is critically important, particularly |
474 | if you have relatively few CPUs. | 474 | if you have relatively few CPUs. |
475 | 475 | ||
476 | Say N if you are unsure. | 476 | Say N if you are unsure. |
477 | 477 | ||
478 | config TREE_RCU_TRACE | 478 | config TREE_RCU_TRACE |
479 | def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) | 479 | def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) |
480 | select DEBUG_FS | 480 | select DEBUG_FS |
481 | help | 481 | help |
482 | This option provides tracing for the TREE_RCU and | 482 | This option provides tracing for the TREE_RCU and |
483 | TREE_PREEMPT_RCU implementations, permitting Makefile to | 483 | TREE_PREEMPT_RCU implementations, permitting Makefile to |
484 | trivially select kernel/rcutree_trace.c. | 484 | trivially select kernel/rcutree_trace.c. |
485 | 485 | ||
486 | config RCU_BOOST | 486 | config RCU_BOOST |
487 | bool "Enable RCU priority boosting" | 487 | bool "Enable RCU priority boosting" |
488 | depends on RT_MUTEXES && TINY_PREEMPT_RCU | 488 | depends on RT_MUTEXES && TINY_PREEMPT_RCU |
489 | default n | 489 | default n |
490 | help | 490 | help |
491 | This option boosts the priority of preempted RCU readers that | 491 | This option boosts the priority of preempted RCU readers that |
492 | block the current preemptible RCU grace period for too long. | 492 | block the current preemptible RCU grace period for too long. |
493 | This option also prevents heavy loads from blocking RCU | 493 | This option also prevents heavy loads from blocking RCU |
494 | callback invocation for all flavors of RCU. | 494 | callback invocation for all flavors of RCU. |
495 | 495 | ||
496 | Say Y here if you are working with real-time apps or heavy loads | 496 | Say Y here if you are working with real-time apps or heavy loads |
497 | Say N here if you are unsure. | 497 | Say N here if you are unsure. |
498 | 498 | ||
499 | config RCU_BOOST_PRIO | 499 | config RCU_BOOST_PRIO |
500 | int "Real-time priority to boost RCU readers to" | 500 | int "Real-time priority to boost RCU readers to" |
501 | range 1 99 | 501 | range 1 99 |
502 | depends on RCU_BOOST | 502 | depends on RCU_BOOST |
503 | default 1 | 503 | default 1 |
504 | help | 504 | help |
505 | This option specifies the real-time priority to which preempted | 505 | This option specifies the real-time priority to which preempted |
506 | RCU readers are to be boosted. If you are working with CPU-bound | 506 | RCU readers are to be boosted. If you are working with CPU-bound |
507 | real-time applications, you should specify a priority higher then | 507 | real-time applications, you should specify a priority higher then |
508 | the highest-priority CPU-bound application. | 508 | the highest-priority CPU-bound application. |
509 | 509 | ||
510 | Specify the real-time priority, or take the default if unsure. | 510 | Specify the real-time priority, or take the default if unsure. |
511 | 511 | ||
512 | config RCU_BOOST_DELAY | 512 | config RCU_BOOST_DELAY |
513 | int "Milliseconds to delay boosting after RCU grace-period start" | 513 | int "Milliseconds to delay boosting after RCU grace-period start" |
514 | range 0 3000 | 514 | range 0 3000 |
515 | depends on RCU_BOOST | 515 | depends on RCU_BOOST |
516 | default 500 | 516 | default 500 |
517 | help | 517 | help |
518 | This option specifies the time to wait after the beginning of | 518 | This option specifies the time to wait after the beginning of |
519 | a given grace period before priority-boosting preempted RCU | 519 | a given grace period before priority-boosting preempted RCU |
520 | readers blocking that grace period. Note that any RCU reader | 520 | readers blocking that grace period. Note that any RCU reader |
521 | blocking an expedited RCU grace period is boosted immediately. | 521 | blocking an expedited RCU grace period is boosted immediately. |
522 | 522 | ||
523 | Accept the default if unsure. | 523 | Accept the default if unsure. |
524 | 524 | ||
525 | endmenu # "RCU Subsystem" | 525 | endmenu # "RCU Subsystem" |
526 | 526 | ||
527 | config IKCONFIG | 527 | config IKCONFIG |
528 | tristate "Kernel .config support" | 528 | tristate "Kernel .config support" |
529 | ---help--- | 529 | ---help--- |
530 | This option enables the complete Linux kernel ".config" file | 530 | This option enables the complete Linux kernel ".config" file |
531 | contents to be saved in the kernel. It provides documentation | 531 | contents to be saved in the kernel. It provides documentation |
532 | of which kernel options are used in a running kernel or in an | 532 | of which kernel options are used in a running kernel or in an |
533 | on-disk kernel. This information can be extracted from the kernel | 533 | on-disk kernel. This information can be extracted from the kernel |
534 | image file with the script scripts/extract-ikconfig and used as | 534 | image file with the script scripts/extract-ikconfig and used as |
535 | input to rebuild the current kernel or to build another kernel. | 535 | input to rebuild the current kernel or to build another kernel. |
536 | It can also be extracted from a running kernel by reading | 536 | It can also be extracted from a running kernel by reading |
537 | /proc/config.gz if enabled (below). | 537 | /proc/config.gz if enabled (below). |
538 | 538 | ||
539 | config IKCONFIG_PROC | 539 | config IKCONFIG_PROC |
540 | bool "Enable access to .config through /proc/config.gz" | 540 | bool "Enable access to .config through /proc/config.gz" |
541 | depends on IKCONFIG && PROC_FS | 541 | depends on IKCONFIG && PROC_FS |
542 | ---help--- | 542 | ---help--- |
543 | This option enables access to the kernel configuration file | 543 | This option enables access to the kernel configuration file |
544 | through /proc/config.gz. | 544 | through /proc/config.gz. |
545 | 545 | ||
546 | config LOG_BUF_SHIFT | 546 | config LOG_BUF_SHIFT |
547 | int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" | 547 | int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" |
548 | range 12 21 | 548 | range 12 21 |
549 | default 17 | 549 | default 17 |
550 | help | 550 | help |
551 | Select kernel log buffer size as a power of 2. | 551 | Select kernel log buffer size as a power of 2. |
552 | Examples: | 552 | Examples: |
553 | 17 => 128 KB | 553 | 17 => 128 KB |
554 | 16 => 64 KB | 554 | 16 => 64 KB |
555 | 15 => 32 KB | 555 | 15 => 32 KB |
556 | 14 => 16 KB | 556 | 14 => 16 KB |
557 | 13 => 8 KB | 557 | 13 => 8 KB |
558 | 12 => 4 KB | 558 | 12 => 4 KB |
559 | 559 | ||
560 | # | 560 | # |
561 | # Architectures with an unreliable sched_clock() should select this: | 561 | # Architectures with an unreliable sched_clock() should select this: |
562 | # | 562 | # |
563 | config HAVE_UNSTABLE_SCHED_CLOCK | 563 | config HAVE_UNSTABLE_SCHED_CLOCK |
564 | bool | 564 | bool |
565 | 565 | ||
566 | menuconfig CGROUPS | 566 | menuconfig CGROUPS |
567 | boolean "Control Group support" | 567 | boolean "Control Group support" |
568 | depends on EVENTFD | 568 | depends on EVENTFD |
569 | help | 569 | help |
570 | This option adds support for grouping sets of processes together, for | 570 | This option adds support for grouping sets of processes together, for |
571 | use with process control subsystems such as Cpusets, CFS, memory | 571 | use with process control subsystems such as Cpusets, CFS, memory |
572 | controls or device isolation. | 572 | controls or device isolation. |
573 | See | 573 | See |
574 | - Documentation/scheduler/sched-design-CFS.txt (CFS) | 574 | - Documentation/scheduler/sched-design-CFS.txt (CFS) |
575 | - Documentation/cgroups/ (features for grouping, isolation | 575 | - Documentation/cgroups/ (features for grouping, isolation |
576 | and resource control) | 576 | and resource control) |
577 | 577 | ||
578 | Say N if unsure. | 578 | Say N if unsure. |
579 | 579 | ||
580 | if CGROUPS | 580 | if CGROUPS |
581 | 581 | ||
582 | config CGROUP_DEBUG | 582 | config CGROUP_DEBUG |
583 | bool "Example debug cgroup subsystem" | 583 | bool "Example debug cgroup subsystem" |
584 | default n | 584 | default n |
585 | help | 585 | help |
586 | This option enables a simple cgroup subsystem that | 586 | This option enables a simple cgroup subsystem that |
587 | exports useful debugging information about the cgroups | 587 | exports useful debugging information about the cgroups |
588 | framework. | 588 | framework. |
589 | 589 | ||
590 | Say N if unsure. | 590 | Say N if unsure. |
591 | 591 | ||
592 | config CGROUP_NS | 592 | config CGROUP_NS |
593 | bool "Namespace cgroup subsystem" | 593 | bool "Namespace cgroup subsystem" |
594 | help | 594 | help |
595 | Provides a simple namespace cgroup subsystem to | 595 | Provides a simple namespace cgroup subsystem to |
596 | provide hierarchical naming of sets of namespaces, | 596 | provide hierarchical naming of sets of namespaces, |
597 | for instance virtual servers and checkpoint/restart | 597 | for instance virtual servers and checkpoint/restart |
598 | jobs. | 598 | jobs. |
599 | 599 | ||
600 | config CGROUP_FREEZER | 600 | config CGROUP_FREEZER |
601 | bool "Freezer cgroup subsystem" | 601 | bool "Freezer cgroup subsystem" |
602 | help | 602 | help |
603 | Provides a way to freeze and unfreeze all tasks in a | 603 | Provides a way to freeze and unfreeze all tasks in a |
604 | cgroup. | 604 | cgroup. |
605 | 605 | ||
606 | config CGROUP_DEVICE | 606 | config CGROUP_DEVICE |
607 | bool "Device controller for cgroups" | 607 | bool "Device controller for cgroups" |
608 | help | 608 | help |
609 | Provides a cgroup implementing whitelists for devices which | 609 | Provides a cgroup implementing whitelists for devices which |
610 | a process in the cgroup can mknod or open. | 610 | a process in the cgroup can mknod or open. |
611 | 611 | ||
612 | config CPUSETS | 612 | config CPUSETS |
613 | bool "Cpuset support" | 613 | bool "Cpuset support" |
614 | help | 614 | help |
615 | This option will let you create and manage CPUSETs which | 615 | This option will let you create and manage CPUSETs which |
616 | allow dynamically partitioning a system into sets of CPUs and | 616 | allow dynamically partitioning a system into sets of CPUs and |
617 | Memory Nodes and assigning tasks to run only within those sets. | 617 | Memory Nodes and assigning tasks to run only within those sets. |
618 | This is primarily useful on large SMP or NUMA systems. | 618 | This is primarily useful on large SMP or NUMA systems. |
619 | 619 | ||
620 | Say N if unsure. | 620 | Say N if unsure. |
621 | 621 | ||
622 | config PROC_PID_CPUSET | 622 | config PROC_PID_CPUSET |
623 | bool "Include legacy /proc/<pid>/cpuset file" | 623 | bool "Include legacy /proc/<pid>/cpuset file" |
624 | depends on CPUSETS | 624 | depends on CPUSETS |
625 | default y | 625 | default y |
626 | 626 | ||
627 | config CGROUP_CPUACCT | 627 | config CGROUP_CPUACCT |
628 | bool "Simple CPU accounting cgroup subsystem" | 628 | bool "Simple CPU accounting cgroup subsystem" |
629 | help | 629 | help |
630 | Provides a simple Resource Controller for monitoring the | 630 | Provides a simple Resource Controller for monitoring the |
631 | total CPU consumed by the tasks in a cgroup. | 631 | total CPU consumed by the tasks in a cgroup. |
632 | 632 | ||
633 | config RESOURCE_COUNTERS | 633 | config RESOURCE_COUNTERS |
634 | bool "Resource counters" | 634 | bool "Resource counters" |
635 | help | 635 | help |
636 | This option enables controller independent resource accounting | 636 | This option enables controller independent resource accounting |
637 | infrastructure that works with cgroups. | 637 | infrastructure that works with cgroups. |
638 | 638 | ||
639 | config CGROUP_MEM_RES_CTLR | 639 | config CGROUP_MEM_RES_CTLR |
640 | bool "Memory Resource Controller for Control Groups" | 640 | bool "Memory Resource Controller for Control Groups" |
641 | depends on RESOURCE_COUNTERS | 641 | depends on RESOURCE_COUNTERS |
642 | select MM_OWNER | 642 | select MM_OWNER |
643 | help | 643 | help |
644 | Provides a memory resource controller that manages both anonymous | 644 | Provides a memory resource controller that manages both anonymous |
645 | memory and page cache. (See Documentation/cgroups/memory.txt) | 645 | memory and page cache. (See Documentation/cgroups/memory.txt) |
646 | 646 | ||
647 | Note that setting this option increases fixed memory overhead | 647 | Note that setting this option increases fixed memory overhead |
648 | associated with each page of memory in the system. By this, | 648 | associated with each page of memory in the system. By this, |
649 | 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory | 649 | 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory |
650 | usage tracking struct at boot. Total amount of this is printed out | 650 | usage tracking struct at boot. Total amount of this is printed out |
651 | at boot. | 651 | at boot. |
652 | 652 | ||
653 | Only enable when you're ok with these trade offs and really | 653 | Only enable when you're ok with these trade offs and really |
654 | sure you need the memory resource controller. Even when you enable | 654 | sure you need the memory resource controller. Even when you enable |
655 | this, you can set "cgroup_disable=memory" at your boot option to | 655 | this, you can set "cgroup_disable=memory" at your boot option to |
656 | disable memory resource controller and you can avoid overheads. | 656 | disable memory resource controller and you can avoid overheads. |
657 | (and lose benefits of memory resource controller) | 657 | (and lose benefits of memory resource controller) |
658 | 658 | ||
659 | This config option also selects MM_OWNER config option, which | 659 | This config option also selects MM_OWNER config option, which |
660 | could in turn add some fork/exit overhead. | 660 | could in turn add some fork/exit overhead. |
661 | 661 | ||
662 | config CGROUP_MEM_RES_CTLR_SWAP | 662 | config CGROUP_MEM_RES_CTLR_SWAP |
663 | bool "Memory Resource Controller Swap Extension" | 663 | bool "Memory Resource Controller Swap Extension" |
664 | depends on CGROUP_MEM_RES_CTLR && SWAP | 664 | depends on CGROUP_MEM_RES_CTLR && SWAP |
665 | help | 665 | help |
666 | Add swap management feature to memory resource controller. When you | 666 | Add swap management feature to memory resource controller. When you |
667 | enable this, you can limit mem+swap usage per cgroup. In other words, | 667 | enable this, you can limit mem+swap usage per cgroup. In other words, |
668 | when you disable this, memory resource controller has no cares to | 668 | when you disable this, memory resource controller has no cares to |
669 | usage of swap...a process can exhaust all of the swap. This extension | 669 | usage of swap...a process can exhaust all of the swap. This extension |
670 | is useful when you want to avoid exhaustion swap but this itself | 670 | is useful when you want to avoid exhaustion swap but this itself |
671 | adds more overheads and consumes memory for remembering information. | 671 | adds more overheads and consumes memory for remembering information. |
672 | Especially if you use 32bit system or small memory system, please | 672 | Especially if you use 32bit system or small memory system, please |
673 | be careful about enabling this. When memory resource controller | 673 | be careful about enabling this. When memory resource controller |
674 | is disabled by boot option, this will be automatically disabled and | 674 | is disabled by boot option, this will be automatically disabled and |
675 | there will be no overhead from this. Even when you set this config=y, | 675 | there will be no overhead from this. Even when you set this config=y, |
676 | if boot option "noswapaccount" is set, swap will not be accounted. | 676 | if boot option "noswapaccount" is set, swap will not be accounted. |
677 | Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page | 677 | Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page |
678 | size is 4096bytes, 512k per 1Gbytes of swap. | 678 | size is 4096bytes, 512k per 1Gbytes of swap. |
679 | config CGROUP_MEM_RES_CTLR_SWAP_ENABLED | 679 | config CGROUP_MEM_RES_CTLR_SWAP_ENABLED |
680 | bool "Memory Resource Controller Swap Extension enabled by default" | 680 | bool "Memory Resource Controller Swap Extension enabled by default" |
681 | depends on CGROUP_MEM_RES_CTLR_SWAP | 681 | depends on CGROUP_MEM_RES_CTLR_SWAP |
682 | default y | 682 | default y |
683 | help | 683 | help |
684 | Memory Resource Controller Swap Extension comes with its price in | 684 | Memory Resource Controller Swap Extension comes with its price in |
685 | a bigger memory consumption. General purpose distribution kernels | 685 | a bigger memory consumption. General purpose distribution kernels |
686 | which want to enable the feature but keep it disabled by default | 686 | which want to enable the feature but keep it disabled by default |
687 | and let the user enable it by swapaccount boot command line | 687 | and let the user enable it by swapaccount boot command line |
688 | parameter should have this option unselected. | 688 | parameter should have this option unselected. |
689 | For those who want to have the feature enabled by default should | 689 | For those who want to have the feature enabled by default should |
690 | select this option (if, for some reason, they need to disable it | 690 | select this option (if, for some reason, they need to disable it |
691 | then noswapaccount does the trick). | 691 | then noswapaccount does the trick). |
692 | 692 | ||
693 | config CGROUP_PERF | 693 | config CGROUP_PERF |
694 | bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" | 694 | bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" |
695 | depends on PERF_EVENTS && CGROUPS | 695 | depends on PERF_EVENTS && CGROUPS |
696 | help | 696 | help |
697 | This option extends the per-cpu mode to restrict monitoring to | 697 | This option extends the per-cpu mode to restrict monitoring to |
698 | threads which belong to the cgroup specified and run on the | 698 | threads which belong to the cgroup specified and run on the |
699 | designated cpu. | 699 | designated cpu. |
700 | 700 | ||
701 | Say N if unsure. | 701 | Say N if unsure. |
702 | 702 | ||
703 | menuconfig CGROUP_SCHED | 703 | menuconfig CGROUP_SCHED |
704 | bool "Group CPU scheduler" | 704 | bool "Group CPU scheduler" |
705 | depends on EXPERIMENTAL | 705 | depends on EXPERIMENTAL |
706 | default n | 706 | default n |
707 | help | 707 | help |
708 | This feature lets CPU scheduler recognize task groups and control CPU | 708 | This feature lets CPU scheduler recognize task groups and control CPU |
709 | bandwidth allocation to such task groups. It uses cgroups to group | 709 | bandwidth allocation to such task groups. It uses cgroups to group |
710 | tasks. | 710 | tasks. |
711 | 711 | ||
712 | if CGROUP_SCHED | 712 | if CGROUP_SCHED |
713 | config FAIR_GROUP_SCHED | 713 | config FAIR_GROUP_SCHED |
714 | bool "Group scheduling for SCHED_OTHER" | 714 | bool "Group scheduling for SCHED_OTHER" |
715 | depends on CGROUP_SCHED | 715 | depends on CGROUP_SCHED |
716 | default CGROUP_SCHED | 716 | default CGROUP_SCHED |
717 | 717 | ||
718 | config RT_GROUP_SCHED | 718 | config RT_GROUP_SCHED |
719 | bool "Group scheduling for SCHED_RR/FIFO" | 719 | bool "Group scheduling for SCHED_RR/FIFO" |
720 | depends on EXPERIMENTAL | 720 | depends on EXPERIMENTAL |
721 | depends on CGROUP_SCHED | 721 | depends on CGROUP_SCHED |
722 | default n | 722 | default n |
723 | help | 723 | help |
724 | This feature lets you explicitly allocate real CPU bandwidth | 724 | This feature lets you explicitly allocate real CPU bandwidth |
725 | to task groups. If enabled, it will also make it impossible to | 725 | to task groups. If enabled, it will also make it impossible to |
726 | schedule realtime tasks for non-root users until you allocate | 726 | schedule realtime tasks for non-root users until you allocate |
727 | realtime bandwidth for them. | 727 | realtime bandwidth for them. |
728 | See Documentation/scheduler/sched-rt-group.txt for more information. | 728 | See Documentation/scheduler/sched-rt-group.txt for more information. |
729 | 729 | ||
730 | endif #CGROUP_SCHED | 730 | endif #CGROUP_SCHED |
731 | 731 | ||
732 | config BLK_CGROUP | 732 | config BLK_CGROUP |
733 | tristate "Block IO controller" | 733 | tristate "Block IO controller" |
734 | depends on BLOCK | 734 | depends on BLOCK |
735 | default n | 735 | default n |
736 | ---help--- | 736 | ---help--- |
737 | Generic block IO controller cgroup interface. This is the common | 737 | Generic block IO controller cgroup interface. This is the common |
738 | cgroup interface which should be used by various IO controlling | 738 | cgroup interface which should be used by various IO controlling |
739 | policies. | 739 | policies. |
740 | 740 | ||
741 | Currently, CFQ IO scheduler uses it to recognize task groups and | 741 | Currently, CFQ IO scheduler uses it to recognize task groups and |
742 | control disk bandwidth allocation (proportional time slice allocation) | 742 | control disk bandwidth allocation (proportional time slice allocation) |
743 | to such task groups. It is also used by bio throttling logic in | 743 | to such task groups. It is also used by bio throttling logic in |
744 | block layer to implement upper limit in IO rates on a device. | 744 | block layer to implement upper limit in IO rates on a device. |
745 | 745 | ||
746 | This option only enables generic Block IO controller infrastructure. | 746 | This option only enables generic Block IO controller infrastructure. |
747 | One needs to also enable actual IO controlling logic/policy. For | 747 | One needs to also enable actual IO controlling logic/policy. For |
748 | enabling proportional weight division of disk bandwidth in CFQ, set | 748 | enabling proportional weight division of disk bandwidth in CFQ, set |
749 | CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set | 749 | CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set |
750 | CONFIG_BLK_DEV_THROTTLING=y. | 750 | CONFIG_BLK_DEV_THROTTLING=y. |
751 | 751 | ||
752 | See Documentation/cgroups/blkio-controller.txt for more information. | 752 | See Documentation/cgroups/blkio-controller.txt for more information. |
753 | 753 | ||
754 | config DEBUG_BLK_CGROUP | 754 | config DEBUG_BLK_CGROUP |
755 | bool "Enable Block IO controller debugging" | 755 | bool "Enable Block IO controller debugging" |
756 | depends on BLK_CGROUP | 756 | depends on BLK_CGROUP |
757 | default n | 757 | default n |
758 | ---help--- | 758 | ---help--- |
759 | Enable some debugging help. Currently it exports additional stat | 759 | Enable some debugging help. Currently it exports additional stat |
760 | files in a cgroup which can be useful for debugging. | 760 | files in a cgroup which can be useful for debugging. |
761 | 761 | ||
762 | endif # CGROUPS | 762 | endif # CGROUPS |
763 | 763 | ||
764 | menuconfig NAMESPACES | 764 | menuconfig NAMESPACES |
765 | bool "Namespaces support" if EXPERT | 765 | bool "Namespaces support" if EXPERT |
766 | default !EXPERT | 766 | default !EXPERT |
767 | help | 767 | help |
768 | Provides the way to make tasks work with different objects using | 768 | Provides the way to make tasks work with different objects using |
769 | the same id. For example same IPC id may refer to different objects | 769 | the same id. For example same IPC id may refer to different objects |
770 | or same user id or pid may refer to different tasks when used in | 770 | or same user id or pid may refer to different tasks when used in |
771 | different namespaces. | 771 | different namespaces. |
772 | 772 | ||
773 | if NAMESPACES | 773 | if NAMESPACES |
774 | 774 | ||
775 | config UTS_NS | 775 | config UTS_NS |
776 | bool "UTS namespace" | 776 | bool "UTS namespace" |
777 | default y | 777 | default y |
778 | help | 778 | help |
779 | In this namespace tasks see different info provided with the | 779 | In this namespace tasks see different info provided with the |
780 | uname() system call | 780 | uname() system call |
781 | 781 | ||
782 | config IPC_NS | 782 | config IPC_NS |
783 | bool "IPC namespace" | 783 | bool "IPC namespace" |
784 | depends on (SYSVIPC || POSIX_MQUEUE) | 784 | depends on (SYSVIPC || POSIX_MQUEUE) |
785 | default y | 785 | default y |
786 | help | 786 | help |
787 | In this namespace tasks work with IPC ids which correspond to | 787 | In this namespace tasks work with IPC ids which correspond to |
788 | different IPC objects in different namespaces. | 788 | different IPC objects in different namespaces. |
789 | 789 | ||
790 | config USER_NS | 790 | config USER_NS |
791 | bool "User namespace (EXPERIMENTAL)" | 791 | bool "User namespace (EXPERIMENTAL)" |
792 | depends on EXPERIMENTAL | 792 | depends on EXPERIMENTAL |
793 | default y | 793 | default y |
794 | help | 794 | help |
795 | This allows containers, i.e. vservers, to use user namespaces | 795 | This allows containers, i.e. vservers, to use user namespaces |
796 | to provide different user info for different servers. | 796 | to provide different user info for different servers. |
797 | If unsure, say N. | 797 | If unsure, say N. |
798 | 798 | ||
799 | config PID_NS | 799 | config PID_NS |
800 | bool "PID Namespaces" | 800 | bool "PID Namespaces" |
801 | default y | 801 | default y |
802 | help | 802 | help |
803 | Support process id namespaces. This allows having multiple | 803 | Support process id namespaces. This allows having multiple |
804 | processes with the same pid as long as they are in different | 804 | processes with the same pid as long as they are in different |
805 | pid namespaces. This is a building block of containers. | 805 | pid namespaces. This is a building block of containers. |
806 | 806 | ||
807 | config NET_NS | 807 | config NET_NS |
808 | bool "Network namespace" | 808 | bool "Network namespace" |
809 | depends on NET | 809 | depends on NET |
810 | default y | 810 | default y |
811 | help | 811 | help |
812 | Allow user space to create what appear to be multiple instances | 812 | Allow user space to create what appear to be multiple instances |
813 | of the network stack. | 813 | of the network stack. |
814 | 814 | ||
815 | endif # NAMESPACES | 815 | endif # NAMESPACES |
816 | 816 | ||
817 | config SCHED_AUTOGROUP | 817 | config SCHED_AUTOGROUP |
818 | bool "Automatic process group scheduling" | 818 | bool "Automatic process group scheduling" |
819 | select EVENTFD | 819 | select EVENTFD |
820 | select CGROUPS | 820 | select CGROUPS |
821 | select CGROUP_SCHED | 821 | select CGROUP_SCHED |
822 | select FAIR_GROUP_SCHED | 822 | select FAIR_GROUP_SCHED |
823 | help | 823 | help |
824 | This option optimizes the scheduler for common desktop workloads by | 824 | This option optimizes the scheduler for common desktop workloads by |
825 | automatically creating and populating task groups. This separation | 825 | automatically creating and populating task groups. This separation |
826 | of workloads isolates aggressive CPU burners (like build jobs) from | 826 | of workloads isolates aggressive CPU burners (like build jobs) from |
827 | desktop applications. Task group autogeneration is currently based | 827 | desktop applications. Task group autogeneration is currently based |
828 | upon task session. | 828 | upon task session. |
829 | 829 | ||
830 | config SCHED_TTWU_QUEUE | ||
831 | bool | ||
832 | depends on !SPARC32 | ||
833 | default y | ||
834 | |||
835 | config MM_OWNER | 830 | config MM_OWNER |
836 | bool | 831 | bool |
837 | 832 | ||
838 | config SYSFS_DEPRECATED | 833 | config SYSFS_DEPRECATED |
839 | bool "Enable deprecated sysfs features to support old userspace tools" | 834 | bool "Enable deprecated sysfs features to support old userspace tools" |
840 | depends on SYSFS | 835 | depends on SYSFS |
841 | default n | 836 | default n |
842 | help | 837 | help |
843 | This option adds code that switches the layout of the "block" class | 838 | This option adds code that switches the layout of the "block" class |
844 | devices, to not show up in /sys/class/block/, but only in | 839 | devices, to not show up in /sys/class/block/, but only in |
845 | /sys/block/. | 840 | /sys/block/. |
846 | 841 | ||
847 | This switch is only active when the sysfs.deprecated=1 boot option is | 842 | This switch is only active when the sysfs.deprecated=1 boot option is |
848 | passed or the SYSFS_DEPRECATED_V2 option is set. | 843 | passed or the SYSFS_DEPRECATED_V2 option is set. |
849 | 844 | ||
850 | This option allows new kernels to run on old distributions and tools, | 845 | This option allows new kernels to run on old distributions and tools, |
851 | which might get confused by /sys/class/block/. Since 2007/2008 all | 846 | which might get confused by /sys/class/block/. Since 2007/2008 all |
852 | major distributions and tools handle this just fine. | 847 | major distributions and tools handle this just fine. |
853 | 848 | ||
854 | Recent distributions and userspace tools after 2009/2010 depend on | 849 | Recent distributions and userspace tools after 2009/2010 depend on |
855 | the existence of /sys/class/block/, and will not work with this | 850 | the existence of /sys/class/block/, and will not work with this |
856 | option enabled. | 851 | option enabled. |
857 | 852 | ||
858 | Only if you are using a new kernel on an old distribution, you might | 853 | Only if you are using a new kernel on an old distribution, you might |
859 | need to say Y here. | 854 | need to say Y here. |
860 | 855 | ||
861 | config SYSFS_DEPRECATED_V2 | 856 | config SYSFS_DEPRECATED_V2 |
862 | bool "Enable deprecated sysfs features by default" | 857 | bool "Enable deprecated sysfs features by default" |
863 | default n | 858 | default n |
864 | depends on SYSFS | 859 | depends on SYSFS |
865 | depends on SYSFS_DEPRECATED | 860 | depends on SYSFS_DEPRECATED |
866 | help | 861 | help |
867 | Enable deprecated sysfs by default. | 862 | Enable deprecated sysfs by default. |
868 | 863 | ||
869 | See the CONFIG_SYSFS_DEPRECATED option for more details about this | 864 | See the CONFIG_SYSFS_DEPRECATED option for more details about this |
870 | option. | 865 | option. |
871 | 866 | ||
872 | Only if you are using a new kernel on an old distribution, you might | 867 | Only if you are using a new kernel on an old distribution, you might |
873 | need to say Y here. Even then, odds are you would not need it | 868 | need to say Y here. Even then, odds are you would not need it |
874 | enabled, you can always pass the boot option if absolutely necessary. | 869 | enabled, you can always pass the boot option if absolutely necessary. |
875 | 870 | ||
876 | config RELAY | 871 | config RELAY |
877 | bool "Kernel->user space relay support (formerly relayfs)" | 872 | bool "Kernel->user space relay support (formerly relayfs)" |
878 | help | 873 | help |
879 | This option enables support for relay interface support in | 874 | This option enables support for relay interface support in |
880 | certain file systems (such as debugfs). | 875 | certain file systems (such as debugfs). |
881 | It is designed to provide an efficient mechanism for tools and | 876 | It is designed to provide an efficient mechanism for tools and |
882 | facilities to relay large amounts of data from kernel space to | 877 | facilities to relay large amounts of data from kernel space to |
883 | user space. | 878 | user space. |
884 | 879 | ||
885 | If unsure, say N. | 880 | If unsure, say N. |
886 | 881 | ||
887 | config BLK_DEV_INITRD | 882 | config BLK_DEV_INITRD |
888 | bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" | 883 | bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" |
889 | depends on BROKEN || !FRV | 884 | depends on BROKEN || !FRV |
890 | help | 885 | help |
891 | The initial RAM filesystem is a ramfs which is loaded by the | 886 | The initial RAM filesystem is a ramfs which is loaded by the |
892 | boot loader (loadlin or lilo) and that is mounted as root | 887 | boot loader (loadlin or lilo) and that is mounted as root |
893 | before the normal boot procedure. It is typically used to | 888 | before the normal boot procedure. It is typically used to |
894 | load modules needed to mount the "real" root file system, | 889 | load modules needed to mount the "real" root file system, |
895 | etc. See <file:Documentation/initrd.txt> for details. | 890 | etc. See <file:Documentation/initrd.txt> for details. |
896 | 891 | ||
897 | If RAM disk support (BLK_DEV_RAM) is also included, this | 892 | If RAM disk support (BLK_DEV_RAM) is also included, this |
898 | also enables initial RAM disk (initrd) support and adds | 893 | also enables initial RAM disk (initrd) support and adds |
899 | 15 Kbytes (more on some other architectures) to the kernel size. | 894 | 15 Kbytes (more on some other architectures) to the kernel size. |
900 | 895 | ||
901 | If unsure say Y. | 896 | If unsure say Y. |
902 | 897 | ||
903 | if BLK_DEV_INITRD | 898 | if BLK_DEV_INITRD |
904 | 899 | ||
905 | source "usr/Kconfig" | 900 | source "usr/Kconfig" |
906 | 901 | ||
907 | endif | 902 | endif |
908 | 903 | ||
909 | config CC_OPTIMIZE_FOR_SIZE | 904 | config CC_OPTIMIZE_FOR_SIZE |
910 | bool "Optimize for size" | 905 | bool "Optimize for size" |
911 | default y | 906 | default y |
912 | help | 907 | help |
913 | Enabling this option will pass "-Os" instead of "-O2" to gcc | 908 | Enabling this option will pass "-Os" instead of "-O2" to gcc |
914 | resulting in a smaller kernel. | 909 | resulting in a smaller kernel. |
915 | 910 | ||
916 | If unsure, say Y. | 911 | If unsure, say Y. |
917 | 912 | ||
918 | config SYSCTL | 913 | config SYSCTL |
919 | bool | 914 | bool |
920 | 915 | ||
921 | config ANON_INODES | 916 | config ANON_INODES |
922 | bool | 917 | bool |
923 | 918 | ||
924 | menuconfig EXPERT | 919 | menuconfig EXPERT |
925 | bool "Configure standard kernel features (expert users)" | 920 | bool "Configure standard kernel features (expert users)" |
926 | help | 921 | help |
927 | This option allows certain base kernel options and settings | 922 | This option allows certain base kernel options and settings |
928 | to be disabled or tweaked. This is for specialized | 923 | to be disabled or tweaked. This is for specialized |
929 | environments which can tolerate a "non-standard" kernel. | 924 | environments which can tolerate a "non-standard" kernel. |
930 | Only use this if you really know what you are doing. | 925 | Only use this if you really know what you are doing. |
931 | 926 | ||
932 | config EMBEDDED | 927 | config EMBEDDED |
933 | bool "Embedded system" | 928 | bool "Embedded system" |
934 | select EXPERT | 929 | select EXPERT |
935 | help | 930 | help |
936 | This option should be enabled if compiling the kernel for | 931 | This option should be enabled if compiling the kernel for |
937 | an embedded system so certain expert options are available | 932 | an embedded system so certain expert options are available |
938 | for configuration. | 933 | for configuration. |
939 | 934 | ||
940 | config UID16 | 935 | config UID16 |
941 | bool "Enable 16-bit UID system calls" if EXPERT | 936 | bool "Enable 16-bit UID system calls" if EXPERT |
942 | depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION) | 937 | depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION) |
943 | default y | 938 | default y |
944 | help | 939 | help |
945 | This enables the legacy 16-bit UID syscall wrappers. | 940 | This enables the legacy 16-bit UID syscall wrappers. |
946 | 941 | ||
947 | config SYSCTL_SYSCALL | 942 | config SYSCTL_SYSCALL |
948 | bool "Sysctl syscall support" if EXPERT | 943 | bool "Sysctl syscall support" if EXPERT |
949 | depends on PROC_SYSCTL | 944 | depends on PROC_SYSCTL |
950 | default y | 945 | default y |
951 | select SYSCTL | 946 | select SYSCTL |
952 | ---help--- | 947 | ---help--- |
953 | sys_sysctl uses binary paths that have been found challenging | 948 | sys_sysctl uses binary paths that have been found challenging |
954 | to properly maintain and use. The interface in /proc/sys | 949 | to properly maintain and use. The interface in /proc/sys |
955 | using paths with ascii names is now the primary path to this | 950 | using paths with ascii names is now the primary path to this |
956 | information. | 951 | information. |
957 | 952 | ||
958 | Almost nothing using the binary sysctl interface so if you are | 953 | Almost nothing using the binary sysctl interface so if you are |
959 | trying to save some space it is probably safe to disable this, | 954 | trying to save some space it is probably safe to disable this, |
960 | making your kernel marginally smaller. | 955 | making your kernel marginally smaller. |
961 | 956 | ||
962 | If unsure say Y here. | 957 | If unsure say Y here. |
963 | 958 | ||
964 | config KALLSYMS | 959 | config KALLSYMS |
965 | bool "Load all symbols for debugging/ksymoops" if EXPERT | 960 | bool "Load all symbols for debugging/ksymoops" if EXPERT |
966 | default y | 961 | default y |
967 | help | 962 | help |
968 | Say Y here to let the kernel print out symbolic crash information and | 963 | Say Y here to let the kernel print out symbolic crash information and |
969 | symbolic stack backtraces. This increases the size of the kernel | 964 | symbolic stack backtraces. This increases the size of the kernel |
970 | somewhat, as all symbols have to be loaded into the kernel image. | 965 | somewhat, as all symbols have to be loaded into the kernel image. |
971 | 966 | ||
972 | config KALLSYMS_ALL | 967 | config KALLSYMS_ALL |
973 | bool "Include all symbols in kallsyms" | 968 | bool "Include all symbols in kallsyms" |
974 | depends on DEBUG_KERNEL && KALLSYMS | 969 | depends on DEBUG_KERNEL && KALLSYMS |
975 | help | 970 | help |
976 | Normally kallsyms only contains the symbols of functions, for nicer | 971 | Normally kallsyms only contains the symbols of functions, for nicer |
977 | OOPS messages. Some debuggers can use kallsyms for other | 972 | OOPS messages. Some debuggers can use kallsyms for other |
978 | symbols too: say Y here to include all symbols, if you need them | 973 | symbols too: say Y here to include all symbols, if you need them |
979 | and you don't care about adding 300k to the size of your kernel. | 974 | and you don't care about adding 300k to the size of your kernel. |
980 | 975 | ||
981 | Say N. | 976 | Say N. |
982 | 977 | ||
983 | config KALLSYMS_EXTRA_PASS | 978 | config KALLSYMS_EXTRA_PASS |
984 | bool "Do an extra kallsyms pass" | 979 | bool "Do an extra kallsyms pass" |
985 | depends on KALLSYMS | 980 | depends on KALLSYMS |
986 | help | 981 | help |
987 | If kallsyms is not working correctly, the build will fail with | 982 | If kallsyms is not working correctly, the build will fail with |
988 | inconsistent kallsyms data. If that occurs, log a bug report and | 983 | inconsistent kallsyms data. If that occurs, log a bug report and |
989 | turn on KALLSYMS_EXTRA_PASS which should result in a stable build. | 984 | turn on KALLSYMS_EXTRA_PASS which should result in a stable build. |
990 | Always say N here unless you find a bug in kallsyms, which must be | 985 | Always say N here unless you find a bug in kallsyms, which must be |
991 | reported. KALLSYMS_EXTRA_PASS is only a temporary workaround while | 986 | reported. KALLSYMS_EXTRA_PASS is only a temporary workaround while |
992 | you wait for kallsyms to be fixed. | 987 | you wait for kallsyms to be fixed. |
993 | 988 | ||
994 | 989 | ||
995 | config HOTPLUG | 990 | config HOTPLUG |
996 | bool "Support for hot-pluggable devices" if EXPERT | 991 | bool "Support for hot-pluggable devices" if EXPERT |
997 | default y | 992 | default y |
998 | help | 993 | help |
999 | This option is provided for the case where no hotplug or uevent | 994 | This option is provided for the case where no hotplug or uevent |
1000 | capabilities is wanted by the kernel. You should only consider | 995 | capabilities is wanted by the kernel. You should only consider |
1001 | disabling this option for embedded systems that do not use modules, a | 996 | disabling this option for embedded systems that do not use modules, a |
1002 | dynamic /dev tree, or dynamic device discovery. Just say Y. | 997 | dynamic /dev tree, or dynamic device discovery. Just say Y. |
1003 | 998 | ||
1004 | config PRINTK | 999 | config PRINTK |
1005 | default y | 1000 | default y |
1006 | bool "Enable support for printk" if EXPERT | 1001 | bool "Enable support for printk" if EXPERT |
1007 | help | 1002 | help |
1008 | This option enables normal printk support. Removing it | 1003 | This option enables normal printk support. Removing it |
1009 | eliminates most of the message strings from the kernel image | 1004 | eliminates most of the message strings from the kernel image |
1010 | and makes the kernel more or less silent. As this makes it | 1005 | and makes the kernel more or less silent. As this makes it |
1011 | very difficult to diagnose system problems, saying N here is | 1006 | very difficult to diagnose system problems, saying N here is |
1012 | strongly discouraged. | 1007 | strongly discouraged. |
1013 | 1008 | ||
1014 | config BUG | 1009 | config BUG |
1015 | bool "BUG() support" if EXPERT | 1010 | bool "BUG() support" if EXPERT |
1016 | default y | 1011 | default y |
1017 | help | 1012 | help |
1018 | Disabling this option eliminates support for BUG and WARN, reducing | 1013 | Disabling this option eliminates support for BUG and WARN, reducing |
1019 | the size of your kernel image and potentially quietly ignoring | 1014 | the size of your kernel image and potentially quietly ignoring |
1020 | numerous fatal conditions. You should only consider disabling this | 1015 | numerous fatal conditions. You should only consider disabling this |
1021 | option for embedded systems with no facilities for reporting errors. | 1016 | option for embedded systems with no facilities for reporting errors. |
1022 | Just say Y. | 1017 | Just say Y. |
1023 | 1018 | ||
1024 | config ELF_CORE | 1019 | config ELF_CORE |
1025 | default y | 1020 | default y |
1026 | bool "Enable ELF core dumps" if EXPERT | 1021 | bool "Enable ELF core dumps" if EXPERT |
1027 | help | 1022 | help |
1028 | Enable support for generating core dumps. Disabling saves about 4k. | 1023 | Enable support for generating core dumps. Disabling saves about 4k. |
1029 | 1024 | ||
1030 | config PCSPKR_PLATFORM | 1025 | config PCSPKR_PLATFORM |
1031 | bool "Enable PC-Speaker support" if EXPERT | 1026 | bool "Enable PC-Speaker support" if EXPERT |
1032 | depends on ALPHA || X86 || MIPS || PPC_PREP || PPC_CHRP || PPC_PSERIES | 1027 | depends on ALPHA || X86 || MIPS || PPC_PREP || PPC_CHRP || PPC_PSERIES |
1033 | default y | 1028 | default y |
1034 | help | 1029 | help |
1035 | This option allows to disable the internal PC-Speaker | 1030 | This option allows to disable the internal PC-Speaker |
1036 | support, saving some memory. | 1031 | support, saving some memory. |
1037 | 1032 | ||
1038 | config BASE_FULL | 1033 | config BASE_FULL |
1039 | default y | 1034 | default y |
1040 | bool "Enable full-sized data structures for core" if EXPERT | 1035 | bool "Enable full-sized data structures for core" if EXPERT |
1041 | help | 1036 | help |
1042 | Disabling this option reduces the size of miscellaneous core | 1037 | Disabling this option reduces the size of miscellaneous core |
1043 | kernel data structures. This saves memory on small machines, | 1038 | kernel data structures. This saves memory on small machines, |
1044 | but may reduce performance. | 1039 | but may reduce performance. |
1045 | 1040 | ||
1046 | config FUTEX | 1041 | config FUTEX |
1047 | bool "Enable futex support" if EXPERT | 1042 | bool "Enable futex support" if EXPERT |
1048 | default y | 1043 | default y |
1049 | select RT_MUTEXES | 1044 | select RT_MUTEXES |
1050 | help | 1045 | help |
1051 | Disabling this option will cause the kernel to be built without | 1046 | Disabling this option will cause the kernel to be built without |
1052 | support for "fast userspace mutexes". The resulting kernel may not | 1047 | support for "fast userspace mutexes". The resulting kernel may not |
1053 | run glibc-based applications correctly. | 1048 | run glibc-based applications correctly. |
1054 | 1049 | ||
1055 | config EPOLL | 1050 | config EPOLL |
1056 | bool "Enable eventpoll support" if EXPERT | 1051 | bool "Enable eventpoll support" if EXPERT |
1057 | default y | 1052 | default y |
1058 | select ANON_INODES | 1053 | select ANON_INODES |
1059 | help | 1054 | help |
1060 | Disabling this option will cause the kernel to be built without | 1055 | Disabling this option will cause the kernel to be built without |
1061 | support for epoll family of system calls. | 1056 | support for epoll family of system calls. |
1062 | 1057 | ||
1063 | config SIGNALFD | 1058 | config SIGNALFD |
1064 | bool "Enable signalfd() system call" if EXPERT | 1059 | bool "Enable signalfd() system call" if EXPERT |
1065 | select ANON_INODES | 1060 | select ANON_INODES |
1066 | default y | 1061 | default y |
1067 | help | 1062 | help |
1068 | Enable the signalfd() system call that allows to receive signals | 1063 | Enable the signalfd() system call that allows to receive signals |
1069 | on a file descriptor. | 1064 | on a file descriptor. |
1070 | 1065 | ||
1071 | If unsure, say Y. | 1066 | If unsure, say Y. |
1072 | 1067 | ||
1073 | config TIMERFD | 1068 | config TIMERFD |
1074 | bool "Enable timerfd() system call" if EXPERT | 1069 | bool "Enable timerfd() system call" if EXPERT |
1075 | select ANON_INODES | 1070 | select ANON_INODES |
1076 | default y | 1071 | default y |
1077 | help | 1072 | help |
1078 | Enable the timerfd() system call that allows to receive timer | 1073 | Enable the timerfd() system call that allows to receive timer |
1079 | events on a file descriptor. | 1074 | events on a file descriptor. |
1080 | 1075 | ||
1081 | If unsure, say Y. | 1076 | If unsure, say Y. |
1082 | 1077 | ||
1083 | config EVENTFD | 1078 | config EVENTFD |
1084 | bool "Enable eventfd() system call" if EXPERT | 1079 | bool "Enable eventfd() system call" if EXPERT |
1085 | select ANON_INODES | 1080 | select ANON_INODES |
1086 | default y | 1081 | default y |
1087 | help | 1082 | help |
1088 | Enable the eventfd() system call that allows to receive both | 1083 | Enable the eventfd() system call that allows to receive both |
1089 | kernel notification (ie. KAIO) or userspace notifications. | 1084 | kernel notification (ie. KAIO) or userspace notifications. |
1090 | 1085 | ||
1091 | If unsure, say Y. | 1086 | If unsure, say Y. |
1092 | 1087 | ||
1093 | config SHMEM | 1088 | config SHMEM |
1094 | bool "Use full shmem filesystem" if EXPERT | 1089 | bool "Use full shmem filesystem" if EXPERT |
1095 | default y | 1090 | default y |
1096 | depends on MMU | 1091 | depends on MMU |
1097 | help | 1092 | help |
1098 | The shmem is an internal filesystem used to manage shared memory. | 1093 | The shmem is an internal filesystem used to manage shared memory. |
1099 | It is backed by swap and manages resource limits. It is also exported | 1094 | It is backed by swap and manages resource limits. It is also exported |
1100 | to userspace as tmpfs if TMPFS is enabled. Disabling this | 1095 | to userspace as tmpfs if TMPFS is enabled. Disabling this |
1101 | option replaces shmem and tmpfs with the much simpler ramfs code, | 1096 | option replaces shmem and tmpfs with the much simpler ramfs code, |
1102 | which may be appropriate on small systems without swap. | 1097 | which may be appropriate on small systems without swap. |
1103 | 1098 | ||
1104 | config AIO | 1099 | config AIO |
1105 | bool "Enable AIO support" if EXPERT | 1100 | bool "Enable AIO support" if EXPERT |
1106 | default y | 1101 | default y |
1107 | help | 1102 | help |
1108 | This option enables POSIX asynchronous I/O which may by used | 1103 | This option enables POSIX asynchronous I/O which may by used |
1109 | by some high performance threaded applications. Disabling | 1104 | by some high performance threaded applications. Disabling |
1110 | this option saves about 7k. | 1105 | this option saves about 7k. |
1111 | 1106 | ||
1112 | config HAVE_PERF_EVENTS | 1107 | config HAVE_PERF_EVENTS |
1113 | bool | 1108 | bool |
1114 | help | 1109 | help |
1115 | See tools/perf/design.txt for details. | 1110 | See tools/perf/design.txt for details. |
1116 | 1111 | ||
1117 | config PERF_USE_VMALLOC | 1112 | config PERF_USE_VMALLOC |
1118 | bool | 1113 | bool |
1119 | help | 1114 | help |
1120 | See tools/perf/design.txt for details | 1115 | See tools/perf/design.txt for details |
1121 | 1116 | ||
1122 | menu "Kernel Performance Events And Counters" | 1117 | menu "Kernel Performance Events And Counters" |
1123 | 1118 | ||
1124 | config PERF_EVENTS | 1119 | config PERF_EVENTS |
1125 | bool "Kernel performance events and counters" | 1120 | bool "Kernel performance events and counters" |
1126 | default y if (PROFILING || PERF_COUNTERS) | 1121 | default y if (PROFILING || PERF_COUNTERS) |
1127 | depends on HAVE_PERF_EVENTS | 1122 | depends on HAVE_PERF_EVENTS |
1128 | select ANON_INODES | 1123 | select ANON_INODES |
1129 | select IRQ_WORK | 1124 | select IRQ_WORK |
1130 | help | 1125 | help |
1131 | Enable kernel support for various performance events provided | 1126 | Enable kernel support for various performance events provided |
1132 | by software and hardware. | 1127 | by software and hardware. |
1133 | 1128 | ||
1134 | Software events are supported either built-in or via the | 1129 | Software events are supported either built-in or via the |
1135 | use of generic tracepoints. | 1130 | use of generic tracepoints. |
1136 | 1131 | ||
1137 | Most modern CPUs support performance events via performance | 1132 | Most modern CPUs support performance events via performance |
1138 | counter registers. These registers count the number of certain | 1133 | counter registers. These registers count the number of certain |
1139 | types of hw events: such as instructions executed, cachemisses | 1134 | types of hw events: such as instructions executed, cachemisses |
1140 | suffered, or branches mis-predicted - without slowing down the | 1135 | suffered, or branches mis-predicted - without slowing down the |
1141 | kernel or applications. These registers can also trigger interrupts | 1136 | kernel or applications. These registers can also trigger interrupts |
1142 | when a threshold number of events have passed - and can thus be | 1137 | when a threshold number of events have passed - and can thus be |
1143 | used to profile the code that runs on that CPU. | 1138 | used to profile the code that runs on that CPU. |
1144 | 1139 | ||
1145 | The Linux Performance Event subsystem provides an abstraction of | 1140 | The Linux Performance Event subsystem provides an abstraction of |
1146 | these software and hardware event capabilities, available via a | 1141 | these software and hardware event capabilities, available via a |
1147 | system call and used by the "perf" utility in tools/perf/. It | 1142 | system call and used by the "perf" utility in tools/perf/. It |
1148 | provides per task and per CPU counters, and it provides event | 1143 | provides per task and per CPU counters, and it provides event |
1149 | capabilities on top of those. | 1144 | capabilities on top of those. |
1150 | 1145 | ||
1151 | Say Y if unsure. | 1146 | Say Y if unsure. |
1152 | 1147 | ||
1153 | config PERF_COUNTERS | 1148 | config PERF_COUNTERS |
1154 | bool "Kernel performance counters (old config option)" | 1149 | bool "Kernel performance counters (old config option)" |
1155 | depends on HAVE_PERF_EVENTS | 1150 | depends on HAVE_PERF_EVENTS |
1156 | help | 1151 | help |
1157 | This config has been obsoleted by the PERF_EVENTS | 1152 | This config has been obsoleted by the PERF_EVENTS |
1158 | config option - please see that one for details. | 1153 | config option - please see that one for details. |
1159 | 1154 | ||
1160 | It has no effect on the kernel whether you enable | 1155 | It has no effect on the kernel whether you enable |
1161 | it or not, it is a compatibility placeholder. | 1156 | it or not, it is a compatibility placeholder. |
1162 | 1157 | ||
1163 | Say N if unsure. | 1158 | Say N if unsure. |
1164 | 1159 | ||
1165 | config DEBUG_PERF_USE_VMALLOC | 1160 | config DEBUG_PERF_USE_VMALLOC |
1166 | default n | 1161 | default n |
1167 | bool "Debug: use vmalloc to back perf mmap() buffers" | 1162 | bool "Debug: use vmalloc to back perf mmap() buffers" |
1168 | depends on PERF_EVENTS && DEBUG_KERNEL | 1163 | depends on PERF_EVENTS && DEBUG_KERNEL |
1169 | select PERF_USE_VMALLOC | 1164 | select PERF_USE_VMALLOC |
1170 | help | 1165 | help |
1171 | Use vmalloc memory to back perf mmap() buffers. | 1166 | Use vmalloc memory to back perf mmap() buffers. |
1172 | 1167 | ||
1173 | Mostly useful for debugging the vmalloc code on platforms | 1168 | Mostly useful for debugging the vmalloc code on platforms |
1174 | that don't require it. | 1169 | that don't require it. |
1175 | 1170 | ||
1176 | Say N if unsure. | 1171 | Say N if unsure. |
1177 | 1172 | ||
1178 | endmenu | 1173 | endmenu |
1179 | 1174 | ||
1180 | config VM_EVENT_COUNTERS | 1175 | config VM_EVENT_COUNTERS |
1181 | default y | 1176 | default y |
1182 | bool "Enable VM event counters for /proc/vmstat" if EXPERT | 1177 | bool "Enable VM event counters for /proc/vmstat" if EXPERT |
1183 | help | 1178 | help |
1184 | VM event counters are needed for event counts to be shown. | 1179 | VM event counters are needed for event counts to be shown. |
1185 | This option allows the disabling of the VM event counters | 1180 | This option allows the disabling of the VM event counters |
1186 | on EXPERT systems. /proc/vmstat will only show page counts | 1181 | on EXPERT systems. /proc/vmstat will only show page counts |
1187 | if VM event counters are disabled. | 1182 | if VM event counters are disabled. |
1188 | 1183 | ||
1189 | config PCI_QUIRKS | 1184 | config PCI_QUIRKS |
1190 | default y | 1185 | default y |
1191 | bool "Enable PCI quirk workarounds" if EXPERT | 1186 | bool "Enable PCI quirk workarounds" if EXPERT |
1192 | depends on PCI | 1187 | depends on PCI |
1193 | help | 1188 | help |
1194 | This enables workarounds for various PCI chipset | 1189 | This enables workarounds for various PCI chipset |
1195 | bugs/quirks. Disable this only if your target machine is | 1190 | bugs/quirks. Disable this only if your target machine is |
1196 | unaffected by PCI quirks. | 1191 | unaffected by PCI quirks. |
1197 | 1192 | ||
1198 | config SLUB_DEBUG | 1193 | config SLUB_DEBUG |
1199 | default y | 1194 | default y |
1200 | bool "Enable SLUB debugging support" if EXPERT | 1195 | bool "Enable SLUB debugging support" if EXPERT |
1201 | depends on SLUB && SYSFS | 1196 | depends on SLUB && SYSFS |
1202 | help | 1197 | help |
1203 | SLUB has extensive debug support features. Disabling these can | 1198 | SLUB has extensive debug support features. Disabling these can |
1204 | result in significant savings in code size. This also disables | 1199 | result in significant savings in code size. This also disables |
1205 | SLUB sysfs support. /sys/slab will not exist and there will be | 1200 | SLUB sysfs support. /sys/slab will not exist and there will be |
1206 | no support for cache validation etc. | 1201 | no support for cache validation etc. |
1207 | 1202 | ||
1208 | config COMPAT_BRK | 1203 | config COMPAT_BRK |
1209 | bool "Disable heap randomization" | 1204 | bool "Disable heap randomization" |
1210 | default y | 1205 | default y |
1211 | help | 1206 | help |
1212 | Randomizing heap placement makes heap exploits harder, but it | 1207 | Randomizing heap placement makes heap exploits harder, but it |
1213 | also breaks ancient binaries (including anything libc5 based). | 1208 | also breaks ancient binaries (including anything libc5 based). |
1214 | This option changes the bootup default to heap randomization | 1209 | This option changes the bootup default to heap randomization |
1215 | disabled, and can be overridden at runtime by setting | 1210 | disabled, and can be overridden at runtime by setting |
1216 | /proc/sys/kernel/randomize_va_space to 2. | 1211 | /proc/sys/kernel/randomize_va_space to 2. |
1217 | 1212 | ||
1218 | On non-ancient distros (post-2000 ones) N is usually a safe choice. | 1213 | On non-ancient distros (post-2000 ones) N is usually a safe choice. |
1219 | 1214 | ||
1220 | choice | 1215 | choice |
1221 | prompt "Choose SLAB allocator" | 1216 | prompt "Choose SLAB allocator" |
1222 | default SLUB | 1217 | default SLUB |
1223 | help | 1218 | help |
1224 | This option allows to select a slab allocator. | 1219 | This option allows to select a slab allocator. |
1225 | 1220 | ||
1226 | config SLAB | 1221 | config SLAB |
1227 | bool "SLAB" | 1222 | bool "SLAB" |
1228 | help | 1223 | help |
1229 | The regular slab allocator that is established and known to work | 1224 | The regular slab allocator that is established and known to work |
1230 | well in all environments. It organizes cache hot objects in | 1225 | well in all environments. It organizes cache hot objects in |
1231 | per cpu and per node queues. | 1226 | per cpu and per node queues. |
1232 | 1227 | ||
1233 | config SLUB | 1228 | config SLUB |
1234 | bool "SLUB (Unqueued Allocator)" | 1229 | bool "SLUB (Unqueued Allocator)" |
1235 | help | 1230 | help |
1236 | SLUB is a slab allocator that minimizes cache line usage | 1231 | SLUB is a slab allocator that minimizes cache line usage |
1237 | instead of managing queues of cached objects (SLAB approach). | 1232 | instead of managing queues of cached objects (SLAB approach). |
1238 | Per cpu caching is realized using slabs of objects instead | 1233 | Per cpu caching is realized using slabs of objects instead |
1239 | of queues of objects. SLUB can use memory efficiently | 1234 | of queues of objects. SLUB can use memory efficiently |
1240 | and has enhanced diagnostics. SLUB is the default choice for | 1235 | and has enhanced diagnostics. SLUB is the default choice for |
1241 | a slab allocator. | 1236 | a slab allocator. |
1242 | 1237 | ||
1243 | config SLOB | 1238 | config SLOB |
1244 | depends on EXPERT | 1239 | depends on EXPERT |
1245 | bool "SLOB (Simple Allocator)" | 1240 | bool "SLOB (Simple Allocator)" |
1246 | help | 1241 | help |
1247 | SLOB replaces the stock allocator with a drastically simpler | 1242 | SLOB replaces the stock allocator with a drastically simpler |
1248 | allocator. SLOB is generally more space efficient but | 1243 | allocator. SLOB is generally more space efficient but |
1249 | does not perform as well on large systems. | 1244 | does not perform as well on large systems. |
1250 | 1245 | ||
1251 | endchoice | 1246 | endchoice |
1252 | 1247 | ||
1253 | config MMAP_ALLOW_UNINITIALIZED | 1248 | config MMAP_ALLOW_UNINITIALIZED |
1254 | bool "Allow mmapped anonymous memory to be uninitialized" | 1249 | bool "Allow mmapped anonymous memory to be uninitialized" |
1255 | depends on EXPERT && !MMU | 1250 | depends on EXPERT && !MMU |
1256 | default n | 1251 | default n |
1257 | help | 1252 | help |
1258 | Normally, and according to the Linux spec, anonymous memory obtained | 1253 | Normally, and according to the Linux spec, anonymous memory obtained |
1259 | from mmap() has it's contents cleared before it is passed to | 1254 | from mmap() has it's contents cleared before it is passed to |
1260 | userspace. Enabling this config option allows you to request that | 1255 | userspace. Enabling this config option allows you to request that |
1261 | mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus | 1256 | mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus |
1262 | providing a huge performance boost. If this option is not enabled, | 1257 | providing a huge performance boost. If this option is not enabled, |
1263 | then the flag will be ignored. | 1258 | then the flag will be ignored. |
1264 | 1259 | ||
1265 | This is taken advantage of by uClibc's malloc(), and also by | 1260 | This is taken advantage of by uClibc's malloc(), and also by |
1266 | ELF-FDPIC binfmt's brk and stack allocator. | 1261 | ELF-FDPIC binfmt's brk and stack allocator. |
1267 | 1262 | ||
1268 | Because of the obvious security issues, this option should only be | 1263 | Because of the obvious security issues, this option should only be |
1269 | enabled on embedded devices where you control what is run in | 1264 | enabled on embedded devices where you control what is run in |
1270 | userspace. Since that isn't generally a problem on no-MMU systems, | 1265 | userspace. Since that isn't generally a problem on no-MMU systems, |
1271 | it is normally safe to say Y here. | 1266 | it is normally safe to say Y here. |
1272 | 1267 | ||
1273 | See Documentation/nommu-mmap.txt for more information. | 1268 | See Documentation/nommu-mmap.txt for more information. |
1274 | 1269 | ||
1275 | config PROFILING | 1270 | config PROFILING |
1276 | bool "Profiling support" | 1271 | bool "Profiling support" |
1277 | help | 1272 | help |
1278 | Say Y here to enable the extended profiling support mechanisms used | 1273 | Say Y here to enable the extended profiling support mechanisms used |
1279 | by profilers such as OProfile. | 1274 | by profilers such as OProfile. |
1280 | 1275 | ||
1281 | # | 1276 | # |
1282 | # Place an empty function call at each tracepoint site. Can be | 1277 | # Place an empty function call at each tracepoint site. Can be |
1283 | # dynamically changed for a probe function. | 1278 | # dynamically changed for a probe function. |
1284 | # | 1279 | # |
1285 | config TRACEPOINTS | 1280 | config TRACEPOINTS |
1286 | bool | 1281 | bool |
1287 | 1282 | ||
1288 | source "arch/Kconfig" | 1283 | source "arch/Kconfig" |
1289 | 1284 | ||
1290 | endmenu # General setup | 1285 | endmenu # General setup |
1291 | 1286 | ||
1292 | config HAVE_GENERIC_DMA_COHERENT | 1287 | config HAVE_GENERIC_DMA_COHERENT |
1293 | bool | 1288 | bool |
1294 | default n | 1289 | default n |
1295 | 1290 | ||
1296 | config SLABINFO | 1291 | config SLABINFO |
1297 | bool | 1292 | bool |
1298 | depends on PROC_FS | 1293 | depends on PROC_FS |
1299 | depends on SLAB || SLUB_DEBUG | 1294 | depends on SLAB || SLUB_DEBUG |
1300 | default y | 1295 | default y |
1301 | 1296 | ||
1302 | config RT_MUTEXES | 1297 | config RT_MUTEXES |
1303 | boolean | 1298 | boolean |
1304 | 1299 | ||
1305 | config BASE_SMALL | 1300 | config BASE_SMALL |
1306 | int | 1301 | int |
1307 | default 0 if BASE_FULL | 1302 | default 0 if BASE_FULL |
1308 | default 1 if !BASE_FULL | 1303 | default 1 if !BASE_FULL |
1309 | 1304 | ||
1310 | menuconfig MODULES | 1305 | menuconfig MODULES |
1311 | bool "Enable loadable module support" | 1306 | bool "Enable loadable module support" |
1312 | help | 1307 | help |
1313 | Kernel modules are small pieces of compiled code which can | 1308 | Kernel modules are small pieces of compiled code which can |
1314 | be inserted in the running kernel, rather than being | 1309 | be inserted in the running kernel, rather than being |
1315 | permanently built into the kernel. You use the "modprobe" | 1310 | permanently built into the kernel. You use the "modprobe" |
1316 | tool to add (and sometimes remove) them. If you say Y here, | 1311 | tool to add (and sometimes remove) them. If you say Y here, |
1317 | many parts of the kernel can be built as modules (by | 1312 | many parts of the kernel can be built as modules (by |
1318 | answering M instead of Y where indicated): this is most | 1313 | answering M instead of Y where indicated): this is most |
1319 | useful for infrequently used options which are not required | 1314 | useful for infrequently used options which are not required |
1320 | for booting. For more information, see the man pages for | 1315 | for booting. For more information, see the man pages for |
1321 | modprobe, lsmod, modinfo, insmod and rmmod. | 1316 | modprobe, lsmod, modinfo, insmod and rmmod. |
1322 | 1317 | ||
1323 | If you say Y here, you will need to run "make | 1318 | If you say Y here, you will need to run "make |
1324 | modules_install" to put the modules under /lib/modules/ | 1319 | modules_install" to put the modules under /lib/modules/ |
1325 | where modprobe can find them (you may need to be root to do | 1320 | where modprobe can find them (you may need to be root to do |
1326 | this). | 1321 | this). |
1327 | 1322 | ||
1328 | If unsure, say Y. | 1323 | If unsure, say Y. |
1329 | 1324 | ||
1330 | if MODULES | 1325 | if MODULES |
1331 | 1326 | ||
1332 | config MODULE_FORCE_LOAD | 1327 | config MODULE_FORCE_LOAD |
1333 | bool "Forced module loading" | 1328 | bool "Forced module loading" |
1334 | default n | 1329 | default n |
1335 | help | 1330 | help |
1336 | Allow loading of modules without version information (ie. modprobe | 1331 | Allow loading of modules without version information (ie. modprobe |
1337 | --force). Forced module loading sets the 'F' (forced) taint flag and | 1332 | --force). Forced module loading sets the 'F' (forced) taint flag and |
1338 | is usually a really bad idea. | 1333 | is usually a really bad idea. |
1339 | 1334 | ||
1340 | config MODULE_UNLOAD | 1335 | config MODULE_UNLOAD |
1341 | bool "Module unloading" | 1336 | bool "Module unloading" |
1342 | help | 1337 | help |
1343 | Without this option you will not be able to unload any | 1338 | Without this option you will not be able to unload any |
1344 | modules (note that some modules may not be unloadable | 1339 | modules (note that some modules may not be unloadable |
1345 | anyway), which makes your kernel smaller, faster | 1340 | anyway), which makes your kernel smaller, faster |
1346 | and simpler. If unsure, say Y. | 1341 | and simpler. If unsure, say Y. |
1347 | 1342 | ||
1348 | config MODULE_FORCE_UNLOAD | 1343 | config MODULE_FORCE_UNLOAD |
1349 | bool "Forced module unloading" | 1344 | bool "Forced module unloading" |
1350 | depends on MODULE_UNLOAD && EXPERIMENTAL | 1345 | depends on MODULE_UNLOAD && EXPERIMENTAL |
1351 | help | 1346 | help |
1352 | This option allows you to force a module to unload, even if the | 1347 | This option allows you to force a module to unload, even if the |
1353 | kernel believes it is unsafe: the kernel will remove the module | 1348 | kernel believes it is unsafe: the kernel will remove the module |
1354 | without waiting for anyone to stop using it (using the -f option to | 1349 | without waiting for anyone to stop using it (using the -f option to |
1355 | rmmod). This is mainly for kernel developers and desperate users. | 1350 | rmmod). This is mainly for kernel developers and desperate users. |
1356 | If unsure, say N. | 1351 | If unsure, say N. |
1357 | 1352 | ||
1358 | config MODVERSIONS | 1353 | config MODVERSIONS |
1359 | bool "Module versioning support" | 1354 | bool "Module versioning support" |
1360 | help | 1355 | help |
1361 | Usually, you have to use modules compiled with your kernel. | 1356 | Usually, you have to use modules compiled with your kernel. |
1362 | Saying Y here makes it sometimes possible to use modules | 1357 | Saying Y here makes it sometimes possible to use modules |
1363 | compiled for different kernels, by adding enough information | 1358 | compiled for different kernels, by adding enough information |
1364 | to the modules to (hopefully) spot any changes which would | 1359 | to the modules to (hopefully) spot any changes which would |
1365 | make them incompatible with the kernel you are running. If | 1360 | make them incompatible with the kernel you are running. If |
1366 | unsure, say N. | 1361 | unsure, say N. |
1367 | 1362 | ||
1368 | config MODULE_SRCVERSION_ALL | 1363 | config MODULE_SRCVERSION_ALL |
1369 | bool "Source checksum for all modules" | 1364 | bool "Source checksum for all modules" |
1370 | help | 1365 | help |
1371 | Modules which contain a MODULE_VERSION get an extra "srcversion" | 1366 | Modules which contain a MODULE_VERSION get an extra "srcversion" |
1372 | field inserted into their modinfo section, which contains a | 1367 | field inserted into their modinfo section, which contains a |
1373 | sum of the source files which made it. This helps maintainers | 1368 | sum of the source files which made it. This helps maintainers |
1374 | see exactly which source was used to build a module (since | 1369 | see exactly which source was used to build a module (since |
1375 | others sometimes change the module source without updating | 1370 | others sometimes change the module source without updating |
1376 | the version). With this option, such a "srcversion" field | 1371 | the version). With this option, such a "srcversion" field |
1377 | will be created for all modules. If unsure, say N. | 1372 | will be created for all modules. If unsure, say N. |
1378 | 1373 | ||
1379 | endif # MODULES | 1374 | endif # MODULES |
1380 | 1375 | ||
1381 | config INIT_ALL_POSSIBLE | 1376 | config INIT_ALL_POSSIBLE |
1382 | bool | 1377 | bool |
1383 | help | 1378 | help |
1384 | Back when each arch used to define their own cpu_online_map and | 1379 | Back when each arch used to define their own cpu_online_map and |
1385 | cpu_possible_map, some of them chose to initialize cpu_possible_map | 1380 | cpu_possible_map, some of them chose to initialize cpu_possible_map |
1386 | with all 1s, and others with all 0s. When they were centralised, | 1381 | with all 1s, and others with all 0s. When they were centralised, |
1387 | it was better to provide this option than to break all the archs | 1382 | it was better to provide this option than to break all the archs |
1388 | and have several arch maintainers pursuing me down dark alleys. | 1383 | and have several arch maintainers pursuing me down dark alleys. |
1389 | 1384 | ||
1390 | config STOP_MACHINE | 1385 | config STOP_MACHINE |
1391 | bool | 1386 | bool |
1392 | default y | 1387 | default y |
1393 | depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU | 1388 | depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU |
1394 | help | 1389 | help |
1395 | Need stop_machine() primitive. | 1390 | Need stop_machine() primitive. |
1396 | 1391 | ||
1397 | source "block/Kconfig" | 1392 | source "block/Kconfig" |
1398 | 1393 | ||
1399 | config PREEMPT_NOTIFIERS | 1394 | config PREEMPT_NOTIFIERS |
1400 | bool | 1395 | bool |
1401 | 1396 | ||
1402 | config PADATA | 1397 | config PADATA |
1403 | depends on SMP | 1398 | depends on SMP |
1404 | bool | 1399 | bool |
1405 | 1400 | ||
1406 | source "kernel/Kconfig.locks" | 1401 | source "kernel/Kconfig.locks" |
1407 | 1402 |
kernel/sched.c
1 | /* | 1 | /* |
2 | * kernel/sched.c | 2 | * kernel/sched.c |
3 | * | 3 | * |
4 | * Kernel scheduler and related syscalls | 4 | * Kernel scheduler and related syscalls |
5 | * | 5 | * |
6 | * Copyright (C) 1991-2002 Linus Torvalds | 6 | * Copyright (C) 1991-2002 Linus Torvalds |
7 | * | 7 | * |
8 | * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and | 8 | * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and |
9 | * make semaphores SMP safe | 9 | * make semaphores SMP safe |
10 | * 1998-11-19 Implemented schedule_timeout() and related stuff | 10 | * 1998-11-19 Implemented schedule_timeout() and related stuff |
11 | * by Andrea Arcangeli | 11 | * by Andrea Arcangeli |
12 | * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: | 12 | * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: |
13 | * hybrid priority-list and round-robin design with | 13 | * hybrid priority-list and round-robin design with |
14 | * an array-switch method of distributing timeslices | 14 | * an array-switch method of distributing timeslices |
15 | * and per-CPU runqueues. Cleanups and useful suggestions | 15 | * and per-CPU runqueues. Cleanups and useful suggestions |
16 | * by Davide Libenzi, preemptible kernel bits by Robert Love. | 16 | * by Davide Libenzi, preemptible kernel bits by Robert Love. |
17 | * 2003-09-03 Interactivity tuning by Con Kolivas. | 17 | * 2003-09-03 Interactivity tuning by Con Kolivas. |
18 | * 2004-04-02 Scheduler domains code by Nick Piggin | 18 | * 2004-04-02 Scheduler domains code by Nick Piggin |
19 | * 2007-04-15 Work begun on replacing all interactivity tuning with a | 19 | * 2007-04-15 Work begun on replacing all interactivity tuning with a |
20 | * fair scheduling design by Con Kolivas. | 20 | * fair scheduling design by Con Kolivas. |
21 | * 2007-05-05 Load balancing (smp-nice) and other improvements | 21 | * 2007-05-05 Load balancing (smp-nice) and other improvements |
22 | * by Peter Williams | 22 | * by Peter Williams |
23 | * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith | 23 | * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith |
24 | * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri | 24 | * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri |
25 | * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, | 25 | * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, |
26 | * Thomas Gleixner, Mike Kravetz | 26 | * Thomas Gleixner, Mike Kravetz |
27 | */ | 27 | */ |
28 | 28 | ||
29 | #include <linux/mm.h> | 29 | #include <linux/mm.h> |
30 | #include <linux/module.h> | 30 | #include <linux/module.h> |
31 | #include <linux/nmi.h> | 31 | #include <linux/nmi.h> |
32 | #include <linux/init.h> | 32 | #include <linux/init.h> |
33 | #include <linux/uaccess.h> | 33 | #include <linux/uaccess.h> |
34 | #include <linux/highmem.h> | 34 | #include <linux/highmem.h> |
35 | #include <asm/mmu_context.h> | 35 | #include <asm/mmu_context.h> |
36 | #include <linux/interrupt.h> | 36 | #include <linux/interrupt.h> |
37 | #include <linux/capability.h> | 37 | #include <linux/capability.h> |
38 | #include <linux/completion.h> | 38 | #include <linux/completion.h> |
39 | #include <linux/kernel_stat.h> | 39 | #include <linux/kernel_stat.h> |
40 | #include <linux/debug_locks.h> | 40 | #include <linux/debug_locks.h> |
41 | #include <linux/perf_event.h> | 41 | #include <linux/perf_event.h> |
42 | #include <linux/security.h> | 42 | #include <linux/security.h> |
43 | #include <linux/notifier.h> | 43 | #include <linux/notifier.h> |
44 | #include <linux/profile.h> | 44 | #include <linux/profile.h> |
45 | #include <linux/freezer.h> | 45 | #include <linux/freezer.h> |
46 | #include <linux/vmalloc.h> | 46 | #include <linux/vmalloc.h> |
47 | #include <linux/blkdev.h> | 47 | #include <linux/blkdev.h> |
48 | #include <linux/delay.h> | 48 | #include <linux/delay.h> |
49 | #include <linux/pid_namespace.h> | 49 | #include <linux/pid_namespace.h> |
50 | #include <linux/smp.h> | 50 | #include <linux/smp.h> |
51 | #include <linux/threads.h> | 51 | #include <linux/threads.h> |
52 | #include <linux/timer.h> | 52 | #include <linux/timer.h> |
53 | #include <linux/rcupdate.h> | 53 | #include <linux/rcupdate.h> |
54 | #include <linux/cpu.h> | 54 | #include <linux/cpu.h> |
55 | #include <linux/cpuset.h> | 55 | #include <linux/cpuset.h> |
56 | #include <linux/percpu.h> | 56 | #include <linux/percpu.h> |
57 | #include <linux/proc_fs.h> | 57 | #include <linux/proc_fs.h> |
58 | #include <linux/seq_file.h> | 58 | #include <linux/seq_file.h> |
59 | #include <linux/stop_machine.h> | 59 | #include <linux/stop_machine.h> |
60 | #include <linux/sysctl.h> | 60 | #include <linux/sysctl.h> |
61 | #include <linux/syscalls.h> | 61 | #include <linux/syscalls.h> |
62 | #include <linux/times.h> | 62 | #include <linux/times.h> |
63 | #include <linux/tsacct_kern.h> | 63 | #include <linux/tsacct_kern.h> |
64 | #include <linux/kprobes.h> | 64 | #include <linux/kprobes.h> |
65 | #include <linux/delayacct.h> | 65 | #include <linux/delayacct.h> |
66 | #include <linux/unistd.h> | 66 | #include <linux/unistd.h> |
67 | #include <linux/pagemap.h> | 67 | #include <linux/pagemap.h> |
68 | #include <linux/hrtimer.h> | 68 | #include <linux/hrtimer.h> |
69 | #include <linux/tick.h> | 69 | #include <linux/tick.h> |
70 | #include <linux/debugfs.h> | 70 | #include <linux/debugfs.h> |
71 | #include <linux/ctype.h> | 71 | #include <linux/ctype.h> |
72 | #include <linux/ftrace.h> | 72 | #include <linux/ftrace.h> |
73 | #include <linux/slab.h> | 73 | #include <linux/slab.h> |
74 | 74 | ||
75 | #include <asm/tlb.h> | 75 | #include <asm/tlb.h> |
76 | #include <asm/irq_regs.h> | 76 | #include <asm/irq_regs.h> |
77 | #include <asm/mutex.h> | 77 | #include <asm/mutex.h> |
78 | 78 | ||
79 | #include "sched_cpupri.h" | 79 | #include "sched_cpupri.h" |
80 | #include "workqueue_sched.h" | 80 | #include "workqueue_sched.h" |
81 | #include "sched_autogroup.h" | 81 | #include "sched_autogroup.h" |
82 | 82 | ||
83 | #define CREATE_TRACE_POINTS | 83 | #define CREATE_TRACE_POINTS |
84 | #include <trace/events/sched.h> | 84 | #include <trace/events/sched.h> |
85 | 85 | ||
86 | /* | 86 | /* |
87 | * Convert user-nice values [ -20 ... 0 ... 19 ] | 87 | * Convert user-nice values [ -20 ... 0 ... 19 ] |
88 | * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], | 88 | * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], |
89 | * and back. | 89 | * and back. |
90 | */ | 90 | */ |
91 | #define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) | 91 | #define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) |
92 | #define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) | 92 | #define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) |
93 | #define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) | 93 | #define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) |
94 | 94 | ||
95 | /* | 95 | /* |
96 | * 'User priority' is the nice value converted to something we | 96 | * 'User priority' is the nice value converted to something we |
97 | * can work with better when scaling various scheduler parameters, | 97 | * can work with better when scaling various scheduler parameters, |
98 | * it's a [ 0 ... 39 ] range. | 98 | * it's a [ 0 ... 39 ] range. |
99 | */ | 99 | */ |
100 | #define USER_PRIO(p) ((p)-MAX_RT_PRIO) | 100 | #define USER_PRIO(p) ((p)-MAX_RT_PRIO) |
101 | #define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) | 101 | #define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) |
102 | #define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) | 102 | #define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) |
103 | 103 | ||
104 | /* | 104 | /* |
105 | * Helpers for converting nanosecond timing to jiffy resolution | 105 | * Helpers for converting nanosecond timing to jiffy resolution |
106 | */ | 106 | */ |
107 | #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) | 107 | #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) |
108 | 108 | ||
109 | #define NICE_0_LOAD SCHED_LOAD_SCALE | 109 | #define NICE_0_LOAD SCHED_LOAD_SCALE |
110 | #define NICE_0_SHIFT SCHED_LOAD_SHIFT | 110 | #define NICE_0_SHIFT SCHED_LOAD_SHIFT |
111 | 111 | ||
112 | /* | 112 | /* |
113 | * These are the 'tuning knobs' of the scheduler: | 113 | * These are the 'tuning knobs' of the scheduler: |
114 | * | 114 | * |
115 | * default timeslice is 100 msecs (used only for SCHED_RR tasks). | 115 | * default timeslice is 100 msecs (used only for SCHED_RR tasks). |
116 | * Timeslices get refilled after they expire. | 116 | * Timeslices get refilled after they expire. |
117 | */ | 117 | */ |
118 | #define DEF_TIMESLICE (100 * HZ / 1000) | 118 | #define DEF_TIMESLICE (100 * HZ / 1000) |
119 | 119 | ||
120 | /* | 120 | /* |
121 | * single value that denotes runtime == period, ie unlimited time. | 121 | * single value that denotes runtime == period, ie unlimited time. |
122 | */ | 122 | */ |
123 | #define RUNTIME_INF ((u64)~0ULL) | 123 | #define RUNTIME_INF ((u64)~0ULL) |
124 | 124 | ||
125 | static inline int rt_policy(int policy) | 125 | static inline int rt_policy(int policy) |
126 | { | 126 | { |
127 | if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) | 127 | if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) |
128 | return 1; | 128 | return 1; |
129 | return 0; | 129 | return 0; |
130 | } | 130 | } |
131 | 131 | ||
132 | static inline int task_has_rt_policy(struct task_struct *p) | 132 | static inline int task_has_rt_policy(struct task_struct *p) |
133 | { | 133 | { |
134 | return rt_policy(p->policy); | 134 | return rt_policy(p->policy); |
135 | } | 135 | } |
136 | 136 | ||
137 | /* | 137 | /* |
138 | * This is the priority-queue data structure of the RT scheduling class: | 138 | * This is the priority-queue data structure of the RT scheduling class: |
139 | */ | 139 | */ |
140 | struct rt_prio_array { | 140 | struct rt_prio_array { |
141 | DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ | 141 | DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ |
142 | struct list_head queue[MAX_RT_PRIO]; | 142 | struct list_head queue[MAX_RT_PRIO]; |
143 | }; | 143 | }; |
144 | 144 | ||
145 | struct rt_bandwidth { | 145 | struct rt_bandwidth { |
146 | /* nests inside the rq lock: */ | 146 | /* nests inside the rq lock: */ |
147 | raw_spinlock_t rt_runtime_lock; | 147 | raw_spinlock_t rt_runtime_lock; |
148 | ktime_t rt_period; | 148 | ktime_t rt_period; |
149 | u64 rt_runtime; | 149 | u64 rt_runtime; |
150 | struct hrtimer rt_period_timer; | 150 | struct hrtimer rt_period_timer; |
151 | }; | 151 | }; |
152 | 152 | ||
153 | static struct rt_bandwidth def_rt_bandwidth; | 153 | static struct rt_bandwidth def_rt_bandwidth; |
154 | 154 | ||
155 | static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); | 155 | static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); |
156 | 156 | ||
157 | static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) | 157 | static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) |
158 | { | 158 | { |
159 | struct rt_bandwidth *rt_b = | 159 | struct rt_bandwidth *rt_b = |
160 | container_of(timer, struct rt_bandwidth, rt_period_timer); | 160 | container_of(timer, struct rt_bandwidth, rt_period_timer); |
161 | ktime_t now; | 161 | ktime_t now; |
162 | int overrun; | 162 | int overrun; |
163 | int idle = 0; | 163 | int idle = 0; |
164 | 164 | ||
165 | for (;;) { | 165 | for (;;) { |
166 | now = hrtimer_cb_get_time(timer); | 166 | now = hrtimer_cb_get_time(timer); |
167 | overrun = hrtimer_forward(timer, now, rt_b->rt_period); | 167 | overrun = hrtimer_forward(timer, now, rt_b->rt_period); |
168 | 168 | ||
169 | if (!overrun) | 169 | if (!overrun) |
170 | break; | 170 | break; |
171 | 171 | ||
172 | idle = do_sched_rt_period_timer(rt_b, overrun); | 172 | idle = do_sched_rt_period_timer(rt_b, overrun); |
173 | } | 173 | } |
174 | 174 | ||
175 | return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; | 175 | return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; |
176 | } | 176 | } |
177 | 177 | ||
178 | static | 178 | static |
179 | void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) | 179 | void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) |
180 | { | 180 | { |
181 | rt_b->rt_period = ns_to_ktime(period); | 181 | rt_b->rt_period = ns_to_ktime(period); |
182 | rt_b->rt_runtime = runtime; | 182 | rt_b->rt_runtime = runtime; |
183 | 183 | ||
184 | raw_spin_lock_init(&rt_b->rt_runtime_lock); | 184 | raw_spin_lock_init(&rt_b->rt_runtime_lock); |
185 | 185 | ||
186 | hrtimer_init(&rt_b->rt_period_timer, | 186 | hrtimer_init(&rt_b->rt_period_timer, |
187 | CLOCK_MONOTONIC, HRTIMER_MODE_REL); | 187 | CLOCK_MONOTONIC, HRTIMER_MODE_REL); |
188 | rt_b->rt_period_timer.function = sched_rt_period_timer; | 188 | rt_b->rt_period_timer.function = sched_rt_period_timer; |
189 | } | 189 | } |
190 | 190 | ||
191 | static inline int rt_bandwidth_enabled(void) | 191 | static inline int rt_bandwidth_enabled(void) |
192 | { | 192 | { |
193 | return sysctl_sched_rt_runtime >= 0; | 193 | return sysctl_sched_rt_runtime >= 0; |
194 | } | 194 | } |
195 | 195 | ||
196 | static void start_rt_bandwidth(struct rt_bandwidth *rt_b) | 196 | static void start_rt_bandwidth(struct rt_bandwidth *rt_b) |
197 | { | 197 | { |
198 | ktime_t now; | 198 | ktime_t now; |
199 | 199 | ||
200 | if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) | 200 | if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) |
201 | return; | 201 | return; |
202 | 202 | ||
203 | if (hrtimer_active(&rt_b->rt_period_timer)) | 203 | if (hrtimer_active(&rt_b->rt_period_timer)) |
204 | return; | 204 | return; |
205 | 205 | ||
206 | raw_spin_lock(&rt_b->rt_runtime_lock); | 206 | raw_spin_lock(&rt_b->rt_runtime_lock); |
207 | for (;;) { | 207 | for (;;) { |
208 | unsigned long delta; | 208 | unsigned long delta; |
209 | ktime_t soft, hard; | 209 | ktime_t soft, hard; |
210 | 210 | ||
211 | if (hrtimer_active(&rt_b->rt_period_timer)) | 211 | if (hrtimer_active(&rt_b->rt_period_timer)) |
212 | break; | 212 | break; |
213 | 213 | ||
214 | now = hrtimer_cb_get_time(&rt_b->rt_period_timer); | 214 | now = hrtimer_cb_get_time(&rt_b->rt_period_timer); |
215 | hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); | 215 | hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); |
216 | 216 | ||
217 | soft = hrtimer_get_softexpires(&rt_b->rt_period_timer); | 217 | soft = hrtimer_get_softexpires(&rt_b->rt_period_timer); |
218 | hard = hrtimer_get_expires(&rt_b->rt_period_timer); | 218 | hard = hrtimer_get_expires(&rt_b->rt_period_timer); |
219 | delta = ktime_to_ns(ktime_sub(hard, soft)); | 219 | delta = ktime_to_ns(ktime_sub(hard, soft)); |
220 | __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, | 220 | __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, |
221 | HRTIMER_MODE_ABS_PINNED, 0); | 221 | HRTIMER_MODE_ABS_PINNED, 0); |
222 | } | 222 | } |
223 | raw_spin_unlock(&rt_b->rt_runtime_lock); | 223 | raw_spin_unlock(&rt_b->rt_runtime_lock); |
224 | } | 224 | } |
225 | 225 | ||
226 | #ifdef CONFIG_RT_GROUP_SCHED | 226 | #ifdef CONFIG_RT_GROUP_SCHED |
227 | static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) | 227 | static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) |
228 | { | 228 | { |
229 | hrtimer_cancel(&rt_b->rt_period_timer); | 229 | hrtimer_cancel(&rt_b->rt_period_timer); |
230 | } | 230 | } |
231 | #endif | 231 | #endif |
232 | 232 | ||
233 | /* | 233 | /* |
234 | * sched_domains_mutex serializes calls to arch_init_sched_domains, | 234 | * sched_domains_mutex serializes calls to arch_init_sched_domains, |
235 | * detach_destroy_domains and partition_sched_domains. | 235 | * detach_destroy_domains and partition_sched_domains. |
236 | */ | 236 | */ |
237 | static DEFINE_MUTEX(sched_domains_mutex); | 237 | static DEFINE_MUTEX(sched_domains_mutex); |
238 | 238 | ||
239 | #ifdef CONFIG_CGROUP_SCHED | 239 | #ifdef CONFIG_CGROUP_SCHED |
240 | 240 | ||
241 | #include <linux/cgroup.h> | 241 | #include <linux/cgroup.h> |
242 | 242 | ||
243 | struct cfs_rq; | 243 | struct cfs_rq; |
244 | 244 | ||
245 | static LIST_HEAD(task_groups); | 245 | static LIST_HEAD(task_groups); |
246 | 246 | ||
247 | /* task group related information */ | 247 | /* task group related information */ |
248 | struct task_group { | 248 | struct task_group { |
249 | struct cgroup_subsys_state css; | 249 | struct cgroup_subsys_state css; |
250 | 250 | ||
251 | #ifdef CONFIG_FAIR_GROUP_SCHED | 251 | #ifdef CONFIG_FAIR_GROUP_SCHED |
252 | /* schedulable entities of this group on each cpu */ | 252 | /* schedulable entities of this group on each cpu */ |
253 | struct sched_entity **se; | 253 | struct sched_entity **se; |
254 | /* runqueue "owned" by this group on each cpu */ | 254 | /* runqueue "owned" by this group on each cpu */ |
255 | struct cfs_rq **cfs_rq; | 255 | struct cfs_rq **cfs_rq; |
256 | unsigned long shares; | 256 | unsigned long shares; |
257 | 257 | ||
258 | atomic_t load_weight; | 258 | atomic_t load_weight; |
259 | #endif | 259 | #endif |
260 | 260 | ||
261 | #ifdef CONFIG_RT_GROUP_SCHED | 261 | #ifdef CONFIG_RT_GROUP_SCHED |
262 | struct sched_rt_entity **rt_se; | 262 | struct sched_rt_entity **rt_se; |
263 | struct rt_rq **rt_rq; | 263 | struct rt_rq **rt_rq; |
264 | 264 | ||
265 | struct rt_bandwidth rt_bandwidth; | 265 | struct rt_bandwidth rt_bandwidth; |
266 | #endif | 266 | #endif |
267 | 267 | ||
268 | struct rcu_head rcu; | 268 | struct rcu_head rcu; |
269 | struct list_head list; | 269 | struct list_head list; |
270 | 270 | ||
271 | struct task_group *parent; | 271 | struct task_group *parent; |
272 | struct list_head siblings; | 272 | struct list_head siblings; |
273 | struct list_head children; | 273 | struct list_head children; |
274 | 274 | ||
275 | #ifdef CONFIG_SCHED_AUTOGROUP | 275 | #ifdef CONFIG_SCHED_AUTOGROUP |
276 | struct autogroup *autogroup; | 276 | struct autogroup *autogroup; |
277 | #endif | 277 | #endif |
278 | }; | 278 | }; |
279 | 279 | ||
280 | /* task_group_lock serializes the addition/removal of task groups */ | 280 | /* task_group_lock serializes the addition/removal of task groups */ |
281 | static DEFINE_SPINLOCK(task_group_lock); | 281 | static DEFINE_SPINLOCK(task_group_lock); |
282 | 282 | ||
283 | #ifdef CONFIG_FAIR_GROUP_SCHED | 283 | #ifdef CONFIG_FAIR_GROUP_SCHED |
284 | 284 | ||
285 | # define ROOT_TASK_GROUP_LOAD NICE_0_LOAD | 285 | # define ROOT_TASK_GROUP_LOAD NICE_0_LOAD |
286 | 286 | ||
287 | /* | 287 | /* |
288 | * A weight of 0 or 1 can cause arithmetics problems. | 288 | * A weight of 0 or 1 can cause arithmetics problems. |
289 | * A weight of a cfs_rq is the sum of weights of which entities | 289 | * A weight of a cfs_rq is the sum of weights of which entities |
290 | * are queued on this cfs_rq, so a weight of a entity should not be | 290 | * are queued on this cfs_rq, so a weight of a entity should not be |
291 | * too large, so as the shares value of a task group. | 291 | * too large, so as the shares value of a task group. |
292 | * (The default weight is 1024 - so there's no practical | 292 | * (The default weight is 1024 - so there's no practical |
293 | * limitation from this.) | 293 | * limitation from this.) |
294 | */ | 294 | */ |
295 | #define MIN_SHARES 2 | 295 | #define MIN_SHARES 2 |
296 | #define MAX_SHARES (1UL << 18) | 296 | #define MAX_SHARES (1UL << 18) |
297 | 297 | ||
298 | static int root_task_group_load = ROOT_TASK_GROUP_LOAD; | 298 | static int root_task_group_load = ROOT_TASK_GROUP_LOAD; |
299 | #endif | 299 | #endif |
300 | 300 | ||
301 | /* Default task group. | 301 | /* Default task group. |
302 | * Every task in system belong to this group at bootup. | 302 | * Every task in system belong to this group at bootup. |
303 | */ | 303 | */ |
304 | struct task_group root_task_group; | 304 | struct task_group root_task_group; |
305 | 305 | ||
306 | #endif /* CONFIG_CGROUP_SCHED */ | 306 | #endif /* CONFIG_CGROUP_SCHED */ |
307 | 307 | ||
308 | /* CFS-related fields in a runqueue */ | 308 | /* CFS-related fields in a runqueue */ |
309 | struct cfs_rq { | 309 | struct cfs_rq { |
310 | struct load_weight load; | 310 | struct load_weight load; |
311 | unsigned long nr_running; | 311 | unsigned long nr_running; |
312 | 312 | ||
313 | u64 exec_clock; | 313 | u64 exec_clock; |
314 | u64 min_vruntime; | 314 | u64 min_vruntime; |
315 | #ifndef CONFIG_64BIT | 315 | #ifndef CONFIG_64BIT |
316 | u64 min_vruntime_copy; | 316 | u64 min_vruntime_copy; |
317 | #endif | 317 | #endif |
318 | 318 | ||
319 | struct rb_root tasks_timeline; | 319 | struct rb_root tasks_timeline; |
320 | struct rb_node *rb_leftmost; | 320 | struct rb_node *rb_leftmost; |
321 | 321 | ||
322 | struct list_head tasks; | 322 | struct list_head tasks; |
323 | struct list_head *balance_iterator; | 323 | struct list_head *balance_iterator; |
324 | 324 | ||
325 | /* | 325 | /* |
326 | * 'curr' points to currently running entity on this cfs_rq. | 326 | * 'curr' points to currently running entity on this cfs_rq. |
327 | * It is set to NULL otherwise (i.e when none are currently running). | 327 | * It is set to NULL otherwise (i.e when none are currently running). |
328 | */ | 328 | */ |
329 | struct sched_entity *curr, *next, *last, *skip; | 329 | struct sched_entity *curr, *next, *last, *skip; |
330 | 330 | ||
331 | unsigned int nr_spread_over; | 331 | unsigned int nr_spread_over; |
332 | 332 | ||
333 | #ifdef CONFIG_FAIR_GROUP_SCHED | 333 | #ifdef CONFIG_FAIR_GROUP_SCHED |
334 | struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ | 334 | struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ |
335 | 335 | ||
336 | /* | 336 | /* |
337 | * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in | 337 | * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in |
338 | * a hierarchy). Non-leaf lrqs hold other higher schedulable entities | 338 | * a hierarchy). Non-leaf lrqs hold other higher schedulable entities |
339 | * (like users, containers etc.) | 339 | * (like users, containers etc.) |
340 | * | 340 | * |
341 | * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This | 341 | * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This |
342 | * list is used during load balance. | 342 | * list is used during load balance. |
343 | */ | 343 | */ |
344 | int on_list; | 344 | int on_list; |
345 | struct list_head leaf_cfs_rq_list; | 345 | struct list_head leaf_cfs_rq_list; |
346 | struct task_group *tg; /* group that "owns" this runqueue */ | 346 | struct task_group *tg; /* group that "owns" this runqueue */ |
347 | 347 | ||
348 | #ifdef CONFIG_SMP | 348 | #ifdef CONFIG_SMP |
349 | /* | 349 | /* |
350 | * the part of load.weight contributed by tasks | 350 | * the part of load.weight contributed by tasks |
351 | */ | 351 | */ |
352 | unsigned long task_weight; | 352 | unsigned long task_weight; |
353 | 353 | ||
354 | /* | 354 | /* |
355 | * h_load = weight * f(tg) | 355 | * h_load = weight * f(tg) |
356 | * | 356 | * |
357 | * Where f(tg) is the recursive weight fraction assigned to | 357 | * Where f(tg) is the recursive weight fraction assigned to |
358 | * this group. | 358 | * this group. |
359 | */ | 359 | */ |
360 | unsigned long h_load; | 360 | unsigned long h_load; |
361 | 361 | ||
362 | /* | 362 | /* |
363 | * Maintaining per-cpu shares distribution for group scheduling | 363 | * Maintaining per-cpu shares distribution for group scheduling |
364 | * | 364 | * |
365 | * load_stamp is the last time we updated the load average | 365 | * load_stamp is the last time we updated the load average |
366 | * load_last is the last time we updated the load average and saw load | 366 | * load_last is the last time we updated the load average and saw load |
367 | * load_unacc_exec_time is currently unaccounted execution time | 367 | * load_unacc_exec_time is currently unaccounted execution time |
368 | */ | 368 | */ |
369 | u64 load_avg; | 369 | u64 load_avg; |
370 | u64 load_period; | 370 | u64 load_period; |
371 | u64 load_stamp, load_last, load_unacc_exec_time; | 371 | u64 load_stamp, load_last, load_unacc_exec_time; |
372 | 372 | ||
373 | unsigned long load_contribution; | 373 | unsigned long load_contribution; |
374 | #endif | 374 | #endif |
375 | #endif | 375 | #endif |
376 | }; | 376 | }; |
377 | 377 | ||
378 | /* Real-Time classes' related field in a runqueue: */ | 378 | /* Real-Time classes' related field in a runqueue: */ |
379 | struct rt_rq { | 379 | struct rt_rq { |
380 | struct rt_prio_array active; | 380 | struct rt_prio_array active; |
381 | unsigned long rt_nr_running; | 381 | unsigned long rt_nr_running; |
382 | #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED | 382 | #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED |
383 | struct { | 383 | struct { |
384 | int curr; /* highest queued rt task prio */ | 384 | int curr; /* highest queued rt task prio */ |
385 | #ifdef CONFIG_SMP | 385 | #ifdef CONFIG_SMP |
386 | int next; /* next highest */ | 386 | int next; /* next highest */ |
387 | #endif | 387 | #endif |
388 | } highest_prio; | 388 | } highest_prio; |
389 | #endif | 389 | #endif |
390 | #ifdef CONFIG_SMP | 390 | #ifdef CONFIG_SMP |
391 | unsigned long rt_nr_migratory; | 391 | unsigned long rt_nr_migratory; |
392 | unsigned long rt_nr_total; | 392 | unsigned long rt_nr_total; |
393 | int overloaded; | 393 | int overloaded; |
394 | struct plist_head pushable_tasks; | 394 | struct plist_head pushable_tasks; |
395 | #endif | 395 | #endif |
396 | int rt_throttled; | 396 | int rt_throttled; |
397 | u64 rt_time; | 397 | u64 rt_time; |
398 | u64 rt_runtime; | 398 | u64 rt_runtime; |
399 | /* Nests inside the rq lock: */ | 399 | /* Nests inside the rq lock: */ |
400 | raw_spinlock_t rt_runtime_lock; | 400 | raw_spinlock_t rt_runtime_lock; |
401 | 401 | ||
402 | #ifdef CONFIG_RT_GROUP_SCHED | 402 | #ifdef CONFIG_RT_GROUP_SCHED |
403 | unsigned long rt_nr_boosted; | 403 | unsigned long rt_nr_boosted; |
404 | 404 | ||
405 | struct rq *rq; | 405 | struct rq *rq; |
406 | struct list_head leaf_rt_rq_list; | 406 | struct list_head leaf_rt_rq_list; |
407 | struct task_group *tg; | 407 | struct task_group *tg; |
408 | #endif | 408 | #endif |
409 | }; | 409 | }; |
410 | 410 | ||
411 | #ifdef CONFIG_SMP | 411 | #ifdef CONFIG_SMP |
412 | 412 | ||
413 | /* | 413 | /* |
414 | * We add the notion of a root-domain which will be used to define per-domain | 414 | * We add the notion of a root-domain which will be used to define per-domain |
415 | * variables. Each exclusive cpuset essentially defines an island domain by | 415 | * variables. Each exclusive cpuset essentially defines an island domain by |
416 | * fully partitioning the member cpus from any other cpuset. Whenever a new | 416 | * fully partitioning the member cpus from any other cpuset. Whenever a new |
417 | * exclusive cpuset is created, we also create and attach a new root-domain | 417 | * exclusive cpuset is created, we also create and attach a new root-domain |
418 | * object. | 418 | * object. |
419 | * | 419 | * |
420 | */ | 420 | */ |
421 | struct root_domain { | 421 | struct root_domain { |
422 | atomic_t refcount; | 422 | atomic_t refcount; |
423 | cpumask_var_t span; | 423 | cpumask_var_t span; |
424 | cpumask_var_t online; | 424 | cpumask_var_t online; |
425 | 425 | ||
426 | /* | 426 | /* |
427 | * The "RT overload" flag: it gets set if a CPU has more than | 427 | * The "RT overload" flag: it gets set if a CPU has more than |
428 | * one runnable RT task. | 428 | * one runnable RT task. |
429 | */ | 429 | */ |
430 | cpumask_var_t rto_mask; | 430 | cpumask_var_t rto_mask; |
431 | atomic_t rto_count; | 431 | atomic_t rto_count; |
432 | struct cpupri cpupri; | 432 | struct cpupri cpupri; |
433 | }; | 433 | }; |
434 | 434 | ||
435 | /* | 435 | /* |
436 | * By default the system creates a single root-domain with all cpus as | 436 | * By default the system creates a single root-domain with all cpus as |
437 | * members (mimicking the global state we have today). | 437 | * members (mimicking the global state we have today). |
438 | */ | 438 | */ |
439 | static struct root_domain def_root_domain; | 439 | static struct root_domain def_root_domain; |
440 | 440 | ||
441 | #endif /* CONFIG_SMP */ | 441 | #endif /* CONFIG_SMP */ |
442 | 442 | ||
443 | /* | 443 | /* |
444 | * This is the main, per-CPU runqueue data structure. | 444 | * This is the main, per-CPU runqueue data structure. |
445 | * | 445 | * |
446 | * Locking rule: those places that want to lock multiple runqueues | 446 | * Locking rule: those places that want to lock multiple runqueues |
447 | * (such as the load balancing or the thread migration code), lock | 447 | * (such as the load balancing or the thread migration code), lock |
448 | * acquire operations must be ordered by ascending &runqueue. | 448 | * acquire operations must be ordered by ascending &runqueue. |
449 | */ | 449 | */ |
450 | struct rq { | 450 | struct rq { |
451 | /* runqueue lock: */ | 451 | /* runqueue lock: */ |
452 | raw_spinlock_t lock; | 452 | raw_spinlock_t lock; |
453 | 453 | ||
454 | /* | 454 | /* |
455 | * nr_running and cpu_load should be in the same cacheline because | 455 | * nr_running and cpu_load should be in the same cacheline because |
456 | * remote CPUs use both these fields when doing load calculation. | 456 | * remote CPUs use both these fields when doing load calculation. |
457 | */ | 457 | */ |
458 | unsigned long nr_running; | 458 | unsigned long nr_running; |
459 | #define CPU_LOAD_IDX_MAX 5 | 459 | #define CPU_LOAD_IDX_MAX 5 |
460 | unsigned long cpu_load[CPU_LOAD_IDX_MAX]; | 460 | unsigned long cpu_load[CPU_LOAD_IDX_MAX]; |
461 | unsigned long last_load_update_tick; | 461 | unsigned long last_load_update_tick; |
462 | #ifdef CONFIG_NO_HZ | 462 | #ifdef CONFIG_NO_HZ |
463 | u64 nohz_stamp; | 463 | u64 nohz_stamp; |
464 | unsigned char nohz_balance_kick; | 464 | unsigned char nohz_balance_kick; |
465 | #endif | 465 | #endif |
466 | unsigned int skip_clock_update; | 466 | unsigned int skip_clock_update; |
467 | 467 | ||
468 | /* capture load from *all* tasks on this cpu: */ | 468 | /* capture load from *all* tasks on this cpu: */ |
469 | struct load_weight load; | 469 | struct load_weight load; |
470 | unsigned long nr_load_updates; | 470 | unsigned long nr_load_updates; |
471 | u64 nr_switches; | 471 | u64 nr_switches; |
472 | 472 | ||
473 | struct cfs_rq cfs; | 473 | struct cfs_rq cfs; |
474 | struct rt_rq rt; | 474 | struct rt_rq rt; |
475 | 475 | ||
476 | #ifdef CONFIG_FAIR_GROUP_SCHED | 476 | #ifdef CONFIG_FAIR_GROUP_SCHED |
477 | /* list of leaf cfs_rq on this cpu: */ | 477 | /* list of leaf cfs_rq on this cpu: */ |
478 | struct list_head leaf_cfs_rq_list; | 478 | struct list_head leaf_cfs_rq_list; |
479 | #endif | 479 | #endif |
480 | #ifdef CONFIG_RT_GROUP_SCHED | 480 | #ifdef CONFIG_RT_GROUP_SCHED |
481 | struct list_head leaf_rt_rq_list; | 481 | struct list_head leaf_rt_rq_list; |
482 | #endif | 482 | #endif |
483 | 483 | ||
484 | /* | 484 | /* |
485 | * This is part of a global counter where only the total sum | 485 | * This is part of a global counter where only the total sum |
486 | * over all CPUs matters. A task can increase this counter on | 486 | * over all CPUs matters. A task can increase this counter on |
487 | * one CPU and if it got migrated afterwards it may decrease | 487 | * one CPU and if it got migrated afterwards it may decrease |
488 | * it on another CPU. Always updated under the runqueue lock: | 488 | * it on another CPU. Always updated under the runqueue lock: |
489 | */ | 489 | */ |
490 | unsigned long nr_uninterruptible; | 490 | unsigned long nr_uninterruptible; |
491 | 491 | ||
492 | struct task_struct *curr, *idle, *stop; | 492 | struct task_struct *curr, *idle, *stop; |
493 | unsigned long next_balance; | 493 | unsigned long next_balance; |
494 | struct mm_struct *prev_mm; | 494 | struct mm_struct *prev_mm; |
495 | 495 | ||
496 | u64 clock; | 496 | u64 clock; |
497 | u64 clock_task; | 497 | u64 clock_task; |
498 | 498 | ||
499 | atomic_t nr_iowait; | 499 | atomic_t nr_iowait; |
500 | 500 | ||
501 | #ifdef CONFIG_SMP | 501 | #ifdef CONFIG_SMP |
502 | struct root_domain *rd; | 502 | struct root_domain *rd; |
503 | struct sched_domain *sd; | 503 | struct sched_domain *sd; |
504 | 504 | ||
505 | unsigned long cpu_power; | 505 | unsigned long cpu_power; |
506 | 506 | ||
507 | unsigned char idle_at_tick; | 507 | unsigned char idle_at_tick; |
508 | /* For active balancing */ | 508 | /* For active balancing */ |
509 | int post_schedule; | 509 | int post_schedule; |
510 | int active_balance; | 510 | int active_balance; |
511 | int push_cpu; | 511 | int push_cpu; |
512 | struct cpu_stop_work active_balance_work; | 512 | struct cpu_stop_work active_balance_work; |
513 | /* cpu of this runqueue: */ | 513 | /* cpu of this runqueue: */ |
514 | int cpu; | 514 | int cpu; |
515 | int online; | 515 | int online; |
516 | 516 | ||
517 | unsigned long avg_load_per_task; | 517 | unsigned long avg_load_per_task; |
518 | 518 | ||
519 | u64 rt_avg; | 519 | u64 rt_avg; |
520 | u64 age_stamp; | 520 | u64 age_stamp; |
521 | u64 idle_stamp; | 521 | u64 idle_stamp; |
522 | u64 avg_idle; | 522 | u64 avg_idle; |
523 | #endif | 523 | #endif |
524 | 524 | ||
525 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING | 525 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING |
526 | u64 prev_irq_time; | 526 | u64 prev_irq_time; |
527 | #endif | 527 | #endif |
528 | 528 | ||
529 | /* calc_load related fields */ | 529 | /* calc_load related fields */ |
530 | unsigned long calc_load_update; | 530 | unsigned long calc_load_update; |
531 | long calc_load_active; | 531 | long calc_load_active; |
532 | 532 | ||
533 | #ifdef CONFIG_SCHED_HRTICK | 533 | #ifdef CONFIG_SCHED_HRTICK |
534 | #ifdef CONFIG_SMP | 534 | #ifdef CONFIG_SMP |
535 | int hrtick_csd_pending; | 535 | int hrtick_csd_pending; |
536 | struct call_single_data hrtick_csd; | 536 | struct call_single_data hrtick_csd; |
537 | #endif | 537 | #endif |
538 | struct hrtimer hrtick_timer; | 538 | struct hrtimer hrtick_timer; |
539 | #endif | 539 | #endif |
540 | 540 | ||
541 | #ifdef CONFIG_SCHEDSTATS | 541 | #ifdef CONFIG_SCHEDSTATS |
542 | /* latency stats */ | 542 | /* latency stats */ |
543 | struct sched_info rq_sched_info; | 543 | struct sched_info rq_sched_info; |
544 | unsigned long long rq_cpu_time; | 544 | unsigned long long rq_cpu_time; |
545 | /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ | 545 | /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ |
546 | 546 | ||
547 | /* sys_sched_yield() stats */ | 547 | /* sys_sched_yield() stats */ |
548 | unsigned int yld_count; | 548 | unsigned int yld_count; |
549 | 549 | ||
550 | /* schedule() stats */ | 550 | /* schedule() stats */ |
551 | unsigned int sched_switch; | 551 | unsigned int sched_switch; |
552 | unsigned int sched_count; | 552 | unsigned int sched_count; |
553 | unsigned int sched_goidle; | 553 | unsigned int sched_goidle; |
554 | 554 | ||
555 | /* try_to_wake_up() stats */ | 555 | /* try_to_wake_up() stats */ |
556 | unsigned int ttwu_count; | 556 | unsigned int ttwu_count; |
557 | unsigned int ttwu_local; | 557 | unsigned int ttwu_local; |
558 | #endif | 558 | #endif |
559 | 559 | ||
560 | #ifdef CONFIG_SMP | 560 | #ifdef CONFIG_SMP |
561 | struct task_struct *wake_list; | 561 | struct task_struct *wake_list; |
562 | #endif | 562 | #endif |
563 | }; | 563 | }; |
564 | 564 | ||
565 | static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); | 565 | static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); |
566 | 566 | ||
567 | 567 | ||
568 | static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); | 568 | static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); |
569 | 569 | ||
570 | static inline int cpu_of(struct rq *rq) | 570 | static inline int cpu_of(struct rq *rq) |
571 | { | 571 | { |
572 | #ifdef CONFIG_SMP | 572 | #ifdef CONFIG_SMP |
573 | return rq->cpu; | 573 | return rq->cpu; |
574 | #else | 574 | #else |
575 | return 0; | 575 | return 0; |
576 | #endif | 576 | #endif |
577 | } | 577 | } |
578 | 578 | ||
579 | #define rcu_dereference_check_sched_domain(p) \ | 579 | #define rcu_dereference_check_sched_domain(p) \ |
580 | rcu_dereference_check((p), \ | 580 | rcu_dereference_check((p), \ |
581 | rcu_read_lock_sched_held() || \ | 581 | rcu_read_lock_sched_held() || \ |
582 | lockdep_is_held(&sched_domains_mutex)) | 582 | lockdep_is_held(&sched_domains_mutex)) |
583 | 583 | ||
584 | /* | 584 | /* |
585 | * The domain tree (rq->sd) is protected by RCU's quiescent state transition. | 585 | * The domain tree (rq->sd) is protected by RCU's quiescent state transition. |
586 | * See detach_destroy_domains: synchronize_sched for details. | 586 | * See detach_destroy_domains: synchronize_sched for details. |
587 | * | 587 | * |
588 | * The domain tree of any CPU may only be accessed from within | 588 | * The domain tree of any CPU may only be accessed from within |
589 | * preempt-disabled sections. | 589 | * preempt-disabled sections. |
590 | */ | 590 | */ |
591 | #define for_each_domain(cpu, __sd) \ | 591 | #define for_each_domain(cpu, __sd) \ |
592 | for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) | 592 | for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) |
593 | 593 | ||
594 | #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) | 594 | #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) |
595 | #define this_rq() (&__get_cpu_var(runqueues)) | 595 | #define this_rq() (&__get_cpu_var(runqueues)) |
596 | #define task_rq(p) cpu_rq(task_cpu(p)) | 596 | #define task_rq(p) cpu_rq(task_cpu(p)) |
597 | #define cpu_curr(cpu) (cpu_rq(cpu)->curr) | 597 | #define cpu_curr(cpu) (cpu_rq(cpu)->curr) |
598 | #define raw_rq() (&__raw_get_cpu_var(runqueues)) | 598 | #define raw_rq() (&__raw_get_cpu_var(runqueues)) |
599 | 599 | ||
600 | #ifdef CONFIG_CGROUP_SCHED | 600 | #ifdef CONFIG_CGROUP_SCHED |
601 | 601 | ||
602 | /* | 602 | /* |
603 | * Return the group to which this tasks belongs. | 603 | * Return the group to which this tasks belongs. |
604 | * | 604 | * |
605 | * We use task_subsys_state_check() and extend the RCU verification | 605 | * We use task_subsys_state_check() and extend the RCU verification |
606 | * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach() | 606 | * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach() |
607 | * holds that lock for each task it moves into the cgroup. Therefore | 607 | * holds that lock for each task it moves into the cgroup. Therefore |
608 | * by holding that lock, we pin the task to the current cgroup. | 608 | * by holding that lock, we pin the task to the current cgroup. |
609 | */ | 609 | */ |
610 | static inline struct task_group *task_group(struct task_struct *p) | 610 | static inline struct task_group *task_group(struct task_struct *p) |
611 | { | 611 | { |
612 | struct task_group *tg; | 612 | struct task_group *tg; |
613 | struct cgroup_subsys_state *css; | 613 | struct cgroup_subsys_state *css; |
614 | 614 | ||
615 | css = task_subsys_state_check(p, cpu_cgroup_subsys_id, | 615 | css = task_subsys_state_check(p, cpu_cgroup_subsys_id, |
616 | lockdep_is_held(&p->pi_lock)); | 616 | lockdep_is_held(&p->pi_lock)); |
617 | tg = container_of(css, struct task_group, css); | 617 | tg = container_of(css, struct task_group, css); |
618 | 618 | ||
619 | return autogroup_task_group(p, tg); | 619 | return autogroup_task_group(p, tg); |
620 | } | 620 | } |
621 | 621 | ||
622 | /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ | 622 | /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ |
623 | static inline void set_task_rq(struct task_struct *p, unsigned int cpu) | 623 | static inline void set_task_rq(struct task_struct *p, unsigned int cpu) |
624 | { | 624 | { |
625 | #ifdef CONFIG_FAIR_GROUP_SCHED | 625 | #ifdef CONFIG_FAIR_GROUP_SCHED |
626 | p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; | 626 | p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; |
627 | p->se.parent = task_group(p)->se[cpu]; | 627 | p->se.parent = task_group(p)->se[cpu]; |
628 | #endif | 628 | #endif |
629 | 629 | ||
630 | #ifdef CONFIG_RT_GROUP_SCHED | 630 | #ifdef CONFIG_RT_GROUP_SCHED |
631 | p->rt.rt_rq = task_group(p)->rt_rq[cpu]; | 631 | p->rt.rt_rq = task_group(p)->rt_rq[cpu]; |
632 | p->rt.parent = task_group(p)->rt_se[cpu]; | 632 | p->rt.parent = task_group(p)->rt_se[cpu]; |
633 | #endif | 633 | #endif |
634 | } | 634 | } |
635 | 635 | ||
636 | #else /* CONFIG_CGROUP_SCHED */ | 636 | #else /* CONFIG_CGROUP_SCHED */ |
637 | 637 | ||
638 | static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } | 638 | static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } |
639 | static inline struct task_group *task_group(struct task_struct *p) | 639 | static inline struct task_group *task_group(struct task_struct *p) |
640 | { | 640 | { |
641 | return NULL; | 641 | return NULL; |
642 | } | 642 | } |
643 | 643 | ||
644 | #endif /* CONFIG_CGROUP_SCHED */ | 644 | #endif /* CONFIG_CGROUP_SCHED */ |
645 | 645 | ||
646 | static void update_rq_clock_task(struct rq *rq, s64 delta); | 646 | static void update_rq_clock_task(struct rq *rq, s64 delta); |
647 | 647 | ||
648 | static void update_rq_clock(struct rq *rq) | 648 | static void update_rq_clock(struct rq *rq) |
649 | { | 649 | { |
650 | s64 delta; | 650 | s64 delta; |
651 | 651 | ||
652 | if (rq->skip_clock_update) | 652 | if (rq->skip_clock_update) |
653 | return; | 653 | return; |
654 | 654 | ||
655 | delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; | 655 | delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; |
656 | rq->clock += delta; | 656 | rq->clock += delta; |
657 | update_rq_clock_task(rq, delta); | 657 | update_rq_clock_task(rq, delta); |
658 | } | 658 | } |
659 | 659 | ||
660 | /* | 660 | /* |
661 | * Tunables that become constants when CONFIG_SCHED_DEBUG is off: | 661 | * Tunables that become constants when CONFIG_SCHED_DEBUG is off: |
662 | */ | 662 | */ |
663 | #ifdef CONFIG_SCHED_DEBUG | 663 | #ifdef CONFIG_SCHED_DEBUG |
664 | # define const_debug __read_mostly | 664 | # define const_debug __read_mostly |
665 | #else | 665 | #else |
666 | # define const_debug static const | 666 | # define const_debug static const |
667 | #endif | 667 | #endif |
668 | 668 | ||
669 | /** | 669 | /** |
670 | * runqueue_is_locked - Returns true if the current cpu runqueue is locked | 670 | * runqueue_is_locked - Returns true if the current cpu runqueue is locked |
671 | * @cpu: the processor in question. | 671 | * @cpu: the processor in question. |
672 | * | 672 | * |
673 | * This interface allows printk to be called with the runqueue lock | 673 | * This interface allows printk to be called with the runqueue lock |
674 | * held and know whether or not it is OK to wake up the klogd. | 674 | * held and know whether or not it is OK to wake up the klogd. |
675 | */ | 675 | */ |
676 | int runqueue_is_locked(int cpu) | 676 | int runqueue_is_locked(int cpu) |
677 | { | 677 | { |
678 | return raw_spin_is_locked(&cpu_rq(cpu)->lock); | 678 | return raw_spin_is_locked(&cpu_rq(cpu)->lock); |
679 | } | 679 | } |
680 | 680 | ||
681 | /* | 681 | /* |
682 | * Debugging: various feature bits | 682 | * Debugging: various feature bits |
683 | */ | 683 | */ |
684 | 684 | ||
685 | #define SCHED_FEAT(name, enabled) \ | 685 | #define SCHED_FEAT(name, enabled) \ |
686 | __SCHED_FEAT_##name , | 686 | __SCHED_FEAT_##name , |
687 | 687 | ||
688 | enum { | 688 | enum { |
689 | #include "sched_features.h" | 689 | #include "sched_features.h" |
690 | }; | 690 | }; |
691 | 691 | ||
692 | #undef SCHED_FEAT | 692 | #undef SCHED_FEAT |
693 | 693 | ||
694 | #define SCHED_FEAT(name, enabled) \ | 694 | #define SCHED_FEAT(name, enabled) \ |
695 | (1UL << __SCHED_FEAT_##name) * enabled | | 695 | (1UL << __SCHED_FEAT_##name) * enabled | |
696 | 696 | ||
697 | const_debug unsigned int sysctl_sched_features = | 697 | const_debug unsigned int sysctl_sched_features = |
698 | #include "sched_features.h" | 698 | #include "sched_features.h" |
699 | 0; | 699 | 0; |
700 | 700 | ||
701 | #undef SCHED_FEAT | 701 | #undef SCHED_FEAT |
702 | 702 | ||
703 | #ifdef CONFIG_SCHED_DEBUG | 703 | #ifdef CONFIG_SCHED_DEBUG |
704 | #define SCHED_FEAT(name, enabled) \ | 704 | #define SCHED_FEAT(name, enabled) \ |
705 | #name , | 705 | #name , |
706 | 706 | ||
707 | static __read_mostly char *sched_feat_names[] = { | 707 | static __read_mostly char *sched_feat_names[] = { |
708 | #include "sched_features.h" | 708 | #include "sched_features.h" |
709 | NULL | 709 | NULL |
710 | }; | 710 | }; |
711 | 711 | ||
712 | #undef SCHED_FEAT | 712 | #undef SCHED_FEAT |
713 | 713 | ||
714 | static int sched_feat_show(struct seq_file *m, void *v) | 714 | static int sched_feat_show(struct seq_file *m, void *v) |
715 | { | 715 | { |
716 | int i; | 716 | int i; |
717 | 717 | ||
718 | for (i = 0; sched_feat_names[i]; i++) { | 718 | for (i = 0; sched_feat_names[i]; i++) { |
719 | if (!(sysctl_sched_features & (1UL << i))) | 719 | if (!(sysctl_sched_features & (1UL << i))) |
720 | seq_puts(m, "NO_"); | 720 | seq_puts(m, "NO_"); |
721 | seq_printf(m, "%s ", sched_feat_names[i]); | 721 | seq_printf(m, "%s ", sched_feat_names[i]); |
722 | } | 722 | } |
723 | seq_puts(m, "\n"); | 723 | seq_puts(m, "\n"); |
724 | 724 | ||
725 | return 0; | 725 | return 0; |
726 | } | 726 | } |
727 | 727 | ||
728 | static ssize_t | 728 | static ssize_t |
729 | sched_feat_write(struct file *filp, const char __user *ubuf, | 729 | sched_feat_write(struct file *filp, const char __user *ubuf, |
730 | size_t cnt, loff_t *ppos) | 730 | size_t cnt, loff_t *ppos) |
731 | { | 731 | { |
732 | char buf[64]; | 732 | char buf[64]; |
733 | char *cmp; | 733 | char *cmp; |
734 | int neg = 0; | 734 | int neg = 0; |
735 | int i; | 735 | int i; |
736 | 736 | ||
737 | if (cnt > 63) | 737 | if (cnt > 63) |
738 | cnt = 63; | 738 | cnt = 63; |
739 | 739 | ||
740 | if (copy_from_user(&buf, ubuf, cnt)) | 740 | if (copy_from_user(&buf, ubuf, cnt)) |
741 | return -EFAULT; | 741 | return -EFAULT; |
742 | 742 | ||
743 | buf[cnt] = 0; | 743 | buf[cnt] = 0; |
744 | cmp = strstrip(buf); | 744 | cmp = strstrip(buf); |
745 | 745 | ||
746 | if (strncmp(cmp, "NO_", 3) == 0) { | 746 | if (strncmp(cmp, "NO_", 3) == 0) { |
747 | neg = 1; | 747 | neg = 1; |
748 | cmp += 3; | 748 | cmp += 3; |
749 | } | 749 | } |
750 | 750 | ||
751 | for (i = 0; sched_feat_names[i]; i++) { | 751 | for (i = 0; sched_feat_names[i]; i++) { |
752 | if (strcmp(cmp, sched_feat_names[i]) == 0) { | 752 | if (strcmp(cmp, sched_feat_names[i]) == 0) { |
753 | if (neg) | 753 | if (neg) |
754 | sysctl_sched_features &= ~(1UL << i); | 754 | sysctl_sched_features &= ~(1UL << i); |
755 | else | 755 | else |
756 | sysctl_sched_features |= (1UL << i); | 756 | sysctl_sched_features |= (1UL << i); |
757 | break; | 757 | break; |
758 | } | 758 | } |
759 | } | 759 | } |
760 | 760 | ||
761 | if (!sched_feat_names[i]) | 761 | if (!sched_feat_names[i]) |
762 | return -EINVAL; | 762 | return -EINVAL; |
763 | 763 | ||
764 | *ppos += cnt; | 764 | *ppos += cnt; |
765 | 765 | ||
766 | return cnt; | 766 | return cnt; |
767 | } | 767 | } |
768 | 768 | ||
769 | static int sched_feat_open(struct inode *inode, struct file *filp) | 769 | static int sched_feat_open(struct inode *inode, struct file *filp) |
770 | { | 770 | { |
771 | return single_open(filp, sched_feat_show, NULL); | 771 | return single_open(filp, sched_feat_show, NULL); |
772 | } | 772 | } |
773 | 773 | ||
774 | static const struct file_operations sched_feat_fops = { | 774 | static const struct file_operations sched_feat_fops = { |
775 | .open = sched_feat_open, | 775 | .open = sched_feat_open, |
776 | .write = sched_feat_write, | 776 | .write = sched_feat_write, |
777 | .read = seq_read, | 777 | .read = seq_read, |
778 | .llseek = seq_lseek, | 778 | .llseek = seq_lseek, |
779 | .release = single_release, | 779 | .release = single_release, |
780 | }; | 780 | }; |
781 | 781 | ||
782 | static __init int sched_init_debug(void) | 782 | static __init int sched_init_debug(void) |
783 | { | 783 | { |
784 | debugfs_create_file("sched_features", 0644, NULL, NULL, | 784 | debugfs_create_file("sched_features", 0644, NULL, NULL, |
785 | &sched_feat_fops); | 785 | &sched_feat_fops); |
786 | 786 | ||
787 | return 0; | 787 | return 0; |
788 | } | 788 | } |
789 | late_initcall(sched_init_debug); | 789 | late_initcall(sched_init_debug); |
790 | 790 | ||
791 | #endif | 791 | #endif |
792 | 792 | ||
793 | #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) | 793 | #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) |
794 | 794 | ||
795 | /* | 795 | /* |
796 | * Number of tasks to iterate in a single balance run. | 796 | * Number of tasks to iterate in a single balance run. |
797 | * Limited because this is done with IRQs disabled. | 797 | * Limited because this is done with IRQs disabled. |
798 | */ | 798 | */ |
799 | const_debug unsigned int sysctl_sched_nr_migrate = 32; | 799 | const_debug unsigned int sysctl_sched_nr_migrate = 32; |
800 | 800 | ||
801 | /* | 801 | /* |
802 | * period over which we average the RT time consumption, measured | 802 | * period over which we average the RT time consumption, measured |
803 | * in ms. | 803 | * in ms. |
804 | * | 804 | * |
805 | * default: 1s | 805 | * default: 1s |
806 | */ | 806 | */ |
807 | const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; | 807 | const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; |
808 | 808 | ||
809 | /* | 809 | /* |
810 | * period over which we measure -rt task cpu usage in us. | 810 | * period over which we measure -rt task cpu usage in us. |
811 | * default: 1s | 811 | * default: 1s |
812 | */ | 812 | */ |
813 | unsigned int sysctl_sched_rt_period = 1000000; | 813 | unsigned int sysctl_sched_rt_period = 1000000; |
814 | 814 | ||
815 | static __read_mostly int scheduler_running; | 815 | static __read_mostly int scheduler_running; |
816 | 816 | ||
817 | /* | 817 | /* |
818 | * part of the period that we allow rt tasks to run in us. | 818 | * part of the period that we allow rt tasks to run in us. |
819 | * default: 0.95s | 819 | * default: 0.95s |
820 | */ | 820 | */ |
821 | int sysctl_sched_rt_runtime = 950000; | 821 | int sysctl_sched_rt_runtime = 950000; |
822 | 822 | ||
823 | static inline u64 global_rt_period(void) | 823 | static inline u64 global_rt_period(void) |
824 | { | 824 | { |
825 | return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; | 825 | return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; |
826 | } | 826 | } |
827 | 827 | ||
828 | static inline u64 global_rt_runtime(void) | 828 | static inline u64 global_rt_runtime(void) |
829 | { | 829 | { |
830 | if (sysctl_sched_rt_runtime < 0) | 830 | if (sysctl_sched_rt_runtime < 0) |
831 | return RUNTIME_INF; | 831 | return RUNTIME_INF; |
832 | 832 | ||
833 | return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; | 833 | return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; |
834 | } | 834 | } |
835 | 835 | ||
836 | #ifndef prepare_arch_switch | 836 | #ifndef prepare_arch_switch |
837 | # define prepare_arch_switch(next) do { } while (0) | 837 | # define prepare_arch_switch(next) do { } while (0) |
838 | #endif | 838 | #endif |
839 | #ifndef finish_arch_switch | 839 | #ifndef finish_arch_switch |
840 | # define finish_arch_switch(prev) do { } while (0) | 840 | # define finish_arch_switch(prev) do { } while (0) |
841 | #endif | 841 | #endif |
842 | 842 | ||
843 | static inline int task_current(struct rq *rq, struct task_struct *p) | 843 | static inline int task_current(struct rq *rq, struct task_struct *p) |
844 | { | 844 | { |
845 | return rq->curr == p; | 845 | return rq->curr == p; |
846 | } | 846 | } |
847 | 847 | ||
848 | static inline int task_running(struct rq *rq, struct task_struct *p) | 848 | static inline int task_running(struct rq *rq, struct task_struct *p) |
849 | { | 849 | { |
850 | #ifdef CONFIG_SMP | 850 | #ifdef CONFIG_SMP |
851 | return p->on_cpu; | 851 | return p->on_cpu; |
852 | #else | 852 | #else |
853 | return task_current(rq, p); | 853 | return task_current(rq, p); |
854 | #endif | 854 | #endif |
855 | } | 855 | } |
856 | 856 | ||
857 | #ifndef __ARCH_WANT_UNLOCKED_CTXSW | 857 | #ifndef __ARCH_WANT_UNLOCKED_CTXSW |
858 | static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) | 858 | static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) |
859 | { | 859 | { |
860 | #ifdef CONFIG_SMP | 860 | #ifdef CONFIG_SMP |
861 | /* | 861 | /* |
862 | * We can optimise this out completely for !SMP, because the | 862 | * We can optimise this out completely for !SMP, because the |
863 | * SMP rebalancing from interrupt is the only thing that cares | 863 | * SMP rebalancing from interrupt is the only thing that cares |
864 | * here. | 864 | * here. |
865 | */ | 865 | */ |
866 | next->on_cpu = 1; | 866 | next->on_cpu = 1; |
867 | #endif | 867 | #endif |
868 | } | 868 | } |
869 | 869 | ||
870 | static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) | 870 | static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) |
871 | { | 871 | { |
872 | #ifdef CONFIG_SMP | 872 | #ifdef CONFIG_SMP |
873 | /* | 873 | /* |
874 | * After ->on_cpu is cleared, the task can be moved to a different CPU. | 874 | * After ->on_cpu is cleared, the task can be moved to a different CPU. |
875 | * We must ensure this doesn't happen until the switch is completely | 875 | * We must ensure this doesn't happen until the switch is completely |
876 | * finished. | 876 | * finished. |
877 | */ | 877 | */ |
878 | smp_wmb(); | 878 | smp_wmb(); |
879 | prev->on_cpu = 0; | 879 | prev->on_cpu = 0; |
880 | #endif | 880 | #endif |
881 | #ifdef CONFIG_DEBUG_SPINLOCK | 881 | #ifdef CONFIG_DEBUG_SPINLOCK |
882 | /* this is a valid case when another task releases the spinlock */ | 882 | /* this is a valid case when another task releases the spinlock */ |
883 | rq->lock.owner = current; | 883 | rq->lock.owner = current; |
884 | #endif | 884 | #endif |
885 | /* | 885 | /* |
886 | * If we are tracking spinlock dependencies then we have to | 886 | * If we are tracking spinlock dependencies then we have to |
887 | * fix up the runqueue lock - which gets 'carried over' from | 887 | * fix up the runqueue lock - which gets 'carried over' from |
888 | * prev into current: | 888 | * prev into current: |
889 | */ | 889 | */ |
890 | spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); | 890 | spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); |
891 | 891 | ||
892 | raw_spin_unlock_irq(&rq->lock); | 892 | raw_spin_unlock_irq(&rq->lock); |
893 | } | 893 | } |
894 | 894 | ||
895 | #else /* __ARCH_WANT_UNLOCKED_CTXSW */ | 895 | #else /* __ARCH_WANT_UNLOCKED_CTXSW */ |
896 | static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) | 896 | static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) |
897 | { | 897 | { |
898 | #ifdef CONFIG_SMP | 898 | #ifdef CONFIG_SMP |
899 | /* | 899 | /* |
900 | * We can optimise this out completely for !SMP, because the | 900 | * We can optimise this out completely for !SMP, because the |
901 | * SMP rebalancing from interrupt is the only thing that cares | 901 | * SMP rebalancing from interrupt is the only thing that cares |
902 | * here. | 902 | * here. |
903 | */ | 903 | */ |
904 | next->on_cpu = 1; | 904 | next->on_cpu = 1; |
905 | #endif | 905 | #endif |
906 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW | 906 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW |
907 | raw_spin_unlock_irq(&rq->lock); | 907 | raw_spin_unlock_irq(&rq->lock); |
908 | #else | 908 | #else |
909 | raw_spin_unlock(&rq->lock); | 909 | raw_spin_unlock(&rq->lock); |
910 | #endif | 910 | #endif |
911 | } | 911 | } |
912 | 912 | ||
913 | static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) | 913 | static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) |
914 | { | 914 | { |
915 | #ifdef CONFIG_SMP | 915 | #ifdef CONFIG_SMP |
916 | /* | 916 | /* |
917 | * After ->on_cpu is cleared, the task can be moved to a different CPU. | 917 | * After ->on_cpu is cleared, the task can be moved to a different CPU. |
918 | * We must ensure this doesn't happen until the switch is completely | 918 | * We must ensure this doesn't happen until the switch is completely |
919 | * finished. | 919 | * finished. |
920 | */ | 920 | */ |
921 | smp_wmb(); | 921 | smp_wmb(); |
922 | prev->on_cpu = 0; | 922 | prev->on_cpu = 0; |
923 | #endif | 923 | #endif |
924 | #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW | 924 | #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW |
925 | local_irq_enable(); | 925 | local_irq_enable(); |
926 | #endif | 926 | #endif |
927 | } | 927 | } |
928 | #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ | 928 | #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ |
929 | 929 | ||
930 | /* | 930 | /* |
931 | * __task_rq_lock - lock the rq @p resides on. | 931 | * __task_rq_lock - lock the rq @p resides on. |
932 | */ | 932 | */ |
933 | static inline struct rq *__task_rq_lock(struct task_struct *p) | 933 | static inline struct rq *__task_rq_lock(struct task_struct *p) |
934 | __acquires(rq->lock) | 934 | __acquires(rq->lock) |
935 | { | 935 | { |
936 | struct rq *rq; | 936 | struct rq *rq; |
937 | 937 | ||
938 | lockdep_assert_held(&p->pi_lock); | 938 | lockdep_assert_held(&p->pi_lock); |
939 | 939 | ||
940 | for (;;) { | 940 | for (;;) { |
941 | rq = task_rq(p); | 941 | rq = task_rq(p); |
942 | raw_spin_lock(&rq->lock); | 942 | raw_spin_lock(&rq->lock); |
943 | if (likely(rq == task_rq(p))) | 943 | if (likely(rq == task_rq(p))) |
944 | return rq; | 944 | return rq; |
945 | raw_spin_unlock(&rq->lock); | 945 | raw_spin_unlock(&rq->lock); |
946 | } | 946 | } |
947 | } | 947 | } |
948 | 948 | ||
949 | /* | 949 | /* |
950 | * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. | 950 | * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. |
951 | */ | 951 | */ |
952 | static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) | 952 | static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) |
953 | __acquires(p->pi_lock) | 953 | __acquires(p->pi_lock) |
954 | __acquires(rq->lock) | 954 | __acquires(rq->lock) |
955 | { | 955 | { |
956 | struct rq *rq; | 956 | struct rq *rq; |
957 | 957 | ||
958 | for (;;) { | 958 | for (;;) { |
959 | raw_spin_lock_irqsave(&p->pi_lock, *flags); | 959 | raw_spin_lock_irqsave(&p->pi_lock, *flags); |
960 | rq = task_rq(p); | 960 | rq = task_rq(p); |
961 | raw_spin_lock(&rq->lock); | 961 | raw_spin_lock(&rq->lock); |
962 | if (likely(rq == task_rq(p))) | 962 | if (likely(rq == task_rq(p))) |
963 | return rq; | 963 | return rq; |
964 | raw_spin_unlock(&rq->lock); | 964 | raw_spin_unlock(&rq->lock); |
965 | raw_spin_unlock_irqrestore(&p->pi_lock, *flags); | 965 | raw_spin_unlock_irqrestore(&p->pi_lock, *flags); |
966 | } | 966 | } |
967 | } | 967 | } |
968 | 968 | ||
969 | static void __task_rq_unlock(struct rq *rq) | 969 | static void __task_rq_unlock(struct rq *rq) |
970 | __releases(rq->lock) | 970 | __releases(rq->lock) |
971 | { | 971 | { |
972 | raw_spin_unlock(&rq->lock); | 972 | raw_spin_unlock(&rq->lock); |
973 | } | 973 | } |
974 | 974 | ||
975 | static inline void | 975 | static inline void |
976 | task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) | 976 | task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) |
977 | __releases(rq->lock) | 977 | __releases(rq->lock) |
978 | __releases(p->pi_lock) | 978 | __releases(p->pi_lock) |
979 | { | 979 | { |
980 | raw_spin_unlock(&rq->lock); | 980 | raw_spin_unlock(&rq->lock); |
981 | raw_spin_unlock_irqrestore(&p->pi_lock, *flags); | 981 | raw_spin_unlock_irqrestore(&p->pi_lock, *flags); |
982 | } | 982 | } |
983 | 983 | ||
984 | /* | 984 | /* |
985 | * this_rq_lock - lock this runqueue and disable interrupts. | 985 | * this_rq_lock - lock this runqueue and disable interrupts. |
986 | */ | 986 | */ |
987 | static struct rq *this_rq_lock(void) | 987 | static struct rq *this_rq_lock(void) |
988 | __acquires(rq->lock) | 988 | __acquires(rq->lock) |
989 | { | 989 | { |
990 | struct rq *rq; | 990 | struct rq *rq; |
991 | 991 | ||
992 | local_irq_disable(); | 992 | local_irq_disable(); |
993 | rq = this_rq(); | 993 | rq = this_rq(); |
994 | raw_spin_lock(&rq->lock); | 994 | raw_spin_lock(&rq->lock); |
995 | 995 | ||
996 | return rq; | 996 | return rq; |
997 | } | 997 | } |
998 | 998 | ||
999 | #ifdef CONFIG_SCHED_HRTICK | 999 | #ifdef CONFIG_SCHED_HRTICK |
1000 | /* | 1000 | /* |
1001 | * Use HR-timers to deliver accurate preemption points. | 1001 | * Use HR-timers to deliver accurate preemption points. |
1002 | * | 1002 | * |
1003 | * Its all a bit involved since we cannot program an hrt while holding the | 1003 | * Its all a bit involved since we cannot program an hrt while holding the |
1004 | * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a | 1004 | * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a |
1005 | * reschedule event. | 1005 | * reschedule event. |
1006 | * | 1006 | * |
1007 | * When we get rescheduled we reprogram the hrtick_timer outside of the | 1007 | * When we get rescheduled we reprogram the hrtick_timer outside of the |
1008 | * rq->lock. | 1008 | * rq->lock. |
1009 | */ | 1009 | */ |
1010 | 1010 | ||
1011 | /* | 1011 | /* |
1012 | * Use hrtick when: | 1012 | * Use hrtick when: |
1013 | * - enabled by features | 1013 | * - enabled by features |
1014 | * - hrtimer is actually high res | 1014 | * - hrtimer is actually high res |
1015 | */ | 1015 | */ |
1016 | static inline int hrtick_enabled(struct rq *rq) | 1016 | static inline int hrtick_enabled(struct rq *rq) |
1017 | { | 1017 | { |
1018 | if (!sched_feat(HRTICK)) | 1018 | if (!sched_feat(HRTICK)) |
1019 | return 0; | 1019 | return 0; |
1020 | if (!cpu_active(cpu_of(rq))) | 1020 | if (!cpu_active(cpu_of(rq))) |
1021 | return 0; | 1021 | return 0; |
1022 | return hrtimer_is_hres_active(&rq->hrtick_timer); | 1022 | return hrtimer_is_hres_active(&rq->hrtick_timer); |
1023 | } | 1023 | } |
1024 | 1024 | ||
1025 | static void hrtick_clear(struct rq *rq) | 1025 | static void hrtick_clear(struct rq *rq) |
1026 | { | 1026 | { |
1027 | if (hrtimer_active(&rq->hrtick_timer)) | 1027 | if (hrtimer_active(&rq->hrtick_timer)) |
1028 | hrtimer_cancel(&rq->hrtick_timer); | 1028 | hrtimer_cancel(&rq->hrtick_timer); |
1029 | } | 1029 | } |
1030 | 1030 | ||
1031 | /* | 1031 | /* |
1032 | * High-resolution timer tick. | 1032 | * High-resolution timer tick. |
1033 | * Runs from hardirq context with interrupts disabled. | 1033 | * Runs from hardirq context with interrupts disabled. |
1034 | */ | 1034 | */ |
1035 | static enum hrtimer_restart hrtick(struct hrtimer *timer) | 1035 | static enum hrtimer_restart hrtick(struct hrtimer *timer) |
1036 | { | 1036 | { |
1037 | struct rq *rq = container_of(timer, struct rq, hrtick_timer); | 1037 | struct rq *rq = container_of(timer, struct rq, hrtick_timer); |
1038 | 1038 | ||
1039 | WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); | 1039 | WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); |
1040 | 1040 | ||
1041 | raw_spin_lock(&rq->lock); | 1041 | raw_spin_lock(&rq->lock); |
1042 | update_rq_clock(rq); | 1042 | update_rq_clock(rq); |
1043 | rq->curr->sched_class->task_tick(rq, rq->curr, 1); | 1043 | rq->curr->sched_class->task_tick(rq, rq->curr, 1); |
1044 | raw_spin_unlock(&rq->lock); | 1044 | raw_spin_unlock(&rq->lock); |
1045 | 1045 | ||
1046 | return HRTIMER_NORESTART; | 1046 | return HRTIMER_NORESTART; |
1047 | } | 1047 | } |
1048 | 1048 | ||
1049 | #ifdef CONFIG_SMP | 1049 | #ifdef CONFIG_SMP |
1050 | /* | 1050 | /* |
1051 | * called from hardirq (IPI) context | 1051 | * called from hardirq (IPI) context |
1052 | */ | 1052 | */ |
1053 | static void __hrtick_start(void *arg) | 1053 | static void __hrtick_start(void *arg) |
1054 | { | 1054 | { |
1055 | struct rq *rq = arg; | 1055 | struct rq *rq = arg; |
1056 | 1056 | ||
1057 | raw_spin_lock(&rq->lock); | 1057 | raw_spin_lock(&rq->lock); |
1058 | hrtimer_restart(&rq->hrtick_timer); | 1058 | hrtimer_restart(&rq->hrtick_timer); |
1059 | rq->hrtick_csd_pending = 0; | 1059 | rq->hrtick_csd_pending = 0; |
1060 | raw_spin_unlock(&rq->lock); | 1060 | raw_spin_unlock(&rq->lock); |
1061 | } | 1061 | } |
1062 | 1062 | ||
1063 | /* | 1063 | /* |
1064 | * Called to set the hrtick timer state. | 1064 | * Called to set the hrtick timer state. |
1065 | * | 1065 | * |
1066 | * called with rq->lock held and irqs disabled | 1066 | * called with rq->lock held and irqs disabled |
1067 | */ | 1067 | */ |
1068 | static void hrtick_start(struct rq *rq, u64 delay) | 1068 | static void hrtick_start(struct rq *rq, u64 delay) |
1069 | { | 1069 | { |
1070 | struct hrtimer *timer = &rq->hrtick_timer; | 1070 | struct hrtimer *timer = &rq->hrtick_timer; |
1071 | ktime_t time = ktime_add_ns(timer->base->get_time(), delay); | 1071 | ktime_t time = ktime_add_ns(timer->base->get_time(), delay); |
1072 | 1072 | ||
1073 | hrtimer_set_expires(timer, time); | 1073 | hrtimer_set_expires(timer, time); |
1074 | 1074 | ||
1075 | if (rq == this_rq()) { | 1075 | if (rq == this_rq()) { |
1076 | hrtimer_restart(timer); | 1076 | hrtimer_restart(timer); |
1077 | } else if (!rq->hrtick_csd_pending) { | 1077 | } else if (!rq->hrtick_csd_pending) { |
1078 | __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); | 1078 | __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); |
1079 | rq->hrtick_csd_pending = 1; | 1079 | rq->hrtick_csd_pending = 1; |
1080 | } | 1080 | } |
1081 | } | 1081 | } |
1082 | 1082 | ||
1083 | static int | 1083 | static int |
1084 | hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) | 1084 | hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) |
1085 | { | 1085 | { |
1086 | int cpu = (int)(long)hcpu; | 1086 | int cpu = (int)(long)hcpu; |
1087 | 1087 | ||
1088 | switch (action) { | 1088 | switch (action) { |
1089 | case CPU_UP_CANCELED: | 1089 | case CPU_UP_CANCELED: |
1090 | case CPU_UP_CANCELED_FROZEN: | 1090 | case CPU_UP_CANCELED_FROZEN: |
1091 | case CPU_DOWN_PREPARE: | 1091 | case CPU_DOWN_PREPARE: |
1092 | case CPU_DOWN_PREPARE_FROZEN: | 1092 | case CPU_DOWN_PREPARE_FROZEN: |
1093 | case CPU_DEAD: | 1093 | case CPU_DEAD: |
1094 | case CPU_DEAD_FROZEN: | 1094 | case CPU_DEAD_FROZEN: |
1095 | hrtick_clear(cpu_rq(cpu)); | 1095 | hrtick_clear(cpu_rq(cpu)); |
1096 | return NOTIFY_OK; | 1096 | return NOTIFY_OK; |
1097 | } | 1097 | } |
1098 | 1098 | ||
1099 | return NOTIFY_DONE; | 1099 | return NOTIFY_DONE; |
1100 | } | 1100 | } |
1101 | 1101 | ||
1102 | static __init void init_hrtick(void) | 1102 | static __init void init_hrtick(void) |
1103 | { | 1103 | { |
1104 | hotcpu_notifier(hotplug_hrtick, 0); | 1104 | hotcpu_notifier(hotplug_hrtick, 0); |
1105 | } | 1105 | } |
1106 | #else | 1106 | #else |
1107 | /* | 1107 | /* |
1108 | * Called to set the hrtick timer state. | 1108 | * Called to set the hrtick timer state. |
1109 | * | 1109 | * |
1110 | * called with rq->lock held and irqs disabled | 1110 | * called with rq->lock held and irqs disabled |
1111 | */ | 1111 | */ |
1112 | static void hrtick_start(struct rq *rq, u64 delay) | 1112 | static void hrtick_start(struct rq *rq, u64 delay) |
1113 | { | 1113 | { |
1114 | __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, | 1114 | __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, |
1115 | HRTIMER_MODE_REL_PINNED, 0); | 1115 | HRTIMER_MODE_REL_PINNED, 0); |
1116 | } | 1116 | } |
1117 | 1117 | ||
1118 | static inline void init_hrtick(void) | 1118 | static inline void init_hrtick(void) |
1119 | { | 1119 | { |
1120 | } | 1120 | } |
1121 | #endif /* CONFIG_SMP */ | 1121 | #endif /* CONFIG_SMP */ |
1122 | 1122 | ||
1123 | static void init_rq_hrtick(struct rq *rq) | 1123 | static void init_rq_hrtick(struct rq *rq) |
1124 | { | 1124 | { |
1125 | #ifdef CONFIG_SMP | 1125 | #ifdef CONFIG_SMP |
1126 | rq->hrtick_csd_pending = 0; | 1126 | rq->hrtick_csd_pending = 0; |
1127 | 1127 | ||
1128 | rq->hrtick_csd.flags = 0; | 1128 | rq->hrtick_csd.flags = 0; |
1129 | rq->hrtick_csd.func = __hrtick_start; | 1129 | rq->hrtick_csd.func = __hrtick_start; |
1130 | rq->hrtick_csd.info = rq; | 1130 | rq->hrtick_csd.info = rq; |
1131 | #endif | 1131 | #endif |
1132 | 1132 | ||
1133 | hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); | 1133 | hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); |
1134 | rq->hrtick_timer.function = hrtick; | 1134 | rq->hrtick_timer.function = hrtick; |
1135 | } | 1135 | } |
1136 | #else /* CONFIG_SCHED_HRTICK */ | 1136 | #else /* CONFIG_SCHED_HRTICK */ |
1137 | static inline void hrtick_clear(struct rq *rq) | 1137 | static inline void hrtick_clear(struct rq *rq) |
1138 | { | 1138 | { |
1139 | } | 1139 | } |
1140 | 1140 | ||
1141 | static inline void init_rq_hrtick(struct rq *rq) | 1141 | static inline void init_rq_hrtick(struct rq *rq) |
1142 | { | 1142 | { |
1143 | } | 1143 | } |
1144 | 1144 | ||
1145 | static inline void init_hrtick(void) | 1145 | static inline void init_hrtick(void) |
1146 | { | 1146 | { |
1147 | } | 1147 | } |
1148 | #endif /* CONFIG_SCHED_HRTICK */ | 1148 | #endif /* CONFIG_SCHED_HRTICK */ |
1149 | 1149 | ||
1150 | /* | 1150 | /* |
1151 | * resched_task - mark a task 'to be rescheduled now'. | 1151 | * resched_task - mark a task 'to be rescheduled now'. |
1152 | * | 1152 | * |
1153 | * On UP this means the setting of the need_resched flag, on SMP it | 1153 | * On UP this means the setting of the need_resched flag, on SMP it |
1154 | * might also involve a cross-CPU call to trigger the scheduler on | 1154 | * might also involve a cross-CPU call to trigger the scheduler on |
1155 | * the target CPU. | 1155 | * the target CPU. |
1156 | */ | 1156 | */ |
1157 | #ifdef CONFIG_SMP | 1157 | #ifdef CONFIG_SMP |
1158 | 1158 | ||
1159 | #ifndef tsk_is_polling | 1159 | #ifndef tsk_is_polling |
1160 | #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) | 1160 | #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) |
1161 | #endif | 1161 | #endif |
1162 | 1162 | ||
1163 | static void resched_task(struct task_struct *p) | 1163 | static void resched_task(struct task_struct *p) |
1164 | { | 1164 | { |
1165 | int cpu; | 1165 | int cpu; |
1166 | 1166 | ||
1167 | assert_raw_spin_locked(&task_rq(p)->lock); | 1167 | assert_raw_spin_locked(&task_rq(p)->lock); |
1168 | 1168 | ||
1169 | if (test_tsk_need_resched(p)) | 1169 | if (test_tsk_need_resched(p)) |
1170 | return; | 1170 | return; |
1171 | 1171 | ||
1172 | set_tsk_need_resched(p); | 1172 | set_tsk_need_resched(p); |
1173 | 1173 | ||
1174 | cpu = task_cpu(p); | 1174 | cpu = task_cpu(p); |
1175 | if (cpu == smp_processor_id()) | 1175 | if (cpu == smp_processor_id()) |
1176 | return; | 1176 | return; |
1177 | 1177 | ||
1178 | /* NEED_RESCHED must be visible before we test polling */ | 1178 | /* NEED_RESCHED must be visible before we test polling */ |
1179 | smp_mb(); | 1179 | smp_mb(); |
1180 | if (!tsk_is_polling(p)) | 1180 | if (!tsk_is_polling(p)) |
1181 | smp_send_reschedule(cpu); | 1181 | smp_send_reschedule(cpu); |
1182 | } | 1182 | } |
1183 | 1183 | ||
1184 | static void resched_cpu(int cpu) | 1184 | static void resched_cpu(int cpu) |
1185 | { | 1185 | { |
1186 | struct rq *rq = cpu_rq(cpu); | 1186 | struct rq *rq = cpu_rq(cpu); |
1187 | unsigned long flags; | 1187 | unsigned long flags; |
1188 | 1188 | ||
1189 | if (!raw_spin_trylock_irqsave(&rq->lock, flags)) | 1189 | if (!raw_spin_trylock_irqsave(&rq->lock, flags)) |
1190 | return; | 1190 | return; |
1191 | resched_task(cpu_curr(cpu)); | 1191 | resched_task(cpu_curr(cpu)); |
1192 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 1192 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
1193 | } | 1193 | } |
1194 | 1194 | ||
1195 | #ifdef CONFIG_NO_HZ | 1195 | #ifdef CONFIG_NO_HZ |
1196 | /* | 1196 | /* |
1197 | * In the semi idle case, use the nearest busy cpu for migrating timers | 1197 | * In the semi idle case, use the nearest busy cpu for migrating timers |
1198 | * from an idle cpu. This is good for power-savings. | 1198 | * from an idle cpu. This is good for power-savings. |
1199 | * | 1199 | * |
1200 | * We don't do similar optimization for completely idle system, as | 1200 | * We don't do similar optimization for completely idle system, as |
1201 | * selecting an idle cpu will add more delays to the timers than intended | 1201 | * selecting an idle cpu will add more delays to the timers than intended |
1202 | * (as that cpu's timer base may not be uptodate wrt jiffies etc). | 1202 | * (as that cpu's timer base may not be uptodate wrt jiffies etc). |
1203 | */ | 1203 | */ |
1204 | int get_nohz_timer_target(void) | 1204 | int get_nohz_timer_target(void) |
1205 | { | 1205 | { |
1206 | int cpu = smp_processor_id(); | 1206 | int cpu = smp_processor_id(); |
1207 | int i; | 1207 | int i; |
1208 | struct sched_domain *sd; | 1208 | struct sched_domain *sd; |
1209 | 1209 | ||
1210 | for_each_domain(cpu, sd) { | 1210 | for_each_domain(cpu, sd) { |
1211 | for_each_cpu(i, sched_domain_span(sd)) | 1211 | for_each_cpu(i, sched_domain_span(sd)) |
1212 | if (!idle_cpu(i)) | 1212 | if (!idle_cpu(i)) |
1213 | return i; | 1213 | return i; |
1214 | } | 1214 | } |
1215 | return cpu; | 1215 | return cpu; |
1216 | } | 1216 | } |
1217 | /* | 1217 | /* |
1218 | * When add_timer_on() enqueues a timer into the timer wheel of an | 1218 | * When add_timer_on() enqueues a timer into the timer wheel of an |
1219 | * idle CPU then this timer might expire before the next timer event | 1219 | * idle CPU then this timer might expire before the next timer event |
1220 | * which is scheduled to wake up that CPU. In case of a completely | 1220 | * which is scheduled to wake up that CPU. In case of a completely |
1221 | * idle system the next event might even be infinite time into the | 1221 | * idle system the next event might even be infinite time into the |
1222 | * future. wake_up_idle_cpu() ensures that the CPU is woken up and | 1222 | * future. wake_up_idle_cpu() ensures that the CPU is woken up and |
1223 | * leaves the inner idle loop so the newly added timer is taken into | 1223 | * leaves the inner idle loop so the newly added timer is taken into |
1224 | * account when the CPU goes back to idle and evaluates the timer | 1224 | * account when the CPU goes back to idle and evaluates the timer |
1225 | * wheel for the next timer event. | 1225 | * wheel for the next timer event. |
1226 | */ | 1226 | */ |
1227 | void wake_up_idle_cpu(int cpu) | 1227 | void wake_up_idle_cpu(int cpu) |
1228 | { | 1228 | { |
1229 | struct rq *rq = cpu_rq(cpu); | 1229 | struct rq *rq = cpu_rq(cpu); |
1230 | 1230 | ||
1231 | if (cpu == smp_processor_id()) | 1231 | if (cpu == smp_processor_id()) |
1232 | return; | 1232 | return; |
1233 | 1233 | ||
1234 | /* | 1234 | /* |
1235 | * This is safe, as this function is called with the timer | 1235 | * This is safe, as this function is called with the timer |
1236 | * wheel base lock of (cpu) held. When the CPU is on the way | 1236 | * wheel base lock of (cpu) held. When the CPU is on the way |
1237 | * to idle and has not yet set rq->curr to idle then it will | 1237 | * to idle and has not yet set rq->curr to idle then it will |
1238 | * be serialized on the timer wheel base lock and take the new | 1238 | * be serialized on the timer wheel base lock and take the new |
1239 | * timer into account automatically. | 1239 | * timer into account automatically. |
1240 | */ | 1240 | */ |
1241 | if (rq->curr != rq->idle) | 1241 | if (rq->curr != rq->idle) |
1242 | return; | 1242 | return; |
1243 | 1243 | ||
1244 | /* | 1244 | /* |
1245 | * We can set TIF_RESCHED on the idle task of the other CPU | 1245 | * We can set TIF_RESCHED on the idle task of the other CPU |
1246 | * lockless. The worst case is that the other CPU runs the | 1246 | * lockless. The worst case is that the other CPU runs the |
1247 | * idle task through an additional NOOP schedule() | 1247 | * idle task through an additional NOOP schedule() |
1248 | */ | 1248 | */ |
1249 | set_tsk_need_resched(rq->idle); | 1249 | set_tsk_need_resched(rq->idle); |
1250 | 1250 | ||
1251 | /* NEED_RESCHED must be visible before we test polling */ | 1251 | /* NEED_RESCHED must be visible before we test polling */ |
1252 | smp_mb(); | 1252 | smp_mb(); |
1253 | if (!tsk_is_polling(rq->idle)) | 1253 | if (!tsk_is_polling(rq->idle)) |
1254 | smp_send_reschedule(cpu); | 1254 | smp_send_reschedule(cpu); |
1255 | } | 1255 | } |
1256 | 1256 | ||
1257 | #endif /* CONFIG_NO_HZ */ | 1257 | #endif /* CONFIG_NO_HZ */ |
1258 | 1258 | ||
1259 | static u64 sched_avg_period(void) | 1259 | static u64 sched_avg_period(void) |
1260 | { | 1260 | { |
1261 | return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; | 1261 | return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; |
1262 | } | 1262 | } |
1263 | 1263 | ||
1264 | static void sched_avg_update(struct rq *rq) | 1264 | static void sched_avg_update(struct rq *rq) |
1265 | { | 1265 | { |
1266 | s64 period = sched_avg_period(); | 1266 | s64 period = sched_avg_period(); |
1267 | 1267 | ||
1268 | while ((s64)(rq->clock - rq->age_stamp) > period) { | 1268 | while ((s64)(rq->clock - rq->age_stamp) > period) { |
1269 | /* | 1269 | /* |
1270 | * Inline assembly required to prevent the compiler | 1270 | * Inline assembly required to prevent the compiler |
1271 | * optimising this loop into a divmod call. | 1271 | * optimising this loop into a divmod call. |
1272 | * See __iter_div_u64_rem() for another example of this. | 1272 | * See __iter_div_u64_rem() for another example of this. |
1273 | */ | 1273 | */ |
1274 | asm("" : "+rm" (rq->age_stamp)); | 1274 | asm("" : "+rm" (rq->age_stamp)); |
1275 | rq->age_stamp += period; | 1275 | rq->age_stamp += period; |
1276 | rq->rt_avg /= 2; | 1276 | rq->rt_avg /= 2; |
1277 | } | 1277 | } |
1278 | } | 1278 | } |
1279 | 1279 | ||
1280 | static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) | 1280 | static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) |
1281 | { | 1281 | { |
1282 | rq->rt_avg += rt_delta; | 1282 | rq->rt_avg += rt_delta; |
1283 | sched_avg_update(rq); | 1283 | sched_avg_update(rq); |
1284 | } | 1284 | } |
1285 | 1285 | ||
1286 | #else /* !CONFIG_SMP */ | 1286 | #else /* !CONFIG_SMP */ |
1287 | static void resched_task(struct task_struct *p) | 1287 | static void resched_task(struct task_struct *p) |
1288 | { | 1288 | { |
1289 | assert_raw_spin_locked(&task_rq(p)->lock); | 1289 | assert_raw_spin_locked(&task_rq(p)->lock); |
1290 | set_tsk_need_resched(p); | 1290 | set_tsk_need_resched(p); |
1291 | } | 1291 | } |
1292 | 1292 | ||
1293 | static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) | 1293 | static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) |
1294 | { | 1294 | { |
1295 | } | 1295 | } |
1296 | 1296 | ||
1297 | static void sched_avg_update(struct rq *rq) | 1297 | static void sched_avg_update(struct rq *rq) |
1298 | { | 1298 | { |
1299 | } | 1299 | } |
1300 | #endif /* CONFIG_SMP */ | 1300 | #endif /* CONFIG_SMP */ |
1301 | 1301 | ||
1302 | #if BITS_PER_LONG == 32 | 1302 | #if BITS_PER_LONG == 32 |
1303 | # define WMULT_CONST (~0UL) | 1303 | # define WMULT_CONST (~0UL) |
1304 | #else | 1304 | #else |
1305 | # define WMULT_CONST (1UL << 32) | 1305 | # define WMULT_CONST (1UL << 32) |
1306 | #endif | 1306 | #endif |
1307 | 1307 | ||
1308 | #define WMULT_SHIFT 32 | 1308 | #define WMULT_SHIFT 32 |
1309 | 1309 | ||
1310 | /* | 1310 | /* |
1311 | * Shift right and round: | 1311 | * Shift right and round: |
1312 | */ | 1312 | */ |
1313 | #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) | 1313 | #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) |
1314 | 1314 | ||
1315 | /* | 1315 | /* |
1316 | * delta *= weight / lw | 1316 | * delta *= weight / lw |
1317 | */ | 1317 | */ |
1318 | static unsigned long | 1318 | static unsigned long |
1319 | calc_delta_mine(unsigned long delta_exec, unsigned long weight, | 1319 | calc_delta_mine(unsigned long delta_exec, unsigned long weight, |
1320 | struct load_weight *lw) | 1320 | struct load_weight *lw) |
1321 | { | 1321 | { |
1322 | u64 tmp; | 1322 | u64 tmp; |
1323 | 1323 | ||
1324 | if (!lw->inv_weight) { | 1324 | if (!lw->inv_weight) { |
1325 | if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) | 1325 | if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) |
1326 | lw->inv_weight = 1; | 1326 | lw->inv_weight = 1; |
1327 | else | 1327 | else |
1328 | lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) | 1328 | lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) |
1329 | / (lw->weight+1); | 1329 | / (lw->weight+1); |
1330 | } | 1330 | } |
1331 | 1331 | ||
1332 | tmp = (u64)delta_exec * weight; | 1332 | tmp = (u64)delta_exec * weight; |
1333 | /* | 1333 | /* |
1334 | * Check whether we'd overflow the 64-bit multiplication: | 1334 | * Check whether we'd overflow the 64-bit multiplication: |
1335 | */ | 1335 | */ |
1336 | if (unlikely(tmp > WMULT_CONST)) | 1336 | if (unlikely(tmp > WMULT_CONST)) |
1337 | tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, | 1337 | tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, |
1338 | WMULT_SHIFT/2); | 1338 | WMULT_SHIFT/2); |
1339 | else | 1339 | else |
1340 | tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); | 1340 | tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); |
1341 | 1341 | ||
1342 | return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); | 1342 | return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); |
1343 | } | 1343 | } |
1344 | 1344 | ||
1345 | static inline void update_load_add(struct load_weight *lw, unsigned long inc) | 1345 | static inline void update_load_add(struct load_weight *lw, unsigned long inc) |
1346 | { | 1346 | { |
1347 | lw->weight += inc; | 1347 | lw->weight += inc; |
1348 | lw->inv_weight = 0; | 1348 | lw->inv_weight = 0; |
1349 | } | 1349 | } |
1350 | 1350 | ||
1351 | static inline void update_load_sub(struct load_weight *lw, unsigned long dec) | 1351 | static inline void update_load_sub(struct load_weight *lw, unsigned long dec) |
1352 | { | 1352 | { |
1353 | lw->weight -= dec; | 1353 | lw->weight -= dec; |
1354 | lw->inv_weight = 0; | 1354 | lw->inv_weight = 0; |
1355 | } | 1355 | } |
1356 | 1356 | ||
1357 | static inline void update_load_set(struct load_weight *lw, unsigned long w) | 1357 | static inline void update_load_set(struct load_weight *lw, unsigned long w) |
1358 | { | 1358 | { |
1359 | lw->weight = w; | 1359 | lw->weight = w; |
1360 | lw->inv_weight = 0; | 1360 | lw->inv_weight = 0; |
1361 | } | 1361 | } |
1362 | 1362 | ||
1363 | /* | 1363 | /* |
1364 | * To aid in avoiding the subversion of "niceness" due to uneven distribution | 1364 | * To aid in avoiding the subversion of "niceness" due to uneven distribution |
1365 | * of tasks with abnormal "nice" values across CPUs the contribution that | 1365 | * of tasks with abnormal "nice" values across CPUs the contribution that |
1366 | * each task makes to its run queue's load is weighted according to its | 1366 | * each task makes to its run queue's load is weighted according to its |
1367 | * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a | 1367 | * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a |
1368 | * scaled version of the new time slice allocation that they receive on time | 1368 | * scaled version of the new time slice allocation that they receive on time |
1369 | * slice expiry etc. | 1369 | * slice expiry etc. |
1370 | */ | 1370 | */ |
1371 | 1371 | ||
1372 | #define WEIGHT_IDLEPRIO 3 | 1372 | #define WEIGHT_IDLEPRIO 3 |
1373 | #define WMULT_IDLEPRIO 1431655765 | 1373 | #define WMULT_IDLEPRIO 1431655765 |
1374 | 1374 | ||
1375 | /* | 1375 | /* |
1376 | * Nice levels are multiplicative, with a gentle 10% change for every | 1376 | * Nice levels are multiplicative, with a gentle 10% change for every |
1377 | * nice level changed. I.e. when a CPU-bound task goes from nice 0 to | 1377 | * nice level changed. I.e. when a CPU-bound task goes from nice 0 to |
1378 | * nice 1, it will get ~10% less CPU time than another CPU-bound task | 1378 | * nice 1, it will get ~10% less CPU time than another CPU-bound task |
1379 | * that remained on nice 0. | 1379 | * that remained on nice 0. |
1380 | * | 1380 | * |
1381 | * The "10% effect" is relative and cumulative: from _any_ nice level, | 1381 | * The "10% effect" is relative and cumulative: from _any_ nice level, |
1382 | * if you go up 1 level, it's -10% CPU usage, if you go down 1 level | 1382 | * if you go up 1 level, it's -10% CPU usage, if you go down 1 level |
1383 | * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. | 1383 | * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. |
1384 | * If a task goes up by ~10% and another task goes down by ~10% then | 1384 | * If a task goes up by ~10% and another task goes down by ~10% then |
1385 | * the relative distance between them is ~25%.) | 1385 | * the relative distance between them is ~25%.) |
1386 | */ | 1386 | */ |
1387 | static const int prio_to_weight[40] = { | 1387 | static const int prio_to_weight[40] = { |
1388 | /* -20 */ 88761, 71755, 56483, 46273, 36291, | 1388 | /* -20 */ 88761, 71755, 56483, 46273, 36291, |
1389 | /* -15 */ 29154, 23254, 18705, 14949, 11916, | 1389 | /* -15 */ 29154, 23254, 18705, 14949, 11916, |
1390 | /* -10 */ 9548, 7620, 6100, 4904, 3906, | 1390 | /* -10 */ 9548, 7620, 6100, 4904, 3906, |
1391 | /* -5 */ 3121, 2501, 1991, 1586, 1277, | 1391 | /* -5 */ 3121, 2501, 1991, 1586, 1277, |
1392 | /* 0 */ 1024, 820, 655, 526, 423, | 1392 | /* 0 */ 1024, 820, 655, 526, 423, |
1393 | /* 5 */ 335, 272, 215, 172, 137, | 1393 | /* 5 */ 335, 272, 215, 172, 137, |
1394 | /* 10 */ 110, 87, 70, 56, 45, | 1394 | /* 10 */ 110, 87, 70, 56, 45, |
1395 | /* 15 */ 36, 29, 23, 18, 15, | 1395 | /* 15 */ 36, 29, 23, 18, 15, |
1396 | }; | 1396 | }; |
1397 | 1397 | ||
1398 | /* | 1398 | /* |
1399 | * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. | 1399 | * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. |
1400 | * | 1400 | * |
1401 | * In cases where the weight does not change often, we can use the | 1401 | * In cases where the weight does not change often, we can use the |
1402 | * precalculated inverse to speed up arithmetics by turning divisions | 1402 | * precalculated inverse to speed up arithmetics by turning divisions |
1403 | * into multiplications: | 1403 | * into multiplications: |
1404 | */ | 1404 | */ |
1405 | static const u32 prio_to_wmult[40] = { | 1405 | static const u32 prio_to_wmult[40] = { |
1406 | /* -20 */ 48388, 59856, 76040, 92818, 118348, | 1406 | /* -20 */ 48388, 59856, 76040, 92818, 118348, |
1407 | /* -15 */ 147320, 184698, 229616, 287308, 360437, | 1407 | /* -15 */ 147320, 184698, 229616, 287308, 360437, |
1408 | /* -10 */ 449829, 563644, 704093, 875809, 1099582, | 1408 | /* -10 */ 449829, 563644, 704093, 875809, 1099582, |
1409 | /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, | 1409 | /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, |
1410 | /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, | 1410 | /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, |
1411 | /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, | 1411 | /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, |
1412 | /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, | 1412 | /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, |
1413 | /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, | 1413 | /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, |
1414 | }; | 1414 | }; |
1415 | 1415 | ||
1416 | /* Time spent by the tasks of the cpu accounting group executing in ... */ | 1416 | /* Time spent by the tasks of the cpu accounting group executing in ... */ |
1417 | enum cpuacct_stat_index { | 1417 | enum cpuacct_stat_index { |
1418 | CPUACCT_STAT_USER, /* ... user mode */ | 1418 | CPUACCT_STAT_USER, /* ... user mode */ |
1419 | CPUACCT_STAT_SYSTEM, /* ... kernel mode */ | 1419 | CPUACCT_STAT_SYSTEM, /* ... kernel mode */ |
1420 | 1420 | ||
1421 | CPUACCT_STAT_NSTATS, | 1421 | CPUACCT_STAT_NSTATS, |
1422 | }; | 1422 | }; |
1423 | 1423 | ||
1424 | #ifdef CONFIG_CGROUP_CPUACCT | 1424 | #ifdef CONFIG_CGROUP_CPUACCT |
1425 | static void cpuacct_charge(struct task_struct *tsk, u64 cputime); | 1425 | static void cpuacct_charge(struct task_struct *tsk, u64 cputime); |
1426 | static void cpuacct_update_stats(struct task_struct *tsk, | 1426 | static void cpuacct_update_stats(struct task_struct *tsk, |
1427 | enum cpuacct_stat_index idx, cputime_t val); | 1427 | enum cpuacct_stat_index idx, cputime_t val); |
1428 | #else | 1428 | #else |
1429 | static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} | 1429 | static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} |
1430 | static inline void cpuacct_update_stats(struct task_struct *tsk, | 1430 | static inline void cpuacct_update_stats(struct task_struct *tsk, |
1431 | enum cpuacct_stat_index idx, cputime_t val) {} | 1431 | enum cpuacct_stat_index idx, cputime_t val) {} |
1432 | #endif | 1432 | #endif |
1433 | 1433 | ||
1434 | static inline void inc_cpu_load(struct rq *rq, unsigned long load) | 1434 | static inline void inc_cpu_load(struct rq *rq, unsigned long load) |
1435 | { | 1435 | { |
1436 | update_load_add(&rq->load, load); | 1436 | update_load_add(&rq->load, load); |
1437 | } | 1437 | } |
1438 | 1438 | ||
1439 | static inline void dec_cpu_load(struct rq *rq, unsigned long load) | 1439 | static inline void dec_cpu_load(struct rq *rq, unsigned long load) |
1440 | { | 1440 | { |
1441 | update_load_sub(&rq->load, load); | 1441 | update_load_sub(&rq->load, load); |
1442 | } | 1442 | } |
1443 | 1443 | ||
1444 | #if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED) | 1444 | #if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED) |
1445 | typedef int (*tg_visitor)(struct task_group *, void *); | 1445 | typedef int (*tg_visitor)(struct task_group *, void *); |
1446 | 1446 | ||
1447 | /* | 1447 | /* |
1448 | * Iterate the full tree, calling @down when first entering a node and @up when | 1448 | * Iterate the full tree, calling @down when first entering a node and @up when |
1449 | * leaving it for the final time. | 1449 | * leaving it for the final time. |
1450 | */ | 1450 | */ |
1451 | static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) | 1451 | static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) |
1452 | { | 1452 | { |
1453 | struct task_group *parent, *child; | 1453 | struct task_group *parent, *child; |
1454 | int ret; | 1454 | int ret; |
1455 | 1455 | ||
1456 | rcu_read_lock(); | 1456 | rcu_read_lock(); |
1457 | parent = &root_task_group; | 1457 | parent = &root_task_group; |
1458 | down: | 1458 | down: |
1459 | ret = (*down)(parent, data); | 1459 | ret = (*down)(parent, data); |
1460 | if (ret) | 1460 | if (ret) |
1461 | goto out_unlock; | 1461 | goto out_unlock; |
1462 | list_for_each_entry_rcu(child, &parent->children, siblings) { | 1462 | list_for_each_entry_rcu(child, &parent->children, siblings) { |
1463 | parent = child; | 1463 | parent = child; |
1464 | goto down; | 1464 | goto down; |
1465 | 1465 | ||
1466 | up: | 1466 | up: |
1467 | continue; | 1467 | continue; |
1468 | } | 1468 | } |
1469 | ret = (*up)(parent, data); | 1469 | ret = (*up)(parent, data); |
1470 | if (ret) | 1470 | if (ret) |
1471 | goto out_unlock; | 1471 | goto out_unlock; |
1472 | 1472 | ||
1473 | child = parent; | 1473 | child = parent; |
1474 | parent = parent->parent; | 1474 | parent = parent->parent; |
1475 | if (parent) | 1475 | if (parent) |
1476 | goto up; | 1476 | goto up; |
1477 | out_unlock: | 1477 | out_unlock: |
1478 | rcu_read_unlock(); | 1478 | rcu_read_unlock(); |
1479 | 1479 | ||
1480 | return ret; | 1480 | return ret; |
1481 | } | 1481 | } |
1482 | 1482 | ||
1483 | static int tg_nop(struct task_group *tg, void *data) | 1483 | static int tg_nop(struct task_group *tg, void *data) |
1484 | { | 1484 | { |
1485 | return 0; | 1485 | return 0; |
1486 | } | 1486 | } |
1487 | #endif | 1487 | #endif |
1488 | 1488 | ||
1489 | #ifdef CONFIG_SMP | 1489 | #ifdef CONFIG_SMP |
1490 | /* Used instead of source_load when we know the type == 0 */ | 1490 | /* Used instead of source_load when we know the type == 0 */ |
1491 | static unsigned long weighted_cpuload(const int cpu) | 1491 | static unsigned long weighted_cpuload(const int cpu) |
1492 | { | 1492 | { |
1493 | return cpu_rq(cpu)->load.weight; | 1493 | return cpu_rq(cpu)->load.weight; |
1494 | } | 1494 | } |
1495 | 1495 | ||
1496 | /* | 1496 | /* |
1497 | * Return a low guess at the load of a migration-source cpu weighted | 1497 | * Return a low guess at the load of a migration-source cpu weighted |
1498 | * according to the scheduling class and "nice" value. | 1498 | * according to the scheduling class and "nice" value. |
1499 | * | 1499 | * |
1500 | * We want to under-estimate the load of migration sources, to | 1500 | * We want to under-estimate the load of migration sources, to |
1501 | * balance conservatively. | 1501 | * balance conservatively. |
1502 | */ | 1502 | */ |
1503 | static unsigned long source_load(int cpu, int type) | 1503 | static unsigned long source_load(int cpu, int type) |
1504 | { | 1504 | { |
1505 | struct rq *rq = cpu_rq(cpu); | 1505 | struct rq *rq = cpu_rq(cpu); |
1506 | unsigned long total = weighted_cpuload(cpu); | 1506 | unsigned long total = weighted_cpuload(cpu); |
1507 | 1507 | ||
1508 | if (type == 0 || !sched_feat(LB_BIAS)) | 1508 | if (type == 0 || !sched_feat(LB_BIAS)) |
1509 | return total; | 1509 | return total; |
1510 | 1510 | ||
1511 | return min(rq->cpu_load[type-1], total); | 1511 | return min(rq->cpu_load[type-1], total); |
1512 | } | 1512 | } |
1513 | 1513 | ||
1514 | /* | 1514 | /* |
1515 | * Return a high guess at the load of a migration-target cpu weighted | 1515 | * Return a high guess at the load of a migration-target cpu weighted |
1516 | * according to the scheduling class and "nice" value. | 1516 | * according to the scheduling class and "nice" value. |
1517 | */ | 1517 | */ |
1518 | static unsigned long target_load(int cpu, int type) | 1518 | static unsigned long target_load(int cpu, int type) |
1519 | { | 1519 | { |
1520 | struct rq *rq = cpu_rq(cpu); | 1520 | struct rq *rq = cpu_rq(cpu); |
1521 | unsigned long total = weighted_cpuload(cpu); | 1521 | unsigned long total = weighted_cpuload(cpu); |
1522 | 1522 | ||
1523 | if (type == 0 || !sched_feat(LB_BIAS)) | 1523 | if (type == 0 || !sched_feat(LB_BIAS)) |
1524 | return total; | 1524 | return total; |
1525 | 1525 | ||
1526 | return max(rq->cpu_load[type-1], total); | 1526 | return max(rq->cpu_load[type-1], total); |
1527 | } | 1527 | } |
1528 | 1528 | ||
1529 | static unsigned long power_of(int cpu) | 1529 | static unsigned long power_of(int cpu) |
1530 | { | 1530 | { |
1531 | return cpu_rq(cpu)->cpu_power; | 1531 | return cpu_rq(cpu)->cpu_power; |
1532 | } | 1532 | } |
1533 | 1533 | ||
1534 | static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); | 1534 | static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); |
1535 | 1535 | ||
1536 | static unsigned long cpu_avg_load_per_task(int cpu) | 1536 | static unsigned long cpu_avg_load_per_task(int cpu) |
1537 | { | 1537 | { |
1538 | struct rq *rq = cpu_rq(cpu); | 1538 | struct rq *rq = cpu_rq(cpu); |
1539 | unsigned long nr_running = ACCESS_ONCE(rq->nr_running); | 1539 | unsigned long nr_running = ACCESS_ONCE(rq->nr_running); |
1540 | 1540 | ||
1541 | if (nr_running) | 1541 | if (nr_running) |
1542 | rq->avg_load_per_task = rq->load.weight / nr_running; | 1542 | rq->avg_load_per_task = rq->load.weight / nr_running; |
1543 | else | 1543 | else |
1544 | rq->avg_load_per_task = 0; | 1544 | rq->avg_load_per_task = 0; |
1545 | 1545 | ||
1546 | return rq->avg_load_per_task; | 1546 | return rq->avg_load_per_task; |
1547 | } | 1547 | } |
1548 | 1548 | ||
1549 | #ifdef CONFIG_FAIR_GROUP_SCHED | 1549 | #ifdef CONFIG_FAIR_GROUP_SCHED |
1550 | 1550 | ||
1551 | /* | 1551 | /* |
1552 | * Compute the cpu's hierarchical load factor for each task group. | 1552 | * Compute the cpu's hierarchical load factor for each task group. |
1553 | * This needs to be done in a top-down fashion because the load of a child | 1553 | * This needs to be done in a top-down fashion because the load of a child |
1554 | * group is a fraction of its parents load. | 1554 | * group is a fraction of its parents load. |
1555 | */ | 1555 | */ |
1556 | static int tg_load_down(struct task_group *tg, void *data) | 1556 | static int tg_load_down(struct task_group *tg, void *data) |
1557 | { | 1557 | { |
1558 | unsigned long load; | 1558 | unsigned long load; |
1559 | long cpu = (long)data; | 1559 | long cpu = (long)data; |
1560 | 1560 | ||
1561 | if (!tg->parent) { | 1561 | if (!tg->parent) { |
1562 | load = cpu_rq(cpu)->load.weight; | 1562 | load = cpu_rq(cpu)->load.weight; |
1563 | } else { | 1563 | } else { |
1564 | load = tg->parent->cfs_rq[cpu]->h_load; | 1564 | load = tg->parent->cfs_rq[cpu]->h_load; |
1565 | load *= tg->se[cpu]->load.weight; | 1565 | load *= tg->se[cpu]->load.weight; |
1566 | load /= tg->parent->cfs_rq[cpu]->load.weight + 1; | 1566 | load /= tg->parent->cfs_rq[cpu]->load.weight + 1; |
1567 | } | 1567 | } |
1568 | 1568 | ||
1569 | tg->cfs_rq[cpu]->h_load = load; | 1569 | tg->cfs_rq[cpu]->h_load = load; |
1570 | 1570 | ||
1571 | return 0; | 1571 | return 0; |
1572 | } | 1572 | } |
1573 | 1573 | ||
1574 | static void update_h_load(long cpu) | 1574 | static void update_h_load(long cpu) |
1575 | { | 1575 | { |
1576 | walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); | 1576 | walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); |
1577 | } | 1577 | } |
1578 | 1578 | ||
1579 | #endif | 1579 | #endif |
1580 | 1580 | ||
1581 | #ifdef CONFIG_PREEMPT | 1581 | #ifdef CONFIG_PREEMPT |
1582 | 1582 | ||
1583 | static void double_rq_lock(struct rq *rq1, struct rq *rq2); | 1583 | static void double_rq_lock(struct rq *rq1, struct rq *rq2); |
1584 | 1584 | ||
1585 | /* | 1585 | /* |
1586 | * fair double_lock_balance: Safely acquires both rq->locks in a fair | 1586 | * fair double_lock_balance: Safely acquires both rq->locks in a fair |
1587 | * way at the expense of forcing extra atomic operations in all | 1587 | * way at the expense of forcing extra atomic operations in all |
1588 | * invocations. This assures that the double_lock is acquired using the | 1588 | * invocations. This assures that the double_lock is acquired using the |
1589 | * same underlying policy as the spinlock_t on this architecture, which | 1589 | * same underlying policy as the spinlock_t on this architecture, which |
1590 | * reduces latency compared to the unfair variant below. However, it | 1590 | * reduces latency compared to the unfair variant below. However, it |
1591 | * also adds more overhead and therefore may reduce throughput. | 1591 | * also adds more overhead and therefore may reduce throughput. |
1592 | */ | 1592 | */ |
1593 | static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) | 1593 | static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) |
1594 | __releases(this_rq->lock) | 1594 | __releases(this_rq->lock) |
1595 | __acquires(busiest->lock) | 1595 | __acquires(busiest->lock) |
1596 | __acquires(this_rq->lock) | 1596 | __acquires(this_rq->lock) |
1597 | { | 1597 | { |
1598 | raw_spin_unlock(&this_rq->lock); | 1598 | raw_spin_unlock(&this_rq->lock); |
1599 | double_rq_lock(this_rq, busiest); | 1599 | double_rq_lock(this_rq, busiest); |
1600 | 1600 | ||
1601 | return 1; | 1601 | return 1; |
1602 | } | 1602 | } |
1603 | 1603 | ||
1604 | #else | 1604 | #else |
1605 | /* | 1605 | /* |
1606 | * Unfair double_lock_balance: Optimizes throughput at the expense of | 1606 | * Unfair double_lock_balance: Optimizes throughput at the expense of |
1607 | * latency by eliminating extra atomic operations when the locks are | 1607 | * latency by eliminating extra atomic operations when the locks are |
1608 | * already in proper order on entry. This favors lower cpu-ids and will | 1608 | * already in proper order on entry. This favors lower cpu-ids and will |
1609 | * grant the double lock to lower cpus over higher ids under contention, | 1609 | * grant the double lock to lower cpus over higher ids under contention, |
1610 | * regardless of entry order into the function. | 1610 | * regardless of entry order into the function. |
1611 | */ | 1611 | */ |
1612 | static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) | 1612 | static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) |
1613 | __releases(this_rq->lock) | 1613 | __releases(this_rq->lock) |
1614 | __acquires(busiest->lock) | 1614 | __acquires(busiest->lock) |
1615 | __acquires(this_rq->lock) | 1615 | __acquires(this_rq->lock) |
1616 | { | 1616 | { |
1617 | int ret = 0; | 1617 | int ret = 0; |
1618 | 1618 | ||
1619 | if (unlikely(!raw_spin_trylock(&busiest->lock))) { | 1619 | if (unlikely(!raw_spin_trylock(&busiest->lock))) { |
1620 | if (busiest < this_rq) { | 1620 | if (busiest < this_rq) { |
1621 | raw_spin_unlock(&this_rq->lock); | 1621 | raw_spin_unlock(&this_rq->lock); |
1622 | raw_spin_lock(&busiest->lock); | 1622 | raw_spin_lock(&busiest->lock); |
1623 | raw_spin_lock_nested(&this_rq->lock, | 1623 | raw_spin_lock_nested(&this_rq->lock, |
1624 | SINGLE_DEPTH_NESTING); | 1624 | SINGLE_DEPTH_NESTING); |
1625 | ret = 1; | 1625 | ret = 1; |
1626 | } else | 1626 | } else |
1627 | raw_spin_lock_nested(&busiest->lock, | 1627 | raw_spin_lock_nested(&busiest->lock, |
1628 | SINGLE_DEPTH_NESTING); | 1628 | SINGLE_DEPTH_NESTING); |
1629 | } | 1629 | } |
1630 | return ret; | 1630 | return ret; |
1631 | } | 1631 | } |
1632 | 1632 | ||
1633 | #endif /* CONFIG_PREEMPT */ | 1633 | #endif /* CONFIG_PREEMPT */ |
1634 | 1634 | ||
1635 | /* | 1635 | /* |
1636 | * double_lock_balance - lock the busiest runqueue, this_rq is locked already. | 1636 | * double_lock_balance - lock the busiest runqueue, this_rq is locked already. |
1637 | */ | 1637 | */ |
1638 | static int double_lock_balance(struct rq *this_rq, struct rq *busiest) | 1638 | static int double_lock_balance(struct rq *this_rq, struct rq *busiest) |
1639 | { | 1639 | { |
1640 | if (unlikely(!irqs_disabled())) { | 1640 | if (unlikely(!irqs_disabled())) { |
1641 | /* printk() doesn't work good under rq->lock */ | 1641 | /* printk() doesn't work good under rq->lock */ |
1642 | raw_spin_unlock(&this_rq->lock); | 1642 | raw_spin_unlock(&this_rq->lock); |
1643 | BUG_ON(1); | 1643 | BUG_ON(1); |
1644 | } | 1644 | } |
1645 | 1645 | ||
1646 | return _double_lock_balance(this_rq, busiest); | 1646 | return _double_lock_balance(this_rq, busiest); |
1647 | } | 1647 | } |
1648 | 1648 | ||
1649 | static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) | 1649 | static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) |
1650 | __releases(busiest->lock) | 1650 | __releases(busiest->lock) |
1651 | { | 1651 | { |
1652 | raw_spin_unlock(&busiest->lock); | 1652 | raw_spin_unlock(&busiest->lock); |
1653 | lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); | 1653 | lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); |
1654 | } | 1654 | } |
1655 | 1655 | ||
1656 | /* | 1656 | /* |
1657 | * double_rq_lock - safely lock two runqueues | 1657 | * double_rq_lock - safely lock two runqueues |
1658 | * | 1658 | * |
1659 | * Note this does not disable interrupts like task_rq_lock, | 1659 | * Note this does not disable interrupts like task_rq_lock, |
1660 | * you need to do so manually before calling. | 1660 | * you need to do so manually before calling. |
1661 | */ | 1661 | */ |
1662 | static void double_rq_lock(struct rq *rq1, struct rq *rq2) | 1662 | static void double_rq_lock(struct rq *rq1, struct rq *rq2) |
1663 | __acquires(rq1->lock) | 1663 | __acquires(rq1->lock) |
1664 | __acquires(rq2->lock) | 1664 | __acquires(rq2->lock) |
1665 | { | 1665 | { |
1666 | BUG_ON(!irqs_disabled()); | 1666 | BUG_ON(!irqs_disabled()); |
1667 | if (rq1 == rq2) { | 1667 | if (rq1 == rq2) { |
1668 | raw_spin_lock(&rq1->lock); | 1668 | raw_spin_lock(&rq1->lock); |
1669 | __acquire(rq2->lock); /* Fake it out ;) */ | 1669 | __acquire(rq2->lock); /* Fake it out ;) */ |
1670 | } else { | 1670 | } else { |
1671 | if (rq1 < rq2) { | 1671 | if (rq1 < rq2) { |
1672 | raw_spin_lock(&rq1->lock); | 1672 | raw_spin_lock(&rq1->lock); |
1673 | raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); | 1673 | raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); |
1674 | } else { | 1674 | } else { |
1675 | raw_spin_lock(&rq2->lock); | 1675 | raw_spin_lock(&rq2->lock); |
1676 | raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); | 1676 | raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); |
1677 | } | 1677 | } |
1678 | } | 1678 | } |
1679 | } | 1679 | } |
1680 | 1680 | ||
1681 | /* | 1681 | /* |
1682 | * double_rq_unlock - safely unlock two runqueues | 1682 | * double_rq_unlock - safely unlock two runqueues |
1683 | * | 1683 | * |
1684 | * Note this does not restore interrupts like task_rq_unlock, | 1684 | * Note this does not restore interrupts like task_rq_unlock, |
1685 | * you need to do so manually after calling. | 1685 | * you need to do so manually after calling. |
1686 | */ | 1686 | */ |
1687 | static void double_rq_unlock(struct rq *rq1, struct rq *rq2) | 1687 | static void double_rq_unlock(struct rq *rq1, struct rq *rq2) |
1688 | __releases(rq1->lock) | 1688 | __releases(rq1->lock) |
1689 | __releases(rq2->lock) | 1689 | __releases(rq2->lock) |
1690 | { | 1690 | { |
1691 | raw_spin_unlock(&rq1->lock); | 1691 | raw_spin_unlock(&rq1->lock); |
1692 | if (rq1 != rq2) | 1692 | if (rq1 != rq2) |
1693 | raw_spin_unlock(&rq2->lock); | 1693 | raw_spin_unlock(&rq2->lock); |
1694 | else | 1694 | else |
1695 | __release(rq2->lock); | 1695 | __release(rq2->lock); |
1696 | } | 1696 | } |
1697 | 1697 | ||
1698 | #else /* CONFIG_SMP */ | 1698 | #else /* CONFIG_SMP */ |
1699 | 1699 | ||
1700 | /* | 1700 | /* |
1701 | * double_rq_lock - safely lock two runqueues | 1701 | * double_rq_lock - safely lock two runqueues |
1702 | * | 1702 | * |
1703 | * Note this does not disable interrupts like task_rq_lock, | 1703 | * Note this does not disable interrupts like task_rq_lock, |
1704 | * you need to do so manually before calling. | 1704 | * you need to do so manually before calling. |
1705 | */ | 1705 | */ |
1706 | static void double_rq_lock(struct rq *rq1, struct rq *rq2) | 1706 | static void double_rq_lock(struct rq *rq1, struct rq *rq2) |
1707 | __acquires(rq1->lock) | 1707 | __acquires(rq1->lock) |
1708 | __acquires(rq2->lock) | 1708 | __acquires(rq2->lock) |
1709 | { | 1709 | { |
1710 | BUG_ON(!irqs_disabled()); | 1710 | BUG_ON(!irqs_disabled()); |
1711 | BUG_ON(rq1 != rq2); | 1711 | BUG_ON(rq1 != rq2); |
1712 | raw_spin_lock(&rq1->lock); | 1712 | raw_spin_lock(&rq1->lock); |
1713 | __acquire(rq2->lock); /* Fake it out ;) */ | 1713 | __acquire(rq2->lock); /* Fake it out ;) */ |
1714 | } | 1714 | } |
1715 | 1715 | ||
1716 | /* | 1716 | /* |
1717 | * double_rq_unlock - safely unlock two runqueues | 1717 | * double_rq_unlock - safely unlock two runqueues |
1718 | * | 1718 | * |
1719 | * Note this does not restore interrupts like task_rq_unlock, | 1719 | * Note this does not restore interrupts like task_rq_unlock, |
1720 | * you need to do so manually after calling. | 1720 | * you need to do so manually after calling. |
1721 | */ | 1721 | */ |
1722 | static void double_rq_unlock(struct rq *rq1, struct rq *rq2) | 1722 | static void double_rq_unlock(struct rq *rq1, struct rq *rq2) |
1723 | __releases(rq1->lock) | 1723 | __releases(rq1->lock) |
1724 | __releases(rq2->lock) | 1724 | __releases(rq2->lock) |
1725 | { | 1725 | { |
1726 | BUG_ON(rq1 != rq2); | 1726 | BUG_ON(rq1 != rq2); |
1727 | raw_spin_unlock(&rq1->lock); | 1727 | raw_spin_unlock(&rq1->lock); |
1728 | __release(rq2->lock); | 1728 | __release(rq2->lock); |
1729 | } | 1729 | } |
1730 | 1730 | ||
1731 | #endif | 1731 | #endif |
1732 | 1732 | ||
1733 | static void calc_load_account_idle(struct rq *this_rq); | 1733 | static void calc_load_account_idle(struct rq *this_rq); |
1734 | static void update_sysctl(void); | 1734 | static void update_sysctl(void); |
1735 | static int get_update_sysctl_factor(void); | 1735 | static int get_update_sysctl_factor(void); |
1736 | static void update_cpu_load(struct rq *this_rq); | 1736 | static void update_cpu_load(struct rq *this_rq); |
1737 | 1737 | ||
1738 | static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) | 1738 | static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) |
1739 | { | 1739 | { |
1740 | set_task_rq(p, cpu); | 1740 | set_task_rq(p, cpu); |
1741 | #ifdef CONFIG_SMP | 1741 | #ifdef CONFIG_SMP |
1742 | /* | 1742 | /* |
1743 | * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be | 1743 | * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be |
1744 | * successfuly executed on another CPU. We must ensure that updates of | 1744 | * successfuly executed on another CPU. We must ensure that updates of |
1745 | * per-task data have been completed by this moment. | 1745 | * per-task data have been completed by this moment. |
1746 | */ | 1746 | */ |
1747 | smp_wmb(); | 1747 | smp_wmb(); |
1748 | task_thread_info(p)->cpu = cpu; | 1748 | task_thread_info(p)->cpu = cpu; |
1749 | #endif | 1749 | #endif |
1750 | } | 1750 | } |
1751 | 1751 | ||
1752 | static const struct sched_class rt_sched_class; | 1752 | static const struct sched_class rt_sched_class; |
1753 | 1753 | ||
1754 | #define sched_class_highest (&stop_sched_class) | 1754 | #define sched_class_highest (&stop_sched_class) |
1755 | #define for_each_class(class) \ | 1755 | #define for_each_class(class) \ |
1756 | for (class = sched_class_highest; class; class = class->next) | 1756 | for (class = sched_class_highest; class; class = class->next) |
1757 | 1757 | ||
1758 | #include "sched_stats.h" | 1758 | #include "sched_stats.h" |
1759 | 1759 | ||
1760 | static void inc_nr_running(struct rq *rq) | 1760 | static void inc_nr_running(struct rq *rq) |
1761 | { | 1761 | { |
1762 | rq->nr_running++; | 1762 | rq->nr_running++; |
1763 | } | 1763 | } |
1764 | 1764 | ||
1765 | static void dec_nr_running(struct rq *rq) | 1765 | static void dec_nr_running(struct rq *rq) |
1766 | { | 1766 | { |
1767 | rq->nr_running--; | 1767 | rq->nr_running--; |
1768 | } | 1768 | } |
1769 | 1769 | ||
1770 | static void set_load_weight(struct task_struct *p) | 1770 | static void set_load_weight(struct task_struct *p) |
1771 | { | 1771 | { |
1772 | /* | 1772 | /* |
1773 | * SCHED_IDLE tasks get minimal weight: | 1773 | * SCHED_IDLE tasks get minimal weight: |
1774 | */ | 1774 | */ |
1775 | if (p->policy == SCHED_IDLE) { | 1775 | if (p->policy == SCHED_IDLE) { |
1776 | p->se.load.weight = WEIGHT_IDLEPRIO; | 1776 | p->se.load.weight = WEIGHT_IDLEPRIO; |
1777 | p->se.load.inv_weight = WMULT_IDLEPRIO; | 1777 | p->se.load.inv_weight = WMULT_IDLEPRIO; |
1778 | return; | 1778 | return; |
1779 | } | 1779 | } |
1780 | 1780 | ||
1781 | p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO]; | 1781 | p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO]; |
1782 | p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; | 1782 | p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; |
1783 | } | 1783 | } |
1784 | 1784 | ||
1785 | static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) | 1785 | static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) |
1786 | { | 1786 | { |
1787 | update_rq_clock(rq); | 1787 | update_rq_clock(rq); |
1788 | sched_info_queued(p); | 1788 | sched_info_queued(p); |
1789 | p->sched_class->enqueue_task(rq, p, flags); | 1789 | p->sched_class->enqueue_task(rq, p, flags); |
1790 | } | 1790 | } |
1791 | 1791 | ||
1792 | static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) | 1792 | static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) |
1793 | { | 1793 | { |
1794 | update_rq_clock(rq); | 1794 | update_rq_clock(rq); |
1795 | sched_info_dequeued(p); | 1795 | sched_info_dequeued(p); |
1796 | p->sched_class->dequeue_task(rq, p, flags); | 1796 | p->sched_class->dequeue_task(rq, p, flags); |
1797 | } | 1797 | } |
1798 | 1798 | ||
1799 | /* | 1799 | /* |
1800 | * activate_task - move a task to the runqueue. | 1800 | * activate_task - move a task to the runqueue. |
1801 | */ | 1801 | */ |
1802 | static void activate_task(struct rq *rq, struct task_struct *p, int flags) | 1802 | static void activate_task(struct rq *rq, struct task_struct *p, int flags) |
1803 | { | 1803 | { |
1804 | if (task_contributes_to_load(p)) | 1804 | if (task_contributes_to_load(p)) |
1805 | rq->nr_uninterruptible--; | 1805 | rq->nr_uninterruptible--; |
1806 | 1806 | ||
1807 | enqueue_task(rq, p, flags); | 1807 | enqueue_task(rq, p, flags); |
1808 | inc_nr_running(rq); | 1808 | inc_nr_running(rq); |
1809 | } | 1809 | } |
1810 | 1810 | ||
1811 | /* | 1811 | /* |
1812 | * deactivate_task - remove a task from the runqueue. | 1812 | * deactivate_task - remove a task from the runqueue. |
1813 | */ | 1813 | */ |
1814 | static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) | 1814 | static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) |
1815 | { | 1815 | { |
1816 | if (task_contributes_to_load(p)) | 1816 | if (task_contributes_to_load(p)) |
1817 | rq->nr_uninterruptible++; | 1817 | rq->nr_uninterruptible++; |
1818 | 1818 | ||
1819 | dequeue_task(rq, p, flags); | 1819 | dequeue_task(rq, p, flags); |
1820 | dec_nr_running(rq); | 1820 | dec_nr_running(rq); |
1821 | } | 1821 | } |
1822 | 1822 | ||
1823 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING | 1823 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING |
1824 | 1824 | ||
1825 | /* | 1825 | /* |
1826 | * There are no locks covering percpu hardirq/softirq time. | 1826 | * There are no locks covering percpu hardirq/softirq time. |
1827 | * They are only modified in account_system_vtime, on corresponding CPU | 1827 | * They are only modified in account_system_vtime, on corresponding CPU |
1828 | * with interrupts disabled. So, writes are safe. | 1828 | * with interrupts disabled. So, writes are safe. |
1829 | * They are read and saved off onto struct rq in update_rq_clock(). | 1829 | * They are read and saved off onto struct rq in update_rq_clock(). |
1830 | * This may result in other CPU reading this CPU's irq time and can | 1830 | * This may result in other CPU reading this CPU's irq time and can |
1831 | * race with irq/account_system_vtime on this CPU. We would either get old | 1831 | * race with irq/account_system_vtime on this CPU. We would either get old |
1832 | * or new value with a side effect of accounting a slice of irq time to wrong | 1832 | * or new value with a side effect of accounting a slice of irq time to wrong |
1833 | * task when irq is in progress while we read rq->clock. That is a worthy | 1833 | * task when irq is in progress while we read rq->clock. That is a worthy |
1834 | * compromise in place of having locks on each irq in account_system_time. | 1834 | * compromise in place of having locks on each irq in account_system_time. |
1835 | */ | 1835 | */ |
1836 | static DEFINE_PER_CPU(u64, cpu_hardirq_time); | 1836 | static DEFINE_PER_CPU(u64, cpu_hardirq_time); |
1837 | static DEFINE_PER_CPU(u64, cpu_softirq_time); | 1837 | static DEFINE_PER_CPU(u64, cpu_softirq_time); |
1838 | 1838 | ||
1839 | static DEFINE_PER_CPU(u64, irq_start_time); | 1839 | static DEFINE_PER_CPU(u64, irq_start_time); |
1840 | static int sched_clock_irqtime; | 1840 | static int sched_clock_irqtime; |
1841 | 1841 | ||
1842 | void enable_sched_clock_irqtime(void) | 1842 | void enable_sched_clock_irqtime(void) |
1843 | { | 1843 | { |
1844 | sched_clock_irqtime = 1; | 1844 | sched_clock_irqtime = 1; |
1845 | } | 1845 | } |
1846 | 1846 | ||
1847 | void disable_sched_clock_irqtime(void) | 1847 | void disable_sched_clock_irqtime(void) |
1848 | { | 1848 | { |
1849 | sched_clock_irqtime = 0; | 1849 | sched_clock_irqtime = 0; |
1850 | } | 1850 | } |
1851 | 1851 | ||
1852 | #ifndef CONFIG_64BIT | 1852 | #ifndef CONFIG_64BIT |
1853 | static DEFINE_PER_CPU(seqcount_t, irq_time_seq); | 1853 | static DEFINE_PER_CPU(seqcount_t, irq_time_seq); |
1854 | 1854 | ||
1855 | static inline void irq_time_write_begin(void) | 1855 | static inline void irq_time_write_begin(void) |
1856 | { | 1856 | { |
1857 | __this_cpu_inc(irq_time_seq.sequence); | 1857 | __this_cpu_inc(irq_time_seq.sequence); |
1858 | smp_wmb(); | 1858 | smp_wmb(); |
1859 | } | 1859 | } |
1860 | 1860 | ||
1861 | static inline void irq_time_write_end(void) | 1861 | static inline void irq_time_write_end(void) |
1862 | { | 1862 | { |
1863 | smp_wmb(); | 1863 | smp_wmb(); |
1864 | __this_cpu_inc(irq_time_seq.sequence); | 1864 | __this_cpu_inc(irq_time_seq.sequence); |
1865 | } | 1865 | } |
1866 | 1866 | ||
1867 | static inline u64 irq_time_read(int cpu) | 1867 | static inline u64 irq_time_read(int cpu) |
1868 | { | 1868 | { |
1869 | u64 irq_time; | 1869 | u64 irq_time; |
1870 | unsigned seq; | 1870 | unsigned seq; |
1871 | 1871 | ||
1872 | do { | 1872 | do { |
1873 | seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); | 1873 | seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); |
1874 | irq_time = per_cpu(cpu_softirq_time, cpu) + | 1874 | irq_time = per_cpu(cpu_softirq_time, cpu) + |
1875 | per_cpu(cpu_hardirq_time, cpu); | 1875 | per_cpu(cpu_hardirq_time, cpu); |
1876 | } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); | 1876 | } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); |
1877 | 1877 | ||
1878 | return irq_time; | 1878 | return irq_time; |
1879 | } | 1879 | } |
1880 | #else /* CONFIG_64BIT */ | 1880 | #else /* CONFIG_64BIT */ |
1881 | static inline void irq_time_write_begin(void) | 1881 | static inline void irq_time_write_begin(void) |
1882 | { | 1882 | { |
1883 | } | 1883 | } |
1884 | 1884 | ||
1885 | static inline void irq_time_write_end(void) | 1885 | static inline void irq_time_write_end(void) |
1886 | { | 1886 | { |
1887 | } | 1887 | } |
1888 | 1888 | ||
1889 | static inline u64 irq_time_read(int cpu) | 1889 | static inline u64 irq_time_read(int cpu) |
1890 | { | 1890 | { |
1891 | return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); | 1891 | return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); |
1892 | } | 1892 | } |
1893 | #endif /* CONFIG_64BIT */ | 1893 | #endif /* CONFIG_64BIT */ |
1894 | 1894 | ||
1895 | /* | 1895 | /* |
1896 | * Called before incrementing preempt_count on {soft,}irq_enter | 1896 | * Called before incrementing preempt_count on {soft,}irq_enter |
1897 | * and before decrementing preempt_count on {soft,}irq_exit. | 1897 | * and before decrementing preempt_count on {soft,}irq_exit. |
1898 | */ | 1898 | */ |
1899 | void account_system_vtime(struct task_struct *curr) | 1899 | void account_system_vtime(struct task_struct *curr) |
1900 | { | 1900 | { |
1901 | unsigned long flags; | 1901 | unsigned long flags; |
1902 | s64 delta; | 1902 | s64 delta; |
1903 | int cpu; | 1903 | int cpu; |
1904 | 1904 | ||
1905 | if (!sched_clock_irqtime) | 1905 | if (!sched_clock_irqtime) |
1906 | return; | 1906 | return; |
1907 | 1907 | ||
1908 | local_irq_save(flags); | 1908 | local_irq_save(flags); |
1909 | 1909 | ||
1910 | cpu = smp_processor_id(); | 1910 | cpu = smp_processor_id(); |
1911 | delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); | 1911 | delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); |
1912 | __this_cpu_add(irq_start_time, delta); | 1912 | __this_cpu_add(irq_start_time, delta); |
1913 | 1913 | ||
1914 | irq_time_write_begin(); | 1914 | irq_time_write_begin(); |
1915 | /* | 1915 | /* |
1916 | * We do not account for softirq time from ksoftirqd here. | 1916 | * We do not account for softirq time from ksoftirqd here. |
1917 | * We want to continue accounting softirq time to ksoftirqd thread | 1917 | * We want to continue accounting softirq time to ksoftirqd thread |
1918 | * in that case, so as not to confuse scheduler with a special task | 1918 | * in that case, so as not to confuse scheduler with a special task |
1919 | * that do not consume any time, but still wants to run. | 1919 | * that do not consume any time, but still wants to run. |
1920 | */ | 1920 | */ |
1921 | if (hardirq_count()) | 1921 | if (hardirq_count()) |
1922 | __this_cpu_add(cpu_hardirq_time, delta); | 1922 | __this_cpu_add(cpu_hardirq_time, delta); |
1923 | else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) | 1923 | else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) |
1924 | __this_cpu_add(cpu_softirq_time, delta); | 1924 | __this_cpu_add(cpu_softirq_time, delta); |
1925 | 1925 | ||
1926 | irq_time_write_end(); | 1926 | irq_time_write_end(); |
1927 | local_irq_restore(flags); | 1927 | local_irq_restore(flags); |
1928 | } | 1928 | } |
1929 | EXPORT_SYMBOL_GPL(account_system_vtime); | 1929 | EXPORT_SYMBOL_GPL(account_system_vtime); |
1930 | 1930 | ||
1931 | static void update_rq_clock_task(struct rq *rq, s64 delta) | 1931 | static void update_rq_clock_task(struct rq *rq, s64 delta) |
1932 | { | 1932 | { |
1933 | s64 irq_delta; | 1933 | s64 irq_delta; |
1934 | 1934 | ||
1935 | irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; | 1935 | irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; |
1936 | 1936 | ||
1937 | /* | 1937 | /* |
1938 | * Since irq_time is only updated on {soft,}irq_exit, we might run into | 1938 | * Since irq_time is only updated on {soft,}irq_exit, we might run into |
1939 | * this case when a previous update_rq_clock() happened inside a | 1939 | * this case when a previous update_rq_clock() happened inside a |
1940 | * {soft,}irq region. | 1940 | * {soft,}irq region. |
1941 | * | 1941 | * |
1942 | * When this happens, we stop ->clock_task and only update the | 1942 | * When this happens, we stop ->clock_task and only update the |
1943 | * prev_irq_time stamp to account for the part that fit, so that a next | 1943 | * prev_irq_time stamp to account for the part that fit, so that a next |
1944 | * update will consume the rest. This ensures ->clock_task is | 1944 | * update will consume the rest. This ensures ->clock_task is |
1945 | * monotonic. | 1945 | * monotonic. |
1946 | * | 1946 | * |
1947 | * It does however cause some slight miss-attribution of {soft,}irq | 1947 | * It does however cause some slight miss-attribution of {soft,}irq |
1948 | * time, a more accurate solution would be to update the irq_time using | 1948 | * time, a more accurate solution would be to update the irq_time using |
1949 | * the current rq->clock timestamp, except that would require using | 1949 | * the current rq->clock timestamp, except that would require using |
1950 | * atomic ops. | 1950 | * atomic ops. |
1951 | */ | 1951 | */ |
1952 | if (irq_delta > delta) | 1952 | if (irq_delta > delta) |
1953 | irq_delta = delta; | 1953 | irq_delta = delta; |
1954 | 1954 | ||
1955 | rq->prev_irq_time += irq_delta; | 1955 | rq->prev_irq_time += irq_delta; |
1956 | delta -= irq_delta; | 1956 | delta -= irq_delta; |
1957 | rq->clock_task += delta; | 1957 | rq->clock_task += delta; |
1958 | 1958 | ||
1959 | if (irq_delta && sched_feat(NONIRQ_POWER)) | 1959 | if (irq_delta && sched_feat(NONIRQ_POWER)) |
1960 | sched_rt_avg_update(rq, irq_delta); | 1960 | sched_rt_avg_update(rq, irq_delta); |
1961 | } | 1961 | } |
1962 | 1962 | ||
1963 | static int irqtime_account_hi_update(void) | 1963 | static int irqtime_account_hi_update(void) |
1964 | { | 1964 | { |
1965 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 1965 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
1966 | unsigned long flags; | 1966 | unsigned long flags; |
1967 | u64 latest_ns; | 1967 | u64 latest_ns; |
1968 | int ret = 0; | 1968 | int ret = 0; |
1969 | 1969 | ||
1970 | local_irq_save(flags); | 1970 | local_irq_save(flags); |
1971 | latest_ns = this_cpu_read(cpu_hardirq_time); | 1971 | latest_ns = this_cpu_read(cpu_hardirq_time); |
1972 | if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq)) | 1972 | if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq)) |
1973 | ret = 1; | 1973 | ret = 1; |
1974 | local_irq_restore(flags); | 1974 | local_irq_restore(flags); |
1975 | return ret; | 1975 | return ret; |
1976 | } | 1976 | } |
1977 | 1977 | ||
1978 | static int irqtime_account_si_update(void) | 1978 | static int irqtime_account_si_update(void) |
1979 | { | 1979 | { |
1980 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 1980 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
1981 | unsigned long flags; | 1981 | unsigned long flags; |
1982 | u64 latest_ns; | 1982 | u64 latest_ns; |
1983 | int ret = 0; | 1983 | int ret = 0; |
1984 | 1984 | ||
1985 | local_irq_save(flags); | 1985 | local_irq_save(flags); |
1986 | latest_ns = this_cpu_read(cpu_softirq_time); | 1986 | latest_ns = this_cpu_read(cpu_softirq_time); |
1987 | if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq)) | 1987 | if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq)) |
1988 | ret = 1; | 1988 | ret = 1; |
1989 | local_irq_restore(flags); | 1989 | local_irq_restore(flags); |
1990 | return ret; | 1990 | return ret; |
1991 | } | 1991 | } |
1992 | 1992 | ||
1993 | #else /* CONFIG_IRQ_TIME_ACCOUNTING */ | 1993 | #else /* CONFIG_IRQ_TIME_ACCOUNTING */ |
1994 | 1994 | ||
1995 | #define sched_clock_irqtime (0) | 1995 | #define sched_clock_irqtime (0) |
1996 | 1996 | ||
1997 | static void update_rq_clock_task(struct rq *rq, s64 delta) | 1997 | static void update_rq_clock_task(struct rq *rq, s64 delta) |
1998 | { | 1998 | { |
1999 | rq->clock_task += delta; | 1999 | rq->clock_task += delta; |
2000 | } | 2000 | } |
2001 | 2001 | ||
2002 | #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ | 2002 | #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ |
2003 | 2003 | ||
2004 | #include "sched_idletask.c" | 2004 | #include "sched_idletask.c" |
2005 | #include "sched_fair.c" | 2005 | #include "sched_fair.c" |
2006 | #include "sched_rt.c" | 2006 | #include "sched_rt.c" |
2007 | #include "sched_autogroup.c" | 2007 | #include "sched_autogroup.c" |
2008 | #include "sched_stoptask.c" | 2008 | #include "sched_stoptask.c" |
2009 | #ifdef CONFIG_SCHED_DEBUG | 2009 | #ifdef CONFIG_SCHED_DEBUG |
2010 | # include "sched_debug.c" | 2010 | # include "sched_debug.c" |
2011 | #endif | 2011 | #endif |
2012 | 2012 | ||
2013 | void sched_set_stop_task(int cpu, struct task_struct *stop) | 2013 | void sched_set_stop_task(int cpu, struct task_struct *stop) |
2014 | { | 2014 | { |
2015 | struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; | 2015 | struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; |
2016 | struct task_struct *old_stop = cpu_rq(cpu)->stop; | 2016 | struct task_struct *old_stop = cpu_rq(cpu)->stop; |
2017 | 2017 | ||
2018 | if (stop) { | 2018 | if (stop) { |
2019 | /* | 2019 | /* |
2020 | * Make it appear like a SCHED_FIFO task, its something | 2020 | * Make it appear like a SCHED_FIFO task, its something |
2021 | * userspace knows about and won't get confused about. | 2021 | * userspace knows about and won't get confused about. |
2022 | * | 2022 | * |
2023 | * Also, it will make PI more or less work without too | 2023 | * Also, it will make PI more or less work without too |
2024 | * much confusion -- but then, stop work should not | 2024 | * much confusion -- but then, stop work should not |
2025 | * rely on PI working anyway. | 2025 | * rely on PI working anyway. |
2026 | */ | 2026 | */ |
2027 | sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); | 2027 | sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); |
2028 | 2028 | ||
2029 | stop->sched_class = &stop_sched_class; | 2029 | stop->sched_class = &stop_sched_class; |
2030 | } | 2030 | } |
2031 | 2031 | ||
2032 | cpu_rq(cpu)->stop = stop; | 2032 | cpu_rq(cpu)->stop = stop; |
2033 | 2033 | ||
2034 | if (old_stop) { | 2034 | if (old_stop) { |
2035 | /* | 2035 | /* |
2036 | * Reset it back to a normal scheduling class so that | 2036 | * Reset it back to a normal scheduling class so that |
2037 | * it can die in pieces. | 2037 | * it can die in pieces. |
2038 | */ | 2038 | */ |
2039 | old_stop->sched_class = &rt_sched_class; | 2039 | old_stop->sched_class = &rt_sched_class; |
2040 | } | 2040 | } |
2041 | } | 2041 | } |
2042 | 2042 | ||
2043 | /* | 2043 | /* |
2044 | * __normal_prio - return the priority that is based on the static prio | 2044 | * __normal_prio - return the priority that is based on the static prio |
2045 | */ | 2045 | */ |
2046 | static inline int __normal_prio(struct task_struct *p) | 2046 | static inline int __normal_prio(struct task_struct *p) |
2047 | { | 2047 | { |
2048 | return p->static_prio; | 2048 | return p->static_prio; |
2049 | } | 2049 | } |
2050 | 2050 | ||
2051 | /* | 2051 | /* |
2052 | * Calculate the expected normal priority: i.e. priority | 2052 | * Calculate the expected normal priority: i.e. priority |
2053 | * without taking RT-inheritance into account. Might be | 2053 | * without taking RT-inheritance into account. Might be |
2054 | * boosted by interactivity modifiers. Changes upon fork, | 2054 | * boosted by interactivity modifiers. Changes upon fork, |
2055 | * setprio syscalls, and whenever the interactivity | 2055 | * setprio syscalls, and whenever the interactivity |
2056 | * estimator recalculates. | 2056 | * estimator recalculates. |
2057 | */ | 2057 | */ |
2058 | static inline int normal_prio(struct task_struct *p) | 2058 | static inline int normal_prio(struct task_struct *p) |
2059 | { | 2059 | { |
2060 | int prio; | 2060 | int prio; |
2061 | 2061 | ||
2062 | if (task_has_rt_policy(p)) | 2062 | if (task_has_rt_policy(p)) |
2063 | prio = MAX_RT_PRIO-1 - p->rt_priority; | 2063 | prio = MAX_RT_PRIO-1 - p->rt_priority; |
2064 | else | 2064 | else |
2065 | prio = __normal_prio(p); | 2065 | prio = __normal_prio(p); |
2066 | return prio; | 2066 | return prio; |
2067 | } | 2067 | } |
2068 | 2068 | ||
2069 | /* | 2069 | /* |
2070 | * Calculate the current priority, i.e. the priority | 2070 | * Calculate the current priority, i.e. the priority |
2071 | * taken into account by the scheduler. This value might | 2071 | * taken into account by the scheduler. This value might |
2072 | * be boosted by RT tasks, or might be boosted by | 2072 | * be boosted by RT tasks, or might be boosted by |
2073 | * interactivity modifiers. Will be RT if the task got | 2073 | * interactivity modifiers. Will be RT if the task got |
2074 | * RT-boosted. If not then it returns p->normal_prio. | 2074 | * RT-boosted. If not then it returns p->normal_prio. |
2075 | */ | 2075 | */ |
2076 | static int effective_prio(struct task_struct *p) | 2076 | static int effective_prio(struct task_struct *p) |
2077 | { | 2077 | { |
2078 | p->normal_prio = normal_prio(p); | 2078 | p->normal_prio = normal_prio(p); |
2079 | /* | 2079 | /* |
2080 | * If we are RT tasks or we were boosted to RT priority, | 2080 | * If we are RT tasks or we were boosted to RT priority, |
2081 | * keep the priority unchanged. Otherwise, update priority | 2081 | * keep the priority unchanged. Otherwise, update priority |
2082 | * to the normal priority: | 2082 | * to the normal priority: |
2083 | */ | 2083 | */ |
2084 | if (!rt_prio(p->prio)) | 2084 | if (!rt_prio(p->prio)) |
2085 | return p->normal_prio; | 2085 | return p->normal_prio; |
2086 | return p->prio; | 2086 | return p->prio; |
2087 | } | 2087 | } |
2088 | 2088 | ||
2089 | /** | 2089 | /** |
2090 | * task_curr - is this task currently executing on a CPU? | 2090 | * task_curr - is this task currently executing on a CPU? |
2091 | * @p: the task in question. | 2091 | * @p: the task in question. |
2092 | */ | 2092 | */ |
2093 | inline int task_curr(const struct task_struct *p) | 2093 | inline int task_curr(const struct task_struct *p) |
2094 | { | 2094 | { |
2095 | return cpu_curr(task_cpu(p)) == p; | 2095 | return cpu_curr(task_cpu(p)) == p; |
2096 | } | 2096 | } |
2097 | 2097 | ||
2098 | static inline void check_class_changed(struct rq *rq, struct task_struct *p, | 2098 | static inline void check_class_changed(struct rq *rq, struct task_struct *p, |
2099 | const struct sched_class *prev_class, | 2099 | const struct sched_class *prev_class, |
2100 | int oldprio) | 2100 | int oldprio) |
2101 | { | 2101 | { |
2102 | if (prev_class != p->sched_class) { | 2102 | if (prev_class != p->sched_class) { |
2103 | if (prev_class->switched_from) | 2103 | if (prev_class->switched_from) |
2104 | prev_class->switched_from(rq, p); | 2104 | prev_class->switched_from(rq, p); |
2105 | p->sched_class->switched_to(rq, p); | 2105 | p->sched_class->switched_to(rq, p); |
2106 | } else if (oldprio != p->prio) | 2106 | } else if (oldprio != p->prio) |
2107 | p->sched_class->prio_changed(rq, p, oldprio); | 2107 | p->sched_class->prio_changed(rq, p, oldprio); |
2108 | } | 2108 | } |
2109 | 2109 | ||
2110 | static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) | 2110 | static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) |
2111 | { | 2111 | { |
2112 | const struct sched_class *class; | 2112 | const struct sched_class *class; |
2113 | 2113 | ||
2114 | if (p->sched_class == rq->curr->sched_class) { | 2114 | if (p->sched_class == rq->curr->sched_class) { |
2115 | rq->curr->sched_class->check_preempt_curr(rq, p, flags); | 2115 | rq->curr->sched_class->check_preempt_curr(rq, p, flags); |
2116 | } else { | 2116 | } else { |
2117 | for_each_class(class) { | 2117 | for_each_class(class) { |
2118 | if (class == rq->curr->sched_class) | 2118 | if (class == rq->curr->sched_class) |
2119 | break; | 2119 | break; |
2120 | if (class == p->sched_class) { | 2120 | if (class == p->sched_class) { |
2121 | resched_task(rq->curr); | 2121 | resched_task(rq->curr); |
2122 | break; | 2122 | break; |
2123 | } | 2123 | } |
2124 | } | 2124 | } |
2125 | } | 2125 | } |
2126 | 2126 | ||
2127 | /* | 2127 | /* |
2128 | * A queue event has occurred, and we're going to schedule. In | 2128 | * A queue event has occurred, and we're going to schedule. In |
2129 | * this case, we can save a useless back to back clock update. | 2129 | * this case, we can save a useless back to back clock update. |
2130 | */ | 2130 | */ |
2131 | if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) | 2131 | if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) |
2132 | rq->skip_clock_update = 1; | 2132 | rq->skip_clock_update = 1; |
2133 | } | 2133 | } |
2134 | 2134 | ||
2135 | #ifdef CONFIG_SMP | 2135 | #ifdef CONFIG_SMP |
2136 | /* | 2136 | /* |
2137 | * Is this task likely cache-hot: | 2137 | * Is this task likely cache-hot: |
2138 | */ | 2138 | */ |
2139 | static int | 2139 | static int |
2140 | task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) | 2140 | task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) |
2141 | { | 2141 | { |
2142 | s64 delta; | 2142 | s64 delta; |
2143 | 2143 | ||
2144 | if (p->sched_class != &fair_sched_class) | 2144 | if (p->sched_class != &fair_sched_class) |
2145 | return 0; | 2145 | return 0; |
2146 | 2146 | ||
2147 | if (unlikely(p->policy == SCHED_IDLE)) | 2147 | if (unlikely(p->policy == SCHED_IDLE)) |
2148 | return 0; | 2148 | return 0; |
2149 | 2149 | ||
2150 | /* | 2150 | /* |
2151 | * Buddy candidates are cache hot: | 2151 | * Buddy candidates are cache hot: |
2152 | */ | 2152 | */ |
2153 | if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && | 2153 | if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && |
2154 | (&p->se == cfs_rq_of(&p->se)->next || | 2154 | (&p->se == cfs_rq_of(&p->se)->next || |
2155 | &p->se == cfs_rq_of(&p->se)->last)) | 2155 | &p->se == cfs_rq_of(&p->se)->last)) |
2156 | return 1; | 2156 | return 1; |
2157 | 2157 | ||
2158 | if (sysctl_sched_migration_cost == -1) | 2158 | if (sysctl_sched_migration_cost == -1) |
2159 | return 1; | 2159 | return 1; |
2160 | if (sysctl_sched_migration_cost == 0) | 2160 | if (sysctl_sched_migration_cost == 0) |
2161 | return 0; | 2161 | return 0; |
2162 | 2162 | ||
2163 | delta = now - p->se.exec_start; | 2163 | delta = now - p->se.exec_start; |
2164 | 2164 | ||
2165 | return delta < (s64)sysctl_sched_migration_cost; | 2165 | return delta < (s64)sysctl_sched_migration_cost; |
2166 | } | 2166 | } |
2167 | 2167 | ||
2168 | void set_task_cpu(struct task_struct *p, unsigned int new_cpu) | 2168 | void set_task_cpu(struct task_struct *p, unsigned int new_cpu) |
2169 | { | 2169 | { |
2170 | #ifdef CONFIG_SCHED_DEBUG | 2170 | #ifdef CONFIG_SCHED_DEBUG |
2171 | /* | 2171 | /* |
2172 | * We should never call set_task_cpu() on a blocked task, | 2172 | * We should never call set_task_cpu() on a blocked task, |
2173 | * ttwu() will sort out the placement. | 2173 | * ttwu() will sort out the placement. |
2174 | */ | 2174 | */ |
2175 | WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && | 2175 | WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && |
2176 | !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); | 2176 | !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); |
2177 | 2177 | ||
2178 | #ifdef CONFIG_LOCKDEP | 2178 | #ifdef CONFIG_LOCKDEP |
2179 | WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || | 2179 | WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || |
2180 | lockdep_is_held(&task_rq(p)->lock))); | 2180 | lockdep_is_held(&task_rq(p)->lock))); |
2181 | #endif | 2181 | #endif |
2182 | #endif | 2182 | #endif |
2183 | 2183 | ||
2184 | trace_sched_migrate_task(p, new_cpu); | 2184 | trace_sched_migrate_task(p, new_cpu); |
2185 | 2185 | ||
2186 | if (task_cpu(p) != new_cpu) { | 2186 | if (task_cpu(p) != new_cpu) { |
2187 | p->se.nr_migrations++; | 2187 | p->se.nr_migrations++; |
2188 | perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); | 2188 | perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); |
2189 | } | 2189 | } |
2190 | 2190 | ||
2191 | __set_task_cpu(p, new_cpu); | 2191 | __set_task_cpu(p, new_cpu); |
2192 | } | 2192 | } |
2193 | 2193 | ||
2194 | struct migration_arg { | 2194 | struct migration_arg { |
2195 | struct task_struct *task; | 2195 | struct task_struct *task; |
2196 | int dest_cpu; | 2196 | int dest_cpu; |
2197 | }; | 2197 | }; |
2198 | 2198 | ||
2199 | static int migration_cpu_stop(void *data); | 2199 | static int migration_cpu_stop(void *data); |
2200 | 2200 | ||
2201 | /* | 2201 | /* |
2202 | * The task's runqueue lock must be held. | 2202 | * The task's runqueue lock must be held. |
2203 | * Returns true if you have to wait for migration thread. | 2203 | * Returns true if you have to wait for migration thread. |
2204 | */ | 2204 | */ |
2205 | static bool need_migrate_task(struct task_struct *p) | 2205 | static bool need_migrate_task(struct task_struct *p) |
2206 | { | 2206 | { |
2207 | /* | 2207 | /* |
2208 | * If the task is not on a runqueue (and not running), then | 2208 | * If the task is not on a runqueue (and not running), then |
2209 | * the next wake-up will properly place the task. | 2209 | * the next wake-up will properly place the task. |
2210 | */ | 2210 | */ |
2211 | bool running = p->on_rq || p->on_cpu; | 2211 | bool running = p->on_rq || p->on_cpu; |
2212 | smp_rmb(); /* finish_lock_switch() */ | 2212 | smp_rmb(); /* finish_lock_switch() */ |
2213 | return running; | 2213 | return running; |
2214 | } | 2214 | } |
2215 | 2215 | ||
2216 | /* | 2216 | /* |
2217 | * wait_task_inactive - wait for a thread to unschedule. | 2217 | * wait_task_inactive - wait for a thread to unschedule. |
2218 | * | 2218 | * |
2219 | * If @match_state is nonzero, it's the @p->state value just checked and | 2219 | * If @match_state is nonzero, it's the @p->state value just checked and |
2220 | * not expected to change. If it changes, i.e. @p might have woken up, | 2220 | * not expected to change. If it changes, i.e. @p might have woken up, |
2221 | * then return zero. When we succeed in waiting for @p to be off its CPU, | 2221 | * then return zero. When we succeed in waiting for @p to be off its CPU, |
2222 | * we return a positive number (its total switch count). If a second call | 2222 | * we return a positive number (its total switch count). If a second call |
2223 | * a short while later returns the same number, the caller can be sure that | 2223 | * a short while later returns the same number, the caller can be sure that |
2224 | * @p has remained unscheduled the whole time. | 2224 | * @p has remained unscheduled the whole time. |
2225 | * | 2225 | * |
2226 | * The caller must ensure that the task *will* unschedule sometime soon, | 2226 | * The caller must ensure that the task *will* unschedule sometime soon, |
2227 | * else this function might spin for a *long* time. This function can't | 2227 | * else this function might spin for a *long* time. This function can't |
2228 | * be called with interrupts off, or it may introduce deadlock with | 2228 | * be called with interrupts off, or it may introduce deadlock with |
2229 | * smp_call_function() if an IPI is sent by the same process we are | 2229 | * smp_call_function() if an IPI is sent by the same process we are |
2230 | * waiting to become inactive. | 2230 | * waiting to become inactive. |
2231 | */ | 2231 | */ |
2232 | unsigned long wait_task_inactive(struct task_struct *p, long match_state) | 2232 | unsigned long wait_task_inactive(struct task_struct *p, long match_state) |
2233 | { | 2233 | { |
2234 | unsigned long flags; | 2234 | unsigned long flags; |
2235 | int running, on_rq; | 2235 | int running, on_rq; |
2236 | unsigned long ncsw; | 2236 | unsigned long ncsw; |
2237 | struct rq *rq; | 2237 | struct rq *rq; |
2238 | 2238 | ||
2239 | for (;;) { | 2239 | for (;;) { |
2240 | /* | 2240 | /* |
2241 | * We do the initial early heuristics without holding | 2241 | * We do the initial early heuristics without holding |
2242 | * any task-queue locks at all. We'll only try to get | 2242 | * any task-queue locks at all. We'll only try to get |
2243 | * the runqueue lock when things look like they will | 2243 | * the runqueue lock when things look like they will |
2244 | * work out! | 2244 | * work out! |
2245 | */ | 2245 | */ |
2246 | rq = task_rq(p); | 2246 | rq = task_rq(p); |
2247 | 2247 | ||
2248 | /* | 2248 | /* |
2249 | * If the task is actively running on another CPU | 2249 | * If the task is actively running on another CPU |
2250 | * still, just relax and busy-wait without holding | 2250 | * still, just relax and busy-wait without holding |
2251 | * any locks. | 2251 | * any locks. |
2252 | * | 2252 | * |
2253 | * NOTE! Since we don't hold any locks, it's not | 2253 | * NOTE! Since we don't hold any locks, it's not |
2254 | * even sure that "rq" stays as the right runqueue! | 2254 | * even sure that "rq" stays as the right runqueue! |
2255 | * But we don't care, since "task_running()" will | 2255 | * But we don't care, since "task_running()" will |
2256 | * return false if the runqueue has changed and p | 2256 | * return false if the runqueue has changed and p |
2257 | * is actually now running somewhere else! | 2257 | * is actually now running somewhere else! |
2258 | */ | 2258 | */ |
2259 | while (task_running(rq, p)) { | 2259 | while (task_running(rq, p)) { |
2260 | if (match_state && unlikely(p->state != match_state)) | 2260 | if (match_state && unlikely(p->state != match_state)) |
2261 | return 0; | 2261 | return 0; |
2262 | cpu_relax(); | 2262 | cpu_relax(); |
2263 | } | 2263 | } |
2264 | 2264 | ||
2265 | /* | 2265 | /* |
2266 | * Ok, time to look more closely! We need the rq | 2266 | * Ok, time to look more closely! We need the rq |
2267 | * lock now, to be *sure*. If we're wrong, we'll | 2267 | * lock now, to be *sure*. If we're wrong, we'll |
2268 | * just go back and repeat. | 2268 | * just go back and repeat. |
2269 | */ | 2269 | */ |
2270 | rq = task_rq_lock(p, &flags); | 2270 | rq = task_rq_lock(p, &flags); |
2271 | trace_sched_wait_task(p); | 2271 | trace_sched_wait_task(p); |
2272 | running = task_running(rq, p); | 2272 | running = task_running(rq, p); |
2273 | on_rq = p->on_rq; | 2273 | on_rq = p->on_rq; |
2274 | ncsw = 0; | 2274 | ncsw = 0; |
2275 | if (!match_state || p->state == match_state) | 2275 | if (!match_state || p->state == match_state) |
2276 | ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ | 2276 | ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ |
2277 | task_rq_unlock(rq, p, &flags); | 2277 | task_rq_unlock(rq, p, &flags); |
2278 | 2278 | ||
2279 | /* | 2279 | /* |
2280 | * If it changed from the expected state, bail out now. | 2280 | * If it changed from the expected state, bail out now. |
2281 | */ | 2281 | */ |
2282 | if (unlikely(!ncsw)) | 2282 | if (unlikely(!ncsw)) |
2283 | break; | 2283 | break; |
2284 | 2284 | ||
2285 | /* | 2285 | /* |
2286 | * Was it really running after all now that we | 2286 | * Was it really running after all now that we |
2287 | * checked with the proper locks actually held? | 2287 | * checked with the proper locks actually held? |
2288 | * | 2288 | * |
2289 | * Oops. Go back and try again.. | 2289 | * Oops. Go back and try again.. |
2290 | */ | 2290 | */ |
2291 | if (unlikely(running)) { | 2291 | if (unlikely(running)) { |
2292 | cpu_relax(); | 2292 | cpu_relax(); |
2293 | continue; | 2293 | continue; |
2294 | } | 2294 | } |
2295 | 2295 | ||
2296 | /* | 2296 | /* |
2297 | * It's not enough that it's not actively running, | 2297 | * It's not enough that it's not actively running, |
2298 | * it must be off the runqueue _entirely_, and not | 2298 | * it must be off the runqueue _entirely_, and not |
2299 | * preempted! | 2299 | * preempted! |
2300 | * | 2300 | * |
2301 | * So if it was still runnable (but just not actively | 2301 | * So if it was still runnable (but just not actively |
2302 | * running right now), it's preempted, and we should | 2302 | * running right now), it's preempted, and we should |
2303 | * yield - it could be a while. | 2303 | * yield - it could be a while. |
2304 | */ | 2304 | */ |
2305 | if (unlikely(on_rq)) { | 2305 | if (unlikely(on_rq)) { |
2306 | ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); | 2306 | ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); |
2307 | 2307 | ||
2308 | set_current_state(TASK_UNINTERRUPTIBLE); | 2308 | set_current_state(TASK_UNINTERRUPTIBLE); |
2309 | schedule_hrtimeout(&to, HRTIMER_MODE_REL); | 2309 | schedule_hrtimeout(&to, HRTIMER_MODE_REL); |
2310 | continue; | 2310 | continue; |
2311 | } | 2311 | } |
2312 | 2312 | ||
2313 | /* | 2313 | /* |
2314 | * Ahh, all good. It wasn't running, and it wasn't | 2314 | * Ahh, all good. It wasn't running, and it wasn't |
2315 | * runnable, which means that it will never become | 2315 | * runnable, which means that it will never become |
2316 | * running in the future either. We're all done! | 2316 | * running in the future either. We're all done! |
2317 | */ | 2317 | */ |
2318 | break; | 2318 | break; |
2319 | } | 2319 | } |
2320 | 2320 | ||
2321 | return ncsw; | 2321 | return ncsw; |
2322 | } | 2322 | } |
2323 | 2323 | ||
2324 | /*** | 2324 | /*** |
2325 | * kick_process - kick a running thread to enter/exit the kernel | 2325 | * kick_process - kick a running thread to enter/exit the kernel |
2326 | * @p: the to-be-kicked thread | 2326 | * @p: the to-be-kicked thread |
2327 | * | 2327 | * |
2328 | * Cause a process which is running on another CPU to enter | 2328 | * Cause a process which is running on another CPU to enter |
2329 | * kernel-mode, without any delay. (to get signals handled.) | 2329 | * kernel-mode, without any delay. (to get signals handled.) |
2330 | * | 2330 | * |
2331 | * NOTE: this function doesn't have to take the runqueue lock, | 2331 | * NOTE: this function doesn't have to take the runqueue lock, |
2332 | * because all it wants to ensure is that the remote task enters | 2332 | * because all it wants to ensure is that the remote task enters |
2333 | * the kernel. If the IPI races and the task has been migrated | 2333 | * the kernel. If the IPI races and the task has been migrated |
2334 | * to another CPU then no harm is done and the purpose has been | 2334 | * to another CPU then no harm is done and the purpose has been |
2335 | * achieved as well. | 2335 | * achieved as well. |
2336 | */ | 2336 | */ |
2337 | void kick_process(struct task_struct *p) | 2337 | void kick_process(struct task_struct *p) |
2338 | { | 2338 | { |
2339 | int cpu; | 2339 | int cpu; |
2340 | 2340 | ||
2341 | preempt_disable(); | 2341 | preempt_disable(); |
2342 | cpu = task_cpu(p); | 2342 | cpu = task_cpu(p); |
2343 | if ((cpu != smp_processor_id()) && task_curr(p)) | 2343 | if ((cpu != smp_processor_id()) && task_curr(p)) |
2344 | smp_send_reschedule(cpu); | 2344 | smp_send_reschedule(cpu); |
2345 | preempt_enable(); | 2345 | preempt_enable(); |
2346 | } | 2346 | } |
2347 | EXPORT_SYMBOL_GPL(kick_process); | 2347 | EXPORT_SYMBOL_GPL(kick_process); |
2348 | #endif /* CONFIG_SMP */ | 2348 | #endif /* CONFIG_SMP */ |
2349 | 2349 | ||
2350 | #ifdef CONFIG_SMP | 2350 | #ifdef CONFIG_SMP |
2351 | /* | 2351 | /* |
2352 | * ->cpus_allowed is protected by both rq->lock and p->pi_lock | 2352 | * ->cpus_allowed is protected by both rq->lock and p->pi_lock |
2353 | */ | 2353 | */ |
2354 | static int select_fallback_rq(int cpu, struct task_struct *p) | 2354 | static int select_fallback_rq(int cpu, struct task_struct *p) |
2355 | { | 2355 | { |
2356 | int dest_cpu; | 2356 | int dest_cpu; |
2357 | const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); | 2357 | const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); |
2358 | 2358 | ||
2359 | /* Look for allowed, online CPU in same node. */ | 2359 | /* Look for allowed, online CPU in same node. */ |
2360 | for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) | 2360 | for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) |
2361 | if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) | 2361 | if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) |
2362 | return dest_cpu; | 2362 | return dest_cpu; |
2363 | 2363 | ||
2364 | /* Any allowed, online CPU? */ | 2364 | /* Any allowed, online CPU? */ |
2365 | dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); | 2365 | dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); |
2366 | if (dest_cpu < nr_cpu_ids) | 2366 | if (dest_cpu < nr_cpu_ids) |
2367 | return dest_cpu; | 2367 | return dest_cpu; |
2368 | 2368 | ||
2369 | /* No more Mr. Nice Guy. */ | 2369 | /* No more Mr. Nice Guy. */ |
2370 | dest_cpu = cpuset_cpus_allowed_fallback(p); | 2370 | dest_cpu = cpuset_cpus_allowed_fallback(p); |
2371 | /* | 2371 | /* |
2372 | * Don't tell them about moving exiting tasks or | 2372 | * Don't tell them about moving exiting tasks or |
2373 | * kernel threads (both mm NULL), since they never | 2373 | * kernel threads (both mm NULL), since they never |
2374 | * leave kernel. | 2374 | * leave kernel. |
2375 | */ | 2375 | */ |
2376 | if (p->mm && printk_ratelimit()) { | 2376 | if (p->mm && printk_ratelimit()) { |
2377 | printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", | 2377 | printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", |
2378 | task_pid_nr(p), p->comm, cpu); | 2378 | task_pid_nr(p), p->comm, cpu); |
2379 | } | 2379 | } |
2380 | 2380 | ||
2381 | return dest_cpu; | 2381 | return dest_cpu; |
2382 | } | 2382 | } |
2383 | 2383 | ||
2384 | /* | 2384 | /* |
2385 | * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. | 2385 | * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. |
2386 | */ | 2386 | */ |
2387 | static inline | 2387 | static inline |
2388 | int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) | 2388 | int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) |
2389 | { | 2389 | { |
2390 | int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); | 2390 | int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); |
2391 | 2391 | ||
2392 | /* | 2392 | /* |
2393 | * In order not to call set_task_cpu() on a blocking task we need | 2393 | * In order not to call set_task_cpu() on a blocking task we need |
2394 | * to rely on ttwu() to place the task on a valid ->cpus_allowed | 2394 | * to rely on ttwu() to place the task on a valid ->cpus_allowed |
2395 | * cpu. | 2395 | * cpu. |
2396 | * | 2396 | * |
2397 | * Since this is common to all placement strategies, this lives here. | 2397 | * Since this is common to all placement strategies, this lives here. |
2398 | * | 2398 | * |
2399 | * [ this allows ->select_task() to simply return task_cpu(p) and | 2399 | * [ this allows ->select_task() to simply return task_cpu(p) and |
2400 | * not worry about this generic constraint ] | 2400 | * not worry about this generic constraint ] |
2401 | */ | 2401 | */ |
2402 | if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || | 2402 | if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || |
2403 | !cpu_online(cpu))) | 2403 | !cpu_online(cpu))) |
2404 | cpu = select_fallback_rq(task_cpu(p), p); | 2404 | cpu = select_fallback_rq(task_cpu(p), p); |
2405 | 2405 | ||
2406 | return cpu; | 2406 | return cpu; |
2407 | } | 2407 | } |
2408 | 2408 | ||
2409 | static void update_avg(u64 *avg, u64 sample) | 2409 | static void update_avg(u64 *avg, u64 sample) |
2410 | { | 2410 | { |
2411 | s64 diff = sample - *avg; | 2411 | s64 diff = sample - *avg; |
2412 | *avg += diff >> 3; | 2412 | *avg += diff >> 3; |
2413 | } | 2413 | } |
2414 | #endif | 2414 | #endif |
2415 | 2415 | ||
2416 | static void | 2416 | static void |
2417 | ttwu_stat(struct task_struct *p, int cpu, int wake_flags) | 2417 | ttwu_stat(struct task_struct *p, int cpu, int wake_flags) |
2418 | { | 2418 | { |
2419 | #ifdef CONFIG_SCHEDSTATS | 2419 | #ifdef CONFIG_SCHEDSTATS |
2420 | struct rq *rq = this_rq(); | 2420 | struct rq *rq = this_rq(); |
2421 | 2421 | ||
2422 | #ifdef CONFIG_SMP | 2422 | #ifdef CONFIG_SMP |
2423 | int this_cpu = smp_processor_id(); | 2423 | int this_cpu = smp_processor_id(); |
2424 | 2424 | ||
2425 | if (cpu == this_cpu) { | 2425 | if (cpu == this_cpu) { |
2426 | schedstat_inc(rq, ttwu_local); | 2426 | schedstat_inc(rq, ttwu_local); |
2427 | schedstat_inc(p, se.statistics.nr_wakeups_local); | 2427 | schedstat_inc(p, se.statistics.nr_wakeups_local); |
2428 | } else { | 2428 | } else { |
2429 | struct sched_domain *sd; | 2429 | struct sched_domain *sd; |
2430 | 2430 | ||
2431 | schedstat_inc(p, se.statistics.nr_wakeups_remote); | 2431 | schedstat_inc(p, se.statistics.nr_wakeups_remote); |
2432 | for_each_domain(this_cpu, sd) { | 2432 | for_each_domain(this_cpu, sd) { |
2433 | if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { | 2433 | if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { |
2434 | schedstat_inc(sd, ttwu_wake_remote); | 2434 | schedstat_inc(sd, ttwu_wake_remote); |
2435 | break; | 2435 | break; |
2436 | } | 2436 | } |
2437 | } | 2437 | } |
2438 | } | 2438 | } |
2439 | #endif /* CONFIG_SMP */ | 2439 | #endif /* CONFIG_SMP */ |
2440 | 2440 | ||
2441 | schedstat_inc(rq, ttwu_count); | 2441 | schedstat_inc(rq, ttwu_count); |
2442 | schedstat_inc(p, se.statistics.nr_wakeups); | 2442 | schedstat_inc(p, se.statistics.nr_wakeups); |
2443 | 2443 | ||
2444 | if (wake_flags & WF_SYNC) | 2444 | if (wake_flags & WF_SYNC) |
2445 | schedstat_inc(p, se.statistics.nr_wakeups_sync); | 2445 | schedstat_inc(p, se.statistics.nr_wakeups_sync); |
2446 | 2446 | ||
2447 | if (cpu != task_cpu(p)) | 2447 | if (cpu != task_cpu(p)) |
2448 | schedstat_inc(p, se.statistics.nr_wakeups_migrate); | 2448 | schedstat_inc(p, se.statistics.nr_wakeups_migrate); |
2449 | 2449 | ||
2450 | #endif /* CONFIG_SCHEDSTATS */ | 2450 | #endif /* CONFIG_SCHEDSTATS */ |
2451 | } | 2451 | } |
2452 | 2452 | ||
2453 | static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) | 2453 | static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) |
2454 | { | 2454 | { |
2455 | activate_task(rq, p, en_flags); | 2455 | activate_task(rq, p, en_flags); |
2456 | p->on_rq = 1; | 2456 | p->on_rq = 1; |
2457 | 2457 | ||
2458 | /* if a worker is waking up, notify workqueue */ | 2458 | /* if a worker is waking up, notify workqueue */ |
2459 | if (p->flags & PF_WQ_WORKER) | 2459 | if (p->flags & PF_WQ_WORKER) |
2460 | wq_worker_waking_up(p, cpu_of(rq)); | 2460 | wq_worker_waking_up(p, cpu_of(rq)); |
2461 | } | 2461 | } |
2462 | 2462 | ||
2463 | /* | 2463 | /* |
2464 | * Mark the task runnable and perform wakeup-preemption. | 2464 | * Mark the task runnable and perform wakeup-preemption. |
2465 | */ | 2465 | */ |
2466 | static void | 2466 | static void |
2467 | ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) | 2467 | ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) |
2468 | { | 2468 | { |
2469 | trace_sched_wakeup(p, true); | 2469 | trace_sched_wakeup(p, true); |
2470 | check_preempt_curr(rq, p, wake_flags); | 2470 | check_preempt_curr(rq, p, wake_flags); |
2471 | 2471 | ||
2472 | p->state = TASK_RUNNING; | 2472 | p->state = TASK_RUNNING; |
2473 | #ifdef CONFIG_SMP | 2473 | #ifdef CONFIG_SMP |
2474 | if (p->sched_class->task_woken) | 2474 | if (p->sched_class->task_woken) |
2475 | p->sched_class->task_woken(rq, p); | 2475 | p->sched_class->task_woken(rq, p); |
2476 | 2476 | ||
2477 | if (unlikely(rq->idle_stamp)) { | 2477 | if (unlikely(rq->idle_stamp)) { |
2478 | u64 delta = rq->clock - rq->idle_stamp; | 2478 | u64 delta = rq->clock - rq->idle_stamp; |
2479 | u64 max = 2*sysctl_sched_migration_cost; | 2479 | u64 max = 2*sysctl_sched_migration_cost; |
2480 | 2480 | ||
2481 | if (delta > max) | 2481 | if (delta > max) |
2482 | rq->avg_idle = max; | 2482 | rq->avg_idle = max; |
2483 | else | 2483 | else |
2484 | update_avg(&rq->avg_idle, delta); | 2484 | update_avg(&rq->avg_idle, delta); |
2485 | rq->idle_stamp = 0; | 2485 | rq->idle_stamp = 0; |
2486 | } | 2486 | } |
2487 | #endif | 2487 | #endif |
2488 | } | 2488 | } |
2489 | 2489 | ||
2490 | static void | 2490 | static void |
2491 | ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) | 2491 | ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) |
2492 | { | 2492 | { |
2493 | #ifdef CONFIG_SMP | 2493 | #ifdef CONFIG_SMP |
2494 | if (p->sched_contributes_to_load) | 2494 | if (p->sched_contributes_to_load) |
2495 | rq->nr_uninterruptible--; | 2495 | rq->nr_uninterruptible--; |
2496 | #endif | 2496 | #endif |
2497 | 2497 | ||
2498 | ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); | 2498 | ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); |
2499 | ttwu_do_wakeup(rq, p, wake_flags); | 2499 | ttwu_do_wakeup(rq, p, wake_flags); |
2500 | } | 2500 | } |
2501 | 2501 | ||
2502 | /* | 2502 | /* |
2503 | * Called in case the task @p isn't fully descheduled from its runqueue, | 2503 | * Called in case the task @p isn't fully descheduled from its runqueue, |
2504 | * in this case we must do a remote wakeup. Its a 'light' wakeup though, | 2504 | * in this case we must do a remote wakeup. Its a 'light' wakeup though, |
2505 | * since all we need to do is flip p->state to TASK_RUNNING, since | 2505 | * since all we need to do is flip p->state to TASK_RUNNING, since |
2506 | * the task is still ->on_rq. | 2506 | * the task is still ->on_rq. |
2507 | */ | 2507 | */ |
2508 | static int ttwu_remote(struct task_struct *p, int wake_flags) | 2508 | static int ttwu_remote(struct task_struct *p, int wake_flags) |
2509 | { | 2509 | { |
2510 | struct rq *rq; | 2510 | struct rq *rq; |
2511 | int ret = 0; | 2511 | int ret = 0; |
2512 | 2512 | ||
2513 | rq = __task_rq_lock(p); | 2513 | rq = __task_rq_lock(p); |
2514 | if (p->on_rq) { | 2514 | if (p->on_rq) { |
2515 | ttwu_do_wakeup(rq, p, wake_flags); | 2515 | ttwu_do_wakeup(rq, p, wake_flags); |
2516 | ret = 1; | 2516 | ret = 1; |
2517 | } | 2517 | } |
2518 | __task_rq_unlock(rq); | 2518 | __task_rq_unlock(rq); |
2519 | 2519 | ||
2520 | return ret; | 2520 | return ret; |
2521 | } | 2521 | } |
2522 | 2522 | ||
2523 | #ifdef CONFIG_SMP | 2523 | #ifdef CONFIG_SMP |
2524 | static void sched_ttwu_pending(void) | 2524 | static void sched_ttwu_pending(void) |
2525 | { | 2525 | { |
2526 | struct rq *rq = this_rq(); | 2526 | struct rq *rq = this_rq(); |
2527 | struct task_struct *list = xchg(&rq->wake_list, NULL); | 2527 | struct task_struct *list = xchg(&rq->wake_list, NULL); |
2528 | 2528 | ||
2529 | if (!list) | 2529 | if (!list) |
2530 | return; | 2530 | return; |
2531 | 2531 | ||
2532 | raw_spin_lock(&rq->lock); | 2532 | raw_spin_lock(&rq->lock); |
2533 | 2533 | ||
2534 | while (list) { | 2534 | while (list) { |
2535 | struct task_struct *p = list; | 2535 | struct task_struct *p = list; |
2536 | list = list->wake_entry; | 2536 | list = list->wake_entry; |
2537 | ttwu_do_activate(rq, p, 0); | 2537 | ttwu_do_activate(rq, p, 0); |
2538 | } | 2538 | } |
2539 | 2539 | ||
2540 | raw_spin_unlock(&rq->lock); | 2540 | raw_spin_unlock(&rq->lock); |
2541 | } | 2541 | } |
2542 | 2542 | ||
2543 | void scheduler_ipi(void) | 2543 | void scheduler_ipi(void) |
2544 | { | 2544 | { |
2545 | sched_ttwu_pending(); | 2545 | sched_ttwu_pending(); |
2546 | } | 2546 | } |
2547 | 2547 | ||
2548 | static void ttwu_queue_remote(struct task_struct *p, int cpu) | 2548 | static void ttwu_queue_remote(struct task_struct *p, int cpu) |
2549 | { | 2549 | { |
2550 | struct rq *rq = cpu_rq(cpu); | 2550 | struct rq *rq = cpu_rq(cpu); |
2551 | struct task_struct *next = rq->wake_list; | 2551 | struct task_struct *next = rq->wake_list; |
2552 | 2552 | ||
2553 | for (;;) { | 2553 | for (;;) { |
2554 | struct task_struct *old = next; | 2554 | struct task_struct *old = next; |
2555 | 2555 | ||
2556 | p->wake_entry = next; | 2556 | p->wake_entry = next; |
2557 | next = cmpxchg(&rq->wake_list, old, p); | 2557 | next = cmpxchg(&rq->wake_list, old, p); |
2558 | if (next == old) | 2558 | if (next == old) |
2559 | break; | 2559 | break; |
2560 | } | 2560 | } |
2561 | 2561 | ||
2562 | if (!next) | 2562 | if (!next) |
2563 | smp_send_reschedule(cpu); | 2563 | smp_send_reschedule(cpu); |
2564 | } | 2564 | } |
2565 | #endif | 2565 | #endif |
2566 | 2566 | ||
2567 | static void ttwu_queue(struct task_struct *p, int cpu) | 2567 | static void ttwu_queue(struct task_struct *p, int cpu) |
2568 | { | 2568 | { |
2569 | struct rq *rq = cpu_rq(cpu); | 2569 | struct rq *rq = cpu_rq(cpu); |
2570 | 2570 | ||
2571 | #if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE) | 2571 | #if defined(CONFIG_SMP) |
2572 | if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { | 2572 | if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { |
2573 | ttwu_queue_remote(p, cpu); | 2573 | ttwu_queue_remote(p, cpu); |
2574 | return; | 2574 | return; |
2575 | } | 2575 | } |
2576 | #endif | 2576 | #endif |
2577 | 2577 | ||
2578 | raw_spin_lock(&rq->lock); | 2578 | raw_spin_lock(&rq->lock); |
2579 | ttwu_do_activate(rq, p, 0); | 2579 | ttwu_do_activate(rq, p, 0); |
2580 | raw_spin_unlock(&rq->lock); | 2580 | raw_spin_unlock(&rq->lock); |
2581 | } | 2581 | } |
2582 | 2582 | ||
2583 | /** | 2583 | /** |
2584 | * try_to_wake_up - wake up a thread | 2584 | * try_to_wake_up - wake up a thread |
2585 | * @p: the thread to be awakened | 2585 | * @p: the thread to be awakened |
2586 | * @state: the mask of task states that can be woken | 2586 | * @state: the mask of task states that can be woken |
2587 | * @wake_flags: wake modifier flags (WF_*) | 2587 | * @wake_flags: wake modifier flags (WF_*) |
2588 | * | 2588 | * |
2589 | * Put it on the run-queue if it's not already there. The "current" | 2589 | * Put it on the run-queue if it's not already there. The "current" |
2590 | * thread is always on the run-queue (except when the actual | 2590 | * thread is always on the run-queue (except when the actual |
2591 | * re-schedule is in progress), and as such you're allowed to do | 2591 | * re-schedule is in progress), and as such you're allowed to do |
2592 | * the simpler "current->state = TASK_RUNNING" to mark yourself | 2592 | * the simpler "current->state = TASK_RUNNING" to mark yourself |
2593 | * runnable without the overhead of this. | 2593 | * runnable without the overhead of this. |
2594 | * | 2594 | * |
2595 | * Returns %true if @p was woken up, %false if it was already running | 2595 | * Returns %true if @p was woken up, %false if it was already running |
2596 | * or @state didn't match @p's state. | 2596 | * or @state didn't match @p's state. |
2597 | */ | 2597 | */ |
2598 | static int | 2598 | static int |
2599 | try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) | 2599 | try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) |
2600 | { | 2600 | { |
2601 | unsigned long flags; | 2601 | unsigned long flags; |
2602 | int cpu, success = 0; | 2602 | int cpu, success = 0; |
2603 | 2603 | ||
2604 | smp_wmb(); | 2604 | smp_wmb(); |
2605 | raw_spin_lock_irqsave(&p->pi_lock, flags); | 2605 | raw_spin_lock_irqsave(&p->pi_lock, flags); |
2606 | if (!(p->state & state)) | 2606 | if (!(p->state & state)) |
2607 | goto out; | 2607 | goto out; |
2608 | 2608 | ||
2609 | success = 1; /* we're going to change ->state */ | 2609 | success = 1; /* we're going to change ->state */ |
2610 | cpu = task_cpu(p); | 2610 | cpu = task_cpu(p); |
2611 | 2611 | ||
2612 | if (p->on_rq && ttwu_remote(p, wake_flags)) | 2612 | if (p->on_rq && ttwu_remote(p, wake_flags)) |
2613 | goto stat; | 2613 | goto stat; |
2614 | 2614 | ||
2615 | #ifdef CONFIG_SMP | 2615 | #ifdef CONFIG_SMP |
2616 | /* | 2616 | /* |
2617 | * If the owning (remote) cpu is still in the middle of schedule() with | 2617 | * If the owning (remote) cpu is still in the middle of schedule() with |
2618 | * this task as prev, wait until its done referencing the task. | 2618 | * this task as prev, wait until its done referencing the task. |
2619 | */ | 2619 | */ |
2620 | while (p->on_cpu) { | 2620 | while (p->on_cpu) { |
2621 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW | 2621 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW |
2622 | /* | 2622 | /* |
2623 | * If called from interrupt context we could have landed in the | 2623 | * If called from interrupt context we could have landed in the |
2624 | * middle of schedule(), in this case we should take care not | 2624 | * middle of schedule(), in this case we should take care not |
2625 | * to spin on ->on_cpu if p is current, since that would | 2625 | * to spin on ->on_cpu if p is current, since that would |
2626 | * deadlock. | 2626 | * deadlock. |
2627 | */ | 2627 | */ |
2628 | if (p == current) { | 2628 | if (p == current) { |
2629 | ttwu_queue(p, cpu); | 2629 | ttwu_queue(p, cpu); |
2630 | goto stat; | 2630 | goto stat; |
2631 | } | 2631 | } |
2632 | #endif | 2632 | #endif |
2633 | cpu_relax(); | 2633 | cpu_relax(); |
2634 | } | 2634 | } |
2635 | /* | 2635 | /* |
2636 | * Pairs with the smp_wmb() in finish_lock_switch(). | 2636 | * Pairs with the smp_wmb() in finish_lock_switch(). |
2637 | */ | 2637 | */ |
2638 | smp_rmb(); | 2638 | smp_rmb(); |
2639 | 2639 | ||
2640 | p->sched_contributes_to_load = !!task_contributes_to_load(p); | 2640 | p->sched_contributes_to_load = !!task_contributes_to_load(p); |
2641 | p->state = TASK_WAKING; | 2641 | p->state = TASK_WAKING; |
2642 | 2642 | ||
2643 | if (p->sched_class->task_waking) | 2643 | if (p->sched_class->task_waking) |
2644 | p->sched_class->task_waking(p); | 2644 | p->sched_class->task_waking(p); |
2645 | 2645 | ||
2646 | cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); | 2646 | cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); |
2647 | if (task_cpu(p) != cpu) | 2647 | if (task_cpu(p) != cpu) |
2648 | set_task_cpu(p, cpu); | 2648 | set_task_cpu(p, cpu); |
2649 | #endif /* CONFIG_SMP */ | 2649 | #endif /* CONFIG_SMP */ |
2650 | 2650 | ||
2651 | ttwu_queue(p, cpu); | 2651 | ttwu_queue(p, cpu); |
2652 | stat: | 2652 | stat: |
2653 | ttwu_stat(p, cpu, wake_flags); | 2653 | ttwu_stat(p, cpu, wake_flags); |
2654 | out: | 2654 | out: |
2655 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 2655 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
2656 | 2656 | ||
2657 | return success; | 2657 | return success; |
2658 | } | 2658 | } |
2659 | 2659 | ||
2660 | /** | 2660 | /** |
2661 | * try_to_wake_up_local - try to wake up a local task with rq lock held | 2661 | * try_to_wake_up_local - try to wake up a local task with rq lock held |
2662 | * @p: the thread to be awakened | 2662 | * @p: the thread to be awakened |
2663 | * | 2663 | * |
2664 | * Put @p on the run-queue if it's not already there. The caller must | 2664 | * Put @p on the run-queue if it's not already there. The caller must |
2665 | * ensure that this_rq() is locked, @p is bound to this_rq() and not | 2665 | * ensure that this_rq() is locked, @p is bound to this_rq() and not |
2666 | * the current task. | 2666 | * the current task. |
2667 | */ | 2667 | */ |
2668 | static void try_to_wake_up_local(struct task_struct *p) | 2668 | static void try_to_wake_up_local(struct task_struct *p) |
2669 | { | 2669 | { |
2670 | struct rq *rq = task_rq(p); | 2670 | struct rq *rq = task_rq(p); |
2671 | 2671 | ||
2672 | BUG_ON(rq != this_rq()); | 2672 | BUG_ON(rq != this_rq()); |
2673 | BUG_ON(p == current); | 2673 | BUG_ON(p == current); |
2674 | lockdep_assert_held(&rq->lock); | 2674 | lockdep_assert_held(&rq->lock); |
2675 | 2675 | ||
2676 | if (!raw_spin_trylock(&p->pi_lock)) { | 2676 | if (!raw_spin_trylock(&p->pi_lock)) { |
2677 | raw_spin_unlock(&rq->lock); | 2677 | raw_spin_unlock(&rq->lock); |
2678 | raw_spin_lock(&p->pi_lock); | 2678 | raw_spin_lock(&p->pi_lock); |
2679 | raw_spin_lock(&rq->lock); | 2679 | raw_spin_lock(&rq->lock); |
2680 | } | 2680 | } |
2681 | 2681 | ||
2682 | if (!(p->state & TASK_NORMAL)) | 2682 | if (!(p->state & TASK_NORMAL)) |
2683 | goto out; | 2683 | goto out; |
2684 | 2684 | ||
2685 | if (!p->on_rq) | 2685 | if (!p->on_rq) |
2686 | ttwu_activate(rq, p, ENQUEUE_WAKEUP); | 2686 | ttwu_activate(rq, p, ENQUEUE_WAKEUP); |
2687 | 2687 | ||
2688 | ttwu_do_wakeup(rq, p, 0); | 2688 | ttwu_do_wakeup(rq, p, 0); |
2689 | ttwu_stat(p, smp_processor_id(), 0); | 2689 | ttwu_stat(p, smp_processor_id(), 0); |
2690 | out: | 2690 | out: |
2691 | raw_spin_unlock(&p->pi_lock); | 2691 | raw_spin_unlock(&p->pi_lock); |
2692 | } | 2692 | } |
2693 | 2693 | ||
2694 | /** | 2694 | /** |
2695 | * wake_up_process - Wake up a specific process | 2695 | * wake_up_process - Wake up a specific process |
2696 | * @p: The process to be woken up. | 2696 | * @p: The process to be woken up. |
2697 | * | 2697 | * |
2698 | * Attempt to wake up the nominated process and move it to the set of runnable | 2698 | * Attempt to wake up the nominated process and move it to the set of runnable |
2699 | * processes. Returns 1 if the process was woken up, 0 if it was already | 2699 | * processes. Returns 1 if the process was woken up, 0 if it was already |
2700 | * running. | 2700 | * running. |
2701 | * | 2701 | * |
2702 | * It may be assumed that this function implies a write memory barrier before | 2702 | * It may be assumed that this function implies a write memory barrier before |
2703 | * changing the task state if and only if any tasks are woken up. | 2703 | * changing the task state if and only if any tasks are woken up. |
2704 | */ | 2704 | */ |
2705 | int wake_up_process(struct task_struct *p) | 2705 | int wake_up_process(struct task_struct *p) |
2706 | { | 2706 | { |
2707 | return try_to_wake_up(p, TASK_ALL, 0); | 2707 | return try_to_wake_up(p, TASK_ALL, 0); |
2708 | } | 2708 | } |
2709 | EXPORT_SYMBOL(wake_up_process); | 2709 | EXPORT_SYMBOL(wake_up_process); |
2710 | 2710 | ||
2711 | int wake_up_state(struct task_struct *p, unsigned int state) | 2711 | int wake_up_state(struct task_struct *p, unsigned int state) |
2712 | { | 2712 | { |
2713 | return try_to_wake_up(p, state, 0); | 2713 | return try_to_wake_up(p, state, 0); |
2714 | } | 2714 | } |
2715 | 2715 | ||
2716 | /* | 2716 | /* |
2717 | * Perform scheduler related setup for a newly forked process p. | 2717 | * Perform scheduler related setup for a newly forked process p. |
2718 | * p is forked by current. | 2718 | * p is forked by current. |
2719 | * | 2719 | * |
2720 | * __sched_fork() is basic setup used by init_idle() too: | 2720 | * __sched_fork() is basic setup used by init_idle() too: |
2721 | */ | 2721 | */ |
2722 | static void __sched_fork(struct task_struct *p) | 2722 | static void __sched_fork(struct task_struct *p) |
2723 | { | 2723 | { |
2724 | p->on_rq = 0; | 2724 | p->on_rq = 0; |
2725 | 2725 | ||
2726 | p->se.on_rq = 0; | 2726 | p->se.on_rq = 0; |
2727 | p->se.exec_start = 0; | 2727 | p->se.exec_start = 0; |
2728 | p->se.sum_exec_runtime = 0; | 2728 | p->se.sum_exec_runtime = 0; |
2729 | p->se.prev_sum_exec_runtime = 0; | 2729 | p->se.prev_sum_exec_runtime = 0; |
2730 | p->se.nr_migrations = 0; | 2730 | p->se.nr_migrations = 0; |
2731 | p->se.vruntime = 0; | 2731 | p->se.vruntime = 0; |
2732 | INIT_LIST_HEAD(&p->se.group_node); | 2732 | INIT_LIST_HEAD(&p->se.group_node); |
2733 | 2733 | ||
2734 | #ifdef CONFIG_SCHEDSTATS | 2734 | #ifdef CONFIG_SCHEDSTATS |
2735 | memset(&p->se.statistics, 0, sizeof(p->se.statistics)); | 2735 | memset(&p->se.statistics, 0, sizeof(p->se.statistics)); |
2736 | #endif | 2736 | #endif |
2737 | 2737 | ||
2738 | INIT_LIST_HEAD(&p->rt.run_list); | 2738 | INIT_LIST_HEAD(&p->rt.run_list); |
2739 | 2739 | ||
2740 | #ifdef CONFIG_PREEMPT_NOTIFIERS | 2740 | #ifdef CONFIG_PREEMPT_NOTIFIERS |
2741 | INIT_HLIST_HEAD(&p->preempt_notifiers); | 2741 | INIT_HLIST_HEAD(&p->preempt_notifiers); |
2742 | #endif | 2742 | #endif |
2743 | } | 2743 | } |
2744 | 2744 | ||
2745 | /* | 2745 | /* |
2746 | * fork()/clone()-time setup: | 2746 | * fork()/clone()-time setup: |
2747 | */ | 2747 | */ |
2748 | void sched_fork(struct task_struct *p, int clone_flags) | 2748 | void sched_fork(struct task_struct *p, int clone_flags) |
2749 | { | 2749 | { |
2750 | unsigned long flags; | 2750 | unsigned long flags; |
2751 | int cpu = get_cpu(); | 2751 | int cpu = get_cpu(); |
2752 | 2752 | ||
2753 | __sched_fork(p); | 2753 | __sched_fork(p); |
2754 | /* | 2754 | /* |
2755 | * We mark the process as running here. This guarantees that | 2755 | * We mark the process as running here. This guarantees that |
2756 | * nobody will actually run it, and a signal or other external | 2756 | * nobody will actually run it, and a signal or other external |
2757 | * event cannot wake it up and insert it on the runqueue either. | 2757 | * event cannot wake it up and insert it on the runqueue either. |
2758 | */ | 2758 | */ |
2759 | p->state = TASK_RUNNING; | 2759 | p->state = TASK_RUNNING; |
2760 | 2760 | ||
2761 | /* | 2761 | /* |
2762 | * Revert to default priority/policy on fork if requested. | 2762 | * Revert to default priority/policy on fork if requested. |
2763 | */ | 2763 | */ |
2764 | if (unlikely(p->sched_reset_on_fork)) { | 2764 | if (unlikely(p->sched_reset_on_fork)) { |
2765 | if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { | 2765 | if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { |
2766 | p->policy = SCHED_NORMAL; | 2766 | p->policy = SCHED_NORMAL; |
2767 | p->normal_prio = p->static_prio; | 2767 | p->normal_prio = p->static_prio; |
2768 | } | 2768 | } |
2769 | 2769 | ||
2770 | if (PRIO_TO_NICE(p->static_prio) < 0) { | 2770 | if (PRIO_TO_NICE(p->static_prio) < 0) { |
2771 | p->static_prio = NICE_TO_PRIO(0); | 2771 | p->static_prio = NICE_TO_PRIO(0); |
2772 | p->normal_prio = p->static_prio; | 2772 | p->normal_prio = p->static_prio; |
2773 | set_load_weight(p); | 2773 | set_load_weight(p); |
2774 | } | 2774 | } |
2775 | 2775 | ||
2776 | /* | 2776 | /* |
2777 | * We don't need the reset flag anymore after the fork. It has | 2777 | * We don't need the reset flag anymore after the fork. It has |
2778 | * fulfilled its duty: | 2778 | * fulfilled its duty: |
2779 | */ | 2779 | */ |
2780 | p->sched_reset_on_fork = 0; | 2780 | p->sched_reset_on_fork = 0; |
2781 | } | 2781 | } |
2782 | 2782 | ||
2783 | /* | 2783 | /* |
2784 | * Make sure we do not leak PI boosting priority to the child. | 2784 | * Make sure we do not leak PI boosting priority to the child. |
2785 | */ | 2785 | */ |
2786 | p->prio = current->normal_prio; | 2786 | p->prio = current->normal_prio; |
2787 | 2787 | ||
2788 | if (!rt_prio(p->prio)) | 2788 | if (!rt_prio(p->prio)) |
2789 | p->sched_class = &fair_sched_class; | 2789 | p->sched_class = &fair_sched_class; |
2790 | 2790 | ||
2791 | if (p->sched_class->task_fork) | 2791 | if (p->sched_class->task_fork) |
2792 | p->sched_class->task_fork(p); | 2792 | p->sched_class->task_fork(p); |
2793 | 2793 | ||
2794 | /* | 2794 | /* |
2795 | * The child is not yet in the pid-hash so no cgroup attach races, | 2795 | * The child is not yet in the pid-hash so no cgroup attach races, |
2796 | * and the cgroup is pinned to this child due to cgroup_fork() | 2796 | * and the cgroup is pinned to this child due to cgroup_fork() |
2797 | * is ran before sched_fork(). | 2797 | * is ran before sched_fork(). |
2798 | * | 2798 | * |
2799 | * Silence PROVE_RCU. | 2799 | * Silence PROVE_RCU. |
2800 | */ | 2800 | */ |
2801 | raw_spin_lock_irqsave(&p->pi_lock, flags); | 2801 | raw_spin_lock_irqsave(&p->pi_lock, flags); |
2802 | set_task_cpu(p, cpu); | 2802 | set_task_cpu(p, cpu); |
2803 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 2803 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
2804 | 2804 | ||
2805 | #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) | 2805 | #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) |
2806 | if (likely(sched_info_on())) | 2806 | if (likely(sched_info_on())) |
2807 | memset(&p->sched_info, 0, sizeof(p->sched_info)); | 2807 | memset(&p->sched_info, 0, sizeof(p->sched_info)); |
2808 | #endif | 2808 | #endif |
2809 | #if defined(CONFIG_SMP) | 2809 | #if defined(CONFIG_SMP) |
2810 | p->on_cpu = 0; | 2810 | p->on_cpu = 0; |
2811 | #endif | 2811 | #endif |
2812 | #ifdef CONFIG_PREEMPT | 2812 | #ifdef CONFIG_PREEMPT |
2813 | /* Want to start with kernel preemption disabled. */ | 2813 | /* Want to start with kernel preemption disabled. */ |
2814 | task_thread_info(p)->preempt_count = 1; | 2814 | task_thread_info(p)->preempt_count = 1; |
2815 | #endif | 2815 | #endif |
2816 | #ifdef CONFIG_SMP | 2816 | #ifdef CONFIG_SMP |
2817 | plist_node_init(&p->pushable_tasks, MAX_PRIO); | 2817 | plist_node_init(&p->pushable_tasks, MAX_PRIO); |
2818 | #endif | 2818 | #endif |
2819 | 2819 | ||
2820 | put_cpu(); | 2820 | put_cpu(); |
2821 | } | 2821 | } |
2822 | 2822 | ||
2823 | /* | 2823 | /* |
2824 | * wake_up_new_task - wake up a newly created task for the first time. | 2824 | * wake_up_new_task - wake up a newly created task for the first time. |
2825 | * | 2825 | * |
2826 | * This function will do some initial scheduler statistics housekeeping | 2826 | * This function will do some initial scheduler statistics housekeeping |
2827 | * that must be done for every newly created context, then puts the task | 2827 | * that must be done for every newly created context, then puts the task |
2828 | * on the runqueue and wakes it. | 2828 | * on the runqueue and wakes it. |
2829 | */ | 2829 | */ |
2830 | void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) | 2830 | void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) |
2831 | { | 2831 | { |
2832 | unsigned long flags; | 2832 | unsigned long flags; |
2833 | struct rq *rq; | 2833 | struct rq *rq; |
2834 | 2834 | ||
2835 | raw_spin_lock_irqsave(&p->pi_lock, flags); | 2835 | raw_spin_lock_irqsave(&p->pi_lock, flags); |
2836 | #ifdef CONFIG_SMP | 2836 | #ifdef CONFIG_SMP |
2837 | /* | 2837 | /* |
2838 | * Fork balancing, do it here and not earlier because: | 2838 | * Fork balancing, do it here and not earlier because: |
2839 | * - cpus_allowed can change in the fork path | 2839 | * - cpus_allowed can change in the fork path |
2840 | * - any previously selected cpu might disappear through hotplug | 2840 | * - any previously selected cpu might disappear through hotplug |
2841 | */ | 2841 | */ |
2842 | set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); | 2842 | set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); |
2843 | #endif | 2843 | #endif |
2844 | 2844 | ||
2845 | rq = __task_rq_lock(p); | 2845 | rq = __task_rq_lock(p); |
2846 | activate_task(rq, p, 0); | 2846 | activate_task(rq, p, 0); |
2847 | p->on_rq = 1; | 2847 | p->on_rq = 1; |
2848 | trace_sched_wakeup_new(p, true); | 2848 | trace_sched_wakeup_new(p, true); |
2849 | check_preempt_curr(rq, p, WF_FORK); | 2849 | check_preempt_curr(rq, p, WF_FORK); |
2850 | #ifdef CONFIG_SMP | 2850 | #ifdef CONFIG_SMP |
2851 | if (p->sched_class->task_woken) | 2851 | if (p->sched_class->task_woken) |
2852 | p->sched_class->task_woken(rq, p); | 2852 | p->sched_class->task_woken(rq, p); |
2853 | #endif | 2853 | #endif |
2854 | task_rq_unlock(rq, p, &flags); | 2854 | task_rq_unlock(rq, p, &flags); |
2855 | } | 2855 | } |
2856 | 2856 | ||
2857 | #ifdef CONFIG_PREEMPT_NOTIFIERS | 2857 | #ifdef CONFIG_PREEMPT_NOTIFIERS |
2858 | 2858 | ||
2859 | /** | 2859 | /** |
2860 | * preempt_notifier_register - tell me when current is being preempted & rescheduled | 2860 | * preempt_notifier_register - tell me when current is being preempted & rescheduled |
2861 | * @notifier: notifier struct to register | 2861 | * @notifier: notifier struct to register |
2862 | */ | 2862 | */ |
2863 | void preempt_notifier_register(struct preempt_notifier *notifier) | 2863 | void preempt_notifier_register(struct preempt_notifier *notifier) |
2864 | { | 2864 | { |
2865 | hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); | 2865 | hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); |
2866 | } | 2866 | } |
2867 | EXPORT_SYMBOL_GPL(preempt_notifier_register); | 2867 | EXPORT_SYMBOL_GPL(preempt_notifier_register); |
2868 | 2868 | ||
2869 | /** | 2869 | /** |
2870 | * preempt_notifier_unregister - no longer interested in preemption notifications | 2870 | * preempt_notifier_unregister - no longer interested in preemption notifications |
2871 | * @notifier: notifier struct to unregister | 2871 | * @notifier: notifier struct to unregister |
2872 | * | 2872 | * |
2873 | * This is safe to call from within a preemption notifier. | 2873 | * This is safe to call from within a preemption notifier. |
2874 | */ | 2874 | */ |
2875 | void preempt_notifier_unregister(struct preempt_notifier *notifier) | 2875 | void preempt_notifier_unregister(struct preempt_notifier *notifier) |
2876 | { | 2876 | { |
2877 | hlist_del(¬ifier->link); | 2877 | hlist_del(¬ifier->link); |
2878 | } | 2878 | } |
2879 | EXPORT_SYMBOL_GPL(preempt_notifier_unregister); | 2879 | EXPORT_SYMBOL_GPL(preempt_notifier_unregister); |
2880 | 2880 | ||
2881 | static void fire_sched_in_preempt_notifiers(struct task_struct *curr) | 2881 | static void fire_sched_in_preempt_notifiers(struct task_struct *curr) |
2882 | { | 2882 | { |
2883 | struct preempt_notifier *notifier; | 2883 | struct preempt_notifier *notifier; |
2884 | struct hlist_node *node; | 2884 | struct hlist_node *node; |
2885 | 2885 | ||
2886 | hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) | 2886 | hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) |
2887 | notifier->ops->sched_in(notifier, raw_smp_processor_id()); | 2887 | notifier->ops->sched_in(notifier, raw_smp_processor_id()); |
2888 | } | 2888 | } |
2889 | 2889 | ||
2890 | static void | 2890 | static void |
2891 | fire_sched_out_preempt_notifiers(struct task_struct *curr, | 2891 | fire_sched_out_preempt_notifiers(struct task_struct *curr, |
2892 | struct task_struct *next) | 2892 | struct task_struct *next) |
2893 | { | 2893 | { |
2894 | struct preempt_notifier *notifier; | 2894 | struct preempt_notifier *notifier; |
2895 | struct hlist_node *node; | 2895 | struct hlist_node *node; |
2896 | 2896 | ||
2897 | hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) | 2897 | hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) |
2898 | notifier->ops->sched_out(notifier, next); | 2898 | notifier->ops->sched_out(notifier, next); |
2899 | } | 2899 | } |
2900 | 2900 | ||
2901 | #else /* !CONFIG_PREEMPT_NOTIFIERS */ | 2901 | #else /* !CONFIG_PREEMPT_NOTIFIERS */ |
2902 | 2902 | ||
2903 | static void fire_sched_in_preempt_notifiers(struct task_struct *curr) | 2903 | static void fire_sched_in_preempt_notifiers(struct task_struct *curr) |
2904 | { | 2904 | { |
2905 | } | 2905 | } |
2906 | 2906 | ||
2907 | static void | 2907 | static void |
2908 | fire_sched_out_preempt_notifiers(struct task_struct *curr, | 2908 | fire_sched_out_preempt_notifiers(struct task_struct *curr, |
2909 | struct task_struct *next) | 2909 | struct task_struct *next) |
2910 | { | 2910 | { |
2911 | } | 2911 | } |
2912 | 2912 | ||
2913 | #endif /* CONFIG_PREEMPT_NOTIFIERS */ | 2913 | #endif /* CONFIG_PREEMPT_NOTIFIERS */ |
2914 | 2914 | ||
2915 | /** | 2915 | /** |
2916 | * prepare_task_switch - prepare to switch tasks | 2916 | * prepare_task_switch - prepare to switch tasks |
2917 | * @rq: the runqueue preparing to switch | 2917 | * @rq: the runqueue preparing to switch |
2918 | * @prev: the current task that is being switched out | 2918 | * @prev: the current task that is being switched out |
2919 | * @next: the task we are going to switch to. | 2919 | * @next: the task we are going to switch to. |
2920 | * | 2920 | * |
2921 | * This is called with the rq lock held and interrupts off. It must | 2921 | * This is called with the rq lock held and interrupts off. It must |
2922 | * be paired with a subsequent finish_task_switch after the context | 2922 | * be paired with a subsequent finish_task_switch after the context |
2923 | * switch. | 2923 | * switch. |
2924 | * | 2924 | * |
2925 | * prepare_task_switch sets up locking and calls architecture specific | 2925 | * prepare_task_switch sets up locking and calls architecture specific |
2926 | * hooks. | 2926 | * hooks. |
2927 | */ | 2927 | */ |
2928 | static inline void | 2928 | static inline void |
2929 | prepare_task_switch(struct rq *rq, struct task_struct *prev, | 2929 | prepare_task_switch(struct rq *rq, struct task_struct *prev, |
2930 | struct task_struct *next) | 2930 | struct task_struct *next) |
2931 | { | 2931 | { |
2932 | sched_info_switch(prev, next); | 2932 | sched_info_switch(prev, next); |
2933 | perf_event_task_sched_out(prev, next); | 2933 | perf_event_task_sched_out(prev, next); |
2934 | fire_sched_out_preempt_notifiers(prev, next); | 2934 | fire_sched_out_preempt_notifiers(prev, next); |
2935 | prepare_lock_switch(rq, next); | 2935 | prepare_lock_switch(rq, next); |
2936 | prepare_arch_switch(next); | 2936 | prepare_arch_switch(next); |
2937 | trace_sched_switch(prev, next); | 2937 | trace_sched_switch(prev, next); |
2938 | } | 2938 | } |
2939 | 2939 | ||
2940 | /** | 2940 | /** |
2941 | * finish_task_switch - clean up after a task-switch | 2941 | * finish_task_switch - clean up after a task-switch |
2942 | * @rq: runqueue associated with task-switch | 2942 | * @rq: runqueue associated with task-switch |
2943 | * @prev: the thread we just switched away from. | 2943 | * @prev: the thread we just switched away from. |
2944 | * | 2944 | * |
2945 | * finish_task_switch must be called after the context switch, paired | 2945 | * finish_task_switch must be called after the context switch, paired |
2946 | * with a prepare_task_switch call before the context switch. | 2946 | * with a prepare_task_switch call before the context switch. |
2947 | * finish_task_switch will reconcile locking set up by prepare_task_switch, | 2947 | * finish_task_switch will reconcile locking set up by prepare_task_switch, |
2948 | * and do any other architecture-specific cleanup actions. | 2948 | * and do any other architecture-specific cleanup actions. |
2949 | * | 2949 | * |
2950 | * Note that we may have delayed dropping an mm in context_switch(). If | 2950 | * Note that we may have delayed dropping an mm in context_switch(). If |
2951 | * so, we finish that here outside of the runqueue lock. (Doing it | 2951 | * so, we finish that here outside of the runqueue lock. (Doing it |
2952 | * with the lock held can cause deadlocks; see schedule() for | 2952 | * with the lock held can cause deadlocks; see schedule() for |
2953 | * details.) | 2953 | * details.) |
2954 | */ | 2954 | */ |
2955 | static void finish_task_switch(struct rq *rq, struct task_struct *prev) | 2955 | static void finish_task_switch(struct rq *rq, struct task_struct *prev) |
2956 | __releases(rq->lock) | 2956 | __releases(rq->lock) |
2957 | { | 2957 | { |
2958 | struct mm_struct *mm = rq->prev_mm; | 2958 | struct mm_struct *mm = rq->prev_mm; |
2959 | long prev_state; | 2959 | long prev_state; |
2960 | 2960 | ||
2961 | rq->prev_mm = NULL; | 2961 | rq->prev_mm = NULL; |
2962 | 2962 | ||
2963 | /* | 2963 | /* |
2964 | * A task struct has one reference for the use as "current". | 2964 | * A task struct has one reference for the use as "current". |
2965 | * If a task dies, then it sets TASK_DEAD in tsk->state and calls | 2965 | * If a task dies, then it sets TASK_DEAD in tsk->state and calls |
2966 | * schedule one last time. The schedule call will never return, and | 2966 | * schedule one last time. The schedule call will never return, and |
2967 | * the scheduled task must drop that reference. | 2967 | * the scheduled task must drop that reference. |
2968 | * The test for TASK_DEAD must occur while the runqueue locks are | 2968 | * The test for TASK_DEAD must occur while the runqueue locks are |
2969 | * still held, otherwise prev could be scheduled on another cpu, die | 2969 | * still held, otherwise prev could be scheduled on another cpu, die |
2970 | * there before we look at prev->state, and then the reference would | 2970 | * there before we look at prev->state, and then the reference would |
2971 | * be dropped twice. | 2971 | * be dropped twice. |
2972 | * Manfred Spraul <manfred@colorfullife.com> | 2972 | * Manfred Spraul <manfred@colorfullife.com> |
2973 | */ | 2973 | */ |
2974 | prev_state = prev->state; | 2974 | prev_state = prev->state; |
2975 | finish_arch_switch(prev); | 2975 | finish_arch_switch(prev); |
2976 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW | 2976 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW |
2977 | local_irq_disable(); | 2977 | local_irq_disable(); |
2978 | #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ | 2978 | #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ |
2979 | perf_event_task_sched_in(current); | 2979 | perf_event_task_sched_in(current); |
2980 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW | 2980 | #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW |
2981 | local_irq_enable(); | 2981 | local_irq_enable(); |
2982 | #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ | 2982 | #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ |
2983 | finish_lock_switch(rq, prev); | 2983 | finish_lock_switch(rq, prev); |
2984 | 2984 | ||
2985 | fire_sched_in_preempt_notifiers(current); | 2985 | fire_sched_in_preempt_notifiers(current); |
2986 | if (mm) | 2986 | if (mm) |
2987 | mmdrop(mm); | 2987 | mmdrop(mm); |
2988 | if (unlikely(prev_state == TASK_DEAD)) { | 2988 | if (unlikely(prev_state == TASK_DEAD)) { |
2989 | /* | 2989 | /* |
2990 | * Remove function-return probe instances associated with this | 2990 | * Remove function-return probe instances associated with this |
2991 | * task and put them back on the free list. | 2991 | * task and put them back on the free list. |
2992 | */ | 2992 | */ |
2993 | kprobe_flush_task(prev); | 2993 | kprobe_flush_task(prev); |
2994 | put_task_struct(prev); | 2994 | put_task_struct(prev); |
2995 | } | 2995 | } |
2996 | } | 2996 | } |
2997 | 2997 | ||
2998 | #ifdef CONFIG_SMP | 2998 | #ifdef CONFIG_SMP |
2999 | 2999 | ||
3000 | /* assumes rq->lock is held */ | 3000 | /* assumes rq->lock is held */ |
3001 | static inline void pre_schedule(struct rq *rq, struct task_struct *prev) | 3001 | static inline void pre_schedule(struct rq *rq, struct task_struct *prev) |
3002 | { | 3002 | { |
3003 | if (prev->sched_class->pre_schedule) | 3003 | if (prev->sched_class->pre_schedule) |
3004 | prev->sched_class->pre_schedule(rq, prev); | 3004 | prev->sched_class->pre_schedule(rq, prev); |
3005 | } | 3005 | } |
3006 | 3006 | ||
3007 | /* rq->lock is NOT held, but preemption is disabled */ | 3007 | /* rq->lock is NOT held, but preemption is disabled */ |
3008 | static inline void post_schedule(struct rq *rq) | 3008 | static inline void post_schedule(struct rq *rq) |
3009 | { | 3009 | { |
3010 | if (rq->post_schedule) { | 3010 | if (rq->post_schedule) { |
3011 | unsigned long flags; | 3011 | unsigned long flags; |
3012 | 3012 | ||
3013 | raw_spin_lock_irqsave(&rq->lock, flags); | 3013 | raw_spin_lock_irqsave(&rq->lock, flags); |
3014 | if (rq->curr->sched_class->post_schedule) | 3014 | if (rq->curr->sched_class->post_schedule) |
3015 | rq->curr->sched_class->post_schedule(rq); | 3015 | rq->curr->sched_class->post_schedule(rq); |
3016 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 3016 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
3017 | 3017 | ||
3018 | rq->post_schedule = 0; | 3018 | rq->post_schedule = 0; |
3019 | } | 3019 | } |
3020 | } | 3020 | } |
3021 | 3021 | ||
3022 | #else | 3022 | #else |
3023 | 3023 | ||
3024 | static inline void pre_schedule(struct rq *rq, struct task_struct *p) | 3024 | static inline void pre_schedule(struct rq *rq, struct task_struct *p) |
3025 | { | 3025 | { |
3026 | } | 3026 | } |
3027 | 3027 | ||
3028 | static inline void post_schedule(struct rq *rq) | 3028 | static inline void post_schedule(struct rq *rq) |
3029 | { | 3029 | { |
3030 | } | 3030 | } |
3031 | 3031 | ||
3032 | #endif | 3032 | #endif |
3033 | 3033 | ||
3034 | /** | 3034 | /** |
3035 | * schedule_tail - first thing a freshly forked thread must call. | 3035 | * schedule_tail - first thing a freshly forked thread must call. |
3036 | * @prev: the thread we just switched away from. | 3036 | * @prev: the thread we just switched away from. |
3037 | */ | 3037 | */ |
3038 | asmlinkage void schedule_tail(struct task_struct *prev) | 3038 | asmlinkage void schedule_tail(struct task_struct *prev) |
3039 | __releases(rq->lock) | 3039 | __releases(rq->lock) |
3040 | { | 3040 | { |
3041 | struct rq *rq = this_rq(); | 3041 | struct rq *rq = this_rq(); |
3042 | 3042 | ||
3043 | finish_task_switch(rq, prev); | 3043 | finish_task_switch(rq, prev); |
3044 | 3044 | ||
3045 | /* | 3045 | /* |
3046 | * FIXME: do we need to worry about rq being invalidated by the | 3046 | * FIXME: do we need to worry about rq being invalidated by the |
3047 | * task_switch? | 3047 | * task_switch? |
3048 | */ | 3048 | */ |
3049 | post_schedule(rq); | 3049 | post_schedule(rq); |
3050 | 3050 | ||
3051 | #ifdef __ARCH_WANT_UNLOCKED_CTXSW | 3051 | #ifdef __ARCH_WANT_UNLOCKED_CTXSW |
3052 | /* In this case, finish_task_switch does not reenable preemption */ | 3052 | /* In this case, finish_task_switch does not reenable preemption */ |
3053 | preempt_enable(); | 3053 | preempt_enable(); |
3054 | #endif | 3054 | #endif |
3055 | if (current->set_child_tid) | 3055 | if (current->set_child_tid) |
3056 | put_user(task_pid_vnr(current), current->set_child_tid); | 3056 | put_user(task_pid_vnr(current), current->set_child_tid); |
3057 | } | 3057 | } |
3058 | 3058 | ||
3059 | /* | 3059 | /* |
3060 | * context_switch - switch to the new MM and the new | 3060 | * context_switch - switch to the new MM and the new |
3061 | * thread's register state. | 3061 | * thread's register state. |
3062 | */ | 3062 | */ |
3063 | static inline void | 3063 | static inline void |
3064 | context_switch(struct rq *rq, struct task_struct *prev, | 3064 | context_switch(struct rq *rq, struct task_struct *prev, |
3065 | struct task_struct *next) | 3065 | struct task_struct *next) |
3066 | { | 3066 | { |
3067 | struct mm_struct *mm, *oldmm; | 3067 | struct mm_struct *mm, *oldmm; |
3068 | 3068 | ||
3069 | prepare_task_switch(rq, prev, next); | 3069 | prepare_task_switch(rq, prev, next); |
3070 | 3070 | ||
3071 | mm = next->mm; | 3071 | mm = next->mm; |
3072 | oldmm = prev->active_mm; | 3072 | oldmm = prev->active_mm; |
3073 | /* | 3073 | /* |
3074 | * For paravirt, this is coupled with an exit in switch_to to | 3074 | * For paravirt, this is coupled with an exit in switch_to to |
3075 | * combine the page table reload and the switch backend into | 3075 | * combine the page table reload and the switch backend into |
3076 | * one hypercall. | 3076 | * one hypercall. |
3077 | */ | 3077 | */ |
3078 | arch_start_context_switch(prev); | 3078 | arch_start_context_switch(prev); |
3079 | 3079 | ||
3080 | if (!mm) { | 3080 | if (!mm) { |
3081 | next->active_mm = oldmm; | 3081 | next->active_mm = oldmm; |
3082 | atomic_inc(&oldmm->mm_count); | 3082 | atomic_inc(&oldmm->mm_count); |
3083 | enter_lazy_tlb(oldmm, next); | 3083 | enter_lazy_tlb(oldmm, next); |
3084 | } else | 3084 | } else |
3085 | switch_mm(oldmm, mm, next); | 3085 | switch_mm(oldmm, mm, next); |
3086 | 3086 | ||
3087 | if (!prev->mm) { | 3087 | if (!prev->mm) { |
3088 | prev->active_mm = NULL; | 3088 | prev->active_mm = NULL; |
3089 | rq->prev_mm = oldmm; | 3089 | rq->prev_mm = oldmm; |
3090 | } | 3090 | } |
3091 | /* | 3091 | /* |
3092 | * Since the runqueue lock will be released by the next | 3092 | * Since the runqueue lock will be released by the next |
3093 | * task (which is an invalid locking op but in the case | 3093 | * task (which is an invalid locking op but in the case |
3094 | * of the scheduler it's an obvious special-case), so we | 3094 | * of the scheduler it's an obvious special-case), so we |
3095 | * do an early lockdep release here: | 3095 | * do an early lockdep release here: |
3096 | */ | 3096 | */ |
3097 | #ifndef __ARCH_WANT_UNLOCKED_CTXSW | 3097 | #ifndef __ARCH_WANT_UNLOCKED_CTXSW |
3098 | spin_release(&rq->lock.dep_map, 1, _THIS_IP_); | 3098 | spin_release(&rq->lock.dep_map, 1, _THIS_IP_); |
3099 | #endif | 3099 | #endif |
3100 | 3100 | ||
3101 | /* Here we just switch the register state and the stack. */ | 3101 | /* Here we just switch the register state and the stack. */ |
3102 | switch_to(prev, next, prev); | 3102 | switch_to(prev, next, prev); |
3103 | 3103 | ||
3104 | barrier(); | 3104 | barrier(); |
3105 | /* | 3105 | /* |
3106 | * this_rq must be evaluated again because prev may have moved | 3106 | * this_rq must be evaluated again because prev may have moved |
3107 | * CPUs since it called schedule(), thus the 'rq' on its stack | 3107 | * CPUs since it called schedule(), thus the 'rq' on its stack |
3108 | * frame will be invalid. | 3108 | * frame will be invalid. |
3109 | */ | 3109 | */ |
3110 | finish_task_switch(this_rq(), prev); | 3110 | finish_task_switch(this_rq(), prev); |
3111 | } | 3111 | } |
3112 | 3112 | ||
3113 | /* | 3113 | /* |
3114 | * nr_running, nr_uninterruptible and nr_context_switches: | 3114 | * nr_running, nr_uninterruptible and nr_context_switches: |
3115 | * | 3115 | * |
3116 | * externally visible scheduler statistics: current number of runnable | 3116 | * externally visible scheduler statistics: current number of runnable |
3117 | * threads, current number of uninterruptible-sleeping threads, total | 3117 | * threads, current number of uninterruptible-sleeping threads, total |
3118 | * number of context switches performed since bootup. | 3118 | * number of context switches performed since bootup. |
3119 | */ | 3119 | */ |
3120 | unsigned long nr_running(void) | 3120 | unsigned long nr_running(void) |
3121 | { | 3121 | { |
3122 | unsigned long i, sum = 0; | 3122 | unsigned long i, sum = 0; |
3123 | 3123 | ||
3124 | for_each_online_cpu(i) | 3124 | for_each_online_cpu(i) |
3125 | sum += cpu_rq(i)->nr_running; | 3125 | sum += cpu_rq(i)->nr_running; |
3126 | 3126 | ||
3127 | return sum; | 3127 | return sum; |
3128 | } | 3128 | } |
3129 | 3129 | ||
3130 | unsigned long nr_uninterruptible(void) | 3130 | unsigned long nr_uninterruptible(void) |
3131 | { | 3131 | { |
3132 | unsigned long i, sum = 0; | 3132 | unsigned long i, sum = 0; |
3133 | 3133 | ||
3134 | for_each_possible_cpu(i) | 3134 | for_each_possible_cpu(i) |
3135 | sum += cpu_rq(i)->nr_uninterruptible; | 3135 | sum += cpu_rq(i)->nr_uninterruptible; |
3136 | 3136 | ||
3137 | /* | 3137 | /* |
3138 | * Since we read the counters lockless, it might be slightly | 3138 | * Since we read the counters lockless, it might be slightly |
3139 | * inaccurate. Do not allow it to go below zero though: | 3139 | * inaccurate. Do not allow it to go below zero though: |
3140 | */ | 3140 | */ |
3141 | if (unlikely((long)sum < 0)) | 3141 | if (unlikely((long)sum < 0)) |
3142 | sum = 0; | 3142 | sum = 0; |
3143 | 3143 | ||
3144 | return sum; | 3144 | return sum; |
3145 | } | 3145 | } |
3146 | 3146 | ||
3147 | unsigned long long nr_context_switches(void) | 3147 | unsigned long long nr_context_switches(void) |
3148 | { | 3148 | { |
3149 | int i; | 3149 | int i; |
3150 | unsigned long long sum = 0; | 3150 | unsigned long long sum = 0; |
3151 | 3151 | ||
3152 | for_each_possible_cpu(i) | 3152 | for_each_possible_cpu(i) |
3153 | sum += cpu_rq(i)->nr_switches; | 3153 | sum += cpu_rq(i)->nr_switches; |
3154 | 3154 | ||
3155 | return sum; | 3155 | return sum; |
3156 | } | 3156 | } |
3157 | 3157 | ||
3158 | unsigned long nr_iowait(void) | 3158 | unsigned long nr_iowait(void) |
3159 | { | 3159 | { |
3160 | unsigned long i, sum = 0; | 3160 | unsigned long i, sum = 0; |
3161 | 3161 | ||
3162 | for_each_possible_cpu(i) | 3162 | for_each_possible_cpu(i) |
3163 | sum += atomic_read(&cpu_rq(i)->nr_iowait); | 3163 | sum += atomic_read(&cpu_rq(i)->nr_iowait); |
3164 | 3164 | ||
3165 | return sum; | 3165 | return sum; |
3166 | } | 3166 | } |
3167 | 3167 | ||
3168 | unsigned long nr_iowait_cpu(int cpu) | 3168 | unsigned long nr_iowait_cpu(int cpu) |
3169 | { | 3169 | { |
3170 | struct rq *this = cpu_rq(cpu); | 3170 | struct rq *this = cpu_rq(cpu); |
3171 | return atomic_read(&this->nr_iowait); | 3171 | return atomic_read(&this->nr_iowait); |
3172 | } | 3172 | } |
3173 | 3173 | ||
3174 | unsigned long this_cpu_load(void) | 3174 | unsigned long this_cpu_load(void) |
3175 | { | 3175 | { |
3176 | struct rq *this = this_rq(); | 3176 | struct rq *this = this_rq(); |
3177 | return this->cpu_load[0]; | 3177 | return this->cpu_load[0]; |
3178 | } | 3178 | } |
3179 | 3179 | ||
3180 | 3180 | ||
3181 | /* Variables and functions for calc_load */ | 3181 | /* Variables and functions for calc_load */ |
3182 | static atomic_long_t calc_load_tasks; | 3182 | static atomic_long_t calc_load_tasks; |
3183 | static unsigned long calc_load_update; | 3183 | static unsigned long calc_load_update; |
3184 | unsigned long avenrun[3]; | 3184 | unsigned long avenrun[3]; |
3185 | EXPORT_SYMBOL(avenrun); | 3185 | EXPORT_SYMBOL(avenrun); |
3186 | 3186 | ||
3187 | static long calc_load_fold_active(struct rq *this_rq) | 3187 | static long calc_load_fold_active(struct rq *this_rq) |
3188 | { | 3188 | { |
3189 | long nr_active, delta = 0; | 3189 | long nr_active, delta = 0; |
3190 | 3190 | ||
3191 | nr_active = this_rq->nr_running; | 3191 | nr_active = this_rq->nr_running; |
3192 | nr_active += (long) this_rq->nr_uninterruptible; | 3192 | nr_active += (long) this_rq->nr_uninterruptible; |
3193 | 3193 | ||
3194 | if (nr_active != this_rq->calc_load_active) { | 3194 | if (nr_active != this_rq->calc_load_active) { |
3195 | delta = nr_active - this_rq->calc_load_active; | 3195 | delta = nr_active - this_rq->calc_load_active; |
3196 | this_rq->calc_load_active = nr_active; | 3196 | this_rq->calc_load_active = nr_active; |
3197 | } | 3197 | } |
3198 | 3198 | ||
3199 | return delta; | 3199 | return delta; |
3200 | } | 3200 | } |
3201 | 3201 | ||
3202 | static unsigned long | 3202 | static unsigned long |
3203 | calc_load(unsigned long load, unsigned long exp, unsigned long active) | 3203 | calc_load(unsigned long load, unsigned long exp, unsigned long active) |
3204 | { | 3204 | { |
3205 | load *= exp; | 3205 | load *= exp; |
3206 | load += active * (FIXED_1 - exp); | 3206 | load += active * (FIXED_1 - exp); |
3207 | load += 1UL << (FSHIFT - 1); | 3207 | load += 1UL << (FSHIFT - 1); |
3208 | return load >> FSHIFT; | 3208 | return load >> FSHIFT; |
3209 | } | 3209 | } |
3210 | 3210 | ||
3211 | #ifdef CONFIG_NO_HZ | 3211 | #ifdef CONFIG_NO_HZ |
3212 | /* | 3212 | /* |
3213 | * For NO_HZ we delay the active fold to the next LOAD_FREQ update. | 3213 | * For NO_HZ we delay the active fold to the next LOAD_FREQ update. |
3214 | * | 3214 | * |
3215 | * When making the ILB scale, we should try to pull this in as well. | 3215 | * When making the ILB scale, we should try to pull this in as well. |
3216 | */ | 3216 | */ |
3217 | static atomic_long_t calc_load_tasks_idle; | 3217 | static atomic_long_t calc_load_tasks_idle; |
3218 | 3218 | ||
3219 | static void calc_load_account_idle(struct rq *this_rq) | 3219 | static void calc_load_account_idle(struct rq *this_rq) |
3220 | { | 3220 | { |
3221 | long delta; | 3221 | long delta; |
3222 | 3222 | ||
3223 | delta = calc_load_fold_active(this_rq); | 3223 | delta = calc_load_fold_active(this_rq); |
3224 | if (delta) | 3224 | if (delta) |
3225 | atomic_long_add(delta, &calc_load_tasks_idle); | 3225 | atomic_long_add(delta, &calc_load_tasks_idle); |
3226 | } | 3226 | } |
3227 | 3227 | ||
3228 | static long calc_load_fold_idle(void) | 3228 | static long calc_load_fold_idle(void) |
3229 | { | 3229 | { |
3230 | long delta = 0; | 3230 | long delta = 0; |
3231 | 3231 | ||
3232 | /* | 3232 | /* |
3233 | * Its got a race, we don't care... | 3233 | * Its got a race, we don't care... |
3234 | */ | 3234 | */ |
3235 | if (atomic_long_read(&calc_load_tasks_idle)) | 3235 | if (atomic_long_read(&calc_load_tasks_idle)) |
3236 | delta = atomic_long_xchg(&calc_load_tasks_idle, 0); | 3236 | delta = atomic_long_xchg(&calc_load_tasks_idle, 0); |
3237 | 3237 | ||
3238 | return delta; | 3238 | return delta; |
3239 | } | 3239 | } |
3240 | 3240 | ||
3241 | /** | 3241 | /** |
3242 | * fixed_power_int - compute: x^n, in O(log n) time | 3242 | * fixed_power_int - compute: x^n, in O(log n) time |
3243 | * | 3243 | * |
3244 | * @x: base of the power | 3244 | * @x: base of the power |
3245 | * @frac_bits: fractional bits of @x | 3245 | * @frac_bits: fractional bits of @x |
3246 | * @n: power to raise @x to. | 3246 | * @n: power to raise @x to. |
3247 | * | 3247 | * |
3248 | * By exploiting the relation between the definition of the natural power | 3248 | * By exploiting the relation between the definition of the natural power |
3249 | * function: x^n := x*x*...*x (x multiplied by itself for n times), and | 3249 | * function: x^n := x*x*...*x (x multiplied by itself for n times), and |
3250 | * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, | 3250 | * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, |
3251 | * (where: n_i \elem {0, 1}, the binary vector representing n), | 3251 | * (where: n_i \elem {0, 1}, the binary vector representing n), |
3252 | * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is | 3252 | * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is |
3253 | * of course trivially computable in O(log_2 n), the length of our binary | 3253 | * of course trivially computable in O(log_2 n), the length of our binary |
3254 | * vector. | 3254 | * vector. |
3255 | */ | 3255 | */ |
3256 | static unsigned long | 3256 | static unsigned long |
3257 | fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) | 3257 | fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) |
3258 | { | 3258 | { |
3259 | unsigned long result = 1UL << frac_bits; | 3259 | unsigned long result = 1UL << frac_bits; |
3260 | 3260 | ||
3261 | if (n) for (;;) { | 3261 | if (n) for (;;) { |
3262 | if (n & 1) { | 3262 | if (n & 1) { |
3263 | result *= x; | 3263 | result *= x; |
3264 | result += 1UL << (frac_bits - 1); | 3264 | result += 1UL << (frac_bits - 1); |
3265 | result >>= frac_bits; | 3265 | result >>= frac_bits; |
3266 | } | 3266 | } |
3267 | n >>= 1; | 3267 | n >>= 1; |
3268 | if (!n) | 3268 | if (!n) |
3269 | break; | 3269 | break; |
3270 | x *= x; | 3270 | x *= x; |
3271 | x += 1UL << (frac_bits - 1); | 3271 | x += 1UL << (frac_bits - 1); |
3272 | x >>= frac_bits; | 3272 | x >>= frac_bits; |
3273 | } | 3273 | } |
3274 | 3274 | ||
3275 | return result; | 3275 | return result; |
3276 | } | 3276 | } |
3277 | 3277 | ||
3278 | /* | 3278 | /* |
3279 | * a1 = a0 * e + a * (1 - e) | 3279 | * a1 = a0 * e + a * (1 - e) |
3280 | * | 3280 | * |
3281 | * a2 = a1 * e + a * (1 - e) | 3281 | * a2 = a1 * e + a * (1 - e) |
3282 | * = (a0 * e + a * (1 - e)) * e + a * (1 - e) | 3282 | * = (a0 * e + a * (1 - e)) * e + a * (1 - e) |
3283 | * = a0 * e^2 + a * (1 - e) * (1 + e) | 3283 | * = a0 * e^2 + a * (1 - e) * (1 + e) |
3284 | * | 3284 | * |
3285 | * a3 = a2 * e + a * (1 - e) | 3285 | * a3 = a2 * e + a * (1 - e) |
3286 | * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) | 3286 | * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) |
3287 | * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) | 3287 | * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) |
3288 | * | 3288 | * |
3289 | * ... | 3289 | * ... |
3290 | * | 3290 | * |
3291 | * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] | 3291 | * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] |
3292 | * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) | 3292 | * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) |
3293 | * = a0 * e^n + a * (1 - e^n) | 3293 | * = a0 * e^n + a * (1 - e^n) |
3294 | * | 3294 | * |
3295 | * [1] application of the geometric series: | 3295 | * [1] application of the geometric series: |
3296 | * | 3296 | * |
3297 | * n 1 - x^(n+1) | 3297 | * n 1 - x^(n+1) |
3298 | * S_n := \Sum x^i = ------------- | 3298 | * S_n := \Sum x^i = ------------- |
3299 | * i=0 1 - x | 3299 | * i=0 1 - x |
3300 | */ | 3300 | */ |
3301 | static unsigned long | 3301 | static unsigned long |
3302 | calc_load_n(unsigned long load, unsigned long exp, | 3302 | calc_load_n(unsigned long load, unsigned long exp, |
3303 | unsigned long active, unsigned int n) | 3303 | unsigned long active, unsigned int n) |
3304 | { | 3304 | { |
3305 | 3305 | ||
3306 | return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); | 3306 | return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); |
3307 | } | 3307 | } |
3308 | 3308 | ||
3309 | /* | 3309 | /* |
3310 | * NO_HZ can leave us missing all per-cpu ticks calling | 3310 | * NO_HZ can leave us missing all per-cpu ticks calling |
3311 | * calc_load_account_active(), but since an idle CPU folds its delta into | 3311 | * calc_load_account_active(), but since an idle CPU folds its delta into |
3312 | * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold | 3312 | * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold |
3313 | * in the pending idle delta if our idle period crossed a load cycle boundary. | 3313 | * in the pending idle delta if our idle period crossed a load cycle boundary. |
3314 | * | 3314 | * |
3315 | * Once we've updated the global active value, we need to apply the exponential | 3315 | * Once we've updated the global active value, we need to apply the exponential |
3316 | * weights adjusted to the number of cycles missed. | 3316 | * weights adjusted to the number of cycles missed. |
3317 | */ | 3317 | */ |
3318 | static void calc_global_nohz(unsigned long ticks) | 3318 | static void calc_global_nohz(unsigned long ticks) |
3319 | { | 3319 | { |
3320 | long delta, active, n; | 3320 | long delta, active, n; |
3321 | 3321 | ||
3322 | if (time_before(jiffies, calc_load_update)) | 3322 | if (time_before(jiffies, calc_load_update)) |
3323 | return; | 3323 | return; |
3324 | 3324 | ||
3325 | /* | 3325 | /* |
3326 | * If we crossed a calc_load_update boundary, make sure to fold | 3326 | * If we crossed a calc_load_update boundary, make sure to fold |
3327 | * any pending idle changes, the respective CPUs might have | 3327 | * any pending idle changes, the respective CPUs might have |
3328 | * missed the tick driven calc_load_account_active() update | 3328 | * missed the tick driven calc_load_account_active() update |
3329 | * due to NO_HZ. | 3329 | * due to NO_HZ. |
3330 | */ | 3330 | */ |
3331 | delta = calc_load_fold_idle(); | 3331 | delta = calc_load_fold_idle(); |
3332 | if (delta) | 3332 | if (delta) |
3333 | atomic_long_add(delta, &calc_load_tasks); | 3333 | atomic_long_add(delta, &calc_load_tasks); |
3334 | 3334 | ||
3335 | /* | 3335 | /* |
3336 | * If we were idle for multiple load cycles, apply them. | 3336 | * If we were idle for multiple load cycles, apply them. |
3337 | */ | 3337 | */ |
3338 | if (ticks >= LOAD_FREQ) { | 3338 | if (ticks >= LOAD_FREQ) { |
3339 | n = ticks / LOAD_FREQ; | 3339 | n = ticks / LOAD_FREQ; |
3340 | 3340 | ||
3341 | active = atomic_long_read(&calc_load_tasks); | 3341 | active = atomic_long_read(&calc_load_tasks); |
3342 | active = active > 0 ? active * FIXED_1 : 0; | 3342 | active = active > 0 ? active * FIXED_1 : 0; |
3343 | 3343 | ||
3344 | avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); | 3344 | avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); |
3345 | avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); | 3345 | avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); |
3346 | avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); | 3346 | avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); |
3347 | 3347 | ||
3348 | calc_load_update += n * LOAD_FREQ; | 3348 | calc_load_update += n * LOAD_FREQ; |
3349 | } | 3349 | } |
3350 | 3350 | ||
3351 | /* | 3351 | /* |
3352 | * Its possible the remainder of the above division also crosses | 3352 | * Its possible the remainder of the above division also crosses |
3353 | * a LOAD_FREQ period, the regular check in calc_global_load() | 3353 | * a LOAD_FREQ period, the regular check in calc_global_load() |
3354 | * which comes after this will take care of that. | 3354 | * which comes after this will take care of that. |
3355 | * | 3355 | * |
3356 | * Consider us being 11 ticks before a cycle completion, and us | 3356 | * Consider us being 11 ticks before a cycle completion, and us |
3357 | * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will | 3357 | * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will |
3358 | * age us 4 cycles, and the test in calc_global_load() will | 3358 | * age us 4 cycles, and the test in calc_global_load() will |
3359 | * pick up the final one. | 3359 | * pick up the final one. |
3360 | */ | 3360 | */ |
3361 | } | 3361 | } |
3362 | #else | 3362 | #else |
3363 | static void calc_load_account_idle(struct rq *this_rq) | 3363 | static void calc_load_account_idle(struct rq *this_rq) |
3364 | { | 3364 | { |
3365 | } | 3365 | } |
3366 | 3366 | ||
3367 | static inline long calc_load_fold_idle(void) | 3367 | static inline long calc_load_fold_idle(void) |
3368 | { | 3368 | { |
3369 | return 0; | 3369 | return 0; |
3370 | } | 3370 | } |
3371 | 3371 | ||
3372 | static void calc_global_nohz(unsigned long ticks) | 3372 | static void calc_global_nohz(unsigned long ticks) |
3373 | { | 3373 | { |
3374 | } | 3374 | } |
3375 | #endif | 3375 | #endif |
3376 | 3376 | ||
3377 | /** | 3377 | /** |
3378 | * get_avenrun - get the load average array | 3378 | * get_avenrun - get the load average array |
3379 | * @loads: pointer to dest load array | 3379 | * @loads: pointer to dest load array |
3380 | * @offset: offset to add | 3380 | * @offset: offset to add |
3381 | * @shift: shift count to shift the result left | 3381 | * @shift: shift count to shift the result left |
3382 | * | 3382 | * |
3383 | * These values are estimates at best, so no need for locking. | 3383 | * These values are estimates at best, so no need for locking. |
3384 | */ | 3384 | */ |
3385 | void get_avenrun(unsigned long *loads, unsigned long offset, int shift) | 3385 | void get_avenrun(unsigned long *loads, unsigned long offset, int shift) |
3386 | { | 3386 | { |
3387 | loads[0] = (avenrun[0] + offset) << shift; | 3387 | loads[0] = (avenrun[0] + offset) << shift; |
3388 | loads[1] = (avenrun[1] + offset) << shift; | 3388 | loads[1] = (avenrun[1] + offset) << shift; |
3389 | loads[2] = (avenrun[2] + offset) << shift; | 3389 | loads[2] = (avenrun[2] + offset) << shift; |
3390 | } | 3390 | } |
3391 | 3391 | ||
3392 | /* | 3392 | /* |
3393 | * calc_load - update the avenrun load estimates 10 ticks after the | 3393 | * calc_load - update the avenrun load estimates 10 ticks after the |
3394 | * CPUs have updated calc_load_tasks. | 3394 | * CPUs have updated calc_load_tasks. |
3395 | */ | 3395 | */ |
3396 | void calc_global_load(unsigned long ticks) | 3396 | void calc_global_load(unsigned long ticks) |
3397 | { | 3397 | { |
3398 | long active; | 3398 | long active; |
3399 | 3399 | ||
3400 | calc_global_nohz(ticks); | 3400 | calc_global_nohz(ticks); |
3401 | 3401 | ||
3402 | if (time_before(jiffies, calc_load_update + 10)) | 3402 | if (time_before(jiffies, calc_load_update + 10)) |
3403 | return; | 3403 | return; |
3404 | 3404 | ||
3405 | active = atomic_long_read(&calc_load_tasks); | 3405 | active = atomic_long_read(&calc_load_tasks); |
3406 | active = active > 0 ? active * FIXED_1 : 0; | 3406 | active = active > 0 ? active * FIXED_1 : 0; |
3407 | 3407 | ||
3408 | avenrun[0] = calc_load(avenrun[0], EXP_1, active); | 3408 | avenrun[0] = calc_load(avenrun[0], EXP_1, active); |
3409 | avenrun[1] = calc_load(avenrun[1], EXP_5, active); | 3409 | avenrun[1] = calc_load(avenrun[1], EXP_5, active); |
3410 | avenrun[2] = calc_load(avenrun[2], EXP_15, active); | 3410 | avenrun[2] = calc_load(avenrun[2], EXP_15, active); |
3411 | 3411 | ||
3412 | calc_load_update += LOAD_FREQ; | 3412 | calc_load_update += LOAD_FREQ; |
3413 | } | 3413 | } |
3414 | 3414 | ||
3415 | /* | 3415 | /* |
3416 | * Called from update_cpu_load() to periodically update this CPU's | 3416 | * Called from update_cpu_load() to periodically update this CPU's |
3417 | * active count. | 3417 | * active count. |
3418 | */ | 3418 | */ |
3419 | static void calc_load_account_active(struct rq *this_rq) | 3419 | static void calc_load_account_active(struct rq *this_rq) |
3420 | { | 3420 | { |
3421 | long delta; | 3421 | long delta; |
3422 | 3422 | ||
3423 | if (time_before(jiffies, this_rq->calc_load_update)) | 3423 | if (time_before(jiffies, this_rq->calc_load_update)) |
3424 | return; | 3424 | return; |
3425 | 3425 | ||
3426 | delta = calc_load_fold_active(this_rq); | 3426 | delta = calc_load_fold_active(this_rq); |
3427 | delta += calc_load_fold_idle(); | 3427 | delta += calc_load_fold_idle(); |
3428 | if (delta) | 3428 | if (delta) |
3429 | atomic_long_add(delta, &calc_load_tasks); | 3429 | atomic_long_add(delta, &calc_load_tasks); |
3430 | 3430 | ||
3431 | this_rq->calc_load_update += LOAD_FREQ; | 3431 | this_rq->calc_load_update += LOAD_FREQ; |
3432 | } | 3432 | } |
3433 | 3433 | ||
3434 | /* | 3434 | /* |
3435 | * The exact cpuload at various idx values, calculated at every tick would be | 3435 | * The exact cpuload at various idx values, calculated at every tick would be |
3436 | * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load | 3436 | * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load |
3437 | * | 3437 | * |
3438 | * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called | 3438 | * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called |
3439 | * on nth tick when cpu may be busy, then we have: | 3439 | * on nth tick when cpu may be busy, then we have: |
3440 | * load = ((2^idx - 1) / 2^idx)^(n-1) * load | 3440 | * load = ((2^idx - 1) / 2^idx)^(n-1) * load |
3441 | * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load | 3441 | * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load |
3442 | * | 3442 | * |
3443 | * decay_load_missed() below does efficient calculation of | 3443 | * decay_load_missed() below does efficient calculation of |
3444 | * load = ((2^idx - 1) / 2^idx)^(n-1) * load | 3444 | * load = ((2^idx - 1) / 2^idx)^(n-1) * load |
3445 | * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load | 3445 | * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load |
3446 | * | 3446 | * |
3447 | * The calculation is approximated on a 128 point scale. | 3447 | * The calculation is approximated on a 128 point scale. |
3448 | * degrade_zero_ticks is the number of ticks after which load at any | 3448 | * degrade_zero_ticks is the number of ticks after which load at any |
3449 | * particular idx is approximated to be zero. | 3449 | * particular idx is approximated to be zero. |
3450 | * degrade_factor is a precomputed table, a row for each load idx. | 3450 | * degrade_factor is a precomputed table, a row for each load idx. |
3451 | * Each column corresponds to degradation factor for a power of two ticks, | 3451 | * Each column corresponds to degradation factor for a power of two ticks, |
3452 | * based on 128 point scale. | 3452 | * based on 128 point scale. |
3453 | * Example: | 3453 | * Example: |
3454 | * row 2, col 3 (=12) says that the degradation at load idx 2 after | 3454 | * row 2, col 3 (=12) says that the degradation at load idx 2 after |
3455 | * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). | 3455 | * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). |
3456 | * | 3456 | * |
3457 | * With this power of 2 load factors, we can degrade the load n times | 3457 | * With this power of 2 load factors, we can degrade the load n times |
3458 | * by looking at 1 bits in n and doing as many mult/shift instead of | 3458 | * by looking at 1 bits in n and doing as many mult/shift instead of |
3459 | * n mult/shifts needed by the exact degradation. | 3459 | * n mult/shifts needed by the exact degradation. |
3460 | */ | 3460 | */ |
3461 | #define DEGRADE_SHIFT 7 | 3461 | #define DEGRADE_SHIFT 7 |
3462 | static const unsigned char | 3462 | static const unsigned char |
3463 | degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; | 3463 | degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; |
3464 | static const unsigned char | 3464 | static const unsigned char |
3465 | degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { | 3465 | degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { |
3466 | {0, 0, 0, 0, 0, 0, 0, 0}, | 3466 | {0, 0, 0, 0, 0, 0, 0, 0}, |
3467 | {64, 32, 8, 0, 0, 0, 0, 0}, | 3467 | {64, 32, 8, 0, 0, 0, 0, 0}, |
3468 | {96, 72, 40, 12, 1, 0, 0}, | 3468 | {96, 72, 40, 12, 1, 0, 0}, |
3469 | {112, 98, 75, 43, 15, 1, 0}, | 3469 | {112, 98, 75, 43, 15, 1, 0}, |
3470 | {120, 112, 98, 76, 45, 16, 2} }; | 3470 | {120, 112, 98, 76, 45, 16, 2} }; |
3471 | 3471 | ||
3472 | /* | 3472 | /* |
3473 | * Update cpu_load for any missed ticks, due to tickless idle. The backlog | 3473 | * Update cpu_load for any missed ticks, due to tickless idle. The backlog |
3474 | * would be when CPU is idle and so we just decay the old load without | 3474 | * would be when CPU is idle and so we just decay the old load without |
3475 | * adding any new load. | 3475 | * adding any new load. |
3476 | */ | 3476 | */ |
3477 | static unsigned long | 3477 | static unsigned long |
3478 | decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) | 3478 | decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) |
3479 | { | 3479 | { |
3480 | int j = 0; | 3480 | int j = 0; |
3481 | 3481 | ||
3482 | if (!missed_updates) | 3482 | if (!missed_updates) |
3483 | return load; | 3483 | return load; |
3484 | 3484 | ||
3485 | if (missed_updates >= degrade_zero_ticks[idx]) | 3485 | if (missed_updates >= degrade_zero_ticks[idx]) |
3486 | return 0; | 3486 | return 0; |
3487 | 3487 | ||
3488 | if (idx == 1) | 3488 | if (idx == 1) |
3489 | return load >> missed_updates; | 3489 | return load >> missed_updates; |
3490 | 3490 | ||
3491 | while (missed_updates) { | 3491 | while (missed_updates) { |
3492 | if (missed_updates % 2) | 3492 | if (missed_updates % 2) |
3493 | load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; | 3493 | load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; |
3494 | 3494 | ||
3495 | missed_updates >>= 1; | 3495 | missed_updates >>= 1; |
3496 | j++; | 3496 | j++; |
3497 | } | 3497 | } |
3498 | return load; | 3498 | return load; |
3499 | } | 3499 | } |
3500 | 3500 | ||
3501 | /* | 3501 | /* |
3502 | * Update rq->cpu_load[] statistics. This function is usually called every | 3502 | * Update rq->cpu_load[] statistics. This function is usually called every |
3503 | * scheduler tick (TICK_NSEC). With tickless idle this will not be called | 3503 | * scheduler tick (TICK_NSEC). With tickless idle this will not be called |
3504 | * every tick. We fix it up based on jiffies. | 3504 | * every tick. We fix it up based on jiffies. |
3505 | */ | 3505 | */ |
3506 | static void update_cpu_load(struct rq *this_rq) | 3506 | static void update_cpu_load(struct rq *this_rq) |
3507 | { | 3507 | { |
3508 | unsigned long this_load = this_rq->load.weight; | 3508 | unsigned long this_load = this_rq->load.weight; |
3509 | unsigned long curr_jiffies = jiffies; | 3509 | unsigned long curr_jiffies = jiffies; |
3510 | unsigned long pending_updates; | 3510 | unsigned long pending_updates; |
3511 | int i, scale; | 3511 | int i, scale; |
3512 | 3512 | ||
3513 | this_rq->nr_load_updates++; | 3513 | this_rq->nr_load_updates++; |
3514 | 3514 | ||
3515 | /* Avoid repeated calls on same jiffy, when moving in and out of idle */ | 3515 | /* Avoid repeated calls on same jiffy, when moving in and out of idle */ |
3516 | if (curr_jiffies == this_rq->last_load_update_tick) | 3516 | if (curr_jiffies == this_rq->last_load_update_tick) |
3517 | return; | 3517 | return; |
3518 | 3518 | ||
3519 | pending_updates = curr_jiffies - this_rq->last_load_update_tick; | 3519 | pending_updates = curr_jiffies - this_rq->last_load_update_tick; |
3520 | this_rq->last_load_update_tick = curr_jiffies; | 3520 | this_rq->last_load_update_tick = curr_jiffies; |
3521 | 3521 | ||
3522 | /* Update our load: */ | 3522 | /* Update our load: */ |
3523 | this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ | 3523 | this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ |
3524 | for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { | 3524 | for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { |
3525 | unsigned long old_load, new_load; | 3525 | unsigned long old_load, new_load; |
3526 | 3526 | ||
3527 | /* scale is effectively 1 << i now, and >> i divides by scale */ | 3527 | /* scale is effectively 1 << i now, and >> i divides by scale */ |
3528 | 3528 | ||
3529 | old_load = this_rq->cpu_load[i]; | 3529 | old_load = this_rq->cpu_load[i]; |
3530 | old_load = decay_load_missed(old_load, pending_updates - 1, i); | 3530 | old_load = decay_load_missed(old_load, pending_updates - 1, i); |
3531 | new_load = this_load; | 3531 | new_load = this_load; |
3532 | /* | 3532 | /* |
3533 | * Round up the averaging division if load is increasing. This | 3533 | * Round up the averaging division if load is increasing. This |
3534 | * prevents us from getting stuck on 9 if the load is 10, for | 3534 | * prevents us from getting stuck on 9 if the load is 10, for |
3535 | * example. | 3535 | * example. |
3536 | */ | 3536 | */ |
3537 | if (new_load > old_load) | 3537 | if (new_load > old_load) |
3538 | new_load += scale - 1; | 3538 | new_load += scale - 1; |
3539 | 3539 | ||
3540 | this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; | 3540 | this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; |
3541 | } | 3541 | } |
3542 | 3542 | ||
3543 | sched_avg_update(this_rq); | 3543 | sched_avg_update(this_rq); |
3544 | } | 3544 | } |
3545 | 3545 | ||
3546 | static void update_cpu_load_active(struct rq *this_rq) | 3546 | static void update_cpu_load_active(struct rq *this_rq) |
3547 | { | 3547 | { |
3548 | update_cpu_load(this_rq); | 3548 | update_cpu_load(this_rq); |
3549 | 3549 | ||
3550 | calc_load_account_active(this_rq); | 3550 | calc_load_account_active(this_rq); |
3551 | } | 3551 | } |
3552 | 3552 | ||
3553 | #ifdef CONFIG_SMP | 3553 | #ifdef CONFIG_SMP |
3554 | 3554 | ||
3555 | /* | 3555 | /* |
3556 | * sched_exec - execve() is a valuable balancing opportunity, because at | 3556 | * sched_exec - execve() is a valuable balancing opportunity, because at |
3557 | * this point the task has the smallest effective memory and cache footprint. | 3557 | * this point the task has the smallest effective memory and cache footprint. |
3558 | */ | 3558 | */ |
3559 | void sched_exec(void) | 3559 | void sched_exec(void) |
3560 | { | 3560 | { |
3561 | struct task_struct *p = current; | 3561 | struct task_struct *p = current; |
3562 | unsigned long flags; | 3562 | unsigned long flags; |
3563 | int dest_cpu; | 3563 | int dest_cpu; |
3564 | 3564 | ||
3565 | raw_spin_lock_irqsave(&p->pi_lock, flags); | 3565 | raw_spin_lock_irqsave(&p->pi_lock, flags); |
3566 | dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); | 3566 | dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); |
3567 | if (dest_cpu == smp_processor_id()) | 3567 | if (dest_cpu == smp_processor_id()) |
3568 | goto unlock; | 3568 | goto unlock; |
3569 | 3569 | ||
3570 | if (likely(cpu_active(dest_cpu))) { | 3570 | if (likely(cpu_active(dest_cpu))) { |
3571 | struct migration_arg arg = { p, dest_cpu }; | 3571 | struct migration_arg arg = { p, dest_cpu }; |
3572 | 3572 | ||
3573 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 3573 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
3574 | stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); | 3574 | stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); |
3575 | return; | 3575 | return; |
3576 | } | 3576 | } |
3577 | unlock: | 3577 | unlock: |
3578 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 3578 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
3579 | } | 3579 | } |
3580 | 3580 | ||
3581 | #endif | 3581 | #endif |
3582 | 3582 | ||
3583 | DEFINE_PER_CPU(struct kernel_stat, kstat); | 3583 | DEFINE_PER_CPU(struct kernel_stat, kstat); |
3584 | 3584 | ||
3585 | EXPORT_PER_CPU_SYMBOL(kstat); | 3585 | EXPORT_PER_CPU_SYMBOL(kstat); |
3586 | 3586 | ||
3587 | /* | 3587 | /* |
3588 | * Return any ns on the sched_clock that have not yet been accounted in | 3588 | * Return any ns on the sched_clock that have not yet been accounted in |
3589 | * @p in case that task is currently running. | 3589 | * @p in case that task is currently running. |
3590 | * | 3590 | * |
3591 | * Called with task_rq_lock() held on @rq. | 3591 | * Called with task_rq_lock() held on @rq. |
3592 | */ | 3592 | */ |
3593 | static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) | 3593 | static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) |
3594 | { | 3594 | { |
3595 | u64 ns = 0; | 3595 | u64 ns = 0; |
3596 | 3596 | ||
3597 | if (task_current(rq, p)) { | 3597 | if (task_current(rq, p)) { |
3598 | update_rq_clock(rq); | 3598 | update_rq_clock(rq); |
3599 | ns = rq->clock_task - p->se.exec_start; | 3599 | ns = rq->clock_task - p->se.exec_start; |
3600 | if ((s64)ns < 0) | 3600 | if ((s64)ns < 0) |
3601 | ns = 0; | 3601 | ns = 0; |
3602 | } | 3602 | } |
3603 | 3603 | ||
3604 | return ns; | 3604 | return ns; |
3605 | } | 3605 | } |
3606 | 3606 | ||
3607 | unsigned long long task_delta_exec(struct task_struct *p) | 3607 | unsigned long long task_delta_exec(struct task_struct *p) |
3608 | { | 3608 | { |
3609 | unsigned long flags; | 3609 | unsigned long flags; |
3610 | struct rq *rq; | 3610 | struct rq *rq; |
3611 | u64 ns = 0; | 3611 | u64 ns = 0; |
3612 | 3612 | ||
3613 | rq = task_rq_lock(p, &flags); | 3613 | rq = task_rq_lock(p, &flags); |
3614 | ns = do_task_delta_exec(p, rq); | 3614 | ns = do_task_delta_exec(p, rq); |
3615 | task_rq_unlock(rq, p, &flags); | 3615 | task_rq_unlock(rq, p, &flags); |
3616 | 3616 | ||
3617 | return ns; | 3617 | return ns; |
3618 | } | 3618 | } |
3619 | 3619 | ||
3620 | /* | 3620 | /* |
3621 | * Return accounted runtime for the task. | 3621 | * Return accounted runtime for the task. |
3622 | * In case the task is currently running, return the runtime plus current's | 3622 | * In case the task is currently running, return the runtime plus current's |
3623 | * pending runtime that have not been accounted yet. | 3623 | * pending runtime that have not been accounted yet. |
3624 | */ | 3624 | */ |
3625 | unsigned long long task_sched_runtime(struct task_struct *p) | 3625 | unsigned long long task_sched_runtime(struct task_struct *p) |
3626 | { | 3626 | { |
3627 | unsigned long flags; | 3627 | unsigned long flags; |
3628 | struct rq *rq; | 3628 | struct rq *rq; |
3629 | u64 ns = 0; | 3629 | u64 ns = 0; |
3630 | 3630 | ||
3631 | rq = task_rq_lock(p, &flags); | 3631 | rq = task_rq_lock(p, &flags); |
3632 | ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); | 3632 | ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); |
3633 | task_rq_unlock(rq, p, &flags); | 3633 | task_rq_unlock(rq, p, &flags); |
3634 | 3634 | ||
3635 | return ns; | 3635 | return ns; |
3636 | } | 3636 | } |
3637 | 3637 | ||
3638 | /* | 3638 | /* |
3639 | * Return sum_exec_runtime for the thread group. | 3639 | * Return sum_exec_runtime for the thread group. |
3640 | * In case the task is currently running, return the sum plus current's | 3640 | * In case the task is currently running, return the sum plus current's |
3641 | * pending runtime that have not been accounted yet. | 3641 | * pending runtime that have not been accounted yet. |
3642 | * | 3642 | * |
3643 | * Note that the thread group might have other running tasks as well, | 3643 | * Note that the thread group might have other running tasks as well, |
3644 | * so the return value not includes other pending runtime that other | 3644 | * so the return value not includes other pending runtime that other |
3645 | * running tasks might have. | 3645 | * running tasks might have. |
3646 | */ | 3646 | */ |
3647 | unsigned long long thread_group_sched_runtime(struct task_struct *p) | 3647 | unsigned long long thread_group_sched_runtime(struct task_struct *p) |
3648 | { | 3648 | { |
3649 | struct task_cputime totals; | 3649 | struct task_cputime totals; |
3650 | unsigned long flags; | 3650 | unsigned long flags; |
3651 | struct rq *rq; | 3651 | struct rq *rq; |
3652 | u64 ns; | 3652 | u64 ns; |
3653 | 3653 | ||
3654 | rq = task_rq_lock(p, &flags); | 3654 | rq = task_rq_lock(p, &flags); |
3655 | thread_group_cputime(p, &totals); | 3655 | thread_group_cputime(p, &totals); |
3656 | ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); | 3656 | ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); |
3657 | task_rq_unlock(rq, p, &flags); | 3657 | task_rq_unlock(rq, p, &flags); |
3658 | 3658 | ||
3659 | return ns; | 3659 | return ns; |
3660 | } | 3660 | } |
3661 | 3661 | ||
3662 | /* | 3662 | /* |
3663 | * Account user cpu time to a process. | 3663 | * Account user cpu time to a process. |
3664 | * @p: the process that the cpu time gets accounted to | 3664 | * @p: the process that the cpu time gets accounted to |
3665 | * @cputime: the cpu time spent in user space since the last update | 3665 | * @cputime: the cpu time spent in user space since the last update |
3666 | * @cputime_scaled: cputime scaled by cpu frequency | 3666 | * @cputime_scaled: cputime scaled by cpu frequency |
3667 | */ | 3667 | */ |
3668 | void account_user_time(struct task_struct *p, cputime_t cputime, | 3668 | void account_user_time(struct task_struct *p, cputime_t cputime, |
3669 | cputime_t cputime_scaled) | 3669 | cputime_t cputime_scaled) |
3670 | { | 3670 | { |
3671 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3671 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3672 | cputime64_t tmp; | 3672 | cputime64_t tmp; |
3673 | 3673 | ||
3674 | /* Add user time to process. */ | 3674 | /* Add user time to process. */ |
3675 | p->utime = cputime_add(p->utime, cputime); | 3675 | p->utime = cputime_add(p->utime, cputime); |
3676 | p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); | 3676 | p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); |
3677 | account_group_user_time(p, cputime); | 3677 | account_group_user_time(p, cputime); |
3678 | 3678 | ||
3679 | /* Add user time to cpustat. */ | 3679 | /* Add user time to cpustat. */ |
3680 | tmp = cputime_to_cputime64(cputime); | 3680 | tmp = cputime_to_cputime64(cputime); |
3681 | if (TASK_NICE(p) > 0) | 3681 | if (TASK_NICE(p) > 0) |
3682 | cpustat->nice = cputime64_add(cpustat->nice, tmp); | 3682 | cpustat->nice = cputime64_add(cpustat->nice, tmp); |
3683 | else | 3683 | else |
3684 | cpustat->user = cputime64_add(cpustat->user, tmp); | 3684 | cpustat->user = cputime64_add(cpustat->user, tmp); |
3685 | 3685 | ||
3686 | cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); | 3686 | cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); |
3687 | /* Account for user time used */ | 3687 | /* Account for user time used */ |
3688 | acct_update_integrals(p); | 3688 | acct_update_integrals(p); |
3689 | } | 3689 | } |
3690 | 3690 | ||
3691 | /* | 3691 | /* |
3692 | * Account guest cpu time to a process. | 3692 | * Account guest cpu time to a process. |
3693 | * @p: the process that the cpu time gets accounted to | 3693 | * @p: the process that the cpu time gets accounted to |
3694 | * @cputime: the cpu time spent in virtual machine since the last update | 3694 | * @cputime: the cpu time spent in virtual machine since the last update |
3695 | * @cputime_scaled: cputime scaled by cpu frequency | 3695 | * @cputime_scaled: cputime scaled by cpu frequency |
3696 | */ | 3696 | */ |
3697 | static void account_guest_time(struct task_struct *p, cputime_t cputime, | 3697 | static void account_guest_time(struct task_struct *p, cputime_t cputime, |
3698 | cputime_t cputime_scaled) | 3698 | cputime_t cputime_scaled) |
3699 | { | 3699 | { |
3700 | cputime64_t tmp; | 3700 | cputime64_t tmp; |
3701 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3701 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3702 | 3702 | ||
3703 | tmp = cputime_to_cputime64(cputime); | 3703 | tmp = cputime_to_cputime64(cputime); |
3704 | 3704 | ||
3705 | /* Add guest time to process. */ | 3705 | /* Add guest time to process. */ |
3706 | p->utime = cputime_add(p->utime, cputime); | 3706 | p->utime = cputime_add(p->utime, cputime); |
3707 | p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); | 3707 | p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); |
3708 | account_group_user_time(p, cputime); | 3708 | account_group_user_time(p, cputime); |
3709 | p->gtime = cputime_add(p->gtime, cputime); | 3709 | p->gtime = cputime_add(p->gtime, cputime); |
3710 | 3710 | ||
3711 | /* Add guest time to cpustat. */ | 3711 | /* Add guest time to cpustat. */ |
3712 | if (TASK_NICE(p) > 0) { | 3712 | if (TASK_NICE(p) > 0) { |
3713 | cpustat->nice = cputime64_add(cpustat->nice, tmp); | 3713 | cpustat->nice = cputime64_add(cpustat->nice, tmp); |
3714 | cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); | 3714 | cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); |
3715 | } else { | 3715 | } else { |
3716 | cpustat->user = cputime64_add(cpustat->user, tmp); | 3716 | cpustat->user = cputime64_add(cpustat->user, tmp); |
3717 | cpustat->guest = cputime64_add(cpustat->guest, tmp); | 3717 | cpustat->guest = cputime64_add(cpustat->guest, tmp); |
3718 | } | 3718 | } |
3719 | } | 3719 | } |
3720 | 3720 | ||
3721 | /* | 3721 | /* |
3722 | * Account system cpu time to a process and desired cpustat field | 3722 | * Account system cpu time to a process and desired cpustat field |
3723 | * @p: the process that the cpu time gets accounted to | 3723 | * @p: the process that the cpu time gets accounted to |
3724 | * @cputime: the cpu time spent in kernel space since the last update | 3724 | * @cputime: the cpu time spent in kernel space since the last update |
3725 | * @cputime_scaled: cputime scaled by cpu frequency | 3725 | * @cputime_scaled: cputime scaled by cpu frequency |
3726 | * @target_cputime64: pointer to cpustat field that has to be updated | 3726 | * @target_cputime64: pointer to cpustat field that has to be updated |
3727 | */ | 3727 | */ |
3728 | static inline | 3728 | static inline |
3729 | void __account_system_time(struct task_struct *p, cputime_t cputime, | 3729 | void __account_system_time(struct task_struct *p, cputime_t cputime, |
3730 | cputime_t cputime_scaled, cputime64_t *target_cputime64) | 3730 | cputime_t cputime_scaled, cputime64_t *target_cputime64) |
3731 | { | 3731 | { |
3732 | cputime64_t tmp = cputime_to_cputime64(cputime); | 3732 | cputime64_t tmp = cputime_to_cputime64(cputime); |
3733 | 3733 | ||
3734 | /* Add system time to process. */ | 3734 | /* Add system time to process. */ |
3735 | p->stime = cputime_add(p->stime, cputime); | 3735 | p->stime = cputime_add(p->stime, cputime); |
3736 | p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); | 3736 | p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); |
3737 | account_group_system_time(p, cputime); | 3737 | account_group_system_time(p, cputime); |
3738 | 3738 | ||
3739 | /* Add system time to cpustat. */ | 3739 | /* Add system time to cpustat. */ |
3740 | *target_cputime64 = cputime64_add(*target_cputime64, tmp); | 3740 | *target_cputime64 = cputime64_add(*target_cputime64, tmp); |
3741 | cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); | 3741 | cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); |
3742 | 3742 | ||
3743 | /* Account for system time used */ | 3743 | /* Account for system time used */ |
3744 | acct_update_integrals(p); | 3744 | acct_update_integrals(p); |
3745 | } | 3745 | } |
3746 | 3746 | ||
3747 | /* | 3747 | /* |
3748 | * Account system cpu time to a process. | 3748 | * Account system cpu time to a process. |
3749 | * @p: the process that the cpu time gets accounted to | 3749 | * @p: the process that the cpu time gets accounted to |
3750 | * @hardirq_offset: the offset to subtract from hardirq_count() | 3750 | * @hardirq_offset: the offset to subtract from hardirq_count() |
3751 | * @cputime: the cpu time spent in kernel space since the last update | 3751 | * @cputime: the cpu time spent in kernel space since the last update |
3752 | * @cputime_scaled: cputime scaled by cpu frequency | 3752 | * @cputime_scaled: cputime scaled by cpu frequency |
3753 | */ | 3753 | */ |
3754 | void account_system_time(struct task_struct *p, int hardirq_offset, | 3754 | void account_system_time(struct task_struct *p, int hardirq_offset, |
3755 | cputime_t cputime, cputime_t cputime_scaled) | 3755 | cputime_t cputime, cputime_t cputime_scaled) |
3756 | { | 3756 | { |
3757 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3757 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3758 | cputime64_t *target_cputime64; | 3758 | cputime64_t *target_cputime64; |
3759 | 3759 | ||
3760 | if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { | 3760 | if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { |
3761 | account_guest_time(p, cputime, cputime_scaled); | 3761 | account_guest_time(p, cputime, cputime_scaled); |
3762 | return; | 3762 | return; |
3763 | } | 3763 | } |
3764 | 3764 | ||
3765 | if (hardirq_count() - hardirq_offset) | 3765 | if (hardirq_count() - hardirq_offset) |
3766 | target_cputime64 = &cpustat->irq; | 3766 | target_cputime64 = &cpustat->irq; |
3767 | else if (in_serving_softirq()) | 3767 | else if (in_serving_softirq()) |
3768 | target_cputime64 = &cpustat->softirq; | 3768 | target_cputime64 = &cpustat->softirq; |
3769 | else | 3769 | else |
3770 | target_cputime64 = &cpustat->system; | 3770 | target_cputime64 = &cpustat->system; |
3771 | 3771 | ||
3772 | __account_system_time(p, cputime, cputime_scaled, target_cputime64); | 3772 | __account_system_time(p, cputime, cputime_scaled, target_cputime64); |
3773 | } | 3773 | } |
3774 | 3774 | ||
3775 | /* | 3775 | /* |
3776 | * Account for involuntary wait time. | 3776 | * Account for involuntary wait time. |
3777 | * @cputime: the cpu time spent in involuntary wait | 3777 | * @cputime: the cpu time spent in involuntary wait |
3778 | */ | 3778 | */ |
3779 | void account_steal_time(cputime_t cputime) | 3779 | void account_steal_time(cputime_t cputime) |
3780 | { | 3780 | { |
3781 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3781 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3782 | cputime64_t cputime64 = cputime_to_cputime64(cputime); | 3782 | cputime64_t cputime64 = cputime_to_cputime64(cputime); |
3783 | 3783 | ||
3784 | cpustat->steal = cputime64_add(cpustat->steal, cputime64); | 3784 | cpustat->steal = cputime64_add(cpustat->steal, cputime64); |
3785 | } | 3785 | } |
3786 | 3786 | ||
3787 | /* | 3787 | /* |
3788 | * Account for idle time. | 3788 | * Account for idle time. |
3789 | * @cputime: the cpu time spent in idle wait | 3789 | * @cputime: the cpu time spent in idle wait |
3790 | */ | 3790 | */ |
3791 | void account_idle_time(cputime_t cputime) | 3791 | void account_idle_time(cputime_t cputime) |
3792 | { | 3792 | { |
3793 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3793 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3794 | cputime64_t cputime64 = cputime_to_cputime64(cputime); | 3794 | cputime64_t cputime64 = cputime_to_cputime64(cputime); |
3795 | struct rq *rq = this_rq(); | 3795 | struct rq *rq = this_rq(); |
3796 | 3796 | ||
3797 | if (atomic_read(&rq->nr_iowait) > 0) | 3797 | if (atomic_read(&rq->nr_iowait) > 0) |
3798 | cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); | 3798 | cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); |
3799 | else | 3799 | else |
3800 | cpustat->idle = cputime64_add(cpustat->idle, cputime64); | 3800 | cpustat->idle = cputime64_add(cpustat->idle, cputime64); |
3801 | } | 3801 | } |
3802 | 3802 | ||
3803 | #ifndef CONFIG_VIRT_CPU_ACCOUNTING | 3803 | #ifndef CONFIG_VIRT_CPU_ACCOUNTING |
3804 | 3804 | ||
3805 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING | 3805 | #ifdef CONFIG_IRQ_TIME_ACCOUNTING |
3806 | /* | 3806 | /* |
3807 | * Account a tick to a process and cpustat | 3807 | * Account a tick to a process and cpustat |
3808 | * @p: the process that the cpu time gets accounted to | 3808 | * @p: the process that the cpu time gets accounted to |
3809 | * @user_tick: is the tick from userspace | 3809 | * @user_tick: is the tick from userspace |
3810 | * @rq: the pointer to rq | 3810 | * @rq: the pointer to rq |
3811 | * | 3811 | * |
3812 | * Tick demultiplexing follows the order | 3812 | * Tick demultiplexing follows the order |
3813 | * - pending hardirq update | 3813 | * - pending hardirq update |
3814 | * - pending softirq update | 3814 | * - pending softirq update |
3815 | * - user_time | 3815 | * - user_time |
3816 | * - idle_time | 3816 | * - idle_time |
3817 | * - system time | 3817 | * - system time |
3818 | * - check for guest_time | 3818 | * - check for guest_time |
3819 | * - else account as system_time | 3819 | * - else account as system_time |
3820 | * | 3820 | * |
3821 | * Check for hardirq is done both for system and user time as there is | 3821 | * Check for hardirq is done both for system and user time as there is |
3822 | * no timer going off while we are on hardirq and hence we may never get an | 3822 | * no timer going off while we are on hardirq and hence we may never get an |
3823 | * opportunity to update it solely in system time. | 3823 | * opportunity to update it solely in system time. |
3824 | * p->stime and friends are only updated on system time and not on irq | 3824 | * p->stime and friends are only updated on system time and not on irq |
3825 | * softirq as those do not count in task exec_runtime any more. | 3825 | * softirq as those do not count in task exec_runtime any more. |
3826 | */ | 3826 | */ |
3827 | static void irqtime_account_process_tick(struct task_struct *p, int user_tick, | 3827 | static void irqtime_account_process_tick(struct task_struct *p, int user_tick, |
3828 | struct rq *rq) | 3828 | struct rq *rq) |
3829 | { | 3829 | { |
3830 | cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); | 3830 | cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); |
3831 | cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); | 3831 | cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); |
3832 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; | 3832 | struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; |
3833 | 3833 | ||
3834 | if (irqtime_account_hi_update()) { | 3834 | if (irqtime_account_hi_update()) { |
3835 | cpustat->irq = cputime64_add(cpustat->irq, tmp); | 3835 | cpustat->irq = cputime64_add(cpustat->irq, tmp); |
3836 | } else if (irqtime_account_si_update()) { | 3836 | } else if (irqtime_account_si_update()) { |
3837 | cpustat->softirq = cputime64_add(cpustat->softirq, tmp); | 3837 | cpustat->softirq = cputime64_add(cpustat->softirq, tmp); |
3838 | } else if (this_cpu_ksoftirqd() == p) { | 3838 | } else if (this_cpu_ksoftirqd() == p) { |
3839 | /* | 3839 | /* |
3840 | * ksoftirqd time do not get accounted in cpu_softirq_time. | 3840 | * ksoftirqd time do not get accounted in cpu_softirq_time. |
3841 | * So, we have to handle it separately here. | 3841 | * So, we have to handle it separately here. |
3842 | * Also, p->stime needs to be updated for ksoftirqd. | 3842 | * Also, p->stime needs to be updated for ksoftirqd. |
3843 | */ | 3843 | */ |
3844 | __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, | 3844 | __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, |
3845 | &cpustat->softirq); | 3845 | &cpustat->softirq); |
3846 | } else if (user_tick) { | 3846 | } else if (user_tick) { |
3847 | account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); | 3847 | account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); |
3848 | } else if (p == rq->idle) { | 3848 | } else if (p == rq->idle) { |
3849 | account_idle_time(cputime_one_jiffy); | 3849 | account_idle_time(cputime_one_jiffy); |
3850 | } else if (p->flags & PF_VCPU) { /* System time or guest time */ | 3850 | } else if (p->flags & PF_VCPU) { /* System time or guest time */ |
3851 | account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); | 3851 | account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); |
3852 | } else { | 3852 | } else { |
3853 | __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, | 3853 | __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, |
3854 | &cpustat->system); | 3854 | &cpustat->system); |
3855 | } | 3855 | } |
3856 | } | 3856 | } |
3857 | 3857 | ||
3858 | static void irqtime_account_idle_ticks(int ticks) | 3858 | static void irqtime_account_idle_ticks(int ticks) |
3859 | { | 3859 | { |
3860 | int i; | 3860 | int i; |
3861 | struct rq *rq = this_rq(); | 3861 | struct rq *rq = this_rq(); |
3862 | 3862 | ||
3863 | for (i = 0; i < ticks; i++) | 3863 | for (i = 0; i < ticks; i++) |
3864 | irqtime_account_process_tick(current, 0, rq); | 3864 | irqtime_account_process_tick(current, 0, rq); |
3865 | } | 3865 | } |
3866 | #else /* CONFIG_IRQ_TIME_ACCOUNTING */ | 3866 | #else /* CONFIG_IRQ_TIME_ACCOUNTING */ |
3867 | static void irqtime_account_idle_ticks(int ticks) {} | 3867 | static void irqtime_account_idle_ticks(int ticks) {} |
3868 | static void irqtime_account_process_tick(struct task_struct *p, int user_tick, | 3868 | static void irqtime_account_process_tick(struct task_struct *p, int user_tick, |
3869 | struct rq *rq) {} | 3869 | struct rq *rq) {} |
3870 | #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ | 3870 | #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ |
3871 | 3871 | ||
3872 | /* | 3872 | /* |
3873 | * Account a single tick of cpu time. | 3873 | * Account a single tick of cpu time. |
3874 | * @p: the process that the cpu time gets accounted to | 3874 | * @p: the process that the cpu time gets accounted to |
3875 | * @user_tick: indicates if the tick is a user or a system tick | 3875 | * @user_tick: indicates if the tick is a user or a system tick |
3876 | */ | 3876 | */ |
3877 | void account_process_tick(struct task_struct *p, int user_tick) | 3877 | void account_process_tick(struct task_struct *p, int user_tick) |
3878 | { | 3878 | { |
3879 | cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); | 3879 | cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); |
3880 | struct rq *rq = this_rq(); | 3880 | struct rq *rq = this_rq(); |
3881 | 3881 | ||
3882 | if (sched_clock_irqtime) { | 3882 | if (sched_clock_irqtime) { |
3883 | irqtime_account_process_tick(p, user_tick, rq); | 3883 | irqtime_account_process_tick(p, user_tick, rq); |
3884 | return; | 3884 | return; |
3885 | } | 3885 | } |
3886 | 3886 | ||
3887 | if (user_tick) | 3887 | if (user_tick) |
3888 | account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); | 3888 | account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); |
3889 | else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) | 3889 | else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) |
3890 | account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, | 3890 | account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, |
3891 | one_jiffy_scaled); | 3891 | one_jiffy_scaled); |
3892 | else | 3892 | else |
3893 | account_idle_time(cputime_one_jiffy); | 3893 | account_idle_time(cputime_one_jiffy); |
3894 | } | 3894 | } |
3895 | 3895 | ||
3896 | /* | 3896 | /* |
3897 | * Account multiple ticks of steal time. | 3897 | * Account multiple ticks of steal time. |
3898 | * @p: the process from which the cpu time has been stolen | 3898 | * @p: the process from which the cpu time has been stolen |
3899 | * @ticks: number of stolen ticks | 3899 | * @ticks: number of stolen ticks |
3900 | */ | 3900 | */ |
3901 | void account_steal_ticks(unsigned long ticks) | 3901 | void account_steal_ticks(unsigned long ticks) |
3902 | { | 3902 | { |
3903 | account_steal_time(jiffies_to_cputime(ticks)); | 3903 | account_steal_time(jiffies_to_cputime(ticks)); |
3904 | } | 3904 | } |
3905 | 3905 | ||
3906 | /* | 3906 | /* |
3907 | * Account multiple ticks of idle time. | 3907 | * Account multiple ticks of idle time. |
3908 | * @ticks: number of stolen ticks | 3908 | * @ticks: number of stolen ticks |
3909 | */ | 3909 | */ |
3910 | void account_idle_ticks(unsigned long ticks) | 3910 | void account_idle_ticks(unsigned long ticks) |
3911 | { | 3911 | { |
3912 | 3912 | ||
3913 | if (sched_clock_irqtime) { | 3913 | if (sched_clock_irqtime) { |
3914 | irqtime_account_idle_ticks(ticks); | 3914 | irqtime_account_idle_ticks(ticks); |
3915 | return; | 3915 | return; |
3916 | } | 3916 | } |
3917 | 3917 | ||
3918 | account_idle_time(jiffies_to_cputime(ticks)); | 3918 | account_idle_time(jiffies_to_cputime(ticks)); |
3919 | } | 3919 | } |
3920 | 3920 | ||
3921 | #endif | 3921 | #endif |
3922 | 3922 | ||
3923 | /* | 3923 | /* |
3924 | * Use precise platform statistics if available: | 3924 | * Use precise platform statistics if available: |
3925 | */ | 3925 | */ |
3926 | #ifdef CONFIG_VIRT_CPU_ACCOUNTING | 3926 | #ifdef CONFIG_VIRT_CPU_ACCOUNTING |
3927 | void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) | 3927 | void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) |
3928 | { | 3928 | { |
3929 | *ut = p->utime; | 3929 | *ut = p->utime; |
3930 | *st = p->stime; | 3930 | *st = p->stime; |
3931 | } | 3931 | } |
3932 | 3932 | ||
3933 | void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) | 3933 | void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) |
3934 | { | 3934 | { |
3935 | struct task_cputime cputime; | 3935 | struct task_cputime cputime; |
3936 | 3936 | ||
3937 | thread_group_cputime(p, &cputime); | 3937 | thread_group_cputime(p, &cputime); |
3938 | 3938 | ||
3939 | *ut = cputime.utime; | 3939 | *ut = cputime.utime; |
3940 | *st = cputime.stime; | 3940 | *st = cputime.stime; |
3941 | } | 3941 | } |
3942 | #else | 3942 | #else |
3943 | 3943 | ||
3944 | #ifndef nsecs_to_cputime | 3944 | #ifndef nsecs_to_cputime |
3945 | # define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) | 3945 | # define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) |
3946 | #endif | 3946 | #endif |
3947 | 3947 | ||
3948 | void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) | 3948 | void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) |
3949 | { | 3949 | { |
3950 | cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); | 3950 | cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); |
3951 | 3951 | ||
3952 | /* | 3952 | /* |
3953 | * Use CFS's precise accounting: | 3953 | * Use CFS's precise accounting: |
3954 | */ | 3954 | */ |
3955 | rtime = nsecs_to_cputime(p->se.sum_exec_runtime); | 3955 | rtime = nsecs_to_cputime(p->se.sum_exec_runtime); |
3956 | 3956 | ||
3957 | if (total) { | 3957 | if (total) { |
3958 | u64 temp = rtime; | 3958 | u64 temp = rtime; |
3959 | 3959 | ||
3960 | temp *= utime; | 3960 | temp *= utime; |
3961 | do_div(temp, total); | 3961 | do_div(temp, total); |
3962 | utime = (cputime_t)temp; | 3962 | utime = (cputime_t)temp; |
3963 | } else | 3963 | } else |
3964 | utime = rtime; | 3964 | utime = rtime; |
3965 | 3965 | ||
3966 | /* | 3966 | /* |
3967 | * Compare with previous values, to keep monotonicity: | 3967 | * Compare with previous values, to keep monotonicity: |
3968 | */ | 3968 | */ |
3969 | p->prev_utime = max(p->prev_utime, utime); | 3969 | p->prev_utime = max(p->prev_utime, utime); |
3970 | p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); | 3970 | p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); |
3971 | 3971 | ||
3972 | *ut = p->prev_utime; | 3972 | *ut = p->prev_utime; |
3973 | *st = p->prev_stime; | 3973 | *st = p->prev_stime; |
3974 | } | 3974 | } |
3975 | 3975 | ||
3976 | /* | 3976 | /* |
3977 | * Must be called with siglock held. | 3977 | * Must be called with siglock held. |
3978 | */ | 3978 | */ |
3979 | void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) | 3979 | void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) |
3980 | { | 3980 | { |
3981 | struct signal_struct *sig = p->signal; | 3981 | struct signal_struct *sig = p->signal; |
3982 | struct task_cputime cputime; | 3982 | struct task_cputime cputime; |
3983 | cputime_t rtime, utime, total; | 3983 | cputime_t rtime, utime, total; |
3984 | 3984 | ||
3985 | thread_group_cputime(p, &cputime); | 3985 | thread_group_cputime(p, &cputime); |
3986 | 3986 | ||
3987 | total = cputime_add(cputime.utime, cputime.stime); | 3987 | total = cputime_add(cputime.utime, cputime.stime); |
3988 | rtime = nsecs_to_cputime(cputime.sum_exec_runtime); | 3988 | rtime = nsecs_to_cputime(cputime.sum_exec_runtime); |
3989 | 3989 | ||
3990 | if (total) { | 3990 | if (total) { |
3991 | u64 temp = rtime; | 3991 | u64 temp = rtime; |
3992 | 3992 | ||
3993 | temp *= cputime.utime; | 3993 | temp *= cputime.utime; |
3994 | do_div(temp, total); | 3994 | do_div(temp, total); |
3995 | utime = (cputime_t)temp; | 3995 | utime = (cputime_t)temp; |
3996 | } else | 3996 | } else |
3997 | utime = rtime; | 3997 | utime = rtime; |
3998 | 3998 | ||
3999 | sig->prev_utime = max(sig->prev_utime, utime); | 3999 | sig->prev_utime = max(sig->prev_utime, utime); |
4000 | sig->prev_stime = max(sig->prev_stime, | 4000 | sig->prev_stime = max(sig->prev_stime, |
4001 | cputime_sub(rtime, sig->prev_utime)); | 4001 | cputime_sub(rtime, sig->prev_utime)); |
4002 | 4002 | ||
4003 | *ut = sig->prev_utime; | 4003 | *ut = sig->prev_utime; |
4004 | *st = sig->prev_stime; | 4004 | *st = sig->prev_stime; |
4005 | } | 4005 | } |
4006 | #endif | 4006 | #endif |
4007 | 4007 | ||
4008 | /* | 4008 | /* |
4009 | * This function gets called by the timer code, with HZ frequency. | 4009 | * This function gets called by the timer code, with HZ frequency. |
4010 | * We call it with interrupts disabled. | 4010 | * We call it with interrupts disabled. |
4011 | * | 4011 | * |
4012 | * It also gets called by the fork code, when changing the parent's | 4012 | * It also gets called by the fork code, when changing the parent's |
4013 | * timeslices. | 4013 | * timeslices. |
4014 | */ | 4014 | */ |
4015 | void scheduler_tick(void) | 4015 | void scheduler_tick(void) |
4016 | { | 4016 | { |
4017 | int cpu = smp_processor_id(); | 4017 | int cpu = smp_processor_id(); |
4018 | struct rq *rq = cpu_rq(cpu); | 4018 | struct rq *rq = cpu_rq(cpu); |
4019 | struct task_struct *curr = rq->curr; | 4019 | struct task_struct *curr = rq->curr; |
4020 | 4020 | ||
4021 | sched_clock_tick(); | 4021 | sched_clock_tick(); |
4022 | 4022 | ||
4023 | raw_spin_lock(&rq->lock); | 4023 | raw_spin_lock(&rq->lock); |
4024 | update_rq_clock(rq); | 4024 | update_rq_clock(rq); |
4025 | update_cpu_load_active(rq); | 4025 | update_cpu_load_active(rq); |
4026 | curr->sched_class->task_tick(rq, curr, 0); | 4026 | curr->sched_class->task_tick(rq, curr, 0); |
4027 | raw_spin_unlock(&rq->lock); | 4027 | raw_spin_unlock(&rq->lock); |
4028 | 4028 | ||
4029 | perf_event_task_tick(); | 4029 | perf_event_task_tick(); |
4030 | 4030 | ||
4031 | #ifdef CONFIG_SMP | 4031 | #ifdef CONFIG_SMP |
4032 | rq->idle_at_tick = idle_cpu(cpu); | 4032 | rq->idle_at_tick = idle_cpu(cpu); |
4033 | trigger_load_balance(rq, cpu); | 4033 | trigger_load_balance(rq, cpu); |
4034 | #endif | 4034 | #endif |
4035 | } | 4035 | } |
4036 | 4036 | ||
4037 | notrace unsigned long get_parent_ip(unsigned long addr) | 4037 | notrace unsigned long get_parent_ip(unsigned long addr) |
4038 | { | 4038 | { |
4039 | if (in_lock_functions(addr)) { | 4039 | if (in_lock_functions(addr)) { |
4040 | addr = CALLER_ADDR2; | 4040 | addr = CALLER_ADDR2; |
4041 | if (in_lock_functions(addr)) | 4041 | if (in_lock_functions(addr)) |
4042 | addr = CALLER_ADDR3; | 4042 | addr = CALLER_ADDR3; |
4043 | } | 4043 | } |
4044 | return addr; | 4044 | return addr; |
4045 | } | 4045 | } |
4046 | 4046 | ||
4047 | #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ | 4047 | #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ |
4048 | defined(CONFIG_PREEMPT_TRACER)) | 4048 | defined(CONFIG_PREEMPT_TRACER)) |
4049 | 4049 | ||
4050 | void __kprobes add_preempt_count(int val) | 4050 | void __kprobes add_preempt_count(int val) |
4051 | { | 4051 | { |
4052 | #ifdef CONFIG_DEBUG_PREEMPT | 4052 | #ifdef CONFIG_DEBUG_PREEMPT |
4053 | /* | 4053 | /* |
4054 | * Underflow? | 4054 | * Underflow? |
4055 | */ | 4055 | */ |
4056 | if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) | 4056 | if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) |
4057 | return; | 4057 | return; |
4058 | #endif | 4058 | #endif |
4059 | preempt_count() += val; | 4059 | preempt_count() += val; |
4060 | #ifdef CONFIG_DEBUG_PREEMPT | 4060 | #ifdef CONFIG_DEBUG_PREEMPT |
4061 | /* | 4061 | /* |
4062 | * Spinlock count overflowing soon? | 4062 | * Spinlock count overflowing soon? |
4063 | */ | 4063 | */ |
4064 | DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= | 4064 | DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= |
4065 | PREEMPT_MASK - 10); | 4065 | PREEMPT_MASK - 10); |
4066 | #endif | 4066 | #endif |
4067 | if (preempt_count() == val) | 4067 | if (preempt_count() == val) |
4068 | trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); | 4068 | trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); |
4069 | } | 4069 | } |
4070 | EXPORT_SYMBOL(add_preempt_count); | 4070 | EXPORT_SYMBOL(add_preempt_count); |
4071 | 4071 | ||
4072 | void __kprobes sub_preempt_count(int val) | 4072 | void __kprobes sub_preempt_count(int val) |
4073 | { | 4073 | { |
4074 | #ifdef CONFIG_DEBUG_PREEMPT | 4074 | #ifdef CONFIG_DEBUG_PREEMPT |
4075 | /* | 4075 | /* |
4076 | * Underflow? | 4076 | * Underflow? |
4077 | */ | 4077 | */ |
4078 | if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) | 4078 | if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) |
4079 | return; | 4079 | return; |
4080 | /* | 4080 | /* |
4081 | * Is the spinlock portion underflowing? | 4081 | * Is the spinlock portion underflowing? |
4082 | */ | 4082 | */ |
4083 | if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && | 4083 | if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && |
4084 | !(preempt_count() & PREEMPT_MASK))) | 4084 | !(preempt_count() & PREEMPT_MASK))) |
4085 | return; | 4085 | return; |
4086 | #endif | 4086 | #endif |
4087 | 4087 | ||
4088 | if (preempt_count() == val) | 4088 | if (preempt_count() == val) |
4089 | trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); | 4089 | trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); |
4090 | preempt_count() -= val; | 4090 | preempt_count() -= val; |
4091 | } | 4091 | } |
4092 | EXPORT_SYMBOL(sub_preempt_count); | 4092 | EXPORT_SYMBOL(sub_preempt_count); |
4093 | 4093 | ||
4094 | #endif | 4094 | #endif |
4095 | 4095 | ||
4096 | /* | 4096 | /* |
4097 | * Print scheduling while atomic bug: | 4097 | * Print scheduling while atomic bug: |
4098 | */ | 4098 | */ |
4099 | static noinline void __schedule_bug(struct task_struct *prev) | 4099 | static noinline void __schedule_bug(struct task_struct *prev) |
4100 | { | 4100 | { |
4101 | struct pt_regs *regs = get_irq_regs(); | 4101 | struct pt_regs *regs = get_irq_regs(); |
4102 | 4102 | ||
4103 | printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", | 4103 | printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", |
4104 | prev->comm, prev->pid, preempt_count()); | 4104 | prev->comm, prev->pid, preempt_count()); |
4105 | 4105 | ||
4106 | debug_show_held_locks(prev); | 4106 | debug_show_held_locks(prev); |
4107 | print_modules(); | 4107 | print_modules(); |
4108 | if (irqs_disabled()) | 4108 | if (irqs_disabled()) |
4109 | print_irqtrace_events(prev); | 4109 | print_irqtrace_events(prev); |
4110 | 4110 | ||
4111 | if (regs) | 4111 | if (regs) |
4112 | show_regs(regs); | 4112 | show_regs(regs); |
4113 | else | 4113 | else |
4114 | dump_stack(); | 4114 | dump_stack(); |
4115 | } | 4115 | } |
4116 | 4116 | ||
4117 | /* | 4117 | /* |
4118 | * Various schedule()-time debugging checks and statistics: | 4118 | * Various schedule()-time debugging checks and statistics: |
4119 | */ | 4119 | */ |
4120 | static inline void schedule_debug(struct task_struct *prev) | 4120 | static inline void schedule_debug(struct task_struct *prev) |
4121 | { | 4121 | { |
4122 | /* | 4122 | /* |
4123 | * Test if we are atomic. Since do_exit() needs to call into | 4123 | * Test if we are atomic. Since do_exit() needs to call into |
4124 | * schedule() atomically, we ignore that path for now. | 4124 | * schedule() atomically, we ignore that path for now. |
4125 | * Otherwise, whine if we are scheduling when we should not be. | 4125 | * Otherwise, whine if we are scheduling when we should not be. |
4126 | */ | 4126 | */ |
4127 | if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) | 4127 | if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) |
4128 | __schedule_bug(prev); | 4128 | __schedule_bug(prev); |
4129 | 4129 | ||
4130 | profile_hit(SCHED_PROFILING, __builtin_return_address(0)); | 4130 | profile_hit(SCHED_PROFILING, __builtin_return_address(0)); |
4131 | 4131 | ||
4132 | schedstat_inc(this_rq(), sched_count); | 4132 | schedstat_inc(this_rq(), sched_count); |
4133 | #ifdef CONFIG_SCHEDSTATS | 4133 | #ifdef CONFIG_SCHEDSTATS |
4134 | if (unlikely(prev->lock_depth >= 0)) { | 4134 | if (unlikely(prev->lock_depth >= 0)) { |
4135 | schedstat_inc(this_rq(), rq_sched_info.bkl_count); | 4135 | schedstat_inc(this_rq(), rq_sched_info.bkl_count); |
4136 | schedstat_inc(prev, sched_info.bkl_count); | 4136 | schedstat_inc(prev, sched_info.bkl_count); |
4137 | } | 4137 | } |
4138 | #endif | 4138 | #endif |
4139 | } | 4139 | } |
4140 | 4140 | ||
4141 | static void put_prev_task(struct rq *rq, struct task_struct *prev) | 4141 | static void put_prev_task(struct rq *rq, struct task_struct *prev) |
4142 | { | 4142 | { |
4143 | if (prev->on_rq) | 4143 | if (prev->on_rq) |
4144 | update_rq_clock(rq); | 4144 | update_rq_clock(rq); |
4145 | prev->sched_class->put_prev_task(rq, prev); | 4145 | prev->sched_class->put_prev_task(rq, prev); |
4146 | } | 4146 | } |
4147 | 4147 | ||
4148 | /* | 4148 | /* |
4149 | * Pick up the highest-prio task: | 4149 | * Pick up the highest-prio task: |
4150 | */ | 4150 | */ |
4151 | static inline struct task_struct * | 4151 | static inline struct task_struct * |
4152 | pick_next_task(struct rq *rq) | 4152 | pick_next_task(struct rq *rq) |
4153 | { | 4153 | { |
4154 | const struct sched_class *class; | 4154 | const struct sched_class *class; |
4155 | struct task_struct *p; | 4155 | struct task_struct *p; |
4156 | 4156 | ||
4157 | /* | 4157 | /* |
4158 | * Optimization: we know that if all tasks are in | 4158 | * Optimization: we know that if all tasks are in |
4159 | * the fair class we can call that function directly: | 4159 | * the fair class we can call that function directly: |
4160 | */ | 4160 | */ |
4161 | if (likely(rq->nr_running == rq->cfs.nr_running)) { | 4161 | if (likely(rq->nr_running == rq->cfs.nr_running)) { |
4162 | p = fair_sched_class.pick_next_task(rq); | 4162 | p = fair_sched_class.pick_next_task(rq); |
4163 | if (likely(p)) | 4163 | if (likely(p)) |
4164 | return p; | 4164 | return p; |
4165 | } | 4165 | } |
4166 | 4166 | ||
4167 | for_each_class(class) { | 4167 | for_each_class(class) { |
4168 | p = class->pick_next_task(rq); | 4168 | p = class->pick_next_task(rq); |
4169 | if (p) | 4169 | if (p) |
4170 | return p; | 4170 | return p; |
4171 | } | 4171 | } |
4172 | 4172 | ||
4173 | BUG(); /* the idle class will always have a runnable task */ | 4173 | BUG(); /* the idle class will always have a runnable task */ |
4174 | } | 4174 | } |
4175 | 4175 | ||
4176 | /* | 4176 | /* |
4177 | * schedule() is the main scheduler function. | 4177 | * schedule() is the main scheduler function. |
4178 | */ | 4178 | */ |
4179 | asmlinkage void __sched schedule(void) | 4179 | asmlinkage void __sched schedule(void) |
4180 | { | 4180 | { |
4181 | struct task_struct *prev, *next; | 4181 | struct task_struct *prev, *next; |
4182 | unsigned long *switch_count; | 4182 | unsigned long *switch_count; |
4183 | struct rq *rq; | 4183 | struct rq *rq; |
4184 | int cpu; | 4184 | int cpu; |
4185 | 4185 | ||
4186 | need_resched: | 4186 | need_resched: |
4187 | preempt_disable(); | 4187 | preempt_disable(); |
4188 | cpu = smp_processor_id(); | 4188 | cpu = smp_processor_id(); |
4189 | rq = cpu_rq(cpu); | 4189 | rq = cpu_rq(cpu); |
4190 | rcu_note_context_switch(cpu); | 4190 | rcu_note_context_switch(cpu); |
4191 | prev = rq->curr; | 4191 | prev = rq->curr; |
4192 | 4192 | ||
4193 | schedule_debug(prev); | 4193 | schedule_debug(prev); |
4194 | 4194 | ||
4195 | if (sched_feat(HRTICK)) | 4195 | if (sched_feat(HRTICK)) |
4196 | hrtick_clear(rq); | 4196 | hrtick_clear(rq); |
4197 | 4197 | ||
4198 | raw_spin_lock_irq(&rq->lock); | 4198 | raw_spin_lock_irq(&rq->lock); |
4199 | 4199 | ||
4200 | switch_count = &prev->nivcsw; | 4200 | switch_count = &prev->nivcsw; |
4201 | if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { | 4201 | if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { |
4202 | if (unlikely(signal_pending_state(prev->state, prev))) { | 4202 | if (unlikely(signal_pending_state(prev->state, prev))) { |
4203 | prev->state = TASK_RUNNING; | 4203 | prev->state = TASK_RUNNING; |
4204 | } else { | 4204 | } else { |
4205 | deactivate_task(rq, prev, DEQUEUE_SLEEP); | 4205 | deactivate_task(rq, prev, DEQUEUE_SLEEP); |
4206 | prev->on_rq = 0; | 4206 | prev->on_rq = 0; |
4207 | 4207 | ||
4208 | /* | 4208 | /* |
4209 | * If a worker went to sleep, notify and ask workqueue | 4209 | * If a worker went to sleep, notify and ask workqueue |
4210 | * whether it wants to wake up a task to maintain | 4210 | * whether it wants to wake up a task to maintain |
4211 | * concurrency. | 4211 | * concurrency. |
4212 | */ | 4212 | */ |
4213 | if (prev->flags & PF_WQ_WORKER) { | 4213 | if (prev->flags & PF_WQ_WORKER) { |
4214 | struct task_struct *to_wakeup; | 4214 | struct task_struct *to_wakeup; |
4215 | 4215 | ||
4216 | to_wakeup = wq_worker_sleeping(prev, cpu); | 4216 | to_wakeup = wq_worker_sleeping(prev, cpu); |
4217 | if (to_wakeup) | 4217 | if (to_wakeup) |
4218 | try_to_wake_up_local(to_wakeup); | 4218 | try_to_wake_up_local(to_wakeup); |
4219 | } | 4219 | } |
4220 | 4220 | ||
4221 | /* | 4221 | /* |
4222 | * If we are going to sleep and we have plugged IO | 4222 | * If we are going to sleep and we have plugged IO |
4223 | * queued, make sure to submit it to avoid deadlocks. | 4223 | * queued, make sure to submit it to avoid deadlocks. |
4224 | */ | 4224 | */ |
4225 | if (blk_needs_flush_plug(prev)) { | 4225 | if (blk_needs_flush_plug(prev)) { |
4226 | raw_spin_unlock(&rq->lock); | 4226 | raw_spin_unlock(&rq->lock); |
4227 | blk_schedule_flush_plug(prev); | 4227 | blk_schedule_flush_plug(prev); |
4228 | raw_spin_lock(&rq->lock); | 4228 | raw_spin_lock(&rq->lock); |
4229 | } | 4229 | } |
4230 | } | 4230 | } |
4231 | switch_count = &prev->nvcsw; | 4231 | switch_count = &prev->nvcsw; |
4232 | } | 4232 | } |
4233 | 4233 | ||
4234 | pre_schedule(rq, prev); | 4234 | pre_schedule(rq, prev); |
4235 | 4235 | ||
4236 | if (unlikely(!rq->nr_running)) | 4236 | if (unlikely(!rq->nr_running)) |
4237 | idle_balance(cpu, rq); | 4237 | idle_balance(cpu, rq); |
4238 | 4238 | ||
4239 | put_prev_task(rq, prev); | 4239 | put_prev_task(rq, prev); |
4240 | next = pick_next_task(rq); | 4240 | next = pick_next_task(rq); |
4241 | clear_tsk_need_resched(prev); | 4241 | clear_tsk_need_resched(prev); |
4242 | rq->skip_clock_update = 0; | 4242 | rq->skip_clock_update = 0; |
4243 | 4243 | ||
4244 | if (likely(prev != next)) { | 4244 | if (likely(prev != next)) { |
4245 | rq->nr_switches++; | 4245 | rq->nr_switches++; |
4246 | rq->curr = next; | 4246 | rq->curr = next; |
4247 | ++*switch_count; | 4247 | ++*switch_count; |
4248 | 4248 | ||
4249 | context_switch(rq, prev, next); /* unlocks the rq */ | 4249 | context_switch(rq, prev, next); /* unlocks the rq */ |
4250 | /* | 4250 | /* |
4251 | * The context switch have flipped the stack from under us | 4251 | * The context switch have flipped the stack from under us |
4252 | * and restored the local variables which were saved when | 4252 | * and restored the local variables which were saved when |
4253 | * this task called schedule() in the past. prev == current | 4253 | * this task called schedule() in the past. prev == current |
4254 | * is still correct, but it can be moved to another cpu/rq. | 4254 | * is still correct, but it can be moved to another cpu/rq. |
4255 | */ | 4255 | */ |
4256 | cpu = smp_processor_id(); | 4256 | cpu = smp_processor_id(); |
4257 | rq = cpu_rq(cpu); | 4257 | rq = cpu_rq(cpu); |
4258 | } else | 4258 | } else |
4259 | raw_spin_unlock_irq(&rq->lock); | 4259 | raw_spin_unlock_irq(&rq->lock); |
4260 | 4260 | ||
4261 | post_schedule(rq); | 4261 | post_schedule(rq); |
4262 | 4262 | ||
4263 | preempt_enable_no_resched(); | 4263 | preempt_enable_no_resched(); |
4264 | if (need_resched()) | 4264 | if (need_resched()) |
4265 | goto need_resched; | 4265 | goto need_resched; |
4266 | } | 4266 | } |
4267 | EXPORT_SYMBOL(schedule); | 4267 | EXPORT_SYMBOL(schedule); |
4268 | 4268 | ||
4269 | #ifdef CONFIG_MUTEX_SPIN_ON_OWNER | 4269 | #ifdef CONFIG_MUTEX_SPIN_ON_OWNER |
4270 | 4270 | ||
4271 | static inline bool owner_running(struct mutex *lock, struct task_struct *owner) | 4271 | static inline bool owner_running(struct mutex *lock, struct task_struct *owner) |
4272 | { | 4272 | { |
4273 | bool ret = false; | 4273 | bool ret = false; |
4274 | 4274 | ||
4275 | rcu_read_lock(); | 4275 | rcu_read_lock(); |
4276 | if (lock->owner != owner) | 4276 | if (lock->owner != owner) |
4277 | goto fail; | 4277 | goto fail; |
4278 | 4278 | ||
4279 | /* | 4279 | /* |
4280 | * Ensure we emit the owner->on_cpu, dereference _after_ checking | 4280 | * Ensure we emit the owner->on_cpu, dereference _after_ checking |
4281 | * lock->owner still matches owner, if that fails, owner might | 4281 | * lock->owner still matches owner, if that fails, owner might |
4282 | * point to free()d memory, if it still matches, the rcu_read_lock() | 4282 | * point to free()d memory, if it still matches, the rcu_read_lock() |
4283 | * ensures the memory stays valid. | 4283 | * ensures the memory stays valid. |
4284 | */ | 4284 | */ |
4285 | barrier(); | 4285 | barrier(); |
4286 | 4286 | ||
4287 | ret = owner->on_cpu; | 4287 | ret = owner->on_cpu; |
4288 | fail: | 4288 | fail: |
4289 | rcu_read_unlock(); | 4289 | rcu_read_unlock(); |
4290 | 4290 | ||
4291 | return ret; | 4291 | return ret; |
4292 | } | 4292 | } |
4293 | 4293 | ||
4294 | /* | 4294 | /* |
4295 | * Look out! "owner" is an entirely speculative pointer | 4295 | * Look out! "owner" is an entirely speculative pointer |
4296 | * access and not reliable. | 4296 | * access and not reliable. |
4297 | */ | 4297 | */ |
4298 | int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) | 4298 | int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) |
4299 | { | 4299 | { |
4300 | if (!sched_feat(OWNER_SPIN)) | 4300 | if (!sched_feat(OWNER_SPIN)) |
4301 | return 0; | 4301 | return 0; |
4302 | 4302 | ||
4303 | while (owner_running(lock, owner)) { | 4303 | while (owner_running(lock, owner)) { |
4304 | if (need_resched()) | 4304 | if (need_resched()) |
4305 | return 0; | 4305 | return 0; |
4306 | 4306 | ||
4307 | arch_mutex_cpu_relax(); | 4307 | arch_mutex_cpu_relax(); |
4308 | } | 4308 | } |
4309 | 4309 | ||
4310 | /* | 4310 | /* |
4311 | * If the owner changed to another task there is likely | 4311 | * If the owner changed to another task there is likely |
4312 | * heavy contention, stop spinning. | 4312 | * heavy contention, stop spinning. |
4313 | */ | 4313 | */ |
4314 | if (lock->owner) | 4314 | if (lock->owner) |
4315 | return 0; | 4315 | return 0; |
4316 | 4316 | ||
4317 | return 1; | 4317 | return 1; |
4318 | } | 4318 | } |
4319 | #endif | 4319 | #endif |
4320 | 4320 | ||
4321 | #ifdef CONFIG_PREEMPT | 4321 | #ifdef CONFIG_PREEMPT |
4322 | /* | 4322 | /* |
4323 | * this is the entry point to schedule() from in-kernel preemption | 4323 | * this is the entry point to schedule() from in-kernel preemption |
4324 | * off of preempt_enable. Kernel preemptions off return from interrupt | 4324 | * off of preempt_enable. Kernel preemptions off return from interrupt |
4325 | * occur there and call schedule directly. | 4325 | * occur there and call schedule directly. |
4326 | */ | 4326 | */ |
4327 | asmlinkage void __sched notrace preempt_schedule(void) | 4327 | asmlinkage void __sched notrace preempt_schedule(void) |
4328 | { | 4328 | { |
4329 | struct thread_info *ti = current_thread_info(); | 4329 | struct thread_info *ti = current_thread_info(); |
4330 | 4330 | ||
4331 | /* | 4331 | /* |
4332 | * If there is a non-zero preempt_count or interrupts are disabled, | 4332 | * If there is a non-zero preempt_count or interrupts are disabled, |
4333 | * we do not want to preempt the current task. Just return.. | 4333 | * we do not want to preempt the current task. Just return.. |
4334 | */ | 4334 | */ |
4335 | if (likely(ti->preempt_count || irqs_disabled())) | 4335 | if (likely(ti->preempt_count || irqs_disabled())) |
4336 | return; | 4336 | return; |
4337 | 4337 | ||
4338 | do { | 4338 | do { |
4339 | add_preempt_count_notrace(PREEMPT_ACTIVE); | 4339 | add_preempt_count_notrace(PREEMPT_ACTIVE); |
4340 | schedule(); | 4340 | schedule(); |
4341 | sub_preempt_count_notrace(PREEMPT_ACTIVE); | 4341 | sub_preempt_count_notrace(PREEMPT_ACTIVE); |
4342 | 4342 | ||
4343 | /* | 4343 | /* |
4344 | * Check again in case we missed a preemption opportunity | 4344 | * Check again in case we missed a preemption opportunity |
4345 | * between schedule and now. | 4345 | * between schedule and now. |
4346 | */ | 4346 | */ |
4347 | barrier(); | 4347 | barrier(); |
4348 | } while (need_resched()); | 4348 | } while (need_resched()); |
4349 | } | 4349 | } |
4350 | EXPORT_SYMBOL(preempt_schedule); | 4350 | EXPORT_SYMBOL(preempt_schedule); |
4351 | 4351 | ||
4352 | /* | 4352 | /* |
4353 | * this is the entry point to schedule() from kernel preemption | 4353 | * this is the entry point to schedule() from kernel preemption |
4354 | * off of irq context. | 4354 | * off of irq context. |
4355 | * Note, that this is called and return with irqs disabled. This will | 4355 | * Note, that this is called and return with irqs disabled. This will |
4356 | * protect us against recursive calling from irq. | 4356 | * protect us against recursive calling from irq. |
4357 | */ | 4357 | */ |
4358 | asmlinkage void __sched preempt_schedule_irq(void) | 4358 | asmlinkage void __sched preempt_schedule_irq(void) |
4359 | { | 4359 | { |
4360 | struct thread_info *ti = current_thread_info(); | 4360 | struct thread_info *ti = current_thread_info(); |
4361 | 4361 | ||
4362 | /* Catch callers which need to be fixed */ | 4362 | /* Catch callers which need to be fixed */ |
4363 | BUG_ON(ti->preempt_count || !irqs_disabled()); | 4363 | BUG_ON(ti->preempt_count || !irqs_disabled()); |
4364 | 4364 | ||
4365 | do { | 4365 | do { |
4366 | add_preempt_count(PREEMPT_ACTIVE); | 4366 | add_preempt_count(PREEMPT_ACTIVE); |
4367 | local_irq_enable(); | 4367 | local_irq_enable(); |
4368 | schedule(); | 4368 | schedule(); |
4369 | local_irq_disable(); | 4369 | local_irq_disable(); |
4370 | sub_preempt_count(PREEMPT_ACTIVE); | 4370 | sub_preempt_count(PREEMPT_ACTIVE); |
4371 | 4371 | ||
4372 | /* | 4372 | /* |
4373 | * Check again in case we missed a preemption opportunity | 4373 | * Check again in case we missed a preemption opportunity |
4374 | * between schedule and now. | 4374 | * between schedule and now. |
4375 | */ | 4375 | */ |
4376 | barrier(); | 4376 | barrier(); |
4377 | } while (need_resched()); | 4377 | } while (need_resched()); |
4378 | } | 4378 | } |
4379 | 4379 | ||
4380 | #endif /* CONFIG_PREEMPT */ | 4380 | #endif /* CONFIG_PREEMPT */ |
4381 | 4381 | ||
4382 | int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, | 4382 | int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, |
4383 | void *key) | 4383 | void *key) |
4384 | { | 4384 | { |
4385 | return try_to_wake_up(curr->private, mode, wake_flags); | 4385 | return try_to_wake_up(curr->private, mode, wake_flags); |
4386 | } | 4386 | } |
4387 | EXPORT_SYMBOL(default_wake_function); | 4387 | EXPORT_SYMBOL(default_wake_function); |
4388 | 4388 | ||
4389 | /* | 4389 | /* |
4390 | * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just | 4390 | * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just |
4391 | * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve | 4391 | * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve |
4392 | * number) then we wake all the non-exclusive tasks and one exclusive task. | 4392 | * number) then we wake all the non-exclusive tasks and one exclusive task. |
4393 | * | 4393 | * |
4394 | * There are circumstances in which we can try to wake a task which has already | 4394 | * There are circumstances in which we can try to wake a task which has already |
4395 | * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns | 4395 | * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns |
4396 | * zero in this (rare) case, and we handle it by continuing to scan the queue. | 4396 | * zero in this (rare) case, and we handle it by continuing to scan the queue. |
4397 | */ | 4397 | */ |
4398 | static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, | 4398 | static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, |
4399 | int nr_exclusive, int wake_flags, void *key) | 4399 | int nr_exclusive, int wake_flags, void *key) |
4400 | { | 4400 | { |
4401 | wait_queue_t *curr, *next; | 4401 | wait_queue_t *curr, *next; |
4402 | 4402 | ||
4403 | list_for_each_entry_safe(curr, next, &q->task_list, task_list) { | 4403 | list_for_each_entry_safe(curr, next, &q->task_list, task_list) { |
4404 | unsigned flags = curr->flags; | 4404 | unsigned flags = curr->flags; |
4405 | 4405 | ||
4406 | if (curr->func(curr, mode, wake_flags, key) && | 4406 | if (curr->func(curr, mode, wake_flags, key) && |
4407 | (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) | 4407 | (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) |
4408 | break; | 4408 | break; |
4409 | } | 4409 | } |
4410 | } | 4410 | } |
4411 | 4411 | ||
4412 | /** | 4412 | /** |
4413 | * __wake_up - wake up threads blocked on a waitqueue. | 4413 | * __wake_up - wake up threads blocked on a waitqueue. |
4414 | * @q: the waitqueue | 4414 | * @q: the waitqueue |
4415 | * @mode: which threads | 4415 | * @mode: which threads |
4416 | * @nr_exclusive: how many wake-one or wake-many threads to wake up | 4416 | * @nr_exclusive: how many wake-one or wake-many threads to wake up |
4417 | * @key: is directly passed to the wakeup function | 4417 | * @key: is directly passed to the wakeup function |
4418 | * | 4418 | * |
4419 | * It may be assumed that this function implies a write memory barrier before | 4419 | * It may be assumed that this function implies a write memory barrier before |
4420 | * changing the task state if and only if any tasks are woken up. | 4420 | * changing the task state if and only if any tasks are woken up. |
4421 | */ | 4421 | */ |
4422 | void __wake_up(wait_queue_head_t *q, unsigned int mode, | 4422 | void __wake_up(wait_queue_head_t *q, unsigned int mode, |
4423 | int nr_exclusive, void *key) | 4423 | int nr_exclusive, void *key) |
4424 | { | 4424 | { |
4425 | unsigned long flags; | 4425 | unsigned long flags; |
4426 | 4426 | ||
4427 | spin_lock_irqsave(&q->lock, flags); | 4427 | spin_lock_irqsave(&q->lock, flags); |
4428 | __wake_up_common(q, mode, nr_exclusive, 0, key); | 4428 | __wake_up_common(q, mode, nr_exclusive, 0, key); |
4429 | spin_unlock_irqrestore(&q->lock, flags); | 4429 | spin_unlock_irqrestore(&q->lock, flags); |
4430 | } | 4430 | } |
4431 | EXPORT_SYMBOL(__wake_up); | 4431 | EXPORT_SYMBOL(__wake_up); |
4432 | 4432 | ||
4433 | /* | 4433 | /* |
4434 | * Same as __wake_up but called with the spinlock in wait_queue_head_t held. | 4434 | * Same as __wake_up but called with the spinlock in wait_queue_head_t held. |
4435 | */ | 4435 | */ |
4436 | void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) | 4436 | void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) |
4437 | { | 4437 | { |
4438 | __wake_up_common(q, mode, 1, 0, NULL); | 4438 | __wake_up_common(q, mode, 1, 0, NULL); |
4439 | } | 4439 | } |
4440 | EXPORT_SYMBOL_GPL(__wake_up_locked); | 4440 | EXPORT_SYMBOL_GPL(__wake_up_locked); |
4441 | 4441 | ||
4442 | void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) | 4442 | void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) |
4443 | { | 4443 | { |
4444 | __wake_up_common(q, mode, 1, 0, key); | 4444 | __wake_up_common(q, mode, 1, 0, key); |
4445 | } | 4445 | } |
4446 | EXPORT_SYMBOL_GPL(__wake_up_locked_key); | 4446 | EXPORT_SYMBOL_GPL(__wake_up_locked_key); |
4447 | 4447 | ||
4448 | /** | 4448 | /** |
4449 | * __wake_up_sync_key - wake up threads blocked on a waitqueue. | 4449 | * __wake_up_sync_key - wake up threads blocked on a waitqueue. |
4450 | * @q: the waitqueue | 4450 | * @q: the waitqueue |
4451 | * @mode: which threads | 4451 | * @mode: which threads |
4452 | * @nr_exclusive: how many wake-one or wake-many threads to wake up | 4452 | * @nr_exclusive: how many wake-one or wake-many threads to wake up |
4453 | * @key: opaque value to be passed to wakeup targets | 4453 | * @key: opaque value to be passed to wakeup targets |
4454 | * | 4454 | * |
4455 | * The sync wakeup differs that the waker knows that it will schedule | 4455 | * The sync wakeup differs that the waker knows that it will schedule |
4456 | * away soon, so while the target thread will be woken up, it will not | 4456 | * away soon, so while the target thread will be woken up, it will not |
4457 | * be migrated to another CPU - ie. the two threads are 'synchronized' | 4457 | * be migrated to another CPU - ie. the two threads are 'synchronized' |
4458 | * with each other. This can prevent needless bouncing between CPUs. | 4458 | * with each other. This can prevent needless bouncing between CPUs. |
4459 | * | 4459 | * |
4460 | * On UP it can prevent extra preemption. | 4460 | * On UP it can prevent extra preemption. |
4461 | * | 4461 | * |
4462 | * It may be assumed that this function implies a write memory barrier before | 4462 | * It may be assumed that this function implies a write memory barrier before |
4463 | * changing the task state if and only if any tasks are woken up. | 4463 | * changing the task state if and only if any tasks are woken up. |
4464 | */ | 4464 | */ |
4465 | void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, | 4465 | void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, |
4466 | int nr_exclusive, void *key) | 4466 | int nr_exclusive, void *key) |
4467 | { | 4467 | { |
4468 | unsigned long flags; | 4468 | unsigned long flags; |
4469 | int wake_flags = WF_SYNC; | 4469 | int wake_flags = WF_SYNC; |
4470 | 4470 | ||
4471 | if (unlikely(!q)) | 4471 | if (unlikely(!q)) |
4472 | return; | 4472 | return; |
4473 | 4473 | ||
4474 | if (unlikely(!nr_exclusive)) | 4474 | if (unlikely(!nr_exclusive)) |
4475 | wake_flags = 0; | 4475 | wake_flags = 0; |
4476 | 4476 | ||
4477 | spin_lock_irqsave(&q->lock, flags); | 4477 | spin_lock_irqsave(&q->lock, flags); |
4478 | __wake_up_common(q, mode, nr_exclusive, wake_flags, key); | 4478 | __wake_up_common(q, mode, nr_exclusive, wake_flags, key); |
4479 | spin_unlock_irqrestore(&q->lock, flags); | 4479 | spin_unlock_irqrestore(&q->lock, flags); |
4480 | } | 4480 | } |
4481 | EXPORT_SYMBOL_GPL(__wake_up_sync_key); | 4481 | EXPORT_SYMBOL_GPL(__wake_up_sync_key); |
4482 | 4482 | ||
4483 | /* | 4483 | /* |
4484 | * __wake_up_sync - see __wake_up_sync_key() | 4484 | * __wake_up_sync - see __wake_up_sync_key() |
4485 | */ | 4485 | */ |
4486 | void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) | 4486 | void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) |
4487 | { | 4487 | { |
4488 | __wake_up_sync_key(q, mode, nr_exclusive, NULL); | 4488 | __wake_up_sync_key(q, mode, nr_exclusive, NULL); |
4489 | } | 4489 | } |
4490 | EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ | 4490 | EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ |
4491 | 4491 | ||
4492 | /** | 4492 | /** |
4493 | * complete: - signals a single thread waiting on this completion | 4493 | * complete: - signals a single thread waiting on this completion |
4494 | * @x: holds the state of this particular completion | 4494 | * @x: holds the state of this particular completion |
4495 | * | 4495 | * |
4496 | * This will wake up a single thread waiting on this completion. Threads will be | 4496 | * This will wake up a single thread waiting on this completion. Threads will be |
4497 | * awakened in the same order in which they were queued. | 4497 | * awakened in the same order in which they were queued. |
4498 | * | 4498 | * |
4499 | * See also complete_all(), wait_for_completion() and related routines. | 4499 | * See also complete_all(), wait_for_completion() and related routines. |
4500 | * | 4500 | * |
4501 | * It may be assumed that this function implies a write memory barrier before | 4501 | * It may be assumed that this function implies a write memory barrier before |
4502 | * changing the task state if and only if any tasks are woken up. | 4502 | * changing the task state if and only if any tasks are woken up. |
4503 | */ | 4503 | */ |
4504 | void complete(struct completion *x) | 4504 | void complete(struct completion *x) |
4505 | { | 4505 | { |
4506 | unsigned long flags; | 4506 | unsigned long flags; |
4507 | 4507 | ||
4508 | spin_lock_irqsave(&x->wait.lock, flags); | 4508 | spin_lock_irqsave(&x->wait.lock, flags); |
4509 | x->done++; | 4509 | x->done++; |
4510 | __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); | 4510 | __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); |
4511 | spin_unlock_irqrestore(&x->wait.lock, flags); | 4511 | spin_unlock_irqrestore(&x->wait.lock, flags); |
4512 | } | 4512 | } |
4513 | EXPORT_SYMBOL(complete); | 4513 | EXPORT_SYMBOL(complete); |
4514 | 4514 | ||
4515 | /** | 4515 | /** |
4516 | * complete_all: - signals all threads waiting on this completion | 4516 | * complete_all: - signals all threads waiting on this completion |
4517 | * @x: holds the state of this particular completion | 4517 | * @x: holds the state of this particular completion |
4518 | * | 4518 | * |
4519 | * This will wake up all threads waiting on this particular completion event. | 4519 | * This will wake up all threads waiting on this particular completion event. |
4520 | * | 4520 | * |
4521 | * It may be assumed that this function implies a write memory barrier before | 4521 | * It may be assumed that this function implies a write memory barrier before |
4522 | * changing the task state if and only if any tasks are woken up. | 4522 | * changing the task state if and only if any tasks are woken up. |
4523 | */ | 4523 | */ |
4524 | void complete_all(struct completion *x) | 4524 | void complete_all(struct completion *x) |
4525 | { | 4525 | { |
4526 | unsigned long flags; | 4526 | unsigned long flags; |
4527 | 4527 | ||
4528 | spin_lock_irqsave(&x->wait.lock, flags); | 4528 | spin_lock_irqsave(&x->wait.lock, flags); |
4529 | x->done += UINT_MAX/2; | 4529 | x->done += UINT_MAX/2; |
4530 | __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); | 4530 | __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); |
4531 | spin_unlock_irqrestore(&x->wait.lock, flags); | 4531 | spin_unlock_irqrestore(&x->wait.lock, flags); |
4532 | } | 4532 | } |
4533 | EXPORT_SYMBOL(complete_all); | 4533 | EXPORT_SYMBOL(complete_all); |
4534 | 4534 | ||
4535 | static inline long __sched | 4535 | static inline long __sched |
4536 | do_wait_for_common(struct completion *x, long timeout, int state) | 4536 | do_wait_for_common(struct completion *x, long timeout, int state) |
4537 | { | 4537 | { |
4538 | if (!x->done) { | 4538 | if (!x->done) { |
4539 | DECLARE_WAITQUEUE(wait, current); | 4539 | DECLARE_WAITQUEUE(wait, current); |
4540 | 4540 | ||
4541 | __add_wait_queue_tail_exclusive(&x->wait, &wait); | 4541 | __add_wait_queue_tail_exclusive(&x->wait, &wait); |
4542 | do { | 4542 | do { |
4543 | if (signal_pending_state(state, current)) { | 4543 | if (signal_pending_state(state, current)) { |
4544 | timeout = -ERESTARTSYS; | 4544 | timeout = -ERESTARTSYS; |
4545 | break; | 4545 | break; |
4546 | } | 4546 | } |
4547 | __set_current_state(state); | 4547 | __set_current_state(state); |
4548 | spin_unlock_irq(&x->wait.lock); | 4548 | spin_unlock_irq(&x->wait.lock); |
4549 | timeout = schedule_timeout(timeout); | 4549 | timeout = schedule_timeout(timeout); |
4550 | spin_lock_irq(&x->wait.lock); | 4550 | spin_lock_irq(&x->wait.lock); |
4551 | } while (!x->done && timeout); | 4551 | } while (!x->done && timeout); |
4552 | __remove_wait_queue(&x->wait, &wait); | 4552 | __remove_wait_queue(&x->wait, &wait); |
4553 | if (!x->done) | 4553 | if (!x->done) |
4554 | return timeout; | 4554 | return timeout; |
4555 | } | 4555 | } |
4556 | x->done--; | 4556 | x->done--; |
4557 | return timeout ?: 1; | 4557 | return timeout ?: 1; |
4558 | } | 4558 | } |
4559 | 4559 | ||
4560 | static long __sched | 4560 | static long __sched |
4561 | wait_for_common(struct completion *x, long timeout, int state) | 4561 | wait_for_common(struct completion *x, long timeout, int state) |
4562 | { | 4562 | { |
4563 | might_sleep(); | 4563 | might_sleep(); |
4564 | 4564 | ||
4565 | spin_lock_irq(&x->wait.lock); | 4565 | spin_lock_irq(&x->wait.lock); |
4566 | timeout = do_wait_for_common(x, timeout, state); | 4566 | timeout = do_wait_for_common(x, timeout, state); |
4567 | spin_unlock_irq(&x->wait.lock); | 4567 | spin_unlock_irq(&x->wait.lock); |
4568 | return timeout; | 4568 | return timeout; |
4569 | } | 4569 | } |
4570 | 4570 | ||
4571 | /** | 4571 | /** |
4572 | * wait_for_completion: - waits for completion of a task | 4572 | * wait_for_completion: - waits for completion of a task |
4573 | * @x: holds the state of this particular completion | 4573 | * @x: holds the state of this particular completion |
4574 | * | 4574 | * |
4575 | * This waits to be signaled for completion of a specific task. It is NOT | 4575 | * This waits to be signaled for completion of a specific task. It is NOT |
4576 | * interruptible and there is no timeout. | 4576 | * interruptible and there is no timeout. |
4577 | * | 4577 | * |
4578 | * See also similar routines (i.e. wait_for_completion_timeout()) with timeout | 4578 | * See also similar routines (i.e. wait_for_completion_timeout()) with timeout |
4579 | * and interrupt capability. Also see complete(). | 4579 | * and interrupt capability. Also see complete(). |
4580 | */ | 4580 | */ |
4581 | void __sched wait_for_completion(struct completion *x) | 4581 | void __sched wait_for_completion(struct completion *x) |
4582 | { | 4582 | { |
4583 | wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); | 4583 | wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); |
4584 | } | 4584 | } |
4585 | EXPORT_SYMBOL(wait_for_completion); | 4585 | EXPORT_SYMBOL(wait_for_completion); |
4586 | 4586 | ||
4587 | /** | 4587 | /** |
4588 | * wait_for_completion_timeout: - waits for completion of a task (w/timeout) | 4588 | * wait_for_completion_timeout: - waits for completion of a task (w/timeout) |
4589 | * @x: holds the state of this particular completion | 4589 | * @x: holds the state of this particular completion |
4590 | * @timeout: timeout value in jiffies | 4590 | * @timeout: timeout value in jiffies |
4591 | * | 4591 | * |
4592 | * This waits for either a completion of a specific task to be signaled or for a | 4592 | * This waits for either a completion of a specific task to be signaled or for a |
4593 | * specified timeout to expire. The timeout is in jiffies. It is not | 4593 | * specified timeout to expire. The timeout is in jiffies. It is not |
4594 | * interruptible. | 4594 | * interruptible. |
4595 | */ | 4595 | */ |
4596 | unsigned long __sched | 4596 | unsigned long __sched |
4597 | wait_for_completion_timeout(struct completion *x, unsigned long timeout) | 4597 | wait_for_completion_timeout(struct completion *x, unsigned long timeout) |
4598 | { | 4598 | { |
4599 | return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); | 4599 | return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); |
4600 | } | 4600 | } |
4601 | EXPORT_SYMBOL(wait_for_completion_timeout); | 4601 | EXPORT_SYMBOL(wait_for_completion_timeout); |
4602 | 4602 | ||
4603 | /** | 4603 | /** |
4604 | * wait_for_completion_interruptible: - waits for completion of a task (w/intr) | 4604 | * wait_for_completion_interruptible: - waits for completion of a task (w/intr) |
4605 | * @x: holds the state of this particular completion | 4605 | * @x: holds the state of this particular completion |
4606 | * | 4606 | * |
4607 | * This waits for completion of a specific task to be signaled. It is | 4607 | * This waits for completion of a specific task to be signaled. It is |
4608 | * interruptible. | 4608 | * interruptible. |
4609 | */ | 4609 | */ |
4610 | int __sched wait_for_completion_interruptible(struct completion *x) | 4610 | int __sched wait_for_completion_interruptible(struct completion *x) |
4611 | { | 4611 | { |
4612 | long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); | 4612 | long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); |
4613 | if (t == -ERESTARTSYS) | 4613 | if (t == -ERESTARTSYS) |
4614 | return t; | 4614 | return t; |
4615 | return 0; | 4615 | return 0; |
4616 | } | 4616 | } |
4617 | EXPORT_SYMBOL(wait_for_completion_interruptible); | 4617 | EXPORT_SYMBOL(wait_for_completion_interruptible); |
4618 | 4618 | ||
4619 | /** | 4619 | /** |
4620 | * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) | 4620 | * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) |
4621 | * @x: holds the state of this particular completion | 4621 | * @x: holds the state of this particular completion |
4622 | * @timeout: timeout value in jiffies | 4622 | * @timeout: timeout value in jiffies |
4623 | * | 4623 | * |
4624 | * This waits for either a completion of a specific task to be signaled or for a | 4624 | * This waits for either a completion of a specific task to be signaled or for a |
4625 | * specified timeout to expire. It is interruptible. The timeout is in jiffies. | 4625 | * specified timeout to expire. It is interruptible. The timeout is in jiffies. |
4626 | */ | 4626 | */ |
4627 | long __sched | 4627 | long __sched |
4628 | wait_for_completion_interruptible_timeout(struct completion *x, | 4628 | wait_for_completion_interruptible_timeout(struct completion *x, |
4629 | unsigned long timeout) | 4629 | unsigned long timeout) |
4630 | { | 4630 | { |
4631 | return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); | 4631 | return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); |
4632 | } | 4632 | } |
4633 | EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); | 4633 | EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); |
4634 | 4634 | ||
4635 | /** | 4635 | /** |
4636 | * wait_for_completion_killable: - waits for completion of a task (killable) | 4636 | * wait_for_completion_killable: - waits for completion of a task (killable) |
4637 | * @x: holds the state of this particular completion | 4637 | * @x: holds the state of this particular completion |
4638 | * | 4638 | * |
4639 | * This waits to be signaled for completion of a specific task. It can be | 4639 | * This waits to be signaled for completion of a specific task. It can be |
4640 | * interrupted by a kill signal. | 4640 | * interrupted by a kill signal. |
4641 | */ | 4641 | */ |
4642 | int __sched wait_for_completion_killable(struct completion *x) | 4642 | int __sched wait_for_completion_killable(struct completion *x) |
4643 | { | 4643 | { |
4644 | long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); | 4644 | long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); |
4645 | if (t == -ERESTARTSYS) | 4645 | if (t == -ERESTARTSYS) |
4646 | return t; | 4646 | return t; |
4647 | return 0; | 4647 | return 0; |
4648 | } | 4648 | } |
4649 | EXPORT_SYMBOL(wait_for_completion_killable); | 4649 | EXPORT_SYMBOL(wait_for_completion_killable); |
4650 | 4650 | ||
4651 | /** | 4651 | /** |
4652 | * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) | 4652 | * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) |
4653 | * @x: holds the state of this particular completion | 4653 | * @x: holds the state of this particular completion |
4654 | * @timeout: timeout value in jiffies | 4654 | * @timeout: timeout value in jiffies |
4655 | * | 4655 | * |
4656 | * This waits for either a completion of a specific task to be | 4656 | * This waits for either a completion of a specific task to be |
4657 | * signaled or for a specified timeout to expire. It can be | 4657 | * signaled or for a specified timeout to expire. It can be |
4658 | * interrupted by a kill signal. The timeout is in jiffies. | 4658 | * interrupted by a kill signal. The timeout is in jiffies. |
4659 | */ | 4659 | */ |
4660 | long __sched | 4660 | long __sched |
4661 | wait_for_completion_killable_timeout(struct completion *x, | 4661 | wait_for_completion_killable_timeout(struct completion *x, |
4662 | unsigned long timeout) | 4662 | unsigned long timeout) |
4663 | { | 4663 | { |
4664 | return wait_for_common(x, timeout, TASK_KILLABLE); | 4664 | return wait_for_common(x, timeout, TASK_KILLABLE); |
4665 | } | 4665 | } |
4666 | EXPORT_SYMBOL(wait_for_completion_killable_timeout); | 4666 | EXPORT_SYMBOL(wait_for_completion_killable_timeout); |
4667 | 4667 | ||
4668 | /** | 4668 | /** |
4669 | * try_wait_for_completion - try to decrement a completion without blocking | 4669 | * try_wait_for_completion - try to decrement a completion without blocking |
4670 | * @x: completion structure | 4670 | * @x: completion structure |
4671 | * | 4671 | * |
4672 | * Returns: 0 if a decrement cannot be done without blocking | 4672 | * Returns: 0 if a decrement cannot be done without blocking |
4673 | * 1 if a decrement succeeded. | 4673 | * 1 if a decrement succeeded. |
4674 | * | 4674 | * |
4675 | * If a completion is being used as a counting completion, | 4675 | * If a completion is being used as a counting completion, |
4676 | * attempt to decrement the counter without blocking. This | 4676 | * attempt to decrement the counter without blocking. This |
4677 | * enables us to avoid waiting if the resource the completion | 4677 | * enables us to avoid waiting if the resource the completion |
4678 | * is protecting is not available. | 4678 | * is protecting is not available. |
4679 | */ | 4679 | */ |
4680 | bool try_wait_for_completion(struct completion *x) | 4680 | bool try_wait_for_completion(struct completion *x) |
4681 | { | 4681 | { |
4682 | unsigned long flags; | 4682 | unsigned long flags; |
4683 | int ret = 1; | 4683 | int ret = 1; |
4684 | 4684 | ||
4685 | spin_lock_irqsave(&x->wait.lock, flags); | 4685 | spin_lock_irqsave(&x->wait.lock, flags); |
4686 | if (!x->done) | 4686 | if (!x->done) |
4687 | ret = 0; | 4687 | ret = 0; |
4688 | else | 4688 | else |
4689 | x->done--; | 4689 | x->done--; |
4690 | spin_unlock_irqrestore(&x->wait.lock, flags); | 4690 | spin_unlock_irqrestore(&x->wait.lock, flags); |
4691 | return ret; | 4691 | return ret; |
4692 | } | 4692 | } |
4693 | EXPORT_SYMBOL(try_wait_for_completion); | 4693 | EXPORT_SYMBOL(try_wait_for_completion); |
4694 | 4694 | ||
4695 | /** | 4695 | /** |
4696 | * completion_done - Test to see if a completion has any waiters | 4696 | * completion_done - Test to see if a completion has any waiters |
4697 | * @x: completion structure | 4697 | * @x: completion structure |
4698 | * | 4698 | * |
4699 | * Returns: 0 if there are waiters (wait_for_completion() in progress) | 4699 | * Returns: 0 if there are waiters (wait_for_completion() in progress) |
4700 | * 1 if there are no waiters. | 4700 | * 1 if there are no waiters. |
4701 | * | 4701 | * |
4702 | */ | 4702 | */ |
4703 | bool completion_done(struct completion *x) | 4703 | bool completion_done(struct completion *x) |
4704 | { | 4704 | { |
4705 | unsigned long flags; | 4705 | unsigned long flags; |
4706 | int ret = 1; | 4706 | int ret = 1; |
4707 | 4707 | ||
4708 | spin_lock_irqsave(&x->wait.lock, flags); | 4708 | spin_lock_irqsave(&x->wait.lock, flags); |
4709 | if (!x->done) | 4709 | if (!x->done) |
4710 | ret = 0; | 4710 | ret = 0; |
4711 | spin_unlock_irqrestore(&x->wait.lock, flags); | 4711 | spin_unlock_irqrestore(&x->wait.lock, flags); |
4712 | return ret; | 4712 | return ret; |
4713 | } | 4713 | } |
4714 | EXPORT_SYMBOL(completion_done); | 4714 | EXPORT_SYMBOL(completion_done); |
4715 | 4715 | ||
4716 | static long __sched | 4716 | static long __sched |
4717 | sleep_on_common(wait_queue_head_t *q, int state, long timeout) | 4717 | sleep_on_common(wait_queue_head_t *q, int state, long timeout) |
4718 | { | 4718 | { |
4719 | unsigned long flags; | 4719 | unsigned long flags; |
4720 | wait_queue_t wait; | 4720 | wait_queue_t wait; |
4721 | 4721 | ||
4722 | init_waitqueue_entry(&wait, current); | 4722 | init_waitqueue_entry(&wait, current); |
4723 | 4723 | ||
4724 | __set_current_state(state); | 4724 | __set_current_state(state); |
4725 | 4725 | ||
4726 | spin_lock_irqsave(&q->lock, flags); | 4726 | spin_lock_irqsave(&q->lock, flags); |
4727 | __add_wait_queue(q, &wait); | 4727 | __add_wait_queue(q, &wait); |
4728 | spin_unlock(&q->lock); | 4728 | spin_unlock(&q->lock); |
4729 | timeout = schedule_timeout(timeout); | 4729 | timeout = schedule_timeout(timeout); |
4730 | spin_lock_irq(&q->lock); | 4730 | spin_lock_irq(&q->lock); |
4731 | __remove_wait_queue(q, &wait); | 4731 | __remove_wait_queue(q, &wait); |
4732 | spin_unlock_irqrestore(&q->lock, flags); | 4732 | spin_unlock_irqrestore(&q->lock, flags); |
4733 | 4733 | ||
4734 | return timeout; | 4734 | return timeout; |
4735 | } | 4735 | } |
4736 | 4736 | ||
4737 | void __sched interruptible_sleep_on(wait_queue_head_t *q) | 4737 | void __sched interruptible_sleep_on(wait_queue_head_t *q) |
4738 | { | 4738 | { |
4739 | sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); | 4739 | sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); |
4740 | } | 4740 | } |
4741 | EXPORT_SYMBOL(interruptible_sleep_on); | 4741 | EXPORT_SYMBOL(interruptible_sleep_on); |
4742 | 4742 | ||
4743 | long __sched | 4743 | long __sched |
4744 | interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) | 4744 | interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) |
4745 | { | 4745 | { |
4746 | return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); | 4746 | return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); |
4747 | } | 4747 | } |
4748 | EXPORT_SYMBOL(interruptible_sleep_on_timeout); | 4748 | EXPORT_SYMBOL(interruptible_sleep_on_timeout); |
4749 | 4749 | ||
4750 | void __sched sleep_on(wait_queue_head_t *q) | 4750 | void __sched sleep_on(wait_queue_head_t *q) |
4751 | { | 4751 | { |
4752 | sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); | 4752 | sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); |
4753 | } | 4753 | } |
4754 | EXPORT_SYMBOL(sleep_on); | 4754 | EXPORT_SYMBOL(sleep_on); |
4755 | 4755 | ||
4756 | long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) | 4756 | long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) |
4757 | { | 4757 | { |
4758 | return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); | 4758 | return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); |
4759 | } | 4759 | } |
4760 | EXPORT_SYMBOL(sleep_on_timeout); | 4760 | EXPORT_SYMBOL(sleep_on_timeout); |
4761 | 4761 | ||
4762 | #ifdef CONFIG_RT_MUTEXES | 4762 | #ifdef CONFIG_RT_MUTEXES |
4763 | 4763 | ||
4764 | /* | 4764 | /* |
4765 | * rt_mutex_setprio - set the current priority of a task | 4765 | * rt_mutex_setprio - set the current priority of a task |
4766 | * @p: task | 4766 | * @p: task |
4767 | * @prio: prio value (kernel-internal form) | 4767 | * @prio: prio value (kernel-internal form) |
4768 | * | 4768 | * |
4769 | * This function changes the 'effective' priority of a task. It does | 4769 | * This function changes the 'effective' priority of a task. It does |
4770 | * not touch ->normal_prio like __setscheduler(). | 4770 | * not touch ->normal_prio like __setscheduler(). |
4771 | * | 4771 | * |
4772 | * Used by the rt_mutex code to implement priority inheritance logic. | 4772 | * Used by the rt_mutex code to implement priority inheritance logic. |
4773 | */ | 4773 | */ |
4774 | void rt_mutex_setprio(struct task_struct *p, int prio) | 4774 | void rt_mutex_setprio(struct task_struct *p, int prio) |
4775 | { | 4775 | { |
4776 | int oldprio, on_rq, running; | 4776 | int oldprio, on_rq, running; |
4777 | struct rq *rq; | 4777 | struct rq *rq; |
4778 | const struct sched_class *prev_class; | 4778 | const struct sched_class *prev_class; |
4779 | 4779 | ||
4780 | BUG_ON(prio < 0 || prio > MAX_PRIO); | 4780 | BUG_ON(prio < 0 || prio > MAX_PRIO); |
4781 | 4781 | ||
4782 | rq = __task_rq_lock(p); | 4782 | rq = __task_rq_lock(p); |
4783 | 4783 | ||
4784 | trace_sched_pi_setprio(p, prio); | 4784 | trace_sched_pi_setprio(p, prio); |
4785 | oldprio = p->prio; | 4785 | oldprio = p->prio; |
4786 | prev_class = p->sched_class; | 4786 | prev_class = p->sched_class; |
4787 | on_rq = p->on_rq; | 4787 | on_rq = p->on_rq; |
4788 | running = task_current(rq, p); | 4788 | running = task_current(rq, p); |
4789 | if (on_rq) | 4789 | if (on_rq) |
4790 | dequeue_task(rq, p, 0); | 4790 | dequeue_task(rq, p, 0); |
4791 | if (running) | 4791 | if (running) |
4792 | p->sched_class->put_prev_task(rq, p); | 4792 | p->sched_class->put_prev_task(rq, p); |
4793 | 4793 | ||
4794 | if (rt_prio(prio)) | 4794 | if (rt_prio(prio)) |
4795 | p->sched_class = &rt_sched_class; | 4795 | p->sched_class = &rt_sched_class; |
4796 | else | 4796 | else |
4797 | p->sched_class = &fair_sched_class; | 4797 | p->sched_class = &fair_sched_class; |
4798 | 4798 | ||
4799 | p->prio = prio; | 4799 | p->prio = prio; |
4800 | 4800 | ||
4801 | if (running) | 4801 | if (running) |
4802 | p->sched_class->set_curr_task(rq); | 4802 | p->sched_class->set_curr_task(rq); |
4803 | if (on_rq) | 4803 | if (on_rq) |
4804 | enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); | 4804 | enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); |
4805 | 4805 | ||
4806 | check_class_changed(rq, p, prev_class, oldprio); | 4806 | check_class_changed(rq, p, prev_class, oldprio); |
4807 | __task_rq_unlock(rq); | 4807 | __task_rq_unlock(rq); |
4808 | } | 4808 | } |
4809 | 4809 | ||
4810 | #endif | 4810 | #endif |
4811 | 4811 | ||
4812 | void set_user_nice(struct task_struct *p, long nice) | 4812 | void set_user_nice(struct task_struct *p, long nice) |
4813 | { | 4813 | { |
4814 | int old_prio, delta, on_rq; | 4814 | int old_prio, delta, on_rq; |
4815 | unsigned long flags; | 4815 | unsigned long flags; |
4816 | struct rq *rq; | 4816 | struct rq *rq; |
4817 | 4817 | ||
4818 | if (TASK_NICE(p) == nice || nice < -20 || nice > 19) | 4818 | if (TASK_NICE(p) == nice || nice < -20 || nice > 19) |
4819 | return; | 4819 | return; |
4820 | /* | 4820 | /* |
4821 | * We have to be careful, if called from sys_setpriority(), | 4821 | * We have to be careful, if called from sys_setpriority(), |
4822 | * the task might be in the middle of scheduling on another CPU. | 4822 | * the task might be in the middle of scheduling on another CPU. |
4823 | */ | 4823 | */ |
4824 | rq = task_rq_lock(p, &flags); | 4824 | rq = task_rq_lock(p, &flags); |
4825 | /* | 4825 | /* |
4826 | * The RT priorities are set via sched_setscheduler(), but we still | 4826 | * The RT priorities are set via sched_setscheduler(), but we still |
4827 | * allow the 'normal' nice value to be set - but as expected | 4827 | * allow the 'normal' nice value to be set - but as expected |
4828 | * it wont have any effect on scheduling until the task is | 4828 | * it wont have any effect on scheduling until the task is |
4829 | * SCHED_FIFO/SCHED_RR: | 4829 | * SCHED_FIFO/SCHED_RR: |
4830 | */ | 4830 | */ |
4831 | if (task_has_rt_policy(p)) { | 4831 | if (task_has_rt_policy(p)) { |
4832 | p->static_prio = NICE_TO_PRIO(nice); | 4832 | p->static_prio = NICE_TO_PRIO(nice); |
4833 | goto out_unlock; | 4833 | goto out_unlock; |
4834 | } | 4834 | } |
4835 | on_rq = p->on_rq; | 4835 | on_rq = p->on_rq; |
4836 | if (on_rq) | 4836 | if (on_rq) |
4837 | dequeue_task(rq, p, 0); | 4837 | dequeue_task(rq, p, 0); |
4838 | 4838 | ||
4839 | p->static_prio = NICE_TO_PRIO(nice); | 4839 | p->static_prio = NICE_TO_PRIO(nice); |
4840 | set_load_weight(p); | 4840 | set_load_weight(p); |
4841 | old_prio = p->prio; | 4841 | old_prio = p->prio; |
4842 | p->prio = effective_prio(p); | 4842 | p->prio = effective_prio(p); |
4843 | delta = p->prio - old_prio; | 4843 | delta = p->prio - old_prio; |
4844 | 4844 | ||
4845 | if (on_rq) { | 4845 | if (on_rq) { |
4846 | enqueue_task(rq, p, 0); | 4846 | enqueue_task(rq, p, 0); |
4847 | /* | 4847 | /* |
4848 | * If the task increased its priority or is running and | 4848 | * If the task increased its priority or is running and |
4849 | * lowered its priority, then reschedule its CPU: | 4849 | * lowered its priority, then reschedule its CPU: |
4850 | */ | 4850 | */ |
4851 | if (delta < 0 || (delta > 0 && task_running(rq, p))) | 4851 | if (delta < 0 || (delta > 0 && task_running(rq, p))) |
4852 | resched_task(rq->curr); | 4852 | resched_task(rq->curr); |
4853 | } | 4853 | } |
4854 | out_unlock: | 4854 | out_unlock: |
4855 | task_rq_unlock(rq, p, &flags); | 4855 | task_rq_unlock(rq, p, &flags); |
4856 | } | 4856 | } |
4857 | EXPORT_SYMBOL(set_user_nice); | 4857 | EXPORT_SYMBOL(set_user_nice); |
4858 | 4858 | ||
4859 | /* | 4859 | /* |
4860 | * can_nice - check if a task can reduce its nice value | 4860 | * can_nice - check if a task can reduce its nice value |
4861 | * @p: task | 4861 | * @p: task |
4862 | * @nice: nice value | 4862 | * @nice: nice value |
4863 | */ | 4863 | */ |
4864 | int can_nice(const struct task_struct *p, const int nice) | 4864 | int can_nice(const struct task_struct *p, const int nice) |
4865 | { | 4865 | { |
4866 | /* convert nice value [19,-20] to rlimit style value [1,40] */ | 4866 | /* convert nice value [19,-20] to rlimit style value [1,40] */ |
4867 | int nice_rlim = 20 - nice; | 4867 | int nice_rlim = 20 - nice; |
4868 | 4868 | ||
4869 | return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || | 4869 | return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || |
4870 | capable(CAP_SYS_NICE)); | 4870 | capable(CAP_SYS_NICE)); |
4871 | } | 4871 | } |
4872 | 4872 | ||
4873 | #ifdef __ARCH_WANT_SYS_NICE | 4873 | #ifdef __ARCH_WANT_SYS_NICE |
4874 | 4874 | ||
4875 | /* | 4875 | /* |
4876 | * sys_nice - change the priority of the current process. | 4876 | * sys_nice - change the priority of the current process. |
4877 | * @increment: priority increment | 4877 | * @increment: priority increment |
4878 | * | 4878 | * |
4879 | * sys_setpriority is a more generic, but much slower function that | 4879 | * sys_setpriority is a more generic, but much slower function that |
4880 | * does similar things. | 4880 | * does similar things. |
4881 | */ | 4881 | */ |
4882 | SYSCALL_DEFINE1(nice, int, increment) | 4882 | SYSCALL_DEFINE1(nice, int, increment) |
4883 | { | 4883 | { |
4884 | long nice, retval; | 4884 | long nice, retval; |
4885 | 4885 | ||
4886 | /* | 4886 | /* |
4887 | * Setpriority might change our priority at the same moment. | 4887 | * Setpriority might change our priority at the same moment. |
4888 | * We don't have to worry. Conceptually one call occurs first | 4888 | * We don't have to worry. Conceptually one call occurs first |
4889 | * and we have a single winner. | 4889 | * and we have a single winner. |
4890 | */ | 4890 | */ |
4891 | if (increment < -40) | 4891 | if (increment < -40) |
4892 | increment = -40; | 4892 | increment = -40; |
4893 | if (increment > 40) | 4893 | if (increment > 40) |
4894 | increment = 40; | 4894 | increment = 40; |
4895 | 4895 | ||
4896 | nice = TASK_NICE(current) + increment; | 4896 | nice = TASK_NICE(current) + increment; |
4897 | if (nice < -20) | 4897 | if (nice < -20) |
4898 | nice = -20; | 4898 | nice = -20; |
4899 | if (nice > 19) | 4899 | if (nice > 19) |
4900 | nice = 19; | 4900 | nice = 19; |
4901 | 4901 | ||
4902 | if (increment < 0 && !can_nice(current, nice)) | 4902 | if (increment < 0 && !can_nice(current, nice)) |
4903 | return -EPERM; | 4903 | return -EPERM; |
4904 | 4904 | ||
4905 | retval = security_task_setnice(current, nice); | 4905 | retval = security_task_setnice(current, nice); |
4906 | if (retval) | 4906 | if (retval) |
4907 | return retval; | 4907 | return retval; |
4908 | 4908 | ||
4909 | set_user_nice(current, nice); | 4909 | set_user_nice(current, nice); |
4910 | return 0; | 4910 | return 0; |
4911 | } | 4911 | } |
4912 | 4912 | ||
4913 | #endif | 4913 | #endif |
4914 | 4914 | ||
4915 | /** | 4915 | /** |
4916 | * task_prio - return the priority value of a given task. | 4916 | * task_prio - return the priority value of a given task. |
4917 | * @p: the task in question. | 4917 | * @p: the task in question. |
4918 | * | 4918 | * |
4919 | * This is the priority value as seen by users in /proc. | 4919 | * This is the priority value as seen by users in /proc. |
4920 | * RT tasks are offset by -200. Normal tasks are centered | 4920 | * RT tasks are offset by -200. Normal tasks are centered |
4921 | * around 0, value goes from -16 to +15. | 4921 | * around 0, value goes from -16 to +15. |
4922 | */ | 4922 | */ |
4923 | int task_prio(const struct task_struct *p) | 4923 | int task_prio(const struct task_struct *p) |
4924 | { | 4924 | { |
4925 | return p->prio - MAX_RT_PRIO; | 4925 | return p->prio - MAX_RT_PRIO; |
4926 | } | 4926 | } |
4927 | 4927 | ||
4928 | /** | 4928 | /** |
4929 | * task_nice - return the nice value of a given task. | 4929 | * task_nice - return the nice value of a given task. |
4930 | * @p: the task in question. | 4930 | * @p: the task in question. |
4931 | */ | 4931 | */ |
4932 | int task_nice(const struct task_struct *p) | 4932 | int task_nice(const struct task_struct *p) |
4933 | { | 4933 | { |
4934 | return TASK_NICE(p); | 4934 | return TASK_NICE(p); |
4935 | } | 4935 | } |
4936 | EXPORT_SYMBOL(task_nice); | 4936 | EXPORT_SYMBOL(task_nice); |
4937 | 4937 | ||
4938 | /** | 4938 | /** |
4939 | * idle_cpu - is a given cpu idle currently? | 4939 | * idle_cpu - is a given cpu idle currently? |
4940 | * @cpu: the processor in question. | 4940 | * @cpu: the processor in question. |
4941 | */ | 4941 | */ |
4942 | int idle_cpu(int cpu) | 4942 | int idle_cpu(int cpu) |
4943 | { | 4943 | { |
4944 | return cpu_curr(cpu) == cpu_rq(cpu)->idle; | 4944 | return cpu_curr(cpu) == cpu_rq(cpu)->idle; |
4945 | } | 4945 | } |
4946 | 4946 | ||
4947 | /** | 4947 | /** |
4948 | * idle_task - return the idle task for a given cpu. | 4948 | * idle_task - return the idle task for a given cpu. |
4949 | * @cpu: the processor in question. | 4949 | * @cpu: the processor in question. |
4950 | */ | 4950 | */ |
4951 | struct task_struct *idle_task(int cpu) | 4951 | struct task_struct *idle_task(int cpu) |
4952 | { | 4952 | { |
4953 | return cpu_rq(cpu)->idle; | 4953 | return cpu_rq(cpu)->idle; |
4954 | } | 4954 | } |
4955 | 4955 | ||
4956 | /** | 4956 | /** |
4957 | * find_process_by_pid - find a process with a matching PID value. | 4957 | * find_process_by_pid - find a process with a matching PID value. |
4958 | * @pid: the pid in question. | 4958 | * @pid: the pid in question. |
4959 | */ | 4959 | */ |
4960 | static struct task_struct *find_process_by_pid(pid_t pid) | 4960 | static struct task_struct *find_process_by_pid(pid_t pid) |
4961 | { | 4961 | { |
4962 | return pid ? find_task_by_vpid(pid) : current; | 4962 | return pid ? find_task_by_vpid(pid) : current; |
4963 | } | 4963 | } |
4964 | 4964 | ||
4965 | /* Actually do priority change: must hold rq lock. */ | 4965 | /* Actually do priority change: must hold rq lock. */ |
4966 | static void | 4966 | static void |
4967 | __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) | 4967 | __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) |
4968 | { | 4968 | { |
4969 | p->policy = policy; | 4969 | p->policy = policy; |
4970 | p->rt_priority = prio; | 4970 | p->rt_priority = prio; |
4971 | p->normal_prio = normal_prio(p); | 4971 | p->normal_prio = normal_prio(p); |
4972 | /* we are holding p->pi_lock already */ | 4972 | /* we are holding p->pi_lock already */ |
4973 | p->prio = rt_mutex_getprio(p); | 4973 | p->prio = rt_mutex_getprio(p); |
4974 | if (rt_prio(p->prio)) | 4974 | if (rt_prio(p->prio)) |
4975 | p->sched_class = &rt_sched_class; | 4975 | p->sched_class = &rt_sched_class; |
4976 | else | 4976 | else |
4977 | p->sched_class = &fair_sched_class; | 4977 | p->sched_class = &fair_sched_class; |
4978 | set_load_weight(p); | 4978 | set_load_weight(p); |
4979 | } | 4979 | } |
4980 | 4980 | ||
4981 | /* | 4981 | /* |
4982 | * check the target process has a UID that matches the current process's | 4982 | * check the target process has a UID that matches the current process's |
4983 | */ | 4983 | */ |
4984 | static bool check_same_owner(struct task_struct *p) | 4984 | static bool check_same_owner(struct task_struct *p) |
4985 | { | 4985 | { |
4986 | const struct cred *cred = current_cred(), *pcred; | 4986 | const struct cred *cred = current_cred(), *pcred; |
4987 | bool match; | 4987 | bool match; |
4988 | 4988 | ||
4989 | rcu_read_lock(); | 4989 | rcu_read_lock(); |
4990 | pcred = __task_cred(p); | 4990 | pcred = __task_cred(p); |
4991 | if (cred->user->user_ns == pcred->user->user_ns) | 4991 | if (cred->user->user_ns == pcred->user->user_ns) |
4992 | match = (cred->euid == pcred->euid || | 4992 | match = (cred->euid == pcred->euid || |
4993 | cred->euid == pcred->uid); | 4993 | cred->euid == pcred->uid); |
4994 | else | 4994 | else |
4995 | match = false; | 4995 | match = false; |
4996 | rcu_read_unlock(); | 4996 | rcu_read_unlock(); |
4997 | return match; | 4997 | return match; |
4998 | } | 4998 | } |
4999 | 4999 | ||
5000 | static int __sched_setscheduler(struct task_struct *p, int policy, | 5000 | static int __sched_setscheduler(struct task_struct *p, int policy, |
5001 | const struct sched_param *param, bool user) | 5001 | const struct sched_param *param, bool user) |
5002 | { | 5002 | { |
5003 | int retval, oldprio, oldpolicy = -1, on_rq, running; | 5003 | int retval, oldprio, oldpolicy = -1, on_rq, running; |
5004 | unsigned long flags; | 5004 | unsigned long flags; |
5005 | const struct sched_class *prev_class; | 5005 | const struct sched_class *prev_class; |
5006 | struct rq *rq; | 5006 | struct rq *rq; |
5007 | int reset_on_fork; | 5007 | int reset_on_fork; |
5008 | 5008 | ||
5009 | /* may grab non-irq protected spin_locks */ | 5009 | /* may grab non-irq protected spin_locks */ |
5010 | BUG_ON(in_interrupt()); | 5010 | BUG_ON(in_interrupt()); |
5011 | recheck: | 5011 | recheck: |
5012 | /* double check policy once rq lock held */ | 5012 | /* double check policy once rq lock held */ |
5013 | if (policy < 0) { | 5013 | if (policy < 0) { |
5014 | reset_on_fork = p->sched_reset_on_fork; | 5014 | reset_on_fork = p->sched_reset_on_fork; |
5015 | policy = oldpolicy = p->policy; | 5015 | policy = oldpolicy = p->policy; |
5016 | } else { | 5016 | } else { |
5017 | reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); | 5017 | reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); |
5018 | policy &= ~SCHED_RESET_ON_FORK; | 5018 | policy &= ~SCHED_RESET_ON_FORK; |
5019 | 5019 | ||
5020 | if (policy != SCHED_FIFO && policy != SCHED_RR && | 5020 | if (policy != SCHED_FIFO && policy != SCHED_RR && |
5021 | policy != SCHED_NORMAL && policy != SCHED_BATCH && | 5021 | policy != SCHED_NORMAL && policy != SCHED_BATCH && |
5022 | policy != SCHED_IDLE) | 5022 | policy != SCHED_IDLE) |
5023 | return -EINVAL; | 5023 | return -EINVAL; |
5024 | } | 5024 | } |
5025 | 5025 | ||
5026 | /* | 5026 | /* |
5027 | * Valid priorities for SCHED_FIFO and SCHED_RR are | 5027 | * Valid priorities for SCHED_FIFO and SCHED_RR are |
5028 | * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, | 5028 | * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, |
5029 | * SCHED_BATCH and SCHED_IDLE is 0. | 5029 | * SCHED_BATCH and SCHED_IDLE is 0. |
5030 | */ | 5030 | */ |
5031 | if (param->sched_priority < 0 || | 5031 | if (param->sched_priority < 0 || |
5032 | (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || | 5032 | (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || |
5033 | (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) | 5033 | (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) |
5034 | return -EINVAL; | 5034 | return -EINVAL; |
5035 | if (rt_policy(policy) != (param->sched_priority != 0)) | 5035 | if (rt_policy(policy) != (param->sched_priority != 0)) |
5036 | return -EINVAL; | 5036 | return -EINVAL; |
5037 | 5037 | ||
5038 | /* | 5038 | /* |
5039 | * Allow unprivileged RT tasks to decrease priority: | 5039 | * Allow unprivileged RT tasks to decrease priority: |
5040 | */ | 5040 | */ |
5041 | if (user && !capable(CAP_SYS_NICE)) { | 5041 | if (user && !capable(CAP_SYS_NICE)) { |
5042 | if (rt_policy(policy)) { | 5042 | if (rt_policy(policy)) { |
5043 | unsigned long rlim_rtprio = | 5043 | unsigned long rlim_rtprio = |
5044 | task_rlimit(p, RLIMIT_RTPRIO); | 5044 | task_rlimit(p, RLIMIT_RTPRIO); |
5045 | 5045 | ||
5046 | /* can't set/change the rt policy */ | 5046 | /* can't set/change the rt policy */ |
5047 | if (policy != p->policy && !rlim_rtprio) | 5047 | if (policy != p->policy && !rlim_rtprio) |
5048 | return -EPERM; | 5048 | return -EPERM; |
5049 | 5049 | ||
5050 | /* can't increase priority */ | 5050 | /* can't increase priority */ |
5051 | if (param->sched_priority > p->rt_priority && | 5051 | if (param->sched_priority > p->rt_priority && |
5052 | param->sched_priority > rlim_rtprio) | 5052 | param->sched_priority > rlim_rtprio) |
5053 | return -EPERM; | 5053 | return -EPERM; |
5054 | } | 5054 | } |
5055 | 5055 | ||
5056 | /* | 5056 | /* |
5057 | * Treat SCHED_IDLE as nice 20. Only allow a switch to | 5057 | * Treat SCHED_IDLE as nice 20. Only allow a switch to |
5058 | * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. | 5058 | * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. |
5059 | */ | 5059 | */ |
5060 | if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { | 5060 | if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { |
5061 | if (!can_nice(p, TASK_NICE(p))) | 5061 | if (!can_nice(p, TASK_NICE(p))) |
5062 | return -EPERM; | 5062 | return -EPERM; |
5063 | } | 5063 | } |
5064 | 5064 | ||
5065 | /* can't change other user's priorities */ | 5065 | /* can't change other user's priorities */ |
5066 | if (!check_same_owner(p)) | 5066 | if (!check_same_owner(p)) |
5067 | return -EPERM; | 5067 | return -EPERM; |
5068 | 5068 | ||
5069 | /* Normal users shall not reset the sched_reset_on_fork flag */ | 5069 | /* Normal users shall not reset the sched_reset_on_fork flag */ |
5070 | if (p->sched_reset_on_fork && !reset_on_fork) | 5070 | if (p->sched_reset_on_fork && !reset_on_fork) |
5071 | return -EPERM; | 5071 | return -EPERM; |
5072 | } | 5072 | } |
5073 | 5073 | ||
5074 | if (user) { | 5074 | if (user) { |
5075 | retval = security_task_setscheduler(p); | 5075 | retval = security_task_setscheduler(p); |
5076 | if (retval) | 5076 | if (retval) |
5077 | return retval; | 5077 | return retval; |
5078 | } | 5078 | } |
5079 | 5079 | ||
5080 | /* | 5080 | /* |
5081 | * make sure no PI-waiters arrive (or leave) while we are | 5081 | * make sure no PI-waiters arrive (or leave) while we are |
5082 | * changing the priority of the task: | 5082 | * changing the priority of the task: |
5083 | * | 5083 | * |
5084 | * To be able to change p->policy safely, the appropriate | 5084 | * To be able to change p->policy safely, the appropriate |
5085 | * runqueue lock must be held. | 5085 | * runqueue lock must be held. |
5086 | */ | 5086 | */ |
5087 | rq = task_rq_lock(p, &flags); | 5087 | rq = task_rq_lock(p, &flags); |
5088 | 5088 | ||
5089 | /* | 5089 | /* |
5090 | * Changing the policy of the stop threads its a very bad idea | 5090 | * Changing the policy of the stop threads its a very bad idea |
5091 | */ | 5091 | */ |
5092 | if (p == rq->stop) { | 5092 | if (p == rq->stop) { |
5093 | task_rq_unlock(rq, p, &flags); | 5093 | task_rq_unlock(rq, p, &flags); |
5094 | return -EINVAL; | 5094 | return -EINVAL; |
5095 | } | 5095 | } |
5096 | 5096 | ||
5097 | /* | 5097 | /* |
5098 | * If not changing anything there's no need to proceed further: | 5098 | * If not changing anything there's no need to proceed further: |
5099 | */ | 5099 | */ |
5100 | if (unlikely(policy == p->policy && (!rt_policy(policy) || | 5100 | if (unlikely(policy == p->policy && (!rt_policy(policy) || |
5101 | param->sched_priority == p->rt_priority))) { | 5101 | param->sched_priority == p->rt_priority))) { |
5102 | 5102 | ||
5103 | __task_rq_unlock(rq); | 5103 | __task_rq_unlock(rq); |
5104 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 5104 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
5105 | return 0; | 5105 | return 0; |
5106 | } | 5106 | } |
5107 | 5107 | ||
5108 | #ifdef CONFIG_RT_GROUP_SCHED | 5108 | #ifdef CONFIG_RT_GROUP_SCHED |
5109 | if (user) { | 5109 | if (user) { |
5110 | /* | 5110 | /* |
5111 | * Do not allow realtime tasks into groups that have no runtime | 5111 | * Do not allow realtime tasks into groups that have no runtime |
5112 | * assigned. | 5112 | * assigned. |
5113 | */ | 5113 | */ |
5114 | if (rt_bandwidth_enabled() && rt_policy(policy) && | 5114 | if (rt_bandwidth_enabled() && rt_policy(policy) && |
5115 | task_group(p)->rt_bandwidth.rt_runtime == 0 && | 5115 | task_group(p)->rt_bandwidth.rt_runtime == 0 && |
5116 | !task_group_is_autogroup(task_group(p))) { | 5116 | !task_group_is_autogroup(task_group(p))) { |
5117 | task_rq_unlock(rq, p, &flags); | 5117 | task_rq_unlock(rq, p, &flags); |
5118 | return -EPERM; | 5118 | return -EPERM; |
5119 | } | 5119 | } |
5120 | } | 5120 | } |
5121 | #endif | 5121 | #endif |
5122 | 5122 | ||
5123 | /* recheck policy now with rq lock held */ | 5123 | /* recheck policy now with rq lock held */ |
5124 | if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { | 5124 | if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { |
5125 | policy = oldpolicy = -1; | 5125 | policy = oldpolicy = -1; |
5126 | task_rq_unlock(rq, p, &flags); | 5126 | task_rq_unlock(rq, p, &flags); |
5127 | goto recheck; | 5127 | goto recheck; |
5128 | } | 5128 | } |
5129 | on_rq = p->on_rq; | 5129 | on_rq = p->on_rq; |
5130 | running = task_current(rq, p); | 5130 | running = task_current(rq, p); |
5131 | if (on_rq) | 5131 | if (on_rq) |
5132 | deactivate_task(rq, p, 0); | 5132 | deactivate_task(rq, p, 0); |
5133 | if (running) | 5133 | if (running) |
5134 | p->sched_class->put_prev_task(rq, p); | 5134 | p->sched_class->put_prev_task(rq, p); |
5135 | 5135 | ||
5136 | p->sched_reset_on_fork = reset_on_fork; | 5136 | p->sched_reset_on_fork = reset_on_fork; |
5137 | 5137 | ||
5138 | oldprio = p->prio; | 5138 | oldprio = p->prio; |
5139 | prev_class = p->sched_class; | 5139 | prev_class = p->sched_class; |
5140 | __setscheduler(rq, p, policy, param->sched_priority); | 5140 | __setscheduler(rq, p, policy, param->sched_priority); |
5141 | 5141 | ||
5142 | if (running) | 5142 | if (running) |
5143 | p->sched_class->set_curr_task(rq); | 5143 | p->sched_class->set_curr_task(rq); |
5144 | if (on_rq) | 5144 | if (on_rq) |
5145 | activate_task(rq, p, 0); | 5145 | activate_task(rq, p, 0); |
5146 | 5146 | ||
5147 | check_class_changed(rq, p, prev_class, oldprio); | 5147 | check_class_changed(rq, p, prev_class, oldprio); |
5148 | task_rq_unlock(rq, p, &flags); | 5148 | task_rq_unlock(rq, p, &flags); |
5149 | 5149 | ||
5150 | rt_mutex_adjust_pi(p); | 5150 | rt_mutex_adjust_pi(p); |
5151 | 5151 | ||
5152 | return 0; | 5152 | return 0; |
5153 | } | 5153 | } |
5154 | 5154 | ||
5155 | /** | 5155 | /** |
5156 | * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. | 5156 | * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. |
5157 | * @p: the task in question. | 5157 | * @p: the task in question. |
5158 | * @policy: new policy. | 5158 | * @policy: new policy. |
5159 | * @param: structure containing the new RT priority. | 5159 | * @param: structure containing the new RT priority. |
5160 | * | 5160 | * |
5161 | * NOTE that the task may be already dead. | 5161 | * NOTE that the task may be already dead. |
5162 | */ | 5162 | */ |
5163 | int sched_setscheduler(struct task_struct *p, int policy, | 5163 | int sched_setscheduler(struct task_struct *p, int policy, |
5164 | const struct sched_param *param) | 5164 | const struct sched_param *param) |
5165 | { | 5165 | { |
5166 | return __sched_setscheduler(p, policy, param, true); | 5166 | return __sched_setscheduler(p, policy, param, true); |
5167 | } | 5167 | } |
5168 | EXPORT_SYMBOL_GPL(sched_setscheduler); | 5168 | EXPORT_SYMBOL_GPL(sched_setscheduler); |
5169 | 5169 | ||
5170 | /** | 5170 | /** |
5171 | * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. | 5171 | * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. |
5172 | * @p: the task in question. | 5172 | * @p: the task in question. |
5173 | * @policy: new policy. | 5173 | * @policy: new policy. |
5174 | * @param: structure containing the new RT priority. | 5174 | * @param: structure containing the new RT priority. |
5175 | * | 5175 | * |
5176 | * Just like sched_setscheduler, only don't bother checking if the | 5176 | * Just like sched_setscheduler, only don't bother checking if the |
5177 | * current context has permission. For example, this is needed in | 5177 | * current context has permission. For example, this is needed in |
5178 | * stop_machine(): we create temporary high priority worker threads, | 5178 | * stop_machine(): we create temporary high priority worker threads, |
5179 | * but our caller might not have that capability. | 5179 | * but our caller might not have that capability. |
5180 | */ | 5180 | */ |
5181 | int sched_setscheduler_nocheck(struct task_struct *p, int policy, | 5181 | int sched_setscheduler_nocheck(struct task_struct *p, int policy, |
5182 | const struct sched_param *param) | 5182 | const struct sched_param *param) |
5183 | { | 5183 | { |
5184 | return __sched_setscheduler(p, policy, param, false); | 5184 | return __sched_setscheduler(p, policy, param, false); |
5185 | } | 5185 | } |
5186 | 5186 | ||
5187 | static int | 5187 | static int |
5188 | do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) | 5188 | do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) |
5189 | { | 5189 | { |
5190 | struct sched_param lparam; | 5190 | struct sched_param lparam; |
5191 | struct task_struct *p; | 5191 | struct task_struct *p; |
5192 | int retval; | 5192 | int retval; |
5193 | 5193 | ||
5194 | if (!param || pid < 0) | 5194 | if (!param || pid < 0) |
5195 | return -EINVAL; | 5195 | return -EINVAL; |
5196 | if (copy_from_user(&lparam, param, sizeof(struct sched_param))) | 5196 | if (copy_from_user(&lparam, param, sizeof(struct sched_param))) |
5197 | return -EFAULT; | 5197 | return -EFAULT; |
5198 | 5198 | ||
5199 | rcu_read_lock(); | 5199 | rcu_read_lock(); |
5200 | retval = -ESRCH; | 5200 | retval = -ESRCH; |
5201 | p = find_process_by_pid(pid); | 5201 | p = find_process_by_pid(pid); |
5202 | if (p != NULL) | 5202 | if (p != NULL) |
5203 | retval = sched_setscheduler(p, policy, &lparam); | 5203 | retval = sched_setscheduler(p, policy, &lparam); |
5204 | rcu_read_unlock(); | 5204 | rcu_read_unlock(); |
5205 | 5205 | ||
5206 | return retval; | 5206 | return retval; |
5207 | } | 5207 | } |
5208 | 5208 | ||
5209 | /** | 5209 | /** |
5210 | * sys_sched_setscheduler - set/change the scheduler policy and RT priority | 5210 | * sys_sched_setscheduler - set/change the scheduler policy and RT priority |
5211 | * @pid: the pid in question. | 5211 | * @pid: the pid in question. |
5212 | * @policy: new policy. | 5212 | * @policy: new policy. |
5213 | * @param: structure containing the new RT priority. | 5213 | * @param: structure containing the new RT priority. |
5214 | */ | 5214 | */ |
5215 | SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, | 5215 | SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, |
5216 | struct sched_param __user *, param) | 5216 | struct sched_param __user *, param) |
5217 | { | 5217 | { |
5218 | /* negative values for policy are not valid */ | 5218 | /* negative values for policy are not valid */ |
5219 | if (policy < 0) | 5219 | if (policy < 0) |
5220 | return -EINVAL; | 5220 | return -EINVAL; |
5221 | 5221 | ||
5222 | return do_sched_setscheduler(pid, policy, param); | 5222 | return do_sched_setscheduler(pid, policy, param); |
5223 | } | 5223 | } |
5224 | 5224 | ||
5225 | /** | 5225 | /** |
5226 | * sys_sched_setparam - set/change the RT priority of a thread | 5226 | * sys_sched_setparam - set/change the RT priority of a thread |
5227 | * @pid: the pid in question. | 5227 | * @pid: the pid in question. |
5228 | * @param: structure containing the new RT priority. | 5228 | * @param: structure containing the new RT priority. |
5229 | */ | 5229 | */ |
5230 | SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) | 5230 | SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) |
5231 | { | 5231 | { |
5232 | return do_sched_setscheduler(pid, -1, param); | 5232 | return do_sched_setscheduler(pid, -1, param); |
5233 | } | 5233 | } |
5234 | 5234 | ||
5235 | /** | 5235 | /** |
5236 | * sys_sched_getscheduler - get the policy (scheduling class) of a thread | 5236 | * sys_sched_getscheduler - get the policy (scheduling class) of a thread |
5237 | * @pid: the pid in question. | 5237 | * @pid: the pid in question. |
5238 | */ | 5238 | */ |
5239 | SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) | 5239 | SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) |
5240 | { | 5240 | { |
5241 | struct task_struct *p; | 5241 | struct task_struct *p; |
5242 | int retval; | 5242 | int retval; |
5243 | 5243 | ||
5244 | if (pid < 0) | 5244 | if (pid < 0) |
5245 | return -EINVAL; | 5245 | return -EINVAL; |
5246 | 5246 | ||
5247 | retval = -ESRCH; | 5247 | retval = -ESRCH; |
5248 | rcu_read_lock(); | 5248 | rcu_read_lock(); |
5249 | p = find_process_by_pid(pid); | 5249 | p = find_process_by_pid(pid); |
5250 | if (p) { | 5250 | if (p) { |
5251 | retval = security_task_getscheduler(p); | 5251 | retval = security_task_getscheduler(p); |
5252 | if (!retval) | 5252 | if (!retval) |
5253 | retval = p->policy | 5253 | retval = p->policy |
5254 | | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); | 5254 | | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); |
5255 | } | 5255 | } |
5256 | rcu_read_unlock(); | 5256 | rcu_read_unlock(); |
5257 | return retval; | 5257 | return retval; |
5258 | } | 5258 | } |
5259 | 5259 | ||
5260 | /** | 5260 | /** |
5261 | * sys_sched_getparam - get the RT priority of a thread | 5261 | * sys_sched_getparam - get the RT priority of a thread |
5262 | * @pid: the pid in question. | 5262 | * @pid: the pid in question. |
5263 | * @param: structure containing the RT priority. | 5263 | * @param: structure containing the RT priority. |
5264 | */ | 5264 | */ |
5265 | SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) | 5265 | SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) |
5266 | { | 5266 | { |
5267 | struct sched_param lp; | 5267 | struct sched_param lp; |
5268 | struct task_struct *p; | 5268 | struct task_struct *p; |
5269 | int retval; | 5269 | int retval; |
5270 | 5270 | ||
5271 | if (!param || pid < 0) | 5271 | if (!param || pid < 0) |
5272 | return -EINVAL; | 5272 | return -EINVAL; |
5273 | 5273 | ||
5274 | rcu_read_lock(); | 5274 | rcu_read_lock(); |
5275 | p = find_process_by_pid(pid); | 5275 | p = find_process_by_pid(pid); |
5276 | retval = -ESRCH; | 5276 | retval = -ESRCH; |
5277 | if (!p) | 5277 | if (!p) |
5278 | goto out_unlock; | 5278 | goto out_unlock; |
5279 | 5279 | ||
5280 | retval = security_task_getscheduler(p); | 5280 | retval = security_task_getscheduler(p); |
5281 | if (retval) | 5281 | if (retval) |
5282 | goto out_unlock; | 5282 | goto out_unlock; |
5283 | 5283 | ||
5284 | lp.sched_priority = p->rt_priority; | 5284 | lp.sched_priority = p->rt_priority; |
5285 | rcu_read_unlock(); | 5285 | rcu_read_unlock(); |
5286 | 5286 | ||
5287 | /* | 5287 | /* |
5288 | * This one might sleep, we cannot do it with a spinlock held ... | 5288 | * This one might sleep, we cannot do it with a spinlock held ... |
5289 | */ | 5289 | */ |
5290 | retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; | 5290 | retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; |
5291 | 5291 | ||
5292 | return retval; | 5292 | return retval; |
5293 | 5293 | ||
5294 | out_unlock: | 5294 | out_unlock: |
5295 | rcu_read_unlock(); | 5295 | rcu_read_unlock(); |
5296 | return retval; | 5296 | return retval; |
5297 | } | 5297 | } |
5298 | 5298 | ||
5299 | long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) | 5299 | long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) |
5300 | { | 5300 | { |
5301 | cpumask_var_t cpus_allowed, new_mask; | 5301 | cpumask_var_t cpus_allowed, new_mask; |
5302 | struct task_struct *p; | 5302 | struct task_struct *p; |
5303 | int retval; | 5303 | int retval; |
5304 | 5304 | ||
5305 | get_online_cpus(); | 5305 | get_online_cpus(); |
5306 | rcu_read_lock(); | 5306 | rcu_read_lock(); |
5307 | 5307 | ||
5308 | p = find_process_by_pid(pid); | 5308 | p = find_process_by_pid(pid); |
5309 | if (!p) { | 5309 | if (!p) { |
5310 | rcu_read_unlock(); | 5310 | rcu_read_unlock(); |
5311 | put_online_cpus(); | 5311 | put_online_cpus(); |
5312 | return -ESRCH; | 5312 | return -ESRCH; |
5313 | } | 5313 | } |
5314 | 5314 | ||
5315 | /* Prevent p going away */ | 5315 | /* Prevent p going away */ |
5316 | get_task_struct(p); | 5316 | get_task_struct(p); |
5317 | rcu_read_unlock(); | 5317 | rcu_read_unlock(); |
5318 | 5318 | ||
5319 | if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { | 5319 | if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { |
5320 | retval = -ENOMEM; | 5320 | retval = -ENOMEM; |
5321 | goto out_put_task; | 5321 | goto out_put_task; |
5322 | } | 5322 | } |
5323 | if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { | 5323 | if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { |
5324 | retval = -ENOMEM; | 5324 | retval = -ENOMEM; |
5325 | goto out_free_cpus_allowed; | 5325 | goto out_free_cpus_allowed; |
5326 | } | 5326 | } |
5327 | retval = -EPERM; | 5327 | retval = -EPERM; |
5328 | if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE)) | 5328 | if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE)) |
5329 | goto out_unlock; | 5329 | goto out_unlock; |
5330 | 5330 | ||
5331 | retval = security_task_setscheduler(p); | 5331 | retval = security_task_setscheduler(p); |
5332 | if (retval) | 5332 | if (retval) |
5333 | goto out_unlock; | 5333 | goto out_unlock; |
5334 | 5334 | ||
5335 | cpuset_cpus_allowed(p, cpus_allowed); | 5335 | cpuset_cpus_allowed(p, cpus_allowed); |
5336 | cpumask_and(new_mask, in_mask, cpus_allowed); | 5336 | cpumask_and(new_mask, in_mask, cpus_allowed); |
5337 | again: | 5337 | again: |
5338 | retval = set_cpus_allowed_ptr(p, new_mask); | 5338 | retval = set_cpus_allowed_ptr(p, new_mask); |
5339 | 5339 | ||
5340 | if (!retval) { | 5340 | if (!retval) { |
5341 | cpuset_cpus_allowed(p, cpus_allowed); | 5341 | cpuset_cpus_allowed(p, cpus_allowed); |
5342 | if (!cpumask_subset(new_mask, cpus_allowed)) { | 5342 | if (!cpumask_subset(new_mask, cpus_allowed)) { |
5343 | /* | 5343 | /* |
5344 | * We must have raced with a concurrent cpuset | 5344 | * We must have raced with a concurrent cpuset |
5345 | * update. Just reset the cpus_allowed to the | 5345 | * update. Just reset the cpus_allowed to the |
5346 | * cpuset's cpus_allowed | 5346 | * cpuset's cpus_allowed |
5347 | */ | 5347 | */ |
5348 | cpumask_copy(new_mask, cpus_allowed); | 5348 | cpumask_copy(new_mask, cpus_allowed); |
5349 | goto again; | 5349 | goto again; |
5350 | } | 5350 | } |
5351 | } | 5351 | } |
5352 | out_unlock: | 5352 | out_unlock: |
5353 | free_cpumask_var(new_mask); | 5353 | free_cpumask_var(new_mask); |
5354 | out_free_cpus_allowed: | 5354 | out_free_cpus_allowed: |
5355 | free_cpumask_var(cpus_allowed); | 5355 | free_cpumask_var(cpus_allowed); |
5356 | out_put_task: | 5356 | out_put_task: |
5357 | put_task_struct(p); | 5357 | put_task_struct(p); |
5358 | put_online_cpus(); | 5358 | put_online_cpus(); |
5359 | return retval; | 5359 | return retval; |
5360 | } | 5360 | } |
5361 | 5361 | ||
5362 | static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, | 5362 | static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, |
5363 | struct cpumask *new_mask) | 5363 | struct cpumask *new_mask) |
5364 | { | 5364 | { |
5365 | if (len < cpumask_size()) | 5365 | if (len < cpumask_size()) |
5366 | cpumask_clear(new_mask); | 5366 | cpumask_clear(new_mask); |
5367 | else if (len > cpumask_size()) | 5367 | else if (len > cpumask_size()) |
5368 | len = cpumask_size(); | 5368 | len = cpumask_size(); |
5369 | 5369 | ||
5370 | return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; | 5370 | return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; |
5371 | } | 5371 | } |
5372 | 5372 | ||
5373 | /** | 5373 | /** |
5374 | * sys_sched_setaffinity - set the cpu affinity of a process | 5374 | * sys_sched_setaffinity - set the cpu affinity of a process |
5375 | * @pid: pid of the process | 5375 | * @pid: pid of the process |
5376 | * @len: length in bytes of the bitmask pointed to by user_mask_ptr | 5376 | * @len: length in bytes of the bitmask pointed to by user_mask_ptr |
5377 | * @user_mask_ptr: user-space pointer to the new cpu mask | 5377 | * @user_mask_ptr: user-space pointer to the new cpu mask |
5378 | */ | 5378 | */ |
5379 | SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, | 5379 | SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, |
5380 | unsigned long __user *, user_mask_ptr) | 5380 | unsigned long __user *, user_mask_ptr) |
5381 | { | 5381 | { |
5382 | cpumask_var_t new_mask; | 5382 | cpumask_var_t new_mask; |
5383 | int retval; | 5383 | int retval; |
5384 | 5384 | ||
5385 | if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) | 5385 | if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) |
5386 | return -ENOMEM; | 5386 | return -ENOMEM; |
5387 | 5387 | ||
5388 | retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); | 5388 | retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); |
5389 | if (retval == 0) | 5389 | if (retval == 0) |
5390 | retval = sched_setaffinity(pid, new_mask); | 5390 | retval = sched_setaffinity(pid, new_mask); |
5391 | free_cpumask_var(new_mask); | 5391 | free_cpumask_var(new_mask); |
5392 | return retval; | 5392 | return retval; |
5393 | } | 5393 | } |
5394 | 5394 | ||
5395 | long sched_getaffinity(pid_t pid, struct cpumask *mask) | 5395 | long sched_getaffinity(pid_t pid, struct cpumask *mask) |
5396 | { | 5396 | { |
5397 | struct task_struct *p; | 5397 | struct task_struct *p; |
5398 | unsigned long flags; | 5398 | unsigned long flags; |
5399 | int retval; | 5399 | int retval; |
5400 | 5400 | ||
5401 | get_online_cpus(); | 5401 | get_online_cpus(); |
5402 | rcu_read_lock(); | 5402 | rcu_read_lock(); |
5403 | 5403 | ||
5404 | retval = -ESRCH; | 5404 | retval = -ESRCH; |
5405 | p = find_process_by_pid(pid); | 5405 | p = find_process_by_pid(pid); |
5406 | if (!p) | 5406 | if (!p) |
5407 | goto out_unlock; | 5407 | goto out_unlock; |
5408 | 5408 | ||
5409 | retval = security_task_getscheduler(p); | 5409 | retval = security_task_getscheduler(p); |
5410 | if (retval) | 5410 | if (retval) |
5411 | goto out_unlock; | 5411 | goto out_unlock; |
5412 | 5412 | ||
5413 | raw_spin_lock_irqsave(&p->pi_lock, flags); | 5413 | raw_spin_lock_irqsave(&p->pi_lock, flags); |
5414 | cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); | 5414 | cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); |
5415 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); | 5415 | raw_spin_unlock_irqrestore(&p->pi_lock, flags); |
5416 | 5416 | ||
5417 | out_unlock: | 5417 | out_unlock: |
5418 | rcu_read_unlock(); | 5418 | rcu_read_unlock(); |
5419 | put_online_cpus(); | 5419 | put_online_cpus(); |
5420 | 5420 | ||
5421 | return retval; | 5421 | return retval; |
5422 | } | 5422 | } |
5423 | 5423 | ||
5424 | /** | 5424 | /** |
5425 | * sys_sched_getaffinity - get the cpu affinity of a process | 5425 | * sys_sched_getaffinity - get the cpu affinity of a process |
5426 | * @pid: pid of the process | 5426 | * @pid: pid of the process |
5427 | * @len: length in bytes of the bitmask pointed to by user_mask_ptr | 5427 | * @len: length in bytes of the bitmask pointed to by user_mask_ptr |
5428 | * @user_mask_ptr: user-space pointer to hold the current cpu mask | 5428 | * @user_mask_ptr: user-space pointer to hold the current cpu mask |
5429 | */ | 5429 | */ |
5430 | SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, | 5430 | SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, |
5431 | unsigned long __user *, user_mask_ptr) | 5431 | unsigned long __user *, user_mask_ptr) |
5432 | { | 5432 | { |
5433 | int ret; | 5433 | int ret; |
5434 | cpumask_var_t mask; | 5434 | cpumask_var_t mask; |
5435 | 5435 | ||
5436 | if ((len * BITS_PER_BYTE) < nr_cpu_ids) | 5436 | if ((len * BITS_PER_BYTE) < nr_cpu_ids) |
5437 | return -EINVAL; | 5437 | return -EINVAL; |
5438 | if (len & (sizeof(unsigned long)-1)) | 5438 | if (len & (sizeof(unsigned long)-1)) |
5439 | return -EINVAL; | 5439 | return -EINVAL; |
5440 | 5440 | ||
5441 | if (!alloc_cpumask_var(&mask, GFP_KERNEL)) | 5441 | if (!alloc_cpumask_var(&mask, GFP_KERNEL)) |
5442 | return -ENOMEM; | 5442 | return -ENOMEM; |
5443 | 5443 | ||
5444 | ret = sched_getaffinity(pid, mask); | 5444 | ret = sched_getaffinity(pid, mask); |
5445 | if (ret == 0) { | 5445 | if (ret == 0) { |
5446 | size_t retlen = min_t(size_t, len, cpumask_size()); | 5446 | size_t retlen = min_t(size_t, len, cpumask_size()); |
5447 | 5447 | ||
5448 | if (copy_to_user(user_mask_ptr, mask, retlen)) | 5448 | if (copy_to_user(user_mask_ptr, mask, retlen)) |
5449 | ret = -EFAULT; | 5449 | ret = -EFAULT; |
5450 | else | 5450 | else |
5451 | ret = retlen; | 5451 | ret = retlen; |
5452 | } | 5452 | } |
5453 | free_cpumask_var(mask); | 5453 | free_cpumask_var(mask); |
5454 | 5454 | ||
5455 | return ret; | 5455 | return ret; |
5456 | } | 5456 | } |
5457 | 5457 | ||
5458 | /** | 5458 | /** |
5459 | * sys_sched_yield - yield the current processor to other threads. | 5459 | * sys_sched_yield - yield the current processor to other threads. |
5460 | * | 5460 | * |
5461 | * This function yields the current CPU to other tasks. If there are no | 5461 | * This function yields the current CPU to other tasks. If there are no |
5462 | * other threads running on this CPU then this function will return. | 5462 | * other threads running on this CPU then this function will return. |
5463 | */ | 5463 | */ |
5464 | SYSCALL_DEFINE0(sched_yield) | 5464 | SYSCALL_DEFINE0(sched_yield) |
5465 | { | 5465 | { |
5466 | struct rq *rq = this_rq_lock(); | 5466 | struct rq *rq = this_rq_lock(); |
5467 | 5467 | ||
5468 | schedstat_inc(rq, yld_count); | 5468 | schedstat_inc(rq, yld_count); |
5469 | current->sched_class->yield_task(rq); | 5469 | current->sched_class->yield_task(rq); |
5470 | 5470 | ||
5471 | /* | 5471 | /* |
5472 | * Since we are going to call schedule() anyway, there's | 5472 | * Since we are going to call schedule() anyway, there's |
5473 | * no need to preempt or enable interrupts: | 5473 | * no need to preempt or enable interrupts: |
5474 | */ | 5474 | */ |
5475 | __release(rq->lock); | 5475 | __release(rq->lock); |
5476 | spin_release(&rq->lock.dep_map, 1, _THIS_IP_); | 5476 | spin_release(&rq->lock.dep_map, 1, _THIS_IP_); |
5477 | do_raw_spin_unlock(&rq->lock); | 5477 | do_raw_spin_unlock(&rq->lock); |
5478 | preempt_enable_no_resched(); | 5478 | preempt_enable_no_resched(); |
5479 | 5479 | ||
5480 | schedule(); | 5480 | schedule(); |
5481 | 5481 | ||
5482 | return 0; | 5482 | return 0; |
5483 | } | 5483 | } |
5484 | 5484 | ||
5485 | static inline int should_resched(void) | 5485 | static inline int should_resched(void) |
5486 | { | 5486 | { |
5487 | return need_resched() && !(preempt_count() & PREEMPT_ACTIVE); | 5487 | return need_resched() && !(preempt_count() & PREEMPT_ACTIVE); |
5488 | } | 5488 | } |
5489 | 5489 | ||
5490 | static void __cond_resched(void) | 5490 | static void __cond_resched(void) |
5491 | { | 5491 | { |
5492 | add_preempt_count(PREEMPT_ACTIVE); | 5492 | add_preempt_count(PREEMPT_ACTIVE); |
5493 | schedule(); | 5493 | schedule(); |
5494 | sub_preempt_count(PREEMPT_ACTIVE); | 5494 | sub_preempt_count(PREEMPT_ACTIVE); |
5495 | } | 5495 | } |
5496 | 5496 | ||
5497 | int __sched _cond_resched(void) | 5497 | int __sched _cond_resched(void) |
5498 | { | 5498 | { |
5499 | if (should_resched()) { | 5499 | if (should_resched()) { |
5500 | __cond_resched(); | 5500 | __cond_resched(); |
5501 | return 1; | 5501 | return 1; |
5502 | } | 5502 | } |
5503 | return 0; | 5503 | return 0; |
5504 | } | 5504 | } |
5505 | EXPORT_SYMBOL(_cond_resched); | 5505 | EXPORT_SYMBOL(_cond_resched); |
5506 | 5506 | ||
5507 | /* | 5507 | /* |
5508 | * __cond_resched_lock() - if a reschedule is pending, drop the given lock, | 5508 | * __cond_resched_lock() - if a reschedule is pending, drop the given lock, |
5509 | * call schedule, and on return reacquire the lock. | 5509 | * call schedule, and on return reacquire the lock. |
5510 | * | 5510 | * |
5511 | * This works OK both with and without CONFIG_PREEMPT. We do strange low-level | 5511 | * This works OK both with and without CONFIG_PREEMPT. We do strange low-level |
5512 | * operations here to prevent schedule() from being called twice (once via | 5512 | * operations here to prevent schedule() from being called twice (once via |
5513 | * spin_unlock(), once by hand). | 5513 | * spin_unlock(), once by hand). |
5514 | */ | 5514 | */ |
5515 | int __cond_resched_lock(spinlock_t *lock) | 5515 | int __cond_resched_lock(spinlock_t *lock) |
5516 | { | 5516 | { |
5517 | int resched = should_resched(); | 5517 | int resched = should_resched(); |
5518 | int ret = 0; | 5518 | int ret = 0; |
5519 | 5519 | ||
5520 | lockdep_assert_held(lock); | 5520 | lockdep_assert_held(lock); |
5521 | 5521 | ||
5522 | if (spin_needbreak(lock) || resched) { | 5522 | if (spin_needbreak(lock) || resched) { |
5523 | spin_unlock(lock); | 5523 | spin_unlock(lock); |
5524 | if (resched) | 5524 | if (resched) |
5525 | __cond_resched(); | 5525 | __cond_resched(); |
5526 | else | 5526 | else |
5527 | cpu_relax(); | 5527 | cpu_relax(); |
5528 | ret = 1; | 5528 | ret = 1; |
5529 | spin_lock(lock); | 5529 | spin_lock(lock); |
5530 | } | 5530 | } |
5531 | return ret; | 5531 | return ret; |
5532 | } | 5532 | } |
5533 | EXPORT_SYMBOL(__cond_resched_lock); | 5533 | EXPORT_SYMBOL(__cond_resched_lock); |
5534 | 5534 | ||
5535 | int __sched __cond_resched_softirq(void) | 5535 | int __sched __cond_resched_softirq(void) |
5536 | { | 5536 | { |
5537 | BUG_ON(!in_softirq()); | 5537 | BUG_ON(!in_softirq()); |
5538 | 5538 | ||
5539 | if (should_resched()) { | 5539 | if (should_resched()) { |
5540 | local_bh_enable(); | 5540 | local_bh_enable(); |
5541 | __cond_resched(); | 5541 | __cond_resched(); |
5542 | local_bh_disable(); | 5542 | local_bh_disable(); |
5543 | return 1; | 5543 | return 1; |
5544 | } | 5544 | } |
5545 | return 0; | 5545 | return 0; |
5546 | } | 5546 | } |
5547 | EXPORT_SYMBOL(__cond_resched_softirq); | 5547 | EXPORT_SYMBOL(__cond_resched_softirq); |
5548 | 5548 | ||
5549 | /** | 5549 | /** |
5550 | * yield - yield the current processor to other threads. | 5550 | * yield - yield the current processor to other threads. |
5551 | * | 5551 | * |
5552 | * This is a shortcut for kernel-space yielding - it marks the | 5552 | * This is a shortcut for kernel-space yielding - it marks the |
5553 | * thread runnable and calls sys_sched_yield(). | 5553 | * thread runnable and calls sys_sched_yield(). |
5554 | */ | 5554 | */ |
5555 | void __sched yield(void) | 5555 | void __sched yield(void) |
5556 | { | 5556 | { |
5557 | set_current_state(TASK_RUNNING); | 5557 | set_current_state(TASK_RUNNING); |
5558 | sys_sched_yield(); | 5558 | sys_sched_yield(); |
5559 | } | 5559 | } |
5560 | EXPORT_SYMBOL(yield); | 5560 | EXPORT_SYMBOL(yield); |
5561 | 5561 | ||
5562 | /** | 5562 | /** |
5563 | * yield_to - yield the current processor to another thread in | 5563 | * yield_to - yield the current processor to another thread in |
5564 | * your thread group, or accelerate that thread toward the | 5564 | * your thread group, or accelerate that thread toward the |
5565 | * processor it's on. | 5565 | * processor it's on. |
5566 | * @p: target task | 5566 | * @p: target task |
5567 | * @preempt: whether task preemption is allowed or not | 5567 | * @preempt: whether task preemption is allowed or not |
5568 | * | 5568 | * |
5569 | * It's the caller's job to ensure that the target task struct | 5569 | * It's the caller's job to ensure that the target task struct |
5570 | * can't go away on us before we can do any checks. | 5570 | * can't go away on us before we can do any checks. |
5571 | * | 5571 | * |
5572 | * Returns true if we indeed boosted the target task. | 5572 | * Returns true if we indeed boosted the target task. |
5573 | */ | 5573 | */ |
5574 | bool __sched yield_to(struct task_struct *p, bool preempt) | 5574 | bool __sched yield_to(struct task_struct *p, bool preempt) |
5575 | { | 5575 | { |
5576 | struct task_struct *curr = current; | 5576 | struct task_struct *curr = current; |
5577 | struct rq *rq, *p_rq; | 5577 | struct rq *rq, *p_rq; |
5578 | unsigned long flags; | 5578 | unsigned long flags; |
5579 | bool yielded = 0; | 5579 | bool yielded = 0; |
5580 | 5580 | ||
5581 | local_irq_save(flags); | 5581 | local_irq_save(flags); |
5582 | rq = this_rq(); | 5582 | rq = this_rq(); |
5583 | 5583 | ||
5584 | again: | 5584 | again: |
5585 | p_rq = task_rq(p); | 5585 | p_rq = task_rq(p); |
5586 | double_rq_lock(rq, p_rq); | 5586 | double_rq_lock(rq, p_rq); |
5587 | while (task_rq(p) != p_rq) { | 5587 | while (task_rq(p) != p_rq) { |
5588 | double_rq_unlock(rq, p_rq); | 5588 | double_rq_unlock(rq, p_rq); |
5589 | goto again; | 5589 | goto again; |
5590 | } | 5590 | } |
5591 | 5591 | ||
5592 | if (!curr->sched_class->yield_to_task) | 5592 | if (!curr->sched_class->yield_to_task) |
5593 | goto out; | 5593 | goto out; |
5594 | 5594 | ||
5595 | if (curr->sched_class != p->sched_class) | 5595 | if (curr->sched_class != p->sched_class) |
5596 | goto out; | 5596 | goto out; |
5597 | 5597 | ||
5598 | if (task_running(p_rq, p) || p->state) | 5598 | if (task_running(p_rq, p) || p->state) |
5599 | goto out; | 5599 | goto out; |
5600 | 5600 | ||
5601 | yielded = curr->sched_class->yield_to_task(rq, p, preempt); | 5601 | yielded = curr->sched_class->yield_to_task(rq, p, preempt); |
5602 | if (yielded) { | 5602 | if (yielded) { |
5603 | schedstat_inc(rq, yld_count); | 5603 | schedstat_inc(rq, yld_count); |
5604 | /* | 5604 | /* |
5605 | * Make p's CPU reschedule; pick_next_entity takes care of | 5605 | * Make p's CPU reschedule; pick_next_entity takes care of |
5606 | * fairness. | 5606 | * fairness. |
5607 | */ | 5607 | */ |
5608 | if (preempt && rq != p_rq) | 5608 | if (preempt && rq != p_rq) |
5609 | resched_task(p_rq->curr); | 5609 | resched_task(p_rq->curr); |
5610 | } | 5610 | } |
5611 | 5611 | ||
5612 | out: | 5612 | out: |
5613 | double_rq_unlock(rq, p_rq); | 5613 | double_rq_unlock(rq, p_rq); |
5614 | local_irq_restore(flags); | 5614 | local_irq_restore(flags); |
5615 | 5615 | ||
5616 | if (yielded) | 5616 | if (yielded) |
5617 | schedule(); | 5617 | schedule(); |
5618 | 5618 | ||
5619 | return yielded; | 5619 | return yielded; |
5620 | } | 5620 | } |
5621 | EXPORT_SYMBOL_GPL(yield_to); | 5621 | EXPORT_SYMBOL_GPL(yield_to); |
5622 | 5622 | ||
5623 | /* | 5623 | /* |
5624 | * This task is about to go to sleep on IO. Increment rq->nr_iowait so | 5624 | * This task is about to go to sleep on IO. Increment rq->nr_iowait so |
5625 | * that process accounting knows that this is a task in IO wait state. | 5625 | * that process accounting knows that this is a task in IO wait state. |
5626 | */ | 5626 | */ |
5627 | void __sched io_schedule(void) | 5627 | void __sched io_schedule(void) |
5628 | { | 5628 | { |
5629 | struct rq *rq = raw_rq(); | 5629 | struct rq *rq = raw_rq(); |
5630 | 5630 | ||
5631 | delayacct_blkio_start(); | 5631 | delayacct_blkio_start(); |
5632 | atomic_inc(&rq->nr_iowait); | 5632 | atomic_inc(&rq->nr_iowait); |
5633 | blk_flush_plug(current); | 5633 | blk_flush_plug(current); |
5634 | current->in_iowait = 1; | 5634 | current->in_iowait = 1; |
5635 | schedule(); | 5635 | schedule(); |
5636 | current->in_iowait = 0; | 5636 | current->in_iowait = 0; |
5637 | atomic_dec(&rq->nr_iowait); | 5637 | atomic_dec(&rq->nr_iowait); |
5638 | delayacct_blkio_end(); | 5638 | delayacct_blkio_end(); |
5639 | } | 5639 | } |
5640 | EXPORT_SYMBOL(io_schedule); | 5640 | EXPORT_SYMBOL(io_schedule); |
5641 | 5641 | ||
5642 | long __sched io_schedule_timeout(long timeout) | 5642 | long __sched io_schedule_timeout(long timeout) |
5643 | { | 5643 | { |
5644 | struct rq *rq = raw_rq(); | 5644 | struct rq *rq = raw_rq(); |
5645 | long ret; | 5645 | long ret; |
5646 | 5646 | ||
5647 | delayacct_blkio_start(); | 5647 | delayacct_blkio_start(); |
5648 | atomic_inc(&rq->nr_iowait); | 5648 | atomic_inc(&rq->nr_iowait); |
5649 | blk_flush_plug(current); | 5649 | blk_flush_plug(current); |
5650 | current->in_iowait = 1; | 5650 | current->in_iowait = 1; |
5651 | ret = schedule_timeout(timeout); | 5651 | ret = schedule_timeout(timeout); |
5652 | current->in_iowait = 0; | 5652 | current->in_iowait = 0; |
5653 | atomic_dec(&rq->nr_iowait); | 5653 | atomic_dec(&rq->nr_iowait); |
5654 | delayacct_blkio_end(); | 5654 | delayacct_blkio_end(); |
5655 | return ret; | 5655 | return ret; |
5656 | } | 5656 | } |
5657 | 5657 | ||
5658 | /** | 5658 | /** |
5659 | * sys_sched_get_priority_max - return maximum RT priority. | 5659 | * sys_sched_get_priority_max - return maximum RT priority. |
5660 | * @policy: scheduling class. | 5660 | * @policy: scheduling class. |
5661 | * | 5661 | * |
5662 | * this syscall returns the maximum rt_priority that can be used | 5662 | * this syscall returns the maximum rt_priority that can be used |
5663 | * by a given scheduling class. | 5663 | * by a given scheduling class. |
5664 | */ | 5664 | */ |
5665 | SYSCALL_DEFINE1(sched_get_priority_max, int, policy) | 5665 | SYSCALL_DEFINE1(sched_get_priority_max, int, policy) |
5666 | { | 5666 | { |
5667 | int ret = -EINVAL; | 5667 | int ret = -EINVAL; |
5668 | 5668 | ||
5669 | switch (policy) { | 5669 | switch (policy) { |
5670 | case SCHED_FIFO: | 5670 | case SCHED_FIFO: |
5671 | case SCHED_RR: | 5671 | case SCHED_RR: |
5672 | ret = MAX_USER_RT_PRIO-1; | 5672 | ret = MAX_USER_RT_PRIO-1; |
5673 | break; | 5673 | break; |
5674 | case SCHED_NORMAL: | 5674 | case SCHED_NORMAL: |
5675 | case SCHED_BATCH: | 5675 | case SCHED_BATCH: |
5676 | case SCHED_IDLE: | 5676 | case SCHED_IDLE: |
5677 | ret = 0; | 5677 | ret = 0; |
5678 | break; | 5678 | break; |
5679 | } | 5679 | } |
5680 | return ret; | 5680 | return ret; |
5681 | } | 5681 | } |
5682 | 5682 | ||
5683 | /** | 5683 | /** |
5684 | * sys_sched_get_priority_min - return minimum RT priority. | 5684 | * sys_sched_get_priority_min - return minimum RT priority. |
5685 | * @policy: scheduling class. | 5685 | * @policy: scheduling class. |
5686 | * | 5686 | * |
5687 | * this syscall returns the minimum rt_priority that can be used | 5687 | * this syscall returns the minimum rt_priority that can be used |
5688 | * by a given scheduling class. | 5688 | * by a given scheduling class. |
5689 | */ | 5689 | */ |
5690 | SYSCALL_DEFINE1(sched_get_priority_min, int, policy) | 5690 | SYSCALL_DEFINE1(sched_get_priority_min, int, policy) |
5691 | { | 5691 | { |
5692 | int ret = -EINVAL; | 5692 | int ret = -EINVAL; |
5693 | 5693 | ||
5694 | switch (policy) { | 5694 | switch (policy) { |
5695 | case SCHED_FIFO: | 5695 | case SCHED_FIFO: |
5696 | case SCHED_RR: | 5696 | case SCHED_RR: |
5697 | ret = 1; | 5697 | ret = 1; |
5698 | break; | 5698 | break; |
5699 | case SCHED_NORMAL: | 5699 | case SCHED_NORMAL: |
5700 | case SCHED_BATCH: | 5700 | case SCHED_BATCH: |
5701 | case SCHED_IDLE: | 5701 | case SCHED_IDLE: |
5702 | ret = 0; | 5702 | ret = 0; |
5703 | } | 5703 | } |
5704 | return ret; | 5704 | return ret; |
5705 | } | 5705 | } |
5706 | 5706 | ||
5707 | /** | 5707 | /** |
5708 | * sys_sched_rr_get_interval - return the default timeslice of a process. | 5708 | * sys_sched_rr_get_interval - return the default timeslice of a process. |
5709 | * @pid: pid of the process. | 5709 | * @pid: pid of the process. |
5710 | * @interval: userspace pointer to the timeslice value. | 5710 | * @interval: userspace pointer to the timeslice value. |
5711 | * | 5711 | * |
5712 | * this syscall writes the default timeslice value of a given process | 5712 | * this syscall writes the default timeslice value of a given process |
5713 | * into the user-space timespec buffer. A value of '0' means infinity. | 5713 | * into the user-space timespec buffer. A value of '0' means infinity. |
5714 | */ | 5714 | */ |
5715 | SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, | 5715 | SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, |
5716 | struct timespec __user *, interval) | 5716 | struct timespec __user *, interval) |
5717 | { | 5717 | { |
5718 | struct task_struct *p; | 5718 | struct task_struct *p; |
5719 | unsigned int time_slice; | 5719 | unsigned int time_slice; |
5720 | unsigned long flags; | 5720 | unsigned long flags; |
5721 | struct rq *rq; | 5721 | struct rq *rq; |
5722 | int retval; | 5722 | int retval; |
5723 | struct timespec t; | 5723 | struct timespec t; |
5724 | 5724 | ||
5725 | if (pid < 0) | 5725 | if (pid < 0) |
5726 | return -EINVAL; | 5726 | return -EINVAL; |
5727 | 5727 | ||
5728 | retval = -ESRCH; | 5728 | retval = -ESRCH; |
5729 | rcu_read_lock(); | 5729 | rcu_read_lock(); |
5730 | p = find_process_by_pid(pid); | 5730 | p = find_process_by_pid(pid); |
5731 | if (!p) | 5731 | if (!p) |
5732 | goto out_unlock; | 5732 | goto out_unlock; |
5733 | 5733 | ||
5734 | retval = security_task_getscheduler(p); | 5734 | retval = security_task_getscheduler(p); |
5735 | if (retval) | 5735 | if (retval) |
5736 | goto out_unlock; | 5736 | goto out_unlock; |
5737 | 5737 | ||
5738 | rq = task_rq_lock(p, &flags); | 5738 | rq = task_rq_lock(p, &flags); |
5739 | time_slice = p->sched_class->get_rr_interval(rq, p); | 5739 | time_slice = p->sched_class->get_rr_interval(rq, p); |
5740 | task_rq_unlock(rq, p, &flags); | 5740 | task_rq_unlock(rq, p, &flags); |
5741 | 5741 | ||
5742 | rcu_read_unlock(); | 5742 | rcu_read_unlock(); |
5743 | jiffies_to_timespec(time_slice, &t); | 5743 | jiffies_to_timespec(time_slice, &t); |
5744 | retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; | 5744 | retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; |
5745 | return retval; | 5745 | return retval; |
5746 | 5746 | ||
5747 | out_unlock: | 5747 | out_unlock: |
5748 | rcu_read_unlock(); | 5748 | rcu_read_unlock(); |
5749 | return retval; | 5749 | return retval; |
5750 | } | 5750 | } |
5751 | 5751 | ||
5752 | static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; | 5752 | static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; |
5753 | 5753 | ||
5754 | void sched_show_task(struct task_struct *p) | 5754 | void sched_show_task(struct task_struct *p) |
5755 | { | 5755 | { |
5756 | unsigned long free = 0; | 5756 | unsigned long free = 0; |
5757 | unsigned state; | 5757 | unsigned state; |
5758 | 5758 | ||
5759 | state = p->state ? __ffs(p->state) + 1 : 0; | 5759 | state = p->state ? __ffs(p->state) + 1 : 0; |
5760 | printk(KERN_INFO "%-15.15s %c", p->comm, | 5760 | printk(KERN_INFO "%-15.15s %c", p->comm, |
5761 | state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); | 5761 | state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); |
5762 | #if BITS_PER_LONG == 32 | 5762 | #if BITS_PER_LONG == 32 |
5763 | if (state == TASK_RUNNING) | 5763 | if (state == TASK_RUNNING) |
5764 | printk(KERN_CONT " running "); | 5764 | printk(KERN_CONT " running "); |
5765 | else | 5765 | else |
5766 | printk(KERN_CONT " %08lx ", thread_saved_pc(p)); | 5766 | printk(KERN_CONT " %08lx ", thread_saved_pc(p)); |
5767 | #else | 5767 | #else |
5768 | if (state == TASK_RUNNING) | 5768 | if (state == TASK_RUNNING) |
5769 | printk(KERN_CONT " running task "); | 5769 | printk(KERN_CONT " running task "); |
5770 | else | 5770 | else |
5771 | printk(KERN_CONT " %016lx ", thread_saved_pc(p)); | 5771 | printk(KERN_CONT " %016lx ", thread_saved_pc(p)); |
5772 | #endif | 5772 | #endif |
5773 | #ifdef CONFIG_DEBUG_STACK_USAGE | 5773 | #ifdef CONFIG_DEBUG_STACK_USAGE |
5774 | free = stack_not_used(p); | 5774 | free = stack_not_used(p); |
5775 | #endif | 5775 | #endif |
5776 | printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, | 5776 | printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, |
5777 | task_pid_nr(p), task_pid_nr(p->real_parent), | 5777 | task_pid_nr(p), task_pid_nr(p->real_parent), |
5778 | (unsigned long)task_thread_info(p)->flags); | 5778 | (unsigned long)task_thread_info(p)->flags); |
5779 | 5779 | ||
5780 | show_stack(p, NULL); | 5780 | show_stack(p, NULL); |
5781 | } | 5781 | } |
5782 | 5782 | ||
5783 | void show_state_filter(unsigned long state_filter) | 5783 | void show_state_filter(unsigned long state_filter) |
5784 | { | 5784 | { |
5785 | struct task_struct *g, *p; | 5785 | struct task_struct *g, *p; |
5786 | 5786 | ||
5787 | #if BITS_PER_LONG == 32 | 5787 | #if BITS_PER_LONG == 32 |
5788 | printk(KERN_INFO | 5788 | printk(KERN_INFO |
5789 | " task PC stack pid father\n"); | 5789 | " task PC stack pid father\n"); |
5790 | #else | 5790 | #else |
5791 | printk(KERN_INFO | 5791 | printk(KERN_INFO |
5792 | " task PC stack pid father\n"); | 5792 | " task PC stack pid father\n"); |
5793 | #endif | 5793 | #endif |
5794 | read_lock(&tasklist_lock); | 5794 | read_lock(&tasklist_lock); |
5795 | do_each_thread(g, p) { | 5795 | do_each_thread(g, p) { |
5796 | /* | 5796 | /* |
5797 | * reset the NMI-timeout, listing all files on a slow | 5797 | * reset the NMI-timeout, listing all files on a slow |
5798 | * console might take a lot of time: | 5798 | * console might take a lot of time: |
5799 | */ | 5799 | */ |
5800 | touch_nmi_watchdog(); | 5800 | touch_nmi_watchdog(); |
5801 | if (!state_filter || (p->state & state_filter)) | 5801 | if (!state_filter || (p->state & state_filter)) |
5802 | sched_show_task(p); | 5802 | sched_show_task(p); |
5803 | } while_each_thread(g, p); | 5803 | } while_each_thread(g, p); |
5804 | 5804 | ||
5805 | touch_all_softlockup_watchdogs(); | 5805 | touch_all_softlockup_watchdogs(); |
5806 | 5806 | ||
5807 | #ifdef CONFIG_SCHED_DEBUG | 5807 | #ifdef CONFIG_SCHED_DEBUG |
5808 | sysrq_sched_debug_show(); | 5808 | sysrq_sched_debug_show(); |
5809 | #endif | 5809 | #endif |
5810 | read_unlock(&tasklist_lock); | 5810 | read_unlock(&tasklist_lock); |
5811 | /* | 5811 | /* |
5812 | * Only show locks if all tasks are dumped: | 5812 | * Only show locks if all tasks are dumped: |
5813 | */ | 5813 | */ |
5814 | if (!state_filter) | 5814 | if (!state_filter) |
5815 | debug_show_all_locks(); | 5815 | debug_show_all_locks(); |
5816 | } | 5816 | } |
5817 | 5817 | ||
5818 | void __cpuinit init_idle_bootup_task(struct task_struct *idle) | 5818 | void __cpuinit init_idle_bootup_task(struct task_struct *idle) |
5819 | { | 5819 | { |
5820 | idle->sched_class = &idle_sched_class; | 5820 | idle->sched_class = &idle_sched_class; |
5821 | } | 5821 | } |
5822 | 5822 | ||
5823 | /** | 5823 | /** |
5824 | * init_idle - set up an idle thread for a given CPU | 5824 | * init_idle - set up an idle thread for a given CPU |
5825 | * @idle: task in question | 5825 | * @idle: task in question |
5826 | * @cpu: cpu the idle task belongs to | 5826 | * @cpu: cpu the idle task belongs to |
5827 | * | 5827 | * |
5828 | * NOTE: this function does not set the idle thread's NEED_RESCHED | 5828 | * NOTE: this function does not set the idle thread's NEED_RESCHED |
5829 | * flag, to make booting more robust. | 5829 | * flag, to make booting more robust. |
5830 | */ | 5830 | */ |
5831 | void __cpuinit init_idle(struct task_struct *idle, int cpu) | 5831 | void __cpuinit init_idle(struct task_struct *idle, int cpu) |
5832 | { | 5832 | { |
5833 | struct rq *rq = cpu_rq(cpu); | 5833 | struct rq *rq = cpu_rq(cpu); |
5834 | unsigned long flags; | 5834 | unsigned long flags; |
5835 | 5835 | ||
5836 | raw_spin_lock_irqsave(&rq->lock, flags); | 5836 | raw_spin_lock_irqsave(&rq->lock, flags); |
5837 | 5837 | ||
5838 | __sched_fork(idle); | 5838 | __sched_fork(idle); |
5839 | idle->state = TASK_RUNNING; | 5839 | idle->state = TASK_RUNNING; |
5840 | idle->se.exec_start = sched_clock(); | 5840 | idle->se.exec_start = sched_clock(); |
5841 | 5841 | ||
5842 | cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); | 5842 | cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); |
5843 | /* | 5843 | /* |
5844 | * We're having a chicken and egg problem, even though we are | 5844 | * We're having a chicken and egg problem, even though we are |
5845 | * holding rq->lock, the cpu isn't yet set to this cpu so the | 5845 | * holding rq->lock, the cpu isn't yet set to this cpu so the |
5846 | * lockdep check in task_group() will fail. | 5846 | * lockdep check in task_group() will fail. |
5847 | * | 5847 | * |
5848 | * Similar case to sched_fork(). / Alternatively we could | 5848 | * Similar case to sched_fork(). / Alternatively we could |
5849 | * use task_rq_lock() here and obtain the other rq->lock. | 5849 | * use task_rq_lock() here and obtain the other rq->lock. |
5850 | * | 5850 | * |
5851 | * Silence PROVE_RCU | 5851 | * Silence PROVE_RCU |
5852 | */ | 5852 | */ |
5853 | rcu_read_lock(); | 5853 | rcu_read_lock(); |
5854 | __set_task_cpu(idle, cpu); | 5854 | __set_task_cpu(idle, cpu); |
5855 | rcu_read_unlock(); | 5855 | rcu_read_unlock(); |
5856 | 5856 | ||
5857 | rq->curr = rq->idle = idle; | 5857 | rq->curr = rq->idle = idle; |
5858 | #if defined(CONFIG_SMP) | 5858 | #if defined(CONFIG_SMP) |
5859 | idle->on_cpu = 1; | 5859 | idle->on_cpu = 1; |
5860 | #endif | 5860 | #endif |
5861 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 5861 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
5862 | 5862 | ||
5863 | /* Set the preempt count _outside_ the spinlocks! */ | 5863 | /* Set the preempt count _outside_ the spinlocks! */ |
5864 | #if defined(CONFIG_PREEMPT) | 5864 | #if defined(CONFIG_PREEMPT) |
5865 | task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); | 5865 | task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); |
5866 | #else | 5866 | #else |
5867 | task_thread_info(idle)->preempt_count = 0; | 5867 | task_thread_info(idle)->preempt_count = 0; |
5868 | #endif | 5868 | #endif |
5869 | /* | 5869 | /* |
5870 | * The idle tasks have their own, simple scheduling class: | 5870 | * The idle tasks have their own, simple scheduling class: |
5871 | */ | 5871 | */ |
5872 | idle->sched_class = &idle_sched_class; | 5872 | idle->sched_class = &idle_sched_class; |
5873 | ftrace_graph_init_idle_task(idle, cpu); | 5873 | ftrace_graph_init_idle_task(idle, cpu); |
5874 | } | 5874 | } |
5875 | 5875 | ||
5876 | /* | 5876 | /* |
5877 | * In a system that switches off the HZ timer nohz_cpu_mask | 5877 | * In a system that switches off the HZ timer nohz_cpu_mask |
5878 | * indicates which cpus entered this state. This is used | 5878 | * indicates which cpus entered this state. This is used |
5879 | * in the rcu update to wait only for active cpus. For system | 5879 | * in the rcu update to wait only for active cpus. For system |
5880 | * which do not switch off the HZ timer nohz_cpu_mask should | 5880 | * which do not switch off the HZ timer nohz_cpu_mask should |
5881 | * always be CPU_BITS_NONE. | 5881 | * always be CPU_BITS_NONE. |
5882 | */ | 5882 | */ |
5883 | cpumask_var_t nohz_cpu_mask; | 5883 | cpumask_var_t nohz_cpu_mask; |
5884 | 5884 | ||
5885 | /* | 5885 | /* |
5886 | * Increase the granularity value when there are more CPUs, | 5886 | * Increase the granularity value when there are more CPUs, |
5887 | * because with more CPUs the 'effective latency' as visible | 5887 | * because with more CPUs the 'effective latency' as visible |
5888 | * to users decreases. But the relationship is not linear, | 5888 | * to users decreases. But the relationship is not linear, |
5889 | * so pick a second-best guess by going with the log2 of the | 5889 | * so pick a second-best guess by going with the log2 of the |
5890 | * number of CPUs. | 5890 | * number of CPUs. |
5891 | * | 5891 | * |
5892 | * This idea comes from the SD scheduler of Con Kolivas: | 5892 | * This idea comes from the SD scheduler of Con Kolivas: |
5893 | */ | 5893 | */ |
5894 | static int get_update_sysctl_factor(void) | 5894 | static int get_update_sysctl_factor(void) |
5895 | { | 5895 | { |
5896 | unsigned int cpus = min_t(int, num_online_cpus(), 8); | 5896 | unsigned int cpus = min_t(int, num_online_cpus(), 8); |
5897 | unsigned int factor; | 5897 | unsigned int factor; |
5898 | 5898 | ||
5899 | switch (sysctl_sched_tunable_scaling) { | 5899 | switch (sysctl_sched_tunable_scaling) { |
5900 | case SCHED_TUNABLESCALING_NONE: | 5900 | case SCHED_TUNABLESCALING_NONE: |
5901 | factor = 1; | 5901 | factor = 1; |
5902 | break; | 5902 | break; |
5903 | case SCHED_TUNABLESCALING_LINEAR: | 5903 | case SCHED_TUNABLESCALING_LINEAR: |
5904 | factor = cpus; | 5904 | factor = cpus; |
5905 | break; | 5905 | break; |
5906 | case SCHED_TUNABLESCALING_LOG: | 5906 | case SCHED_TUNABLESCALING_LOG: |
5907 | default: | 5907 | default: |
5908 | factor = 1 + ilog2(cpus); | 5908 | factor = 1 + ilog2(cpus); |
5909 | break; | 5909 | break; |
5910 | } | 5910 | } |
5911 | 5911 | ||
5912 | return factor; | 5912 | return factor; |
5913 | } | 5913 | } |
5914 | 5914 | ||
5915 | static void update_sysctl(void) | 5915 | static void update_sysctl(void) |
5916 | { | 5916 | { |
5917 | unsigned int factor = get_update_sysctl_factor(); | 5917 | unsigned int factor = get_update_sysctl_factor(); |
5918 | 5918 | ||
5919 | #define SET_SYSCTL(name) \ | 5919 | #define SET_SYSCTL(name) \ |
5920 | (sysctl_##name = (factor) * normalized_sysctl_##name) | 5920 | (sysctl_##name = (factor) * normalized_sysctl_##name) |
5921 | SET_SYSCTL(sched_min_granularity); | 5921 | SET_SYSCTL(sched_min_granularity); |
5922 | SET_SYSCTL(sched_latency); | 5922 | SET_SYSCTL(sched_latency); |
5923 | SET_SYSCTL(sched_wakeup_granularity); | 5923 | SET_SYSCTL(sched_wakeup_granularity); |
5924 | #undef SET_SYSCTL | 5924 | #undef SET_SYSCTL |
5925 | } | 5925 | } |
5926 | 5926 | ||
5927 | static inline void sched_init_granularity(void) | 5927 | static inline void sched_init_granularity(void) |
5928 | { | 5928 | { |
5929 | update_sysctl(); | 5929 | update_sysctl(); |
5930 | } | 5930 | } |
5931 | 5931 | ||
5932 | #ifdef CONFIG_SMP | 5932 | #ifdef CONFIG_SMP |
5933 | /* | 5933 | /* |
5934 | * This is how migration works: | 5934 | * This is how migration works: |
5935 | * | 5935 | * |
5936 | * 1) we invoke migration_cpu_stop() on the target CPU using | 5936 | * 1) we invoke migration_cpu_stop() on the target CPU using |
5937 | * stop_one_cpu(). | 5937 | * stop_one_cpu(). |
5938 | * 2) stopper starts to run (implicitly forcing the migrated thread | 5938 | * 2) stopper starts to run (implicitly forcing the migrated thread |
5939 | * off the CPU) | 5939 | * off the CPU) |
5940 | * 3) it checks whether the migrated task is still in the wrong runqueue. | 5940 | * 3) it checks whether the migrated task is still in the wrong runqueue. |
5941 | * 4) if it's in the wrong runqueue then the migration thread removes | 5941 | * 4) if it's in the wrong runqueue then the migration thread removes |
5942 | * it and puts it into the right queue. | 5942 | * it and puts it into the right queue. |
5943 | * 5) stopper completes and stop_one_cpu() returns and the migration | 5943 | * 5) stopper completes and stop_one_cpu() returns and the migration |
5944 | * is done. | 5944 | * is done. |
5945 | */ | 5945 | */ |
5946 | 5946 | ||
5947 | /* | 5947 | /* |
5948 | * Change a given task's CPU affinity. Migrate the thread to a | 5948 | * Change a given task's CPU affinity. Migrate the thread to a |
5949 | * proper CPU and schedule it away if the CPU it's executing on | 5949 | * proper CPU and schedule it away if the CPU it's executing on |
5950 | * is removed from the allowed bitmask. | 5950 | * is removed from the allowed bitmask. |
5951 | * | 5951 | * |
5952 | * NOTE: the caller must have a valid reference to the task, the | 5952 | * NOTE: the caller must have a valid reference to the task, the |
5953 | * task must not exit() & deallocate itself prematurely. The | 5953 | * task must not exit() & deallocate itself prematurely. The |
5954 | * call is not atomic; no spinlocks may be held. | 5954 | * call is not atomic; no spinlocks may be held. |
5955 | */ | 5955 | */ |
5956 | int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) | 5956 | int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) |
5957 | { | 5957 | { |
5958 | unsigned long flags; | 5958 | unsigned long flags; |
5959 | struct rq *rq; | 5959 | struct rq *rq; |
5960 | unsigned int dest_cpu; | 5960 | unsigned int dest_cpu; |
5961 | int ret = 0; | 5961 | int ret = 0; |
5962 | 5962 | ||
5963 | rq = task_rq_lock(p, &flags); | 5963 | rq = task_rq_lock(p, &flags); |
5964 | 5964 | ||
5965 | if (!cpumask_intersects(new_mask, cpu_active_mask)) { | 5965 | if (!cpumask_intersects(new_mask, cpu_active_mask)) { |
5966 | ret = -EINVAL; | 5966 | ret = -EINVAL; |
5967 | goto out; | 5967 | goto out; |
5968 | } | 5968 | } |
5969 | 5969 | ||
5970 | if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && | 5970 | if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && |
5971 | !cpumask_equal(&p->cpus_allowed, new_mask))) { | 5971 | !cpumask_equal(&p->cpus_allowed, new_mask))) { |
5972 | ret = -EINVAL; | 5972 | ret = -EINVAL; |
5973 | goto out; | 5973 | goto out; |
5974 | } | 5974 | } |
5975 | 5975 | ||
5976 | if (p->sched_class->set_cpus_allowed) | 5976 | if (p->sched_class->set_cpus_allowed) |
5977 | p->sched_class->set_cpus_allowed(p, new_mask); | 5977 | p->sched_class->set_cpus_allowed(p, new_mask); |
5978 | else { | 5978 | else { |
5979 | cpumask_copy(&p->cpus_allowed, new_mask); | 5979 | cpumask_copy(&p->cpus_allowed, new_mask); |
5980 | p->rt.nr_cpus_allowed = cpumask_weight(new_mask); | 5980 | p->rt.nr_cpus_allowed = cpumask_weight(new_mask); |
5981 | } | 5981 | } |
5982 | 5982 | ||
5983 | /* Can the task run on the task's current CPU? If so, we're done */ | 5983 | /* Can the task run on the task's current CPU? If so, we're done */ |
5984 | if (cpumask_test_cpu(task_cpu(p), new_mask)) | 5984 | if (cpumask_test_cpu(task_cpu(p), new_mask)) |
5985 | goto out; | 5985 | goto out; |
5986 | 5986 | ||
5987 | dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); | 5987 | dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); |
5988 | if (need_migrate_task(p)) { | 5988 | if (need_migrate_task(p)) { |
5989 | struct migration_arg arg = { p, dest_cpu }; | 5989 | struct migration_arg arg = { p, dest_cpu }; |
5990 | /* Need help from migration thread: drop lock and wait. */ | 5990 | /* Need help from migration thread: drop lock and wait. */ |
5991 | task_rq_unlock(rq, p, &flags); | 5991 | task_rq_unlock(rq, p, &flags); |
5992 | stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); | 5992 | stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); |
5993 | tlb_migrate_finish(p->mm); | 5993 | tlb_migrate_finish(p->mm); |
5994 | return 0; | 5994 | return 0; |
5995 | } | 5995 | } |
5996 | out: | 5996 | out: |
5997 | task_rq_unlock(rq, p, &flags); | 5997 | task_rq_unlock(rq, p, &flags); |
5998 | 5998 | ||
5999 | return ret; | 5999 | return ret; |
6000 | } | 6000 | } |
6001 | EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); | 6001 | EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); |
6002 | 6002 | ||
6003 | /* | 6003 | /* |
6004 | * Move (not current) task off this cpu, onto dest cpu. We're doing | 6004 | * Move (not current) task off this cpu, onto dest cpu. We're doing |
6005 | * this because either it can't run here any more (set_cpus_allowed() | 6005 | * this because either it can't run here any more (set_cpus_allowed() |
6006 | * away from this CPU, or CPU going down), or because we're | 6006 | * away from this CPU, or CPU going down), or because we're |
6007 | * attempting to rebalance this task on exec (sched_exec). | 6007 | * attempting to rebalance this task on exec (sched_exec). |
6008 | * | 6008 | * |
6009 | * So we race with normal scheduler movements, but that's OK, as long | 6009 | * So we race with normal scheduler movements, but that's OK, as long |
6010 | * as the task is no longer on this CPU. | 6010 | * as the task is no longer on this CPU. |
6011 | * | 6011 | * |
6012 | * Returns non-zero if task was successfully migrated. | 6012 | * Returns non-zero if task was successfully migrated. |
6013 | */ | 6013 | */ |
6014 | static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) | 6014 | static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) |
6015 | { | 6015 | { |
6016 | struct rq *rq_dest, *rq_src; | 6016 | struct rq *rq_dest, *rq_src; |
6017 | int ret = 0; | 6017 | int ret = 0; |
6018 | 6018 | ||
6019 | if (unlikely(!cpu_active(dest_cpu))) | 6019 | if (unlikely(!cpu_active(dest_cpu))) |
6020 | return ret; | 6020 | return ret; |
6021 | 6021 | ||
6022 | rq_src = cpu_rq(src_cpu); | 6022 | rq_src = cpu_rq(src_cpu); |
6023 | rq_dest = cpu_rq(dest_cpu); | 6023 | rq_dest = cpu_rq(dest_cpu); |
6024 | 6024 | ||
6025 | raw_spin_lock(&p->pi_lock); | 6025 | raw_spin_lock(&p->pi_lock); |
6026 | double_rq_lock(rq_src, rq_dest); | 6026 | double_rq_lock(rq_src, rq_dest); |
6027 | /* Already moved. */ | 6027 | /* Already moved. */ |
6028 | if (task_cpu(p) != src_cpu) | 6028 | if (task_cpu(p) != src_cpu) |
6029 | goto done; | 6029 | goto done; |
6030 | /* Affinity changed (again). */ | 6030 | /* Affinity changed (again). */ |
6031 | if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) | 6031 | if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) |
6032 | goto fail; | 6032 | goto fail; |
6033 | 6033 | ||
6034 | /* | 6034 | /* |
6035 | * If we're not on a rq, the next wake-up will ensure we're | 6035 | * If we're not on a rq, the next wake-up will ensure we're |
6036 | * placed properly. | 6036 | * placed properly. |
6037 | */ | 6037 | */ |
6038 | if (p->on_rq) { | 6038 | if (p->on_rq) { |
6039 | deactivate_task(rq_src, p, 0); | 6039 | deactivate_task(rq_src, p, 0); |
6040 | set_task_cpu(p, dest_cpu); | 6040 | set_task_cpu(p, dest_cpu); |
6041 | activate_task(rq_dest, p, 0); | 6041 | activate_task(rq_dest, p, 0); |
6042 | check_preempt_curr(rq_dest, p, 0); | 6042 | check_preempt_curr(rq_dest, p, 0); |
6043 | } | 6043 | } |
6044 | done: | 6044 | done: |
6045 | ret = 1; | 6045 | ret = 1; |
6046 | fail: | 6046 | fail: |
6047 | double_rq_unlock(rq_src, rq_dest); | 6047 | double_rq_unlock(rq_src, rq_dest); |
6048 | raw_spin_unlock(&p->pi_lock); | 6048 | raw_spin_unlock(&p->pi_lock); |
6049 | return ret; | 6049 | return ret; |
6050 | } | 6050 | } |
6051 | 6051 | ||
6052 | /* | 6052 | /* |
6053 | * migration_cpu_stop - this will be executed by a highprio stopper thread | 6053 | * migration_cpu_stop - this will be executed by a highprio stopper thread |
6054 | * and performs thread migration by bumping thread off CPU then | 6054 | * and performs thread migration by bumping thread off CPU then |
6055 | * 'pushing' onto another runqueue. | 6055 | * 'pushing' onto another runqueue. |
6056 | */ | 6056 | */ |
6057 | static int migration_cpu_stop(void *data) | 6057 | static int migration_cpu_stop(void *data) |
6058 | { | 6058 | { |
6059 | struct migration_arg *arg = data; | 6059 | struct migration_arg *arg = data; |
6060 | 6060 | ||
6061 | /* | 6061 | /* |
6062 | * The original target cpu might have gone down and we might | 6062 | * The original target cpu might have gone down and we might |
6063 | * be on another cpu but it doesn't matter. | 6063 | * be on another cpu but it doesn't matter. |
6064 | */ | 6064 | */ |
6065 | local_irq_disable(); | 6065 | local_irq_disable(); |
6066 | __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); | 6066 | __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); |
6067 | local_irq_enable(); | 6067 | local_irq_enable(); |
6068 | return 0; | 6068 | return 0; |
6069 | } | 6069 | } |
6070 | 6070 | ||
6071 | #ifdef CONFIG_HOTPLUG_CPU | 6071 | #ifdef CONFIG_HOTPLUG_CPU |
6072 | 6072 | ||
6073 | /* | 6073 | /* |
6074 | * Ensures that the idle task is using init_mm right before its cpu goes | 6074 | * Ensures that the idle task is using init_mm right before its cpu goes |
6075 | * offline. | 6075 | * offline. |
6076 | */ | 6076 | */ |
6077 | void idle_task_exit(void) | 6077 | void idle_task_exit(void) |
6078 | { | 6078 | { |
6079 | struct mm_struct *mm = current->active_mm; | 6079 | struct mm_struct *mm = current->active_mm; |
6080 | 6080 | ||
6081 | BUG_ON(cpu_online(smp_processor_id())); | 6081 | BUG_ON(cpu_online(smp_processor_id())); |
6082 | 6082 | ||
6083 | if (mm != &init_mm) | 6083 | if (mm != &init_mm) |
6084 | switch_mm(mm, &init_mm, current); | 6084 | switch_mm(mm, &init_mm, current); |
6085 | mmdrop(mm); | 6085 | mmdrop(mm); |
6086 | } | 6086 | } |
6087 | 6087 | ||
6088 | /* | 6088 | /* |
6089 | * While a dead CPU has no uninterruptible tasks queued at this point, | 6089 | * While a dead CPU has no uninterruptible tasks queued at this point, |
6090 | * it might still have a nonzero ->nr_uninterruptible counter, because | 6090 | * it might still have a nonzero ->nr_uninterruptible counter, because |
6091 | * for performance reasons the counter is not stricly tracking tasks to | 6091 | * for performance reasons the counter is not stricly tracking tasks to |
6092 | * their home CPUs. So we just add the counter to another CPU's counter, | 6092 | * their home CPUs. So we just add the counter to another CPU's counter, |
6093 | * to keep the global sum constant after CPU-down: | 6093 | * to keep the global sum constant after CPU-down: |
6094 | */ | 6094 | */ |
6095 | static void migrate_nr_uninterruptible(struct rq *rq_src) | 6095 | static void migrate_nr_uninterruptible(struct rq *rq_src) |
6096 | { | 6096 | { |
6097 | struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); | 6097 | struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); |
6098 | 6098 | ||
6099 | rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; | 6099 | rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; |
6100 | rq_src->nr_uninterruptible = 0; | 6100 | rq_src->nr_uninterruptible = 0; |
6101 | } | 6101 | } |
6102 | 6102 | ||
6103 | /* | 6103 | /* |
6104 | * remove the tasks which were accounted by rq from calc_load_tasks. | 6104 | * remove the tasks which were accounted by rq from calc_load_tasks. |
6105 | */ | 6105 | */ |
6106 | static void calc_global_load_remove(struct rq *rq) | 6106 | static void calc_global_load_remove(struct rq *rq) |
6107 | { | 6107 | { |
6108 | atomic_long_sub(rq->calc_load_active, &calc_load_tasks); | 6108 | atomic_long_sub(rq->calc_load_active, &calc_load_tasks); |
6109 | rq->calc_load_active = 0; | 6109 | rq->calc_load_active = 0; |
6110 | } | 6110 | } |
6111 | 6111 | ||
6112 | /* | 6112 | /* |
6113 | * Migrate all tasks from the rq, sleeping tasks will be migrated by | 6113 | * Migrate all tasks from the rq, sleeping tasks will be migrated by |
6114 | * try_to_wake_up()->select_task_rq(). | 6114 | * try_to_wake_up()->select_task_rq(). |
6115 | * | 6115 | * |
6116 | * Called with rq->lock held even though we'er in stop_machine() and | 6116 | * Called with rq->lock held even though we'er in stop_machine() and |
6117 | * there's no concurrency possible, we hold the required locks anyway | 6117 | * there's no concurrency possible, we hold the required locks anyway |
6118 | * because of lock validation efforts. | 6118 | * because of lock validation efforts. |
6119 | */ | 6119 | */ |
6120 | static void migrate_tasks(unsigned int dead_cpu) | 6120 | static void migrate_tasks(unsigned int dead_cpu) |
6121 | { | 6121 | { |
6122 | struct rq *rq = cpu_rq(dead_cpu); | 6122 | struct rq *rq = cpu_rq(dead_cpu); |
6123 | struct task_struct *next, *stop = rq->stop; | 6123 | struct task_struct *next, *stop = rq->stop; |
6124 | int dest_cpu; | 6124 | int dest_cpu; |
6125 | 6125 | ||
6126 | /* | 6126 | /* |
6127 | * Fudge the rq selection such that the below task selection loop | 6127 | * Fudge the rq selection such that the below task selection loop |
6128 | * doesn't get stuck on the currently eligible stop task. | 6128 | * doesn't get stuck on the currently eligible stop task. |
6129 | * | 6129 | * |
6130 | * We're currently inside stop_machine() and the rq is either stuck | 6130 | * We're currently inside stop_machine() and the rq is either stuck |
6131 | * in the stop_machine_cpu_stop() loop, or we're executing this code, | 6131 | * in the stop_machine_cpu_stop() loop, or we're executing this code, |
6132 | * either way we should never end up calling schedule() until we're | 6132 | * either way we should never end up calling schedule() until we're |
6133 | * done here. | 6133 | * done here. |
6134 | */ | 6134 | */ |
6135 | rq->stop = NULL; | 6135 | rq->stop = NULL; |
6136 | 6136 | ||
6137 | for ( ; ; ) { | 6137 | for ( ; ; ) { |
6138 | /* | 6138 | /* |
6139 | * There's this thread running, bail when that's the only | 6139 | * There's this thread running, bail when that's the only |
6140 | * remaining thread. | 6140 | * remaining thread. |
6141 | */ | 6141 | */ |
6142 | if (rq->nr_running == 1) | 6142 | if (rq->nr_running == 1) |
6143 | break; | 6143 | break; |
6144 | 6144 | ||
6145 | next = pick_next_task(rq); | 6145 | next = pick_next_task(rq); |
6146 | BUG_ON(!next); | 6146 | BUG_ON(!next); |
6147 | next->sched_class->put_prev_task(rq, next); | 6147 | next->sched_class->put_prev_task(rq, next); |
6148 | 6148 | ||
6149 | /* Find suitable destination for @next, with force if needed. */ | 6149 | /* Find suitable destination for @next, with force if needed. */ |
6150 | dest_cpu = select_fallback_rq(dead_cpu, next); | 6150 | dest_cpu = select_fallback_rq(dead_cpu, next); |
6151 | raw_spin_unlock(&rq->lock); | 6151 | raw_spin_unlock(&rq->lock); |
6152 | 6152 | ||
6153 | __migrate_task(next, dead_cpu, dest_cpu); | 6153 | __migrate_task(next, dead_cpu, dest_cpu); |
6154 | 6154 | ||
6155 | raw_spin_lock(&rq->lock); | 6155 | raw_spin_lock(&rq->lock); |
6156 | } | 6156 | } |
6157 | 6157 | ||
6158 | rq->stop = stop; | 6158 | rq->stop = stop; |
6159 | } | 6159 | } |
6160 | 6160 | ||
6161 | #endif /* CONFIG_HOTPLUG_CPU */ | 6161 | #endif /* CONFIG_HOTPLUG_CPU */ |
6162 | 6162 | ||
6163 | #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) | 6163 | #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) |
6164 | 6164 | ||
6165 | static struct ctl_table sd_ctl_dir[] = { | 6165 | static struct ctl_table sd_ctl_dir[] = { |
6166 | { | 6166 | { |
6167 | .procname = "sched_domain", | 6167 | .procname = "sched_domain", |
6168 | .mode = 0555, | 6168 | .mode = 0555, |
6169 | }, | 6169 | }, |
6170 | {} | 6170 | {} |
6171 | }; | 6171 | }; |
6172 | 6172 | ||
6173 | static struct ctl_table sd_ctl_root[] = { | 6173 | static struct ctl_table sd_ctl_root[] = { |
6174 | { | 6174 | { |
6175 | .procname = "kernel", | 6175 | .procname = "kernel", |
6176 | .mode = 0555, | 6176 | .mode = 0555, |
6177 | .child = sd_ctl_dir, | 6177 | .child = sd_ctl_dir, |
6178 | }, | 6178 | }, |
6179 | {} | 6179 | {} |
6180 | }; | 6180 | }; |
6181 | 6181 | ||
6182 | static struct ctl_table *sd_alloc_ctl_entry(int n) | 6182 | static struct ctl_table *sd_alloc_ctl_entry(int n) |
6183 | { | 6183 | { |
6184 | struct ctl_table *entry = | 6184 | struct ctl_table *entry = |
6185 | kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); | 6185 | kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); |
6186 | 6186 | ||
6187 | return entry; | 6187 | return entry; |
6188 | } | 6188 | } |
6189 | 6189 | ||
6190 | static void sd_free_ctl_entry(struct ctl_table **tablep) | 6190 | static void sd_free_ctl_entry(struct ctl_table **tablep) |
6191 | { | 6191 | { |
6192 | struct ctl_table *entry; | 6192 | struct ctl_table *entry; |
6193 | 6193 | ||
6194 | /* | 6194 | /* |
6195 | * In the intermediate directories, both the child directory and | 6195 | * In the intermediate directories, both the child directory and |
6196 | * procname are dynamically allocated and could fail but the mode | 6196 | * procname are dynamically allocated and could fail but the mode |
6197 | * will always be set. In the lowest directory the names are | 6197 | * will always be set. In the lowest directory the names are |
6198 | * static strings and all have proc handlers. | 6198 | * static strings and all have proc handlers. |
6199 | */ | 6199 | */ |
6200 | for (entry = *tablep; entry->mode; entry++) { | 6200 | for (entry = *tablep; entry->mode; entry++) { |
6201 | if (entry->child) | 6201 | if (entry->child) |
6202 | sd_free_ctl_entry(&entry->child); | 6202 | sd_free_ctl_entry(&entry->child); |
6203 | if (entry->proc_handler == NULL) | 6203 | if (entry->proc_handler == NULL) |
6204 | kfree(entry->procname); | 6204 | kfree(entry->procname); |
6205 | } | 6205 | } |
6206 | 6206 | ||
6207 | kfree(*tablep); | 6207 | kfree(*tablep); |
6208 | *tablep = NULL; | 6208 | *tablep = NULL; |
6209 | } | 6209 | } |
6210 | 6210 | ||
6211 | static void | 6211 | static void |
6212 | set_table_entry(struct ctl_table *entry, | 6212 | set_table_entry(struct ctl_table *entry, |
6213 | const char *procname, void *data, int maxlen, | 6213 | const char *procname, void *data, int maxlen, |
6214 | mode_t mode, proc_handler *proc_handler) | 6214 | mode_t mode, proc_handler *proc_handler) |
6215 | { | 6215 | { |
6216 | entry->procname = procname; | 6216 | entry->procname = procname; |
6217 | entry->data = data; | 6217 | entry->data = data; |
6218 | entry->maxlen = maxlen; | 6218 | entry->maxlen = maxlen; |
6219 | entry->mode = mode; | 6219 | entry->mode = mode; |
6220 | entry->proc_handler = proc_handler; | 6220 | entry->proc_handler = proc_handler; |
6221 | } | 6221 | } |
6222 | 6222 | ||
6223 | static struct ctl_table * | 6223 | static struct ctl_table * |
6224 | sd_alloc_ctl_domain_table(struct sched_domain *sd) | 6224 | sd_alloc_ctl_domain_table(struct sched_domain *sd) |
6225 | { | 6225 | { |
6226 | struct ctl_table *table = sd_alloc_ctl_entry(13); | 6226 | struct ctl_table *table = sd_alloc_ctl_entry(13); |
6227 | 6227 | ||
6228 | if (table == NULL) | 6228 | if (table == NULL) |
6229 | return NULL; | 6229 | return NULL; |
6230 | 6230 | ||
6231 | set_table_entry(&table[0], "min_interval", &sd->min_interval, | 6231 | set_table_entry(&table[0], "min_interval", &sd->min_interval, |
6232 | sizeof(long), 0644, proc_doulongvec_minmax); | 6232 | sizeof(long), 0644, proc_doulongvec_minmax); |
6233 | set_table_entry(&table[1], "max_interval", &sd->max_interval, | 6233 | set_table_entry(&table[1], "max_interval", &sd->max_interval, |
6234 | sizeof(long), 0644, proc_doulongvec_minmax); | 6234 | sizeof(long), 0644, proc_doulongvec_minmax); |
6235 | set_table_entry(&table[2], "busy_idx", &sd->busy_idx, | 6235 | set_table_entry(&table[2], "busy_idx", &sd->busy_idx, |
6236 | sizeof(int), 0644, proc_dointvec_minmax); | 6236 | sizeof(int), 0644, proc_dointvec_minmax); |
6237 | set_table_entry(&table[3], "idle_idx", &sd->idle_idx, | 6237 | set_table_entry(&table[3], "idle_idx", &sd->idle_idx, |
6238 | sizeof(int), 0644, proc_dointvec_minmax); | 6238 | sizeof(int), 0644, proc_dointvec_minmax); |
6239 | set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, | 6239 | set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, |
6240 | sizeof(int), 0644, proc_dointvec_minmax); | 6240 | sizeof(int), 0644, proc_dointvec_minmax); |
6241 | set_table_entry(&table[5], "wake_idx", &sd->wake_idx, | 6241 | set_table_entry(&table[5], "wake_idx", &sd->wake_idx, |
6242 | sizeof(int), 0644, proc_dointvec_minmax); | 6242 | sizeof(int), 0644, proc_dointvec_minmax); |
6243 | set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, | 6243 | set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, |
6244 | sizeof(int), 0644, proc_dointvec_minmax); | 6244 | sizeof(int), 0644, proc_dointvec_minmax); |
6245 | set_table_entry(&table[7], "busy_factor", &sd->busy_factor, | 6245 | set_table_entry(&table[7], "busy_factor", &sd->busy_factor, |
6246 | sizeof(int), 0644, proc_dointvec_minmax); | 6246 | sizeof(int), 0644, proc_dointvec_minmax); |
6247 | set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, | 6247 | set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, |
6248 | sizeof(int), 0644, proc_dointvec_minmax); | 6248 | sizeof(int), 0644, proc_dointvec_minmax); |
6249 | set_table_entry(&table[9], "cache_nice_tries", | 6249 | set_table_entry(&table[9], "cache_nice_tries", |
6250 | &sd->cache_nice_tries, | 6250 | &sd->cache_nice_tries, |
6251 | sizeof(int), 0644, proc_dointvec_minmax); | 6251 | sizeof(int), 0644, proc_dointvec_minmax); |
6252 | set_table_entry(&table[10], "flags", &sd->flags, | 6252 | set_table_entry(&table[10], "flags", &sd->flags, |
6253 | sizeof(int), 0644, proc_dointvec_minmax); | 6253 | sizeof(int), 0644, proc_dointvec_minmax); |
6254 | set_table_entry(&table[11], "name", sd->name, | 6254 | set_table_entry(&table[11], "name", sd->name, |
6255 | CORENAME_MAX_SIZE, 0444, proc_dostring); | 6255 | CORENAME_MAX_SIZE, 0444, proc_dostring); |
6256 | /* &table[12] is terminator */ | 6256 | /* &table[12] is terminator */ |
6257 | 6257 | ||
6258 | return table; | 6258 | return table; |
6259 | } | 6259 | } |
6260 | 6260 | ||
6261 | static ctl_table *sd_alloc_ctl_cpu_table(int cpu) | 6261 | static ctl_table *sd_alloc_ctl_cpu_table(int cpu) |
6262 | { | 6262 | { |
6263 | struct ctl_table *entry, *table; | 6263 | struct ctl_table *entry, *table; |
6264 | struct sched_domain *sd; | 6264 | struct sched_domain *sd; |
6265 | int domain_num = 0, i; | 6265 | int domain_num = 0, i; |
6266 | char buf[32]; | 6266 | char buf[32]; |
6267 | 6267 | ||
6268 | for_each_domain(cpu, sd) | 6268 | for_each_domain(cpu, sd) |
6269 | domain_num++; | 6269 | domain_num++; |
6270 | entry = table = sd_alloc_ctl_entry(domain_num + 1); | 6270 | entry = table = sd_alloc_ctl_entry(domain_num + 1); |
6271 | if (table == NULL) | 6271 | if (table == NULL) |
6272 | return NULL; | 6272 | return NULL; |
6273 | 6273 | ||
6274 | i = 0; | 6274 | i = 0; |
6275 | for_each_domain(cpu, sd) { | 6275 | for_each_domain(cpu, sd) { |
6276 | snprintf(buf, 32, "domain%d", i); | 6276 | snprintf(buf, 32, "domain%d", i); |
6277 | entry->procname = kstrdup(buf, GFP_KERNEL); | 6277 | entry->procname = kstrdup(buf, GFP_KERNEL); |
6278 | entry->mode = 0555; | 6278 | entry->mode = 0555; |
6279 | entry->child = sd_alloc_ctl_domain_table(sd); | 6279 | entry->child = sd_alloc_ctl_domain_table(sd); |
6280 | entry++; | 6280 | entry++; |
6281 | i++; | 6281 | i++; |
6282 | } | 6282 | } |
6283 | return table; | 6283 | return table; |
6284 | } | 6284 | } |
6285 | 6285 | ||
6286 | static struct ctl_table_header *sd_sysctl_header; | 6286 | static struct ctl_table_header *sd_sysctl_header; |
6287 | static void register_sched_domain_sysctl(void) | 6287 | static void register_sched_domain_sysctl(void) |
6288 | { | 6288 | { |
6289 | int i, cpu_num = num_possible_cpus(); | 6289 | int i, cpu_num = num_possible_cpus(); |
6290 | struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); | 6290 | struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); |
6291 | char buf[32]; | 6291 | char buf[32]; |
6292 | 6292 | ||
6293 | WARN_ON(sd_ctl_dir[0].child); | 6293 | WARN_ON(sd_ctl_dir[0].child); |
6294 | sd_ctl_dir[0].child = entry; | 6294 | sd_ctl_dir[0].child = entry; |
6295 | 6295 | ||
6296 | if (entry == NULL) | 6296 | if (entry == NULL) |
6297 | return; | 6297 | return; |
6298 | 6298 | ||
6299 | for_each_possible_cpu(i) { | 6299 | for_each_possible_cpu(i) { |
6300 | snprintf(buf, 32, "cpu%d", i); | 6300 | snprintf(buf, 32, "cpu%d", i); |
6301 | entry->procname = kstrdup(buf, GFP_KERNEL); | 6301 | entry->procname = kstrdup(buf, GFP_KERNEL); |
6302 | entry->mode = 0555; | 6302 | entry->mode = 0555; |
6303 | entry->child = sd_alloc_ctl_cpu_table(i); | 6303 | entry->child = sd_alloc_ctl_cpu_table(i); |
6304 | entry++; | 6304 | entry++; |
6305 | } | 6305 | } |
6306 | 6306 | ||
6307 | WARN_ON(sd_sysctl_header); | 6307 | WARN_ON(sd_sysctl_header); |
6308 | sd_sysctl_header = register_sysctl_table(sd_ctl_root); | 6308 | sd_sysctl_header = register_sysctl_table(sd_ctl_root); |
6309 | } | 6309 | } |
6310 | 6310 | ||
6311 | /* may be called multiple times per register */ | 6311 | /* may be called multiple times per register */ |
6312 | static void unregister_sched_domain_sysctl(void) | 6312 | static void unregister_sched_domain_sysctl(void) |
6313 | { | 6313 | { |
6314 | if (sd_sysctl_header) | 6314 | if (sd_sysctl_header) |
6315 | unregister_sysctl_table(sd_sysctl_header); | 6315 | unregister_sysctl_table(sd_sysctl_header); |
6316 | sd_sysctl_header = NULL; | 6316 | sd_sysctl_header = NULL; |
6317 | if (sd_ctl_dir[0].child) | 6317 | if (sd_ctl_dir[0].child) |
6318 | sd_free_ctl_entry(&sd_ctl_dir[0].child); | 6318 | sd_free_ctl_entry(&sd_ctl_dir[0].child); |
6319 | } | 6319 | } |
6320 | #else | 6320 | #else |
6321 | static void register_sched_domain_sysctl(void) | 6321 | static void register_sched_domain_sysctl(void) |
6322 | { | 6322 | { |
6323 | } | 6323 | } |
6324 | static void unregister_sched_domain_sysctl(void) | 6324 | static void unregister_sched_domain_sysctl(void) |
6325 | { | 6325 | { |
6326 | } | 6326 | } |
6327 | #endif | 6327 | #endif |
6328 | 6328 | ||
6329 | static void set_rq_online(struct rq *rq) | 6329 | static void set_rq_online(struct rq *rq) |
6330 | { | 6330 | { |
6331 | if (!rq->online) { | 6331 | if (!rq->online) { |
6332 | const struct sched_class *class; | 6332 | const struct sched_class *class; |
6333 | 6333 | ||
6334 | cpumask_set_cpu(rq->cpu, rq->rd->online); | 6334 | cpumask_set_cpu(rq->cpu, rq->rd->online); |
6335 | rq->online = 1; | 6335 | rq->online = 1; |
6336 | 6336 | ||
6337 | for_each_class(class) { | 6337 | for_each_class(class) { |
6338 | if (class->rq_online) | 6338 | if (class->rq_online) |
6339 | class->rq_online(rq); | 6339 | class->rq_online(rq); |
6340 | } | 6340 | } |
6341 | } | 6341 | } |
6342 | } | 6342 | } |
6343 | 6343 | ||
6344 | static void set_rq_offline(struct rq *rq) | 6344 | static void set_rq_offline(struct rq *rq) |
6345 | { | 6345 | { |
6346 | if (rq->online) { | 6346 | if (rq->online) { |
6347 | const struct sched_class *class; | 6347 | const struct sched_class *class; |
6348 | 6348 | ||
6349 | for_each_class(class) { | 6349 | for_each_class(class) { |
6350 | if (class->rq_offline) | 6350 | if (class->rq_offline) |
6351 | class->rq_offline(rq); | 6351 | class->rq_offline(rq); |
6352 | } | 6352 | } |
6353 | 6353 | ||
6354 | cpumask_clear_cpu(rq->cpu, rq->rd->online); | 6354 | cpumask_clear_cpu(rq->cpu, rq->rd->online); |
6355 | rq->online = 0; | 6355 | rq->online = 0; |
6356 | } | 6356 | } |
6357 | } | 6357 | } |
6358 | 6358 | ||
6359 | /* | 6359 | /* |
6360 | * migration_call - callback that gets triggered when a CPU is added. | 6360 | * migration_call - callback that gets triggered when a CPU is added. |
6361 | * Here we can start up the necessary migration thread for the new CPU. | 6361 | * Here we can start up the necessary migration thread for the new CPU. |
6362 | */ | 6362 | */ |
6363 | static int __cpuinit | 6363 | static int __cpuinit |
6364 | migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) | 6364 | migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) |
6365 | { | 6365 | { |
6366 | int cpu = (long)hcpu; | 6366 | int cpu = (long)hcpu; |
6367 | unsigned long flags; | 6367 | unsigned long flags; |
6368 | struct rq *rq = cpu_rq(cpu); | 6368 | struct rq *rq = cpu_rq(cpu); |
6369 | 6369 | ||
6370 | switch (action & ~CPU_TASKS_FROZEN) { | 6370 | switch (action & ~CPU_TASKS_FROZEN) { |
6371 | 6371 | ||
6372 | case CPU_UP_PREPARE: | 6372 | case CPU_UP_PREPARE: |
6373 | rq->calc_load_update = calc_load_update; | 6373 | rq->calc_load_update = calc_load_update; |
6374 | break; | 6374 | break; |
6375 | 6375 | ||
6376 | case CPU_ONLINE: | 6376 | case CPU_ONLINE: |
6377 | /* Update our root-domain */ | 6377 | /* Update our root-domain */ |
6378 | raw_spin_lock_irqsave(&rq->lock, flags); | 6378 | raw_spin_lock_irqsave(&rq->lock, flags); |
6379 | if (rq->rd) { | 6379 | if (rq->rd) { |
6380 | BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); | 6380 | BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); |
6381 | 6381 | ||
6382 | set_rq_online(rq); | 6382 | set_rq_online(rq); |
6383 | } | 6383 | } |
6384 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 6384 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
6385 | break; | 6385 | break; |
6386 | 6386 | ||
6387 | #ifdef CONFIG_HOTPLUG_CPU | 6387 | #ifdef CONFIG_HOTPLUG_CPU |
6388 | case CPU_DYING: | 6388 | case CPU_DYING: |
6389 | sched_ttwu_pending(); | 6389 | sched_ttwu_pending(); |
6390 | /* Update our root-domain */ | 6390 | /* Update our root-domain */ |
6391 | raw_spin_lock_irqsave(&rq->lock, flags); | 6391 | raw_spin_lock_irqsave(&rq->lock, flags); |
6392 | if (rq->rd) { | 6392 | if (rq->rd) { |
6393 | BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); | 6393 | BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); |
6394 | set_rq_offline(rq); | 6394 | set_rq_offline(rq); |
6395 | } | 6395 | } |
6396 | migrate_tasks(cpu); | 6396 | migrate_tasks(cpu); |
6397 | BUG_ON(rq->nr_running != 1); /* the migration thread */ | 6397 | BUG_ON(rq->nr_running != 1); /* the migration thread */ |
6398 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 6398 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
6399 | 6399 | ||
6400 | migrate_nr_uninterruptible(rq); | 6400 | migrate_nr_uninterruptible(rq); |
6401 | calc_global_load_remove(rq); | 6401 | calc_global_load_remove(rq); |
6402 | break; | 6402 | break; |
6403 | #endif | 6403 | #endif |
6404 | } | 6404 | } |
6405 | 6405 | ||
6406 | update_max_interval(); | 6406 | update_max_interval(); |
6407 | 6407 | ||
6408 | return NOTIFY_OK; | 6408 | return NOTIFY_OK; |
6409 | } | 6409 | } |
6410 | 6410 | ||
6411 | /* | 6411 | /* |
6412 | * Register at high priority so that task migration (migrate_all_tasks) | 6412 | * Register at high priority so that task migration (migrate_all_tasks) |
6413 | * happens before everything else. This has to be lower priority than | 6413 | * happens before everything else. This has to be lower priority than |
6414 | * the notifier in the perf_event subsystem, though. | 6414 | * the notifier in the perf_event subsystem, though. |
6415 | */ | 6415 | */ |
6416 | static struct notifier_block __cpuinitdata migration_notifier = { | 6416 | static struct notifier_block __cpuinitdata migration_notifier = { |
6417 | .notifier_call = migration_call, | 6417 | .notifier_call = migration_call, |
6418 | .priority = CPU_PRI_MIGRATION, | 6418 | .priority = CPU_PRI_MIGRATION, |
6419 | }; | 6419 | }; |
6420 | 6420 | ||
6421 | static int __cpuinit sched_cpu_active(struct notifier_block *nfb, | 6421 | static int __cpuinit sched_cpu_active(struct notifier_block *nfb, |
6422 | unsigned long action, void *hcpu) | 6422 | unsigned long action, void *hcpu) |
6423 | { | 6423 | { |
6424 | switch (action & ~CPU_TASKS_FROZEN) { | 6424 | switch (action & ~CPU_TASKS_FROZEN) { |
6425 | case CPU_ONLINE: | 6425 | case CPU_ONLINE: |
6426 | case CPU_DOWN_FAILED: | 6426 | case CPU_DOWN_FAILED: |
6427 | set_cpu_active((long)hcpu, true); | 6427 | set_cpu_active((long)hcpu, true); |
6428 | return NOTIFY_OK; | 6428 | return NOTIFY_OK; |
6429 | default: | 6429 | default: |
6430 | return NOTIFY_DONE; | 6430 | return NOTIFY_DONE; |
6431 | } | 6431 | } |
6432 | } | 6432 | } |
6433 | 6433 | ||
6434 | static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, | 6434 | static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, |
6435 | unsigned long action, void *hcpu) | 6435 | unsigned long action, void *hcpu) |
6436 | { | 6436 | { |
6437 | switch (action & ~CPU_TASKS_FROZEN) { | 6437 | switch (action & ~CPU_TASKS_FROZEN) { |
6438 | case CPU_DOWN_PREPARE: | 6438 | case CPU_DOWN_PREPARE: |
6439 | set_cpu_active((long)hcpu, false); | 6439 | set_cpu_active((long)hcpu, false); |
6440 | return NOTIFY_OK; | 6440 | return NOTIFY_OK; |
6441 | default: | 6441 | default: |
6442 | return NOTIFY_DONE; | 6442 | return NOTIFY_DONE; |
6443 | } | 6443 | } |
6444 | } | 6444 | } |
6445 | 6445 | ||
6446 | static int __init migration_init(void) | 6446 | static int __init migration_init(void) |
6447 | { | 6447 | { |
6448 | void *cpu = (void *)(long)smp_processor_id(); | 6448 | void *cpu = (void *)(long)smp_processor_id(); |
6449 | int err; | 6449 | int err; |
6450 | 6450 | ||
6451 | /* Initialize migration for the boot CPU */ | 6451 | /* Initialize migration for the boot CPU */ |
6452 | err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); | 6452 | err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); |
6453 | BUG_ON(err == NOTIFY_BAD); | 6453 | BUG_ON(err == NOTIFY_BAD); |
6454 | migration_call(&migration_notifier, CPU_ONLINE, cpu); | 6454 | migration_call(&migration_notifier, CPU_ONLINE, cpu); |
6455 | register_cpu_notifier(&migration_notifier); | 6455 | register_cpu_notifier(&migration_notifier); |
6456 | 6456 | ||
6457 | /* Register cpu active notifiers */ | 6457 | /* Register cpu active notifiers */ |
6458 | cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); | 6458 | cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); |
6459 | cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); | 6459 | cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); |
6460 | 6460 | ||
6461 | return 0; | 6461 | return 0; |
6462 | } | 6462 | } |
6463 | early_initcall(migration_init); | 6463 | early_initcall(migration_init); |
6464 | #endif | 6464 | #endif |
6465 | 6465 | ||
6466 | #ifdef CONFIG_SMP | 6466 | #ifdef CONFIG_SMP |
6467 | 6467 | ||
6468 | #ifdef CONFIG_SCHED_DEBUG | 6468 | #ifdef CONFIG_SCHED_DEBUG |
6469 | 6469 | ||
6470 | static __read_mostly int sched_domain_debug_enabled; | 6470 | static __read_mostly int sched_domain_debug_enabled; |
6471 | 6471 | ||
6472 | static int __init sched_domain_debug_setup(char *str) | 6472 | static int __init sched_domain_debug_setup(char *str) |
6473 | { | 6473 | { |
6474 | sched_domain_debug_enabled = 1; | 6474 | sched_domain_debug_enabled = 1; |
6475 | 6475 | ||
6476 | return 0; | 6476 | return 0; |
6477 | } | 6477 | } |
6478 | early_param("sched_debug", sched_domain_debug_setup); | 6478 | early_param("sched_debug", sched_domain_debug_setup); |
6479 | 6479 | ||
6480 | static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, | 6480 | static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, |
6481 | struct cpumask *groupmask) | 6481 | struct cpumask *groupmask) |
6482 | { | 6482 | { |
6483 | struct sched_group *group = sd->groups; | 6483 | struct sched_group *group = sd->groups; |
6484 | char str[256]; | 6484 | char str[256]; |
6485 | 6485 | ||
6486 | cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); | 6486 | cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); |
6487 | cpumask_clear(groupmask); | 6487 | cpumask_clear(groupmask); |
6488 | 6488 | ||
6489 | printk(KERN_DEBUG "%*s domain %d: ", level, "", level); | 6489 | printk(KERN_DEBUG "%*s domain %d: ", level, "", level); |
6490 | 6490 | ||
6491 | if (!(sd->flags & SD_LOAD_BALANCE)) { | 6491 | if (!(sd->flags & SD_LOAD_BALANCE)) { |
6492 | printk("does not load-balance\n"); | 6492 | printk("does not load-balance\n"); |
6493 | if (sd->parent) | 6493 | if (sd->parent) |
6494 | printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" | 6494 | printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" |
6495 | " has parent"); | 6495 | " has parent"); |
6496 | return -1; | 6496 | return -1; |
6497 | } | 6497 | } |
6498 | 6498 | ||
6499 | printk(KERN_CONT "span %s level %s\n", str, sd->name); | 6499 | printk(KERN_CONT "span %s level %s\n", str, sd->name); |
6500 | 6500 | ||
6501 | if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { | 6501 | if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { |
6502 | printk(KERN_ERR "ERROR: domain->span does not contain " | 6502 | printk(KERN_ERR "ERROR: domain->span does not contain " |
6503 | "CPU%d\n", cpu); | 6503 | "CPU%d\n", cpu); |
6504 | } | 6504 | } |
6505 | if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { | 6505 | if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { |
6506 | printk(KERN_ERR "ERROR: domain->groups does not contain" | 6506 | printk(KERN_ERR "ERROR: domain->groups does not contain" |
6507 | " CPU%d\n", cpu); | 6507 | " CPU%d\n", cpu); |
6508 | } | 6508 | } |
6509 | 6509 | ||
6510 | printk(KERN_DEBUG "%*s groups:", level + 1, ""); | 6510 | printk(KERN_DEBUG "%*s groups:", level + 1, ""); |
6511 | do { | 6511 | do { |
6512 | if (!group) { | 6512 | if (!group) { |
6513 | printk("\n"); | 6513 | printk("\n"); |
6514 | printk(KERN_ERR "ERROR: group is NULL\n"); | 6514 | printk(KERN_ERR "ERROR: group is NULL\n"); |
6515 | break; | 6515 | break; |
6516 | } | 6516 | } |
6517 | 6517 | ||
6518 | if (!group->cpu_power) { | 6518 | if (!group->cpu_power) { |
6519 | printk(KERN_CONT "\n"); | 6519 | printk(KERN_CONT "\n"); |
6520 | printk(KERN_ERR "ERROR: domain->cpu_power not " | 6520 | printk(KERN_ERR "ERROR: domain->cpu_power not " |
6521 | "set\n"); | 6521 | "set\n"); |
6522 | break; | 6522 | break; |
6523 | } | 6523 | } |
6524 | 6524 | ||
6525 | if (!cpumask_weight(sched_group_cpus(group))) { | 6525 | if (!cpumask_weight(sched_group_cpus(group))) { |
6526 | printk(KERN_CONT "\n"); | 6526 | printk(KERN_CONT "\n"); |
6527 | printk(KERN_ERR "ERROR: empty group\n"); | 6527 | printk(KERN_ERR "ERROR: empty group\n"); |
6528 | break; | 6528 | break; |
6529 | } | 6529 | } |
6530 | 6530 | ||
6531 | if (cpumask_intersects(groupmask, sched_group_cpus(group))) { | 6531 | if (cpumask_intersects(groupmask, sched_group_cpus(group))) { |
6532 | printk(KERN_CONT "\n"); | 6532 | printk(KERN_CONT "\n"); |
6533 | printk(KERN_ERR "ERROR: repeated CPUs\n"); | 6533 | printk(KERN_ERR "ERROR: repeated CPUs\n"); |
6534 | break; | 6534 | break; |
6535 | } | 6535 | } |
6536 | 6536 | ||
6537 | cpumask_or(groupmask, groupmask, sched_group_cpus(group)); | 6537 | cpumask_or(groupmask, groupmask, sched_group_cpus(group)); |
6538 | 6538 | ||
6539 | cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); | 6539 | cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); |
6540 | 6540 | ||
6541 | printk(KERN_CONT " %s", str); | 6541 | printk(KERN_CONT " %s", str); |
6542 | if (group->cpu_power != SCHED_LOAD_SCALE) { | 6542 | if (group->cpu_power != SCHED_LOAD_SCALE) { |
6543 | printk(KERN_CONT " (cpu_power = %d)", | 6543 | printk(KERN_CONT " (cpu_power = %d)", |
6544 | group->cpu_power); | 6544 | group->cpu_power); |
6545 | } | 6545 | } |
6546 | 6546 | ||
6547 | group = group->next; | 6547 | group = group->next; |
6548 | } while (group != sd->groups); | 6548 | } while (group != sd->groups); |
6549 | printk(KERN_CONT "\n"); | 6549 | printk(KERN_CONT "\n"); |
6550 | 6550 | ||
6551 | if (!cpumask_equal(sched_domain_span(sd), groupmask)) | 6551 | if (!cpumask_equal(sched_domain_span(sd), groupmask)) |
6552 | printk(KERN_ERR "ERROR: groups don't span domain->span\n"); | 6552 | printk(KERN_ERR "ERROR: groups don't span domain->span\n"); |
6553 | 6553 | ||
6554 | if (sd->parent && | 6554 | if (sd->parent && |
6555 | !cpumask_subset(groupmask, sched_domain_span(sd->parent))) | 6555 | !cpumask_subset(groupmask, sched_domain_span(sd->parent))) |
6556 | printk(KERN_ERR "ERROR: parent span is not a superset " | 6556 | printk(KERN_ERR "ERROR: parent span is not a superset " |
6557 | "of domain->span\n"); | 6557 | "of domain->span\n"); |
6558 | return 0; | 6558 | return 0; |
6559 | } | 6559 | } |
6560 | 6560 | ||
6561 | static void sched_domain_debug(struct sched_domain *sd, int cpu) | 6561 | static void sched_domain_debug(struct sched_domain *sd, int cpu) |
6562 | { | 6562 | { |
6563 | cpumask_var_t groupmask; | 6563 | cpumask_var_t groupmask; |
6564 | int level = 0; | 6564 | int level = 0; |
6565 | 6565 | ||
6566 | if (!sched_domain_debug_enabled) | 6566 | if (!sched_domain_debug_enabled) |
6567 | return; | 6567 | return; |
6568 | 6568 | ||
6569 | if (!sd) { | 6569 | if (!sd) { |
6570 | printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); | 6570 | printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); |
6571 | return; | 6571 | return; |
6572 | } | 6572 | } |
6573 | 6573 | ||
6574 | printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); | 6574 | printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); |
6575 | 6575 | ||
6576 | if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { | 6576 | if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { |
6577 | printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); | 6577 | printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); |
6578 | return; | 6578 | return; |
6579 | } | 6579 | } |
6580 | 6580 | ||
6581 | for (;;) { | 6581 | for (;;) { |
6582 | if (sched_domain_debug_one(sd, cpu, level, groupmask)) | 6582 | if (sched_domain_debug_one(sd, cpu, level, groupmask)) |
6583 | break; | 6583 | break; |
6584 | level++; | 6584 | level++; |
6585 | sd = sd->parent; | 6585 | sd = sd->parent; |
6586 | if (!sd) | 6586 | if (!sd) |
6587 | break; | 6587 | break; |
6588 | } | 6588 | } |
6589 | free_cpumask_var(groupmask); | 6589 | free_cpumask_var(groupmask); |
6590 | } | 6590 | } |
6591 | #else /* !CONFIG_SCHED_DEBUG */ | 6591 | #else /* !CONFIG_SCHED_DEBUG */ |
6592 | # define sched_domain_debug(sd, cpu) do { } while (0) | 6592 | # define sched_domain_debug(sd, cpu) do { } while (0) |
6593 | #endif /* CONFIG_SCHED_DEBUG */ | 6593 | #endif /* CONFIG_SCHED_DEBUG */ |
6594 | 6594 | ||
6595 | static int sd_degenerate(struct sched_domain *sd) | 6595 | static int sd_degenerate(struct sched_domain *sd) |
6596 | { | 6596 | { |
6597 | if (cpumask_weight(sched_domain_span(sd)) == 1) | 6597 | if (cpumask_weight(sched_domain_span(sd)) == 1) |
6598 | return 1; | 6598 | return 1; |
6599 | 6599 | ||
6600 | /* Following flags need at least 2 groups */ | 6600 | /* Following flags need at least 2 groups */ |
6601 | if (sd->flags & (SD_LOAD_BALANCE | | 6601 | if (sd->flags & (SD_LOAD_BALANCE | |
6602 | SD_BALANCE_NEWIDLE | | 6602 | SD_BALANCE_NEWIDLE | |
6603 | SD_BALANCE_FORK | | 6603 | SD_BALANCE_FORK | |
6604 | SD_BALANCE_EXEC | | 6604 | SD_BALANCE_EXEC | |
6605 | SD_SHARE_CPUPOWER | | 6605 | SD_SHARE_CPUPOWER | |
6606 | SD_SHARE_PKG_RESOURCES)) { | 6606 | SD_SHARE_PKG_RESOURCES)) { |
6607 | if (sd->groups != sd->groups->next) | 6607 | if (sd->groups != sd->groups->next) |
6608 | return 0; | 6608 | return 0; |
6609 | } | 6609 | } |
6610 | 6610 | ||
6611 | /* Following flags don't use groups */ | 6611 | /* Following flags don't use groups */ |
6612 | if (sd->flags & (SD_WAKE_AFFINE)) | 6612 | if (sd->flags & (SD_WAKE_AFFINE)) |
6613 | return 0; | 6613 | return 0; |
6614 | 6614 | ||
6615 | return 1; | 6615 | return 1; |
6616 | } | 6616 | } |
6617 | 6617 | ||
6618 | static int | 6618 | static int |
6619 | sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) | 6619 | sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) |
6620 | { | 6620 | { |
6621 | unsigned long cflags = sd->flags, pflags = parent->flags; | 6621 | unsigned long cflags = sd->flags, pflags = parent->flags; |
6622 | 6622 | ||
6623 | if (sd_degenerate(parent)) | 6623 | if (sd_degenerate(parent)) |
6624 | return 1; | 6624 | return 1; |
6625 | 6625 | ||
6626 | if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) | 6626 | if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) |
6627 | return 0; | 6627 | return 0; |
6628 | 6628 | ||
6629 | /* Flags needing groups don't count if only 1 group in parent */ | 6629 | /* Flags needing groups don't count if only 1 group in parent */ |
6630 | if (parent->groups == parent->groups->next) { | 6630 | if (parent->groups == parent->groups->next) { |
6631 | pflags &= ~(SD_LOAD_BALANCE | | 6631 | pflags &= ~(SD_LOAD_BALANCE | |
6632 | SD_BALANCE_NEWIDLE | | 6632 | SD_BALANCE_NEWIDLE | |
6633 | SD_BALANCE_FORK | | 6633 | SD_BALANCE_FORK | |
6634 | SD_BALANCE_EXEC | | 6634 | SD_BALANCE_EXEC | |
6635 | SD_SHARE_CPUPOWER | | 6635 | SD_SHARE_CPUPOWER | |
6636 | SD_SHARE_PKG_RESOURCES); | 6636 | SD_SHARE_PKG_RESOURCES); |
6637 | if (nr_node_ids == 1) | 6637 | if (nr_node_ids == 1) |
6638 | pflags &= ~SD_SERIALIZE; | 6638 | pflags &= ~SD_SERIALIZE; |
6639 | } | 6639 | } |
6640 | if (~cflags & pflags) | 6640 | if (~cflags & pflags) |
6641 | return 0; | 6641 | return 0; |
6642 | 6642 | ||
6643 | return 1; | 6643 | return 1; |
6644 | } | 6644 | } |
6645 | 6645 | ||
6646 | static void free_rootdomain(struct root_domain *rd) | 6646 | static void free_rootdomain(struct root_domain *rd) |
6647 | { | 6647 | { |
6648 | synchronize_sched(); | 6648 | synchronize_sched(); |
6649 | 6649 | ||
6650 | cpupri_cleanup(&rd->cpupri); | 6650 | cpupri_cleanup(&rd->cpupri); |
6651 | 6651 | ||
6652 | free_cpumask_var(rd->rto_mask); | 6652 | free_cpumask_var(rd->rto_mask); |
6653 | free_cpumask_var(rd->online); | 6653 | free_cpumask_var(rd->online); |
6654 | free_cpumask_var(rd->span); | 6654 | free_cpumask_var(rd->span); |
6655 | kfree(rd); | 6655 | kfree(rd); |
6656 | } | 6656 | } |
6657 | 6657 | ||
6658 | static void rq_attach_root(struct rq *rq, struct root_domain *rd) | 6658 | static void rq_attach_root(struct rq *rq, struct root_domain *rd) |
6659 | { | 6659 | { |
6660 | struct root_domain *old_rd = NULL; | 6660 | struct root_domain *old_rd = NULL; |
6661 | unsigned long flags; | 6661 | unsigned long flags; |
6662 | 6662 | ||
6663 | raw_spin_lock_irqsave(&rq->lock, flags); | 6663 | raw_spin_lock_irqsave(&rq->lock, flags); |
6664 | 6664 | ||
6665 | if (rq->rd) { | 6665 | if (rq->rd) { |
6666 | old_rd = rq->rd; | 6666 | old_rd = rq->rd; |
6667 | 6667 | ||
6668 | if (cpumask_test_cpu(rq->cpu, old_rd->online)) | 6668 | if (cpumask_test_cpu(rq->cpu, old_rd->online)) |
6669 | set_rq_offline(rq); | 6669 | set_rq_offline(rq); |
6670 | 6670 | ||
6671 | cpumask_clear_cpu(rq->cpu, old_rd->span); | 6671 | cpumask_clear_cpu(rq->cpu, old_rd->span); |
6672 | 6672 | ||
6673 | /* | 6673 | /* |
6674 | * If we dont want to free the old_rt yet then | 6674 | * If we dont want to free the old_rt yet then |
6675 | * set old_rd to NULL to skip the freeing later | 6675 | * set old_rd to NULL to skip the freeing later |
6676 | * in this function: | 6676 | * in this function: |
6677 | */ | 6677 | */ |
6678 | if (!atomic_dec_and_test(&old_rd->refcount)) | 6678 | if (!atomic_dec_and_test(&old_rd->refcount)) |
6679 | old_rd = NULL; | 6679 | old_rd = NULL; |
6680 | } | 6680 | } |
6681 | 6681 | ||
6682 | atomic_inc(&rd->refcount); | 6682 | atomic_inc(&rd->refcount); |
6683 | rq->rd = rd; | 6683 | rq->rd = rd; |
6684 | 6684 | ||
6685 | cpumask_set_cpu(rq->cpu, rd->span); | 6685 | cpumask_set_cpu(rq->cpu, rd->span); |
6686 | if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) | 6686 | if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) |
6687 | set_rq_online(rq); | 6687 | set_rq_online(rq); |
6688 | 6688 | ||
6689 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 6689 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
6690 | 6690 | ||
6691 | if (old_rd) | 6691 | if (old_rd) |
6692 | free_rootdomain(old_rd); | 6692 | free_rootdomain(old_rd); |
6693 | } | 6693 | } |
6694 | 6694 | ||
6695 | static int init_rootdomain(struct root_domain *rd) | 6695 | static int init_rootdomain(struct root_domain *rd) |
6696 | { | 6696 | { |
6697 | memset(rd, 0, sizeof(*rd)); | 6697 | memset(rd, 0, sizeof(*rd)); |
6698 | 6698 | ||
6699 | if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) | 6699 | if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) |
6700 | goto out; | 6700 | goto out; |
6701 | if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) | 6701 | if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) |
6702 | goto free_span; | 6702 | goto free_span; |
6703 | if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) | 6703 | if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) |
6704 | goto free_online; | 6704 | goto free_online; |
6705 | 6705 | ||
6706 | if (cpupri_init(&rd->cpupri) != 0) | 6706 | if (cpupri_init(&rd->cpupri) != 0) |
6707 | goto free_rto_mask; | 6707 | goto free_rto_mask; |
6708 | return 0; | 6708 | return 0; |
6709 | 6709 | ||
6710 | free_rto_mask: | 6710 | free_rto_mask: |
6711 | free_cpumask_var(rd->rto_mask); | 6711 | free_cpumask_var(rd->rto_mask); |
6712 | free_online: | 6712 | free_online: |
6713 | free_cpumask_var(rd->online); | 6713 | free_cpumask_var(rd->online); |
6714 | free_span: | 6714 | free_span: |
6715 | free_cpumask_var(rd->span); | 6715 | free_cpumask_var(rd->span); |
6716 | out: | 6716 | out: |
6717 | return -ENOMEM; | 6717 | return -ENOMEM; |
6718 | } | 6718 | } |
6719 | 6719 | ||
6720 | static void init_defrootdomain(void) | 6720 | static void init_defrootdomain(void) |
6721 | { | 6721 | { |
6722 | init_rootdomain(&def_root_domain); | 6722 | init_rootdomain(&def_root_domain); |
6723 | 6723 | ||
6724 | atomic_set(&def_root_domain.refcount, 1); | 6724 | atomic_set(&def_root_domain.refcount, 1); |
6725 | } | 6725 | } |
6726 | 6726 | ||
6727 | static struct root_domain *alloc_rootdomain(void) | 6727 | static struct root_domain *alloc_rootdomain(void) |
6728 | { | 6728 | { |
6729 | struct root_domain *rd; | 6729 | struct root_domain *rd; |
6730 | 6730 | ||
6731 | rd = kmalloc(sizeof(*rd), GFP_KERNEL); | 6731 | rd = kmalloc(sizeof(*rd), GFP_KERNEL); |
6732 | if (!rd) | 6732 | if (!rd) |
6733 | return NULL; | 6733 | return NULL; |
6734 | 6734 | ||
6735 | if (init_rootdomain(rd) != 0) { | 6735 | if (init_rootdomain(rd) != 0) { |
6736 | kfree(rd); | 6736 | kfree(rd); |
6737 | return NULL; | 6737 | return NULL; |
6738 | } | 6738 | } |
6739 | 6739 | ||
6740 | return rd; | 6740 | return rd; |
6741 | } | 6741 | } |
6742 | 6742 | ||
6743 | /* | 6743 | /* |
6744 | * Attach the domain 'sd' to 'cpu' as its base domain. Callers must | 6744 | * Attach the domain 'sd' to 'cpu' as its base domain. Callers must |
6745 | * hold the hotplug lock. | 6745 | * hold the hotplug lock. |
6746 | */ | 6746 | */ |
6747 | static void | 6747 | static void |
6748 | cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) | 6748 | cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) |
6749 | { | 6749 | { |
6750 | struct rq *rq = cpu_rq(cpu); | 6750 | struct rq *rq = cpu_rq(cpu); |
6751 | struct sched_domain *tmp; | 6751 | struct sched_domain *tmp; |
6752 | 6752 | ||
6753 | for (tmp = sd; tmp; tmp = tmp->parent) | 6753 | for (tmp = sd; tmp; tmp = tmp->parent) |
6754 | tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); | 6754 | tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); |
6755 | 6755 | ||
6756 | /* Remove the sched domains which do not contribute to scheduling. */ | 6756 | /* Remove the sched domains which do not contribute to scheduling. */ |
6757 | for (tmp = sd; tmp; ) { | 6757 | for (tmp = sd; tmp; ) { |
6758 | struct sched_domain *parent = tmp->parent; | 6758 | struct sched_domain *parent = tmp->parent; |
6759 | if (!parent) | 6759 | if (!parent) |
6760 | break; | 6760 | break; |
6761 | 6761 | ||
6762 | if (sd_parent_degenerate(tmp, parent)) { | 6762 | if (sd_parent_degenerate(tmp, parent)) { |
6763 | tmp->parent = parent->parent; | 6763 | tmp->parent = parent->parent; |
6764 | if (parent->parent) | 6764 | if (parent->parent) |
6765 | parent->parent->child = tmp; | 6765 | parent->parent->child = tmp; |
6766 | } else | 6766 | } else |
6767 | tmp = tmp->parent; | 6767 | tmp = tmp->parent; |
6768 | } | 6768 | } |
6769 | 6769 | ||
6770 | if (sd && sd_degenerate(sd)) { | 6770 | if (sd && sd_degenerate(sd)) { |
6771 | sd = sd->parent; | 6771 | sd = sd->parent; |
6772 | if (sd) | 6772 | if (sd) |
6773 | sd->child = NULL; | 6773 | sd->child = NULL; |
6774 | } | 6774 | } |
6775 | 6775 | ||
6776 | sched_domain_debug(sd, cpu); | 6776 | sched_domain_debug(sd, cpu); |
6777 | 6777 | ||
6778 | rq_attach_root(rq, rd); | 6778 | rq_attach_root(rq, rd); |
6779 | rcu_assign_pointer(rq->sd, sd); | 6779 | rcu_assign_pointer(rq->sd, sd); |
6780 | } | 6780 | } |
6781 | 6781 | ||
6782 | /* cpus with isolated domains */ | 6782 | /* cpus with isolated domains */ |
6783 | static cpumask_var_t cpu_isolated_map; | 6783 | static cpumask_var_t cpu_isolated_map; |
6784 | 6784 | ||
6785 | /* Setup the mask of cpus configured for isolated domains */ | 6785 | /* Setup the mask of cpus configured for isolated domains */ |
6786 | static int __init isolated_cpu_setup(char *str) | 6786 | static int __init isolated_cpu_setup(char *str) |
6787 | { | 6787 | { |
6788 | alloc_bootmem_cpumask_var(&cpu_isolated_map); | 6788 | alloc_bootmem_cpumask_var(&cpu_isolated_map); |
6789 | cpulist_parse(str, cpu_isolated_map); | 6789 | cpulist_parse(str, cpu_isolated_map); |
6790 | return 1; | 6790 | return 1; |
6791 | } | 6791 | } |
6792 | 6792 | ||
6793 | __setup("isolcpus=", isolated_cpu_setup); | 6793 | __setup("isolcpus=", isolated_cpu_setup); |
6794 | 6794 | ||
6795 | /* | 6795 | /* |
6796 | * init_sched_build_groups takes the cpumask we wish to span, and a pointer | 6796 | * init_sched_build_groups takes the cpumask we wish to span, and a pointer |
6797 | * to a function which identifies what group(along with sched group) a CPU | 6797 | * to a function which identifies what group(along with sched group) a CPU |
6798 | * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids | 6798 | * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids |
6799 | * (due to the fact that we keep track of groups covered with a struct cpumask). | 6799 | * (due to the fact that we keep track of groups covered with a struct cpumask). |
6800 | * | 6800 | * |
6801 | * init_sched_build_groups will build a circular linked list of the groups | 6801 | * init_sched_build_groups will build a circular linked list of the groups |
6802 | * covered by the given span, and will set each group's ->cpumask correctly, | 6802 | * covered by the given span, and will set each group's ->cpumask correctly, |
6803 | * and ->cpu_power to 0. | 6803 | * and ->cpu_power to 0. |
6804 | */ | 6804 | */ |
6805 | static void | 6805 | static void |
6806 | init_sched_build_groups(const struct cpumask *span, | 6806 | init_sched_build_groups(const struct cpumask *span, |
6807 | const struct cpumask *cpu_map, | 6807 | const struct cpumask *cpu_map, |
6808 | int (*group_fn)(int cpu, const struct cpumask *cpu_map, | 6808 | int (*group_fn)(int cpu, const struct cpumask *cpu_map, |
6809 | struct sched_group **sg, | 6809 | struct sched_group **sg, |
6810 | struct cpumask *tmpmask), | 6810 | struct cpumask *tmpmask), |
6811 | struct cpumask *covered, struct cpumask *tmpmask) | 6811 | struct cpumask *covered, struct cpumask *tmpmask) |
6812 | { | 6812 | { |
6813 | struct sched_group *first = NULL, *last = NULL; | 6813 | struct sched_group *first = NULL, *last = NULL; |
6814 | int i; | 6814 | int i; |
6815 | 6815 | ||
6816 | cpumask_clear(covered); | 6816 | cpumask_clear(covered); |
6817 | 6817 | ||
6818 | for_each_cpu(i, span) { | 6818 | for_each_cpu(i, span) { |
6819 | struct sched_group *sg; | 6819 | struct sched_group *sg; |
6820 | int group = group_fn(i, cpu_map, &sg, tmpmask); | 6820 | int group = group_fn(i, cpu_map, &sg, tmpmask); |
6821 | int j; | 6821 | int j; |
6822 | 6822 | ||
6823 | if (cpumask_test_cpu(i, covered)) | 6823 | if (cpumask_test_cpu(i, covered)) |
6824 | continue; | 6824 | continue; |
6825 | 6825 | ||
6826 | cpumask_clear(sched_group_cpus(sg)); | 6826 | cpumask_clear(sched_group_cpus(sg)); |
6827 | sg->cpu_power = 0; | 6827 | sg->cpu_power = 0; |
6828 | 6828 | ||
6829 | for_each_cpu(j, span) { | 6829 | for_each_cpu(j, span) { |
6830 | if (group_fn(j, cpu_map, NULL, tmpmask) != group) | 6830 | if (group_fn(j, cpu_map, NULL, tmpmask) != group) |
6831 | continue; | 6831 | continue; |
6832 | 6832 | ||
6833 | cpumask_set_cpu(j, covered); | 6833 | cpumask_set_cpu(j, covered); |
6834 | cpumask_set_cpu(j, sched_group_cpus(sg)); | 6834 | cpumask_set_cpu(j, sched_group_cpus(sg)); |
6835 | } | 6835 | } |
6836 | if (!first) | 6836 | if (!first) |
6837 | first = sg; | 6837 | first = sg; |
6838 | if (last) | 6838 | if (last) |
6839 | last->next = sg; | 6839 | last->next = sg; |
6840 | last = sg; | 6840 | last = sg; |
6841 | } | 6841 | } |
6842 | last->next = first; | 6842 | last->next = first; |
6843 | } | 6843 | } |
6844 | 6844 | ||
6845 | #define SD_NODES_PER_DOMAIN 16 | 6845 | #define SD_NODES_PER_DOMAIN 16 |
6846 | 6846 | ||
6847 | #ifdef CONFIG_NUMA | 6847 | #ifdef CONFIG_NUMA |
6848 | 6848 | ||
6849 | /** | 6849 | /** |
6850 | * find_next_best_node - find the next node to include in a sched_domain | 6850 | * find_next_best_node - find the next node to include in a sched_domain |
6851 | * @node: node whose sched_domain we're building | 6851 | * @node: node whose sched_domain we're building |
6852 | * @used_nodes: nodes already in the sched_domain | 6852 | * @used_nodes: nodes already in the sched_domain |
6853 | * | 6853 | * |
6854 | * Find the next node to include in a given scheduling domain. Simply | 6854 | * Find the next node to include in a given scheduling domain. Simply |
6855 | * finds the closest node not already in the @used_nodes map. | 6855 | * finds the closest node not already in the @used_nodes map. |
6856 | * | 6856 | * |
6857 | * Should use nodemask_t. | 6857 | * Should use nodemask_t. |
6858 | */ | 6858 | */ |
6859 | static int find_next_best_node(int node, nodemask_t *used_nodes) | 6859 | static int find_next_best_node(int node, nodemask_t *used_nodes) |
6860 | { | 6860 | { |
6861 | int i, n, val, min_val, best_node = 0; | 6861 | int i, n, val, min_val, best_node = 0; |
6862 | 6862 | ||
6863 | min_val = INT_MAX; | 6863 | min_val = INT_MAX; |
6864 | 6864 | ||
6865 | for (i = 0; i < nr_node_ids; i++) { | 6865 | for (i = 0; i < nr_node_ids; i++) { |
6866 | /* Start at @node */ | 6866 | /* Start at @node */ |
6867 | n = (node + i) % nr_node_ids; | 6867 | n = (node + i) % nr_node_ids; |
6868 | 6868 | ||
6869 | if (!nr_cpus_node(n)) | 6869 | if (!nr_cpus_node(n)) |
6870 | continue; | 6870 | continue; |
6871 | 6871 | ||
6872 | /* Skip already used nodes */ | 6872 | /* Skip already used nodes */ |
6873 | if (node_isset(n, *used_nodes)) | 6873 | if (node_isset(n, *used_nodes)) |
6874 | continue; | 6874 | continue; |
6875 | 6875 | ||
6876 | /* Simple min distance search */ | 6876 | /* Simple min distance search */ |
6877 | val = node_distance(node, n); | 6877 | val = node_distance(node, n); |
6878 | 6878 | ||
6879 | if (val < min_val) { | 6879 | if (val < min_val) { |
6880 | min_val = val; | 6880 | min_val = val; |
6881 | best_node = n; | 6881 | best_node = n; |
6882 | } | 6882 | } |
6883 | } | 6883 | } |
6884 | 6884 | ||
6885 | node_set(best_node, *used_nodes); | 6885 | node_set(best_node, *used_nodes); |
6886 | return best_node; | 6886 | return best_node; |
6887 | } | 6887 | } |
6888 | 6888 | ||
6889 | /** | 6889 | /** |
6890 | * sched_domain_node_span - get a cpumask for a node's sched_domain | 6890 | * sched_domain_node_span - get a cpumask for a node's sched_domain |
6891 | * @node: node whose cpumask we're constructing | 6891 | * @node: node whose cpumask we're constructing |
6892 | * @span: resulting cpumask | 6892 | * @span: resulting cpumask |
6893 | * | 6893 | * |
6894 | * Given a node, construct a good cpumask for its sched_domain to span. It | 6894 | * Given a node, construct a good cpumask for its sched_domain to span. It |
6895 | * should be one that prevents unnecessary balancing, but also spreads tasks | 6895 | * should be one that prevents unnecessary balancing, but also spreads tasks |
6896 | * out optimally. | 6896 | * out optimally. |
6897 | */ | 6897 | */ |
6898 | static void sched_domain_node_span(int node, struct cpumask *span) | 6898 | static void sched_domain_node_span(int node, struct cpumask *span) |
6899 | { | 6899 | { |
6900 | nodemask_t used_nodes; | 6900 | nodemask_t used_nodes; |
6901 | int i; | 6901 | int i; |
6902 | 6902 | ||
6903 | cpumask_clear(span); | 6903 | cpumask_clear(span); |
6904 | nodes_clear(used_nodes); | 6904 | nodes_clear(used_nodes); |
6905 | 6905 | ||
6906 | cpumask_or(span, span, cpumask_of_node(node)); | 6906 | cpumask_or(span, span, cpumask_of_node(node)); |
6907 | node_set(node, used_nodes); | 6907 | node_set(node, used_nodes); |
6908 | 6908 | ||
6909 | for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { | 6909 | for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { |
6910 | int next_node = find_next_best_node(node, &used_nodes); | 6910 | int next_node = find_next_best_node(node, &used_nodes); |
6911 | 6911 | ||
6912 | cpumask_or(span, span, cpumask_of_node(next_node)); | 6912 | cpumask_or(span, span, cpumask_of_node(next_node)); |
6913 | } | 6913 | } |
6914 | } | 6914 | } |
6915 | #endif /* CONFIG_NUMA */ | 6915 | #endif /* CONFIG_NUMA */ |
6916 | 6916 | ||
6917 | int sched_smt_power_savings = 0, sched_mc_power_savings = 0; | 6917 | int sched_smt_power_savings = 0, sched_mc_power_savings = 0; |
6918 | 6918 | ||
6919 | /* | 6919 | /* |
6920 | * The cpus mask in sched_group and sched_domain hangs off the end. | 6920 | * The cpus mask in sched_group and sched_domain hangs off the end. |
6921 | * | 6921 | * |
6922 | * ( See the the comments in include/linux/sched.h:struct sched_group | 6922 | * ( See the the comments in include/linux/sched.h:struct sched_group |
6923 | * and struct sched_domain. ) | 6923 | * and struct sched_domain. ) |
6924 | */ | 6924 | */ |
6925 | struct static_sched_group { | 6925 | struct static_sched_group { |
6926 | struct sched_group sg; | 6926 | struct sched_group sg; |
6927 | DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); | 6927 | DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); |
6928 | }; | 6928 | }; |
6929 | 6929 | ||
6930 | struct static_sched_domain { | 6930 | struct static_sched_domain { |
6931 | struct sched_domain sd; | 6931 | struct sched_domain sd; |
6932 | DECLARE_BITMAP(span, CONFIG_NR_CPUS); | 6932 | DECLARE_BITMAP(span, CONFIG_NR_CPUS); |
6933 | }; | 6933 | }; |
6934 | 6934 | ||
6935 | struct s_data { | 6935 | struct s_data { |
6936 | #ifdef CONFIG_NUMA | 6936 | #ifdef CONFIG_NUMA |
6937 | int sd_allnodes; | 6937 | int sd_allnodes; |
6938 | cpumask_var_t domainspan; | 6938 | cpumask_var_t domainspan; |
6939 | cpumask_var_t covered; | 6939 | cpumask_var_t covered; |
6940 | cpumask_var_t notcovered; | 6940 | cpumask_var_t notcovered; |
6941 | #endif | 6941 | #endif |
6942 | cpumask_var_t nodemask; | 6942 | cpumask_var_t nodemask; |
6943 | cpumask_var_t this_sibling_map; | 6943 | cpumask_var_t this_sibling_map; |
6944 | cpumask_var_t this_core_map; | 6944 | cpumask_var_t this_core_map; |
6945 | cpumask_var_t this_book_map; | 6945 | cpumask_var_t this_book_map; |
6946 | cpumask_var_t send_covered; | 6946 | cpumask_var_t send_covered; |
6947 | cpumask_var_t tmpmask; | 6947 | cpumask_var_t tmpmask; |
6948 | struct sched_group **sched_group_nodes; | 6948 | struct sched_group **sched_group_nodes; |
6949 | struct root_domain *rd; | 6949 | struct root_domain *rd; |
6950 | }; | 6950 | }; |
6951 | 6951 | ||
6952 | enum s_alloc { | 6952 | enum s_alloc { |
6953 | sa_sched_groups = 0, | 6953 | sa_sched_groups = 0, |
6954 | sa_rootdomain, | 6954 | sa_rootdomain, |
6955 | sa_tmpmask, | 6955 | sa_tmpmask, |
6956 | sa_send_covered, | 6956 | sa_send_covered, |
6957 | sa_this_book_map, | 6957 | sa_this_book_map, |
6958 | sa_this_core_map, | 6958 | sa_this_core_map, |
6959 | sa_this_sibling_map, | 6959 | sa_this_sibling_map, |
6960 | sa_nodemask, | 6960 | sa_nodemask, |
6961 | sa_sched_group_nodes, | 6961 | sa_sched_group_nodes, |
6962 | #ifdef CONFIG_NUMA | 6962 | #ifdef CONFIG_NUMA |
6963 | sa_notcovered, | 6963 | sa_notcovered, |
6964 | sa_covered, | 6964 | sa_covered, |
6965 | sa_domainspan, | 6965 | sa_domainspan, |
6966 | #endif | 6966 | #endif |
6967 | sa_none, | 6967 | sa_none, |
6968 | }; | 6968 | }; |
6969 | 6969 | ||
6970 | /* | 6970 | /* |
6971 | * SMT sched-domains: | 6971 | * SMT sched-domains: |
6972 | */ | 6972 | */ |
6973 | #ifdef CONFIG_SCHED_SMT | 6973 | #ifdef CONFIG_SCHED_SMT |
6974 | static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); | 6974 | static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); |
6975 | static DEFINE_PER_CPU(struct static_sched_group, sched_groups); | 6975 | static DEFINE_PER_CPU(struct static_sched_group, sched_groups); |
6976 | 6976 | ||
6977 | static int | 6977 | static int |
6978 | cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, | 6978 | cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, |
6979 | struct sched_group **sg, struct cpumask *unused) | 6979 | struct sched_group **sg, struct cpumask *unused) |
6980 | { | 6980 | { |
6981 | if (sg) | 6981 | if (sg) |
6982 | *sg = &per_cpu(sched_groups, cpu).sg; | 6982 | *sg = &per_cpu(sched_groups, cpu).sg; |
6983 | return cpu; | 6983 | return cpu; |
6984 | } | 6984 | } |
6985 | #endif /* CONFIG_SCHED_SMT */ | 6985 | #endif /* CONFIG_SCHED_SMT */ |
6986 | 6986 | ||
6987 | /* | 6987 | /* |
6988 | * multi-core sched-domains: | 6988 | * multi-core sched-domains: |
6989 | */ | 6989 | */ |
6990 | #ifdef CONFIG_SCHED_MC | 6990 | #ifdef CONFIG_SCHED_MC |
6991 | static DEFINE_PER_CPU(struct static_sched_domain, core_domains); | 6991 | static DEFINE_PER_CPU(struct static_sched_domain, core_domains); |
6992 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); | 6992 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); |
6993 | 6993 | ||
6994 | static int | 6994 | static int |
6995 | cpu_to_core_group(int cpu, const struct cpumask *cpu_map, | 6995 | cpu_to_core_group(int cpu, const struct cpumask *cpu_map, |
6996 | struct sched_group **sg, struct cpumask *mask) | 6996 | struct sched_group **sg, struct cpumask *mask) |
6997 | { | 6997 | { |
6998 | int group; | 6998 | int group; |
6999 | #ifdef CONFIG_SCHED_SMT | 6999 | #ifdef CONFIG_SCHED_SMT |
7000 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); | 7000 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); |
7001 | group = cpumask_first(mask); | 7001 | group = cpumask_first(mask); |
7002 | #else | 7002 | #else |
7003 | group = cpu; | 7003 | group = cpu; |
7004 | #endif | 7004 | #endif |
7005 | if (sg) | 7005 | if (sg) |
7006 | *sg = &per_cpu(sched_group_core, group).sg; | 7006 | *sg = &per_cpu(sched_group_core, group).sg; |
7007 | return group; | 7007 | return group; |
7008 | } | 7008 | } |
7009 | #endif /* CONFIG_SCHED_MC */ | 7009 | #endif /* CONFIG_SCHED_MC */ |
7010 | 7010 | ||
7011 | /* | 7011 | /* |
7012 | * book sched-domains: | 7012 | * book sched-domains: |
7013 | */ | 7013 | */ |
7014 | #ifdef CONFIG_SCHED_BOOK | 7014 | #ifdef CONFIG_SCHED_BOOK |
7015 | static DEFINE_PER_CPU(struct static_sched_domain, book_domains); | 7015 | static DEFINE_PER_CPU(struct static_sched_domain, book_domains); |
7016 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); | 7016 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); |
7017 | 7017 | ||
7018 | static int | 7018 | static int |
7019 | cpu_to_book_group(int cpu, const struct cpumask *cpu_map, | 7019 | cpu_to_book_group(int cpu, const struct cpumask *cpu_map, |
7020 | struct sched_group **sg, struct cpumask *mask) | 7020 | struct sched_group **sg, struct cpumask *mask) |
7021 | { | 7021 | { |
7022 | int group = cpu; | 7022 | int group = cpu; |
7023 | #ifdef CONFIG_SCHED_MC | 7023 | #ifdef CONFIG_SCHED_MC |
7024 | cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); | 7024 | cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); |
7025 | group = cpumask_first(mask); | 7025 | group = cpumask_first(mask); |
7026 | #elif defined(CONFIG_SCHED_SMT) | 7026 | #elif defined(CONFIG_SCHED_SMT) |
7027 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); | 7027 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); |
7028 | group = cpumask_first(mask); | 7028 | group = cpumask_first(mask); |
7029 | #endif | 7029 | #endif |
7030 | if (sg) | 7030 | if (sg) |
7031 | *sg = &per_cpu(sched_group_book, group).sg; | 7031 | *sg = &per_cpu(sched_group_book, group).sg; |
7032 | return group; | 7032 | return group; |
7033 | } | 7033 | } |
7034 | #endif /* CONFIG_SCHED_BOOK */ | 7034 | #endif /* CONFIG_SCHED_BOOK */ |
7035 | 7035 | ||
7036 | static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); | 7036 | static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); |
7037 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); | 7037 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); |
7038 | 7038 | ||
7039 | static int | 7039 | static int |
7040 | cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, | 7040 | cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, |
7041 | struct sched_group **sg, struct cpumask *mask) | 7041 | struct sched_group **sg, struct cpumask *mask) |
7042 | { | 7042 | { |
7043 | int group; | 7043 | int group; |
7044 | #ifdef CONFIG_SCHED_BOOK | 7044 | #ifdef CONFIG_SCHED_BOOK |
7045 | cpumask_and(mask, cpu_book_mask(cpu), cpu_map); | 7045 | cpumask_and(mask, cpu_book_mask(cpu), cpu_map); |
7046 | group = cpumask_first(mask); | 7046 | group = cpumask_first(mask); |
7047 | #elif defined(CONFIG_SCHED_MC) | 7047 | #elif defined(CONFIG_SCHED_MC) |
7048 | cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); | 7048 | cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); |
7049 | group = cpumask_first(mask); | 7049 | group = cpumask_first(mask); |
7050 | #elif defined(CONFIG_SCHED_SMT) | 7050 | #elif defined(CONFIG_SCHED_SMT) |
7051 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); | 7051 | cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); |
7052 | group = cpumask_first(mask); | 7052 | group = cpumask_first(mask); |
7053 | #else | 7053 | #else |
7054 | group = cpu; | 7054 | group = cpu; |
7055 | #endif | 7055 | #endif |
7056 | if (sg) | 7056 | if (sg) |
7057 | *sg = &per_cpu(sched_group_phys, group).sg; | 7057 | *sg = &per_cpu(sched_group_phys, group).sg; |
7058 | return group; | 7058 | return group; |
7059 | } | 7059 | } |
7060 | 7060 | ||
7061 | #ifdef CONFIG_NUMA | 7061 | #ifdef CONFIG_NUMA |
7062 | /* | 7062 | /* |
7063 | * The init_sched_build_groups can't handle what we want to do with node | 7063 | * The init_sched_build_groups can't handle what we want to do with node |
7064 | * groups, so roll our own. Now each node has its own list of groups which | 7064 | * groups, so roll our own. Now each node has its own list of groups which |
7065 | * gets dynamically allocated. | 7065 | * gets dynamically allocated. |
7066 | */ | 7066 | */ |
7067 | static DEFINE_PER_CPU(struct static_sched_domain, node_domains); | 7067 | static DEFINE_PER_CPU(struct static_sched_domain, node_domains); |
7068 | static struct sched_group ***sched_group_nodes_bycpu; | 7068 | static struct sched_group ***sched_group_nodes_bycpu; |
7069 | 7069 | ||
7070 | static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); | 7070 | static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); |
7071 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); | 7071 | static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); |
7072 | 7072 | ||
7073 | static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, | 7073 | static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, |
7074 | struct sched_group **sg, | 7074 | struct sched_group **sg, |
7075 | struct cpumask *nodemask) | 7075 | struct cpumask *nodemask) |
7076 | { | 7076 | { |
7077 | int group; | 7077 | int group; |
7078 | 7078 | ||
7079 | cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); | 7079 | cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); |
7080 | group = cpumask_first(nodemask); | 7080 | group = cpumask_first(nodemask); |
7081 | 7081 | ||
7082 | if (sg) | 7082 | if (sg) |
7083 | *sg = &per_cpu(sched_group_allnodes, group).sg; | 7083 | *sg = &per_cpu(sched_group_allnodes, group).sg; |
7084 | return group; | 7084 | return group; |
7085 | } | 7085 | } |
7086 | 7086 | ||
7087 | static void init_numa_sched_groups_power(struct sched_group *group_head) | 7087 | static void init_numa_sched_groups_power(struct sched_group *group_head) |
7088 | { | 7088 | { |
7089 | struct sched_group *sg = group_head; | 7089 | struct sched_group *sg = group_head; |
7090 | int j; | 7090 | int j; |
7091 | 7091 | ||
7092 | if (!sg) | 7092 | if (!sg) |
7093 | return; | 7093 | return; |
7094 | do { | 7094 | do { |
7095 | for_each_cpu(j, sched_group_cpus(sg)) { | 7095 | for_each_cpu(j, sched_group_cpus(sg)) { |
7096 | struct sched_domain *sd; | 7096 | struct sched_domain *sd; |
7097 | 7097 | ||
7098 | sd = &per_cpu(phys_domains, j).sd; | 7098 | sd = &per_cpu(phys_domains, j).sd; |
7099 | if (j != group_first_cpu(sd->groups)) { | 7099 | if (j != group_first_cpu(sd->groups)) { |
7100 | /* | 7100 | /* |
7101 | * Only add "power" once for each | 7101 | * Only add "power" once for each |
7102 | * physical package. | 7102 | * physical package. |
7103 | */ | 7103 | */ |
7104 | continue; | 7104 | continue; |
7105 | } | 7105 | } |
7106 | 7106 | ||
7107 | sg->cpu_power += sd->groups->cpu_power; | 7107 | sg->cpu_power += sd->groups->cpu_power; |
7108 | } | 7108 | } |
7109 | sg = sg->next; | 7109 | sg = sg->next; |
7110 | } while (sg != group_head); | 7110 | } while (sg != group_head); |
7111 | } | 7111 | } |
7112 | 7112 | ||
7113 | static int build_numa_sched_groups(struct s_data *d, | 7113 | static int build_numa_sched_groups(struct s_data *d, |
7114 | const struct cpumask *cpu_map, int num) | 7114 | const struct cpumask *cpu_map, int num) |
7115 | { | 7115 | { |
7116 | struct sched_domain *sd; | 7116 | struct sched_domain *sd; |
7117 | struct sched_group *sg, *prev; | 7117 | struct sched_group *sg, *prev; |
7118 | int n, j; | 7118 | int n, j; |
7119 | 7119 | ||
7120 | cpumask_clear(d->covered); | 7120 | cpumask_clear(d->covered); |
7121 | cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map); | 7121 | cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map); |
7122 | if (cpumask_empty(d->nodemask)) { | 7122 | if (cpumask_empty(d->nodemask)) { |
7123 | d->sched_group_nodes[num] = NULL; | 7123 | d->sched_group_nodes[num] = NULL; |
7124 | goto out; | 7124 | goto out; |
7125 | } | 7125 | } |
7126 | 7126 | ||
7127 | sched_domain_node_span(num, d->domainspan); | 7127 | sched_domain_node_span(num, d->domainspan); |
7128 | cpumask_and(d->domainspan, d->domainspan, cpu_map); | 7128 | cpumask_and(d->domainspan, d->domainspan, cpu_map); |
7129 | 7129 | ||
7130 | sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), | 7130 | sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), |
7131 | GFP_KERNEL, num); | 7131 | GFP_KERNEL, num); |
7132 | if (!sg) { | 7132 | if (!sg) { |
7133 | printk(KERN_WARNING "Can not alloc domain group for node %d\n", | 7133 | printk(KERN_WARNING "Can not alloc domain group for node %d\n", |
7134 | num); | 7134 | num); |
7135 | return -ENOMEM; | 7135 | return -ENOMEM; |
7136 | } | 7136 | } |
7137 | d->sched_group_nodes[num] = sg; | 7137 | d->sched_group_nodes[num] = sg; |
7138 | 7138 | ||
7139 | for_each_cpu(j, d->nodemask) { | 7139 | for_each_cpu(j, d->nodemask) { |
7140 | sd = &per_cpu(node_domains, j).sd; | 7140 | sd = &per_cpu(node_domains, j).sd; |
7141 | sd->groups = sg; | 7141 | sd->groups = sg; |
7142 | } | 7142 | } |
7143 | 7143 | ||
7144 | sg->cpu_power = 0; | 7144 | sg->cpu_power = 0; |
7145 | cpumask_copy(sched_group_cpus(sg), d->nodemask); | 7145 | cpumask_copy(sched_group_cpus(sg), d->nodemask); |
7146 | sg->next = sg; | 7146 | sg->next = sg; |
7147 | cpumask_or(d->covered, d->covered, d->nodemask); | 7147 | cpumask_or(d->covered, d->covered, d->nodemask); |
7148 | 7148 | ||
7149 | prev = sg; | 7149 | prev = sg; |
7150 | for (j = 0; j < nr_node_ids; j++) { | 7150 | for (j = 0; j < nr_node_ids; j++) { |
7151 | n = (num + j) % nr_node_ids; | 7151 | n = (num + j) % nr_node_ids; |
7152 | cpumask_complement(d->notcovered, d->covered); | 7152 | cpumask_complement(d->notcovered, d->covered); |
7153 | cpumask_and(d->tmpmask, d->notcovered, cpu_map); | 7153 | cpumask_and(d->tmpmask, d->notcovered, cpu_map); |
7154 | cpumask_and(d->tmpmask, d->tmpmask, d->domainspan); | 7154 | cpumask_and(d->tmpmask, d->tmpmask, d->domainspan); |
7155 | if (cpumask_empty(d->tmpmask)) | 7155 | if (cpumask_empty(d->tmpmask)) |
7156 | break; | 7156 | break; |
7157 | cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n)); | 7157 | cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n)); |
7158 | if (cpumask_empty(d->tmpmask)) | 7158 | if (cpumask_empty(d->tmpmask)) |
7159 | continue; | 7159 | continue; |
7160 | sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), | 7160 | sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), |
7161 | GFP_KERNEL, num); | 7161 | GFP_KERNEL, num); |
7162 | if (!sg) { | 7162 | if (!sg) { |
7163 | printk(KERN_WARNING | 7163 | printk(KERN_WARNING |
7164 | "Can not alloc domain group for node %d\n", j); | 7164 | "Can not alloc domain group for node %d\n", j); |
7165 | return -ENOMEM; | 7165 | return -ENOMEM; |
7166 | } | 7166 | } |
7167 | sg->cpu_power = 0; | 7167 | sg->cpu_power = 0; |
7168 | cpumask_copy(sched_group_cpus(sg), d->tmpmask); | 7168 | cpumask_copy(sched_group_cpus(sg), d->tmpmask); |
7169 | sg->next = prev->next; | 7169 | sg->next = prev->next; |
7170 | cpumask_or(d->covered, d->covered, d->tmpmask); | 7170 | cpumask_or(d->covered, d->covered, d->tmpmask); |
7171 | prev->next = sg; | 7171 | prev->next = sg; |
7172 | prev = sg; | 7172 | prev = sg; |
7173 | } | 7173 | } |
7174 | out: | 7174 | out: |
7175 | return 0; | 7175 | return 0; |
7176 | } | 7176 | } |
7177 | #endif /* CONFIG_NUMA */ | 7177 | #endif /* CONFIG_NUMA */ |
7178 | 7178 | ||
7179 | #ifdef CONFIG_NUMA | 7179 | #ifdef CONFIG_NUMA |
7180 | /* Free memory allocated for various sched_group structures */ | 7180 | /* Free memory allocated for various sched_group structures */ |
7181 | static void free_sched_groups(const struct cpumask *cpu_map, | 7181 | static void free_sched_groups(const struct cpumask *cpu_map, |
7182 | struct cpumask *nodemask) | 7182 | struct cpumask *nodemask) |
7183 | { | 7183 | { |
7184 | int cpu, i; | 7184 | int cpu, i; |
7185 | 7185 | ||
7186 | for_each_cpu(cpu, cpu_map) { | 7186 | for_each_cpu(cpu, cpu_map) { |
7187 | struct sched_group **sched_group_nodes | 7187 | struct sched_group **sched_group_nodes |
7188 | = sched_group_nodes_bycpu[cpu]; | 7188 | = sched_group_nodes_bycpu[cpu]; |
7189 | 7189 | ||
7190 | if (!sched_group_nodes) | 7190 | if (!sched_group_nodes) |
7191 | continue; | 7191 | continue; |
7192 | 7192 | ||
7193 | for (i = 0; i < nr_node_ids; i++) { | 7193 | for (i = 0; i < nr_node_ids; i++) { |
7194 | struct sched_group *oldsg, *sg = sched_group_nodes[i]; | 7194 | struct sched_group *oldsg, *sg = sched_group_nodes[i]; |
7195 | 7195 | ||
7196 | cpumask_and(nodemask, cpumask_of_node(i), cpu_map); | 7196 | cpumask_and(nodemask, cpumask_of_node(i), cpu_map); |
7197 | if (cpumask_empty(nodemask)) | 7197 | if (cpumask_empty(nodemask)) |
7198 | continue; | 7198 | continue; |
7199 | 7199 | ||
7200 | if (sg == NULL) | 7200 | if (sg == NULL) |
7201 | continue; | 7201 | continue; |
7202 | sg = sg->next; | 7202 | sg = sg->next; |
7203 | next_sg: | 7203 | next_sg: |
7204 | oldsg = sg; | 7204 | oldsg = sg; |
7205 | sg = sg->next; | 7205 | sg = sg->next; |
7206 | kfree(oldsg); | 7206 | kfree(oldsg); |
7207 | if (oldsg != sched_group_nodes[i]) | 7207 | if (oldsg != sched_group_nodes[i]) |
7208 | goto next_sg; | 7208 | goto next_sg; |
7209 | } | 7209 | } |
7210 | kfree(sched_group_nodes); | 7210 | kfree(sched_group_nodes); |
7211 | sched_group_nodes_bycpu[cpu] = NULL; | 7211 | sched_group_nodes_bycpu[cpu] = NULL; |
7212 | } | 7212 | } |
7213 | } | 7213 | } |
7214 | #else /* !CONFIG_NUMA */ | 7214 | #else /* !CONFIG_NUMA */ |
7215 | static void free_sched_groups(const struct cpumask *cpu_map, | 7215 | static void free_sched_groups(const struct cpumask *cpu_map, |
7216 | struct cpumask *nodemask) | 7216 | struct cpumask *nodemask) |
7217 | { | 7217 | { |
7218 | } | 7218 | } |
7219 | #endif /* CONFIG_NUMA */ | 7219 | #endif /* CONFIG_NUMA */ |
7220 | 7220 | ||
7221 | /* | 7221 | /* |
7222 | * Initialize sched groups cpu_power. | 7222 | * Initialize sched groups cpu_power. |
7223 | * | 7223 | * |
7224 | * cpu_power indicates the capacity of sched group, which is used while | 7224 | * cpu_power indicates the capacity of sched group, which is used while |
7225 | * distributing the load between different sched groups in a sched domain. | 7225 | * distributing the load between different sched groups in a sched domain. |
7226 | * Typically cpu_power for all the groups in a sched domain will be same unless | 7226 | * Typically cpu_power for all the groups in a sched domain will be same unless |
7227 | * there are asymmetries in the topology. If there are asymmetries, group | 7227 | * there are asymmetries in the topology. If there are asymmetries, group |
7228 | * having more cpu_power will pickup more load compared to the group having | 7228 | * having more cpu_power will pickup more load compared to the group having |
7229 | * less cpu_power. | 7229 | * less cpu_power. |
7230 | */ | 7230 | */ |
7231 | static void init_sched_groups_power(int cpu, struct sched_domain *sd) | 7231 | static void init_sched_groups_power(int cpu, struct sched_domain *sd) |
7232 | { | 7232 | { |
7233 | struct sched_domain *child; | 7233 | struct sched_domain *child; |
7234 | struct sched_group *group; | 7234 | struct sched_group *group; |
7235 | long power; | 7235 | long power; |
7236 | int weight; | 7236 | int weight; |
7237 | 7237 | ||
7238 | WARN_ON(!sd || !sd->groups); | 7238 | WARN_ON(!sd || !sd->groups); |
7239 | 7239 | ||
7240 | if (cpu != group_first_cpu(sd->groups)) | 7240 | if (cpu != group_first_cpu(sd->groups)) |
7241 | return; | 7241 | return; |
7242 | 7242 | ||
7243 | sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); | 7243 | sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); |
7244 | 7244 | ||
7245 | child = sd->child; | 7245 | child = sd->child; |
7246 | 7246 | ||
7247 | sd->groups->cpu_power = 0; | 7247 | sd->groups->cpu_power = 0; |
7248 | 7248 | ||
7249 | if (!child) { | 7249 | if (!child) { |
7250 | power = SCHED_LOAD_SCALE; | 7250 | power = SCHED_LOAD_SCALE; |
7251 | weight = cpumask_weight(sched_domain_span(sd)); | 7251 | weight = cpumask_weight(sched_domain_span(sd)); |
7252 | /* | 7252 | /* |
7253 | * SMT siblings share the power of a single core. | 7253 | * SMT siblings share the power of a single core. |
7254 | * Usually multiple threads get a better yield out of | 7254 | * Usually multiple threads get a better yield out of |
7255 | * that one core than a single thread would have, | 7255 | * that one core than a single thread would have, |
7256 | * reflect that in sd->smt_gain. | 7256 | * reflect that in sd->smt_gain. |
7257 | */ | 7257 | */ |
7258 | if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { | 7258 | if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { |
7259 | power *= sd->smt_gain; | 7259 | power *= sd->smt_gain; |
7260 | power /= weight; | 7260 | power /= weight; |
7261 | power >>= SCHED_LOAD_SHIFT; | 7261 | power >>= SCHED_LOAD_SHIFT; |
7262 | } | 7262 | } |
7263 | sd->groups->cpu_power += power; | 7263 | sd->groups->cpu_power += power; |
7264 | return; | 7264 | return; |
7265 | } | 7265 | } |
7266 | 7266 | ||
7267 | /* | 7267 | /* |
7268 | * Add cpu_power of each child group to this groups cpu_power. | 7268 | * Add cpu_power of each child group to this groups cpu_power. |
7269 | */ | 7269 | */ |
7270 | group = child->groups; | 7270 | group = child->groups; |
7271 | do { | 7271 | do { |
7272 | sd->groups->cpu_power += group->cpu_power; | 7272 | sd->groups->cpu_power += group->cpu_power; |
7273 | group = group->next; | 7273 | group = group->next; |
7274 | } while (group != child->groups); | 7274 | } while (group != child->groups); |
7275 | } | 7275 | } |
7276 | 7276 | ||
7277 | /* | 7277 | /* |
7278 | * Initializers for schedule domains | 7278 | * Initializers for schedule domains |
7279 | * Non-inlined to reduce accumulated stack pressure in build_sched_domains() | 7279 | * Non-inlined to reduce accumulated stack pressure in build_sched_domains() |
7280 | */ | 7280 | */ |
7281 | 7281 | ||
7282 | #ifdef CONFIG_SCHED_DEBUG | 7282 | #ifdef CONFIG_SCHED_DEBUG |
7283 | # define SD_INIT_NAME(sd, type) sd->name = #type | 7283 | # define SD_INIT_NAME(sd, type) sd->name = #type |
7284 | #else | 7284 | #else |
7285 | # define SD_INIT_NAME(sd, type) do { } while (0) | 7285 | # define SD_INIT_NAME(sd, type) do { } while (0) |
7286 | #endif | 7286 | #endif |
7287 | 7287 | ||
7288 | #define SD_INIT(sd, type) sd_init_##type(sd) | 7288 | #define SD_INIT(sd, type) sd_init_##type(sd) |
7289 | 7289 | ||
7290 | #define SD_INIT_FUNC(type) \ | 7290 | #define SD_INIT_FUNC(type) \ |
7291 | static noinline void sd_init_##type(struct sched_domain *sd) \ | 7291 | static noinline void sd_init_##type(struct sched_domain *sd) \ |
7292 | { \ | 7292 | { \ |
7293 | memset(sd, 0, sizeof(*sd)); \ | 7293 | memset(sd, 0, sizeof(*sd)); \ |
7294 | *sd = SD_##type##_INIT; \ | 7294 | *sd = SD_##type##_INIT; \ |
7295 | sd->level = SD_LV_##type; \ | 7295 | sd->level = SD_LV_##type; \ |
7296 | SD_INIT_NAME(sd, type); \ | 7296 | SD_INIT_NAME(sd, type); \ |
7297 | } | 7297 | } |
7298 | 7298 | ||
7299 | SD_INIT_FUNC(CPU) | 7299 | SD_INIT_FUNC(CPU) |
7300 | #ifdef CONFIG_NUMA | 7300 | #ifdef CONFIG_NUMA |
7301 | SD_INIT_FUNC(ALLNODES) | 7301 | SD_INIT_FUNC(ALLNODES) |
7302 | SD_INIT_FUNC(NODE) | 7302 | SD_INIT_FUNC(NODE) |
7303 | #endif | 7303 | #endif |
7304 | #ifdef CONFIG_SCHED_SMT | 7304 | #ifdef CONFIG_SCHED_SMT |
7305 | SD_INIT_FUNC(SIBLING) | 7305 | SD_INIT_FUNC(SIBLING) |
7306 | #endif | 7306 | #endif |
7307 | #ifdef CONFIG_SCHED_MC | 7307 | #ifdef CONFIG_SCHED_MC |
7308 | SD_INIT_FUNC(MC) | 7308 | SD_INIT_FUNC(MC) |
7309 | #endif | 7309 | #endif |
7310 | #ifdef CONFIG_SCHED_BOOK | 7310 | #ifdef CONFIG_SCHED_BOOK |
7311 | SD_INIT_FUNC(BOOK) | 7311 | SD_INIT_FUNC(BOOK) |
7312 | #endif | 7312 | #endif |
7313 | 7313 | ||
7314 | static int default_relax_domain_level = -1; | 7314 | static int default_relax_domain_level = -1; |
7315 | 7315 | ||
7316 | static int __init setup_relax_domain_level(char *str) | 7316 | static int __init setup_relax_domain_level(char *str) |
7317 | { | 7317 | { |
7318 | unsigned long val; | 7318 | unsigned long val; |
7319 | 7319 | ||
7320 | val = simple_strtoul(str, NULL, 0); | 7320 | val = simple_strtoul(str, NULL, 0); |
7321 | if (val < SD_LV_MAX) | 7321 | if (val < SD_LV_MAX) |
7322 | default_relax_domain_level = val; | 7322 | default_relax_domain_level = val; |
7323 | 7323 | ||
7324 | return 1; | 7324 | return 1; |
7325 | } | 7325 | } |
7326 | __setup("relax_domain_level=", setup_relax_domain_level); | 7326 | __setup("relax_domain_level=", setup_relax_domain_level); |
7327 | 7327 | ||
7328 | static void set_domain_attribute(struct sched_domain *sd, | 7328 | static void set_domain_attribute(struct sched_domain *sd, |
7329 | struct sched_domain_attr *attr) | 7329 | struct sched_domain_attr *attr) |
7330 | { | 7330 | { |
7331 | int request; | 7331 | int request; |
7332 | 7332 | ||
7333 | if (!attr || attr->relax_domain_level < 0) { | 7333 | if (!attr || attr->relax_domain_level < 0) { |
7334 | if (default_relax_domain_level < 0) | 7334 | if (default_relax_domain_level < 0) |
7335 | return; | 7335 | return; |
7336 | else | 7336 | else |
7337 | request = default_relax_domain_level; | 7337 | request = default_relax_domain_level; |
7338 | } else | 7338 | } else |
7339 | request = attr->relax_domain_level; | 7339 | request = attr->relax_domain_level; |
7340 | if (request < sd->level) { | 7340 | if (request < sd->level) { |
7341 | /* turn off idle balance on this domain */ | 7341 | /* turn off idle balance on this domain */ |
7342 | sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); | 7342 | sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); |
7343 | } else { | 7343 | } else { |
7344 | /* turn on idle balance on this domain */ | 7344 | /* turn on idle balance on this domain */ |
7345 | sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); | 7345 | sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); |
7346 | } | 7346 | } |
7347 | } | 7347 | } |
7348 | 7348 | ||
7349 | static void __free_domain_allocs(struct s_data *d, enum s_alloc what, | 7349 | static void __free_domain_allocs(struct s_data *d, enum s_alloc what, |
7350 | const struct cpumask *cpu_map) | 7350 | const struct cpumask *cpu_map) |
7351 | { | 7351 | { |
7352 | switch (what) { | 7352 | switch (what) { |
7353 | case sa_sched_groups: | 7353 | case sa_sched_groups: |
7354 | free_sched_groups(cpu_map, d->tmpmask); /* fall through */ | 7354 | free_sched_groups(cpu_map, d->tmpmask); /* fall through */ |
7355 | d->sched_group_nodes = NULL; | 7355 | d->sched_group_nodes = NULL; |
7356 | case sa_rootdomain: | 7356 | case sa_rootdomain: |
7357 | free_rootdomain(d->rd); /* fall through */ | 7357 | free_rootdomain(d->rd); /* fall through */ |
7358 | case sa_tmpmask: | 7358 | case sa_tmpmask: |
7359 | free_cpumask_var(d->tmpmask); /* fall through */ | 7359 | free_cpumask_var(d->tmpmask); /* fall through */ |
7360 | case sa_send_covered: | 7360 | case sa_send_covered: |
7361 | free_cpumask_var(d->send_covered); /* fall through */ | 7361 | free_cpumask_var(d->send_covered); /* fall through */ |
7362 | case sa_this_book_map: | 7362 | case sa_this_book_map: |
7363 | free_cpumask_var(d->this_book_map); /* fall through */ | 7363 | free_cpumask_var(d->this_book_map); /* fall through */ |
7364 | case sa_this_core_map: | 7364 | case sa_this_core_map: |
7365 | free_cpumask_var(d->this_core_map); /* fall through */ | 7365 | free_cpumask_var(d->this_core_map); /* fall through */ |
7366 | case sa_this_sibling_map: | 7366 | case sa_this_sibling_map: |
7367 | free_cpumask_var(d->this_sibling_map); /* fall through */ | 7367 | free_cpumask_var(d->this_sibling_map); /* fall through */ |
7368 | case sa_nodemask: | 7368 | case sa_nodemask: |
7369 | free_cpumask_var(d->nodemask); /* fall through */ | 7369 | free_cpumask_var(d->nodemask); /* fall through */ |
7370 | case sa_sched_group_nodes: | 7370 | case sa_sched_group_nodes: |
7371 | #ifdef CONFIG_NUMA | 7371 | #ifdef CONFIG_NUMA |
7372 | kfree(d->sched_group_nodes); /* fall through */ | 7372 | kfree(d->sched_group_nodes); /* fall through */ |
7373 | case sa_notcovered: | 7373 | case sa_notcovered: |
7374 | free_cpumask_var(d->notcovered); /* fall through */ | 7374 | free_cpumask_var(d->notcovered); /* fall through */ |
7375 | case sa_covered: | 7375 | case sa_covered: |
7376 | free_cpumask_var(d->covered); /* fall through */ | 7376 | free_cpumask_var(d->covered); /* fall through */ |
7377 | case sa_domainspan: | 7377 | case sa_domainspan: |
7378 | free_cpumask_var(d->domainspan); /* fall through */ | 7378 | free_cpumask_var(d->domainspan); /* fall through */ |
7379 | #endif | 7379 | #endif |
7380 | case sa_none: | 7380 | case sa_none: |
7381 | break; | 7381 | break; |
7382 | } | 7382 | } |
7383 | } | 7383 | } |
7384 | 7384 | ||
7385 | static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, | 7385 | static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, |
7386 | const struct cpumask *cpu_map) | 7386 | const struct cpumask *cpu_map) |
7387 | { | 7387 | { |
7388 | #ifdef CONFIG_NUMA | 7388 | #ifdef CONFIG_NUMA |
7389 | if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL)) | 7389 | if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL)) |
7390 | return sa_none; | 7390 | return sa_none; |
7391 | if (!alloc_cpumask_var(&d->covered, GFP_KERNEL)) | 7391 | if (!alloc_cpumask_var(&d->covered, GFP_KERNEL)) |
7392 | return sa_domainspan; | 7392 | return sa_domainspan; |
7393 | if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL)) | 7393 | if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL)) |
7394 | return sa_covered; | 7394 | return sa_covered; |
7395 | /* Allocate the per-node list of sched groups */ | 7395 | /* Allocate the per-node list of sched groups */ |
7396 | d->sched_group_nodes = kcalloc(nr_node_ids, | 7396 | d->sched_group_nodes = kcalloc(nr_node_ids, |
7397 | sizeof(struct sched_group *), GFP_KERNEL); | 7397 | sizeof(struct sched_group *), GFP_KERNEL); |
7398 | if (!d->sched_group_nodes) { | 7398 | if (!d->sched_group_nodes) { |
7399 | printk(KERN_WARNING "Can not alloc sched group node list\n"); | 7399 | printk(KERN_WARNING "Can not alloc sched group node list\n"); |
7400 | return sa_notcovered; | 7400 | return sa_notcovered; |
7401 | } | 7401 | } |
7402 | sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes; | 7402 | sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes; |
7403 | #endif | 7403 | #endif |
7404 | if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) | 7404 | if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) |
7405 | return sa_sched_group_nodes; | 7405 | return sa_sched_group_nodes; |
7406 | if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL)) | 7406 | if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL)) |
7407 | return sa_nodemask; | 7407 | return sa_nodemask; |
7408 | if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL)) | 7408 | if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL)) |
7409 | return sa_this_sibling_map; | 7409 | return sa_this_sibling_map; |
7410 | if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL)) | 7410 | if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL)) |
7411 | return sa_this_core_map; | 7411 | return sa_this_core_map; |
7412 | if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) | 7412 | if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) |
7413 | return sa_this_book_map; | 7413 | return sa_this_book_map; |
7414 | if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) | 7414 | if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) |
7415 | return sa_send_covered; | 7415 | return sa_send_covered; |
7416 | d->rd = alloc_rootdomain(); | 7416 | d->rd = alloc_rootdomain(); |
7417 | if (!d->rd) { | 7417 | if (!d->rd) { |
7418 | printk(KERN_WARNING "Cannot alloc root domain\n"); | 7418 | printk(KERN_WARNING "Cannot alloc root domain\n"); |
7419 | return sa_tmpmask; | 7419 | return sa_tmpmask; |
7420 | } | 7420 | } |
7421 | return sa_rootdomain; | 7421 | return sa_rootdomain; |
7422 | } | 7422 | } |
7423 | 7423 | ||
7424 | static struct sched_domain *__build_numa_sched_domains(struct s_data *d, | 7424 | static struct sched_domain *__build_numa_sched_domains(struct s_data *d, |
7425 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) | 7425 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) |
7426 | { | 7426 | { |
7427 | struct sched_domain *sd = NULL; | 7427 | struct sched_domain *sd = NULL; |
7428 | #ifdef CONFIG_NUMA | 7428 | #ifdef CONFIG_NUMA |
7429 | struct sched_domain *parent; | 7429 | struct sched_domain *parent; |
7430 | 7430 | ||
7431 | d->sd_allnodes = 0; | 7431 | d->sd_allnodes = 0; |
7432 | if (cpumask_weight(cpu_map) > | 7432 | if (cpumask_weight(cpu_map) > |
7433 | SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { | 7433 | SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { |
7434 | sd = &per_cpu(allnodes_domains, i).sd; | 7434 | sd = &per_cpu(allnodes_domains, i).sd; |
7435 | SD_INIT(sd, ALLNODES); | 7435 | SD_INIT(sd, ALLNODES); |
7436 | set_domain_attribute(sd, attr); | 7436 | set_domain_attribute(sd, attr); |
7437 | cpumask_copy(sched_domain_span(sd), cpu_map); | 7437 | cpumask_copy(sched_domain_span(sd), cpu_map); |
7438 | cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); | 7438 | cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); |
7439 | d->sd_allnodes = 1; | 7439 | d->sd_allnodes = 1; |
7440 | } | 7440 | } |
7441 | parent = sd; | 7441 | parent = sd; |
7442 | 7442 | ||
7443 | sd = &per_cpu(node_domains, i).sd; | 7443 | sd = &per_cpu(node_domains, i).sd; |
7444 | SD_INIT(sd, NODE); | 7444 | SD_INIT(sd, NODE); |
7445 | set_domain_attribute(sd, attr); | 7445 | set_domain_attribute(sd, attr); |
7446 | sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); | 7446 | sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); |
7447 | sd->parent = parent; | 7447 | sd->parent = parent; |
7448 | if (parent) | 7448 | if (parent) |
7449 | parent->child = sd; | 7449 | parent->child = sd; |
7450 | cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); | 7450 | cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); |
7451 | #endif | 7451 | #endif |
7452 | return sd; | 7452 | return sd; |
7453 | } | 7453 | } |
7454 | 7454 | ||
7455 | static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, | 7455 | static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, |
7456 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, | 7456 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, |
7457 | struct sched_domain *parent, int i) | 7457 | struct sched_domain *parent, int i) |
7458 | { | 7458 | { |
7459 | struct sched_domain *sd; | 7459 | struct sched_domain *sd; |
7460 | sd = &per_cpu(phys_domains, i).sd; | 7460 | sd = &per_cpu(phys_domains, i).sd; |
7461 | SD_INIT(sd, CPU); | 7461 | SD_INIT(sd, CPU); |
7462 | set_domain_attribute(sd, attr); | 7462 | set_domain_attribute(sd, attr); |
7463 | cpumask_copy(sched_domain_span(sd), d->nodemask); | 7463 | cpumask_copy(sched_domain_span(sd), d->nodemask); |
7464 | sd->parent = parent; | 7464 | sd->parent = parent; |
7465 | if (parent) | 7465 | if (parent) |
7466 | parent->child = sd; | 7466 | parent->child = sd; |
7467 | cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); | 7467 | cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); |
7468 | return sd; | 7468 | return sd; |
7469 | } | 7469 | } |
7470 | 7470 | ||
7471 | static struct sched_domain *__build_book_sched_domain(struct s_data *d, | 7471 | static struct sched_domain *__build_book_sched_domain(struct s_data *d, |
7472 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, | 7472 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, |
7473 | struct sched_domain *parent, int i) | 7473 | struct sched_domain *parent, int i) |
7474 | { | 7474 | { |
7475 | struct sched_domain *sd = parent; | 7475 | struct sched_domain *sd = parent; |
7476 | #ifdef CONFIG_SCHED_BOOK | 7476 | #ifdef CONFIG_SCHED_BOOK |
7477 | sd = &per_cpu(book_domains, i).sd; | 7477 | sd = &per_cpu(book_domains, i).sd; |
7478 | SD_INIT(sd, BOOK); | 7478 | SD_INIT(sd, BOOK); |
7479 | set_domain_attribute(sd, attr); | 7479 | set_domain_attribute(sd, attr); |
7480 | cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); | 7480 | cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); |
7481 | sd->parent = parent; | 7481 | sd->parent = parent; |
7482 | parent->child = sd; | 7482 | parent->child = sd; |
7483 | cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); | 7483 | cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); |
7484 | #endif | 7484 | #endif |
7485 | return sd; | 7485 | return sd; |
7486 | } | 7486 | } |
7487 | 7487 | ||
7488 | static struct sched_domain *__build_mc_sched_domain(struct s_data *d, | 7488 | static struct sched_domain *__build_mc_sched_domain(struct s_data *d, |
7489 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, | 7489 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, |
7490 | struct sched_domain *parent, int i) | 7490 | struct sched_domain *parent, int i) |
7491 | { | 7491 | { |
7492 | struct sched_domain *sd = parent; | 7492 | struct sched_domain *sd = parent; |
7493 | #ifdef CONFIG_SCHED_MC | 7493 | #ifdef CONFIG_SCHED_MC |
7494 | sd = &per_cpu(core_domains, i).sd; | 7494 | sd = &per_cpu(core_domains, i).sd; |
7495 | SD_INIT(sd, MC); | 7495 | SD_INIT(sd, MC); |
7496 | set_domain_attribute(sd, attr); | 7496 | set_domain_attribute(sd, attr); |
7497 | cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); | 7497 | cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); |
7498 | sd->parent = parent; | 7498 | sd->parent = parent; |
7499 | parent->child = sd; | 7499 | parent->child = sd; |
7500 | cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); | 7500 | cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); |
7501 | #endif | 7501 | #endif |
7502 | return sd; | 7502 | return sd; |
7503 | } | 7503 | } |
7504 | 7504 | ||
7505 | static struct sched_domain *__build_smt_sched_domain(struct s_data *d, | 7505 | static struct sched_domain *__build_smt_sched_domain(struct s_data *d, |
7506 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, | 7506 | const struct cpumask *cpu_map, struct sched_domain_attr *attr, |
7507 | struct sched_domain *parent, int i) | 7507 | struct sched_domain *parent, int i) |
7508 | { | 7508 | { |
7509 | struct sched_domain *sd = parent; | 7509 | struct sched_domain *sd = parent; |
7510 | #ifdef CONFIG_SCHED_SMT | 7510 | #ifdef CONFIG_SCHED_SMT |
7511 | sd = &per_cpu(cpu_domains, i).sd; | 7511 | sd = &per_cpu(cpu_domains, i).sd; |
7512 | SD_INIT(sd, SIBLING); | 7512 | SD_INIT(sd, SIBLING); |
7513 | set_domain_attribute(sd, attr); | 7513 | set_domain_attribute(sd, attr); |
7514 | cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); | 7514 | cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); |
7515 | sd->parent = parent; | 7515 | sd->parent = parent; |
7516 | parent->child = sd; | 7516 | parent->child = sd; |
7517 | cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); | 7517 | cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); |
7518 | #endif | 7518 | #endif |
7519 | return sd; | 7519 | return sd; |
7520 | } | 7520 | } |
7521 | 7521 | ||
7522 | static void build_sched_groups(struct s_data *d, enum sched_domain_level l, | 7522 | static void build_sched_groups(struct s_data *d, enum sched_domain_level l, |
7523 | const struct cpumask *cpu_map, int cpu) | 7523 | const struct cpumask *cpu_map, int cpu) |
7524 | { | 7524 | { |
7525 | switch (l) { | 7525 | switch (l) { |
7526 | #ifdef CONFIG_SCHED_SMT | 7526 | #ifdef CONFIG_SCHED_SMT |
7527 | case SD_LV_SIBLING: /* set up CPU (sibling) groups */ | 7527 | case SD_LV_SIBLING: /* set up CPU (sibling) groups */ |
7528 | cpumask_and(d->this_sibling_map, cpu_map, | 7528 | cpumask_and(d->this_sibling_map, cpu_map, |
7529 | topology_thread_cpumask(cpu)); | 7529 | topology_thread_cpumask(cpu)); |
7530 | if (cpu == cpumask_first(d->this_sibling_map)) | 7530 | if (cpu == cpumask_first(d->this_sibling_map)) |
7531 | init_sched_build_groups(d->this_sibling_map, cpu_map, | 7531 | init_sched_build_groups(d->this_sibling_map, cpu_map, |
7532 | &cpu_to_cpu_group, | 7532 | &cpu_to_cpu_group, |
7533 | d->send_covered, d->tmpmask); | 7533 | d->send_covered, d->tmpmask); |
7534 | break; | 7534 | break; |
7535 | #endif | 7535 | #endif |
7536 | #ifdef CONFIG_SCHED_MC | 7536 | #ifdef CONFIG_SCHED_MC |
7537 | case SD_LV_MC: /* set up multi-core groups */ | 7537 | case SD_LV_MC: /* set up multi-core groups */ |
7538 | cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu)); | 7538 | cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu)); |
7539 | if (cpu == cpumask_first(d->this_core_map)) | 7539 | if (cpu == cpumask_first(d->this_core_map)) |
7540 | init_sched_build_groups(d->this_core_map, cpu_map, | 7540 | init_sched_build_groups(d->this_core_map, cpu_map, |
7541 | &cpu_to_core_group, | 7541 | &cpu_to_core_group, |
7542 | d->send_covered, d->tmpmask); | 7542 | d->send_covered, d->tmpmask); |
7543 | break; | 7543 | break; |
7544 | #endif | 7544 | #endif |
7545 | #ifdef CONFIG_SCHED_BOOK | 7545 | #ifdef CONFIG_SCHED_BOOK |
7546 | case SD_LV_BOOK: /* set up book groups */ | 7546 | case SD_LV_BOOK: /* set up book groups */ |
7547 | cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu)); | 7547 | cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu)); |
7548 | if (cpu == cpumask_first(d->this_book_map)) | 7548 | if (cpu == cpumask_first(d->this_book_map)) |
7549 | init_sched_build_groups(d->this_book_map, cpu_map, | 7549 | init_sched_build_groups(d->this_book_map, cpu_map, |
7550 | &cpu_to_book_group, | 7550 | &cpu_to_book_group, |
7551 | d->send_covered, d->tmpmask); | 7551 | d->send_covered, d->tmpmask); |
7552 | break; | 7552 | break; |
7553 | #endif | 7553 | #endif |
7554 | case SD_LV_CPU: /* set up physical groups */ | 7554 | case SD_LV_CPU: /* set up physical groups */ |
7555 | cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map); | 7555 | cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map); |
7556 | if (!cpumask_empty(d->nodemask)) | 7556 | if (!cpumask_empty(d->nodemask)) |
7557 | init_sched_build_groups(d->nodemask, cpu_map, | 7557 | init_sched_build_groups(d->nodemask, cpu_map, |
7558 | &cpu_to_phys_group, | 7558 | &cpu_to_phys_group, |
7559 | d->send_covered, d->tmpmask); | 7559 | d->send_covered, d->tmpmask); |
7560 | break; | 7560 | break; |
7561 | #ifdef CONFIG_NUMA | 7561 | #ifdef CONFIG_NUMA |
7562 | case SD_LV_ALLNODES: | 7562 | case SD_LV_ALLNODES: |
7563 | init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, | 7563 | init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, |
7564 | d->send_covered, d->tmpmask); | 7564 | d->send_covered, d->tmpmask); |
7565 | break; | 7565 | break; |
7566 | #endif | 7566 | #endif |
7567 | default: | 7567 | default: |
7568 | break; | 7568 | break; |
7569 | } | 7569 | } |
7570 | } | 7570 | } |
7571 | 7571 | ||
7572 | /* | 7572 | /* |
7573 | * Build sched domains for a given set of cpus and attach the sched domains | 7573 | * Build sched domains for a given set of cpus and attach the sched domains |
7574 | * to the individual cpus | 7574 | * to the individual cpus |
7575 | */ | 7575 | */ |
7576 | static int __build_sched_domains(const struct cpumask *cpu_map, | 7576 | static int __build_sched_domains(const struct cpumask *cpu_map, |
7577 | struct sched_domain_attr *attr) | 7577 | struct sched_domain_attr *attr) |
7578 | { | 7578 | { |
7579 | enum s_alloc alloc_state = sa_none; | 7579 | enum s_alloc alloc_state = sa_none; |
7580 | struct s_data d; | 7580 | struct s_data d; |
7581 | struct sched_domain *sd; | 7581 | struct sched_domain *sd; |
7582 | int i; | 7582 | int i; |
7583 | #ifdef CONFIG_NUMA | 7583 | #ifdef CONFIG_NUMA |
7584 | d.sd_allnodes = 0; | 7584 | d.sd_allnodes = 0; |
7585 | #endif | 7585 | #endif |
7586 | 7586 | ||
7587 | alloc_state = __visit_domain_allocation_hell(&d, cpu_map); | 7587 | alloc_state = __visit_domain_allocation_hell(&d, cpu_map); |
7588 | if (alloc_state != sa_rootdomain) | 7588 | if (alloc_state != sa_rootdomain) |
7589 | goto error; | 7589 | goto error; |
7590 | alloc_state = sa_sched_groups; | 7590 | alloc_state = sa_sched_groups; |
7591 | 7591 | ||
7592 | /* | 7592 | /* |
7593 | * Set up domains for cpus specified by the cpu_map. | 7593 | * Set up domains for cpus specified by the cpu_map. |
7594 | */ | 7594 | */ |
7595 | for_each_cpu(i, cpu_map) { | 7595 | for_each_cpu(i, cpu_map) { |
7596 | cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), | 7596 | cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), |
7597 | cpu_map); | 7597 | cpu_map); |
7598 | 7598 | ||
7599 | sd = __build_numa_sched_domains(&d, cpu_map, attr, i); | 7599 | sd = __build_numa_sched_domains(&d, cpu_map, attr, i); |
7600 | sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i); | 7600 | sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i); |
7601 | sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i); | 7601 | sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i); |
7602 | sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i); | 7602 | sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i); |
7603 | sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); | 7603 | sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); |
7604 | } | 7604 | } |
7605 | 7605 | ||
7606 | for_each_cpu(i, cpu_map) { | 7606 | for_each_cpu(i, cpu_map) { |
7607 | build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i); | 7607 | build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i); |
7608 | build_sched_groups(&d, SD_LV_BOOK, cpu_map, i); | 7608 | build_sched_groups(&d, SD_LV_BOOK, cpu_map, i); |
7609 | build_sched_groups(&d, SD_LV_MC, cpu_map, i); | 7609 | build_sched_groups(&d, SD_LV_MC, cpu_map, i); |
7610 | } | 7610 | } |
7611 | 7611 | ||
7612 | /* Set up physical groups */ | 7612 | /* Set up physical groups */ |
7613 | for (i = 0; i < nr_node_ids; i++) | 7613 | for (i = 0; i < nr_node_ids; i++) |
7614 | build_sched_groups(&d, SD_LV_CPU, cpu_map, i); | 7614 | build_sched_groups(&d, SD_LV_CPU, cpu_map, i); |
7615 | 7615 | ||
7616 | #ifdef CONFIG_NUMA | 7616 | #ifdef CONFIG_NUMA |
7617 | /* Set up node groups */ | 7617 | /* Set up node groups */ |
7618 | if (d.sd_allnodes) | 7618 | if (d.sd_allnodes) |
7619 | build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0); | 7619 | build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0); |
7620 | 7620 | ||
7621 | for (i = 0; i < nr_node_ids; i++) | 7621 | for (i = 0; i < nr_node_ids; i++) |
7622 | if (build_numa_sched_groups(&d, cpu_map, i)) | 7622 | if (build_numa_sched_groups(&d, cpu_map, i)) |
7623 | goto error; | 7623 | goto error; |
7624 | #endif | 7624 | #endif |
7625 | 7625 | ||
7626 | /* Calculate CPU power for physical packages and nodes */ | 7626 | /* Calculate CPU power for physical packages and nodes */ |
7627 | #ifdef CONFIG_SCHED_SMT | 7627 | #ifdef CONFIG_SCHED_SMT |
7628 | for_each_cpu(i, cpu_map) { | 7628 | for_each_cpu(i, cpu_map) { |
7629 | sd = &per_cpu(cpu_domains, i).sd; | 7629 | sd = &per_cpu(cpu_domains, i).sd; |
7630 | init_sched_groups_power(i, sd); | 7630 | init_sched_groups_power(i, sd); |
7631 | } | 7631 | } |
7632 | #endif | 7632 | #endif |
7633 | #ifdef CONFIG_SCHED_MC | 7633 | #ifdef CONFIG_SCHED_MC |
7634 | for_each_cpu(i, cpu_map) { | 7634 | for_each_cpu(i, cpu_map) { |
7635 | sd = &per_cpu(core_domains, i).sd; | 7635 | sd = &per_cpu(core_domains, i).sd; |
7636 | init_sched_groups_power(i, sd); | 7636 | init_sched_groups_power(i, sd); |
7637 | } | 7637 | } |
7638 | #endif | 7638 | #endif |
7639 | #ifdef CONFIG_SCHED_BOOK | 7639 | #ifdef CONFIG_SCHED_BOOK |
7640 | for_each_cpu(i, cpu_map) { | 7640 | for_each_cpu(i, cpu_map) { |
7641 | sd = &per_cpu(book_domains, i).sd; | 7641 | sd = &per_cpu(book_domains, i).sd; |
7642 | init_sched_groups_power(i, sd); | 7642 | init_sched_groups_power(i, sd); |
7643 | } | 7643 | } |
7644 | #endif | 7644 | #endif |
7645 | 7645 | ||
7646 | for_each_cpu(i, cpu_map) { | 7646 | for_each_cpu(i, cpu_map) { |
7647 | sd = &per_cpu(phys_domains, i).sd; | 7647 | sd = &per_cpu(phys_domains, i).sd; |
7648 | init_sched_groups_power(i, sd); | 7648 | init_sched_groups_power(i, sd); |
7649 | } | 7649 | } |
7650 | 7650 | ||
7651 | #ifdef CONFIG_NUMA | 7651 | #ifdef CONFIG_NUMA |
7652 | for (i = 0; i < nr_node_ids; i++) | 7652 | for (i = 0; i < nr_node_ids; i++) |
7653 | init_numa_sched_groups_power(d.sched_group_nodes[i]); | 7653 | init_numa_sched_groups_power(d.sched_group_nodes[i]); |
7654 | 7654 | ||
7655 | if (d.sd_allnodes) { | 7655 | if (d.sd_allnodes) { |
7656 | struct sched_group *sg; | 7656 | struct sched_group *sg; |
7657 | 7657 | ||
7658 | cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, | 7658 | cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, |
7659 | d.tmpmask); | 7659 | d.tmpmask); |
7660 | init_numa_sched_groups_power(sg); | 7660 | init_numa_sched_groups_power(sg); |
7661 | } | 7661 | } |
7662 | #endif | 7662 | #endif |
7663 | 7663 | ||
7664 | /* Attach the domains */ | 7664 | /* Attach the domains */ |
7665 | for_each_cpu(i, cpu_map) { | 7665 | for_each_cpu(i, cpu_map) { |
7666 | #ifdef CONFIG_SCHED_SMT | 7666 | #ifdef CONFIG_SCHED_SMT |
7667 | sd = &per_cpu(cpu_domains, i).sd; | 7667 | sd = &per_cpu(cpu_domains, i).sd; |
7668 | #elif defined(CONFIG_SCHED_MC) | 7668 | #elif defined(CONFIG_SCHED_MC) |
7669 | sd = &per_cpu(core_domains, i).sd; | 7669 | sd = &per_cpu(core_domains, i).sd; |
7670 | #elif defined(CONFIG_SCHED_BOOK) | 7670 | #elif defined(CONFIG_SCHED_BOOK) |
7671 | sd = &per_cpu(book_domains, i).sd; | 7671 | sd = &per_cpu(book_domains, i).sd; |
7672 | #else | 7672 | #else |
7673 | sd = &per_cpu(phys_domains, i).sd; | 7673 | sd = &per_cpu(phys_domains, i).sd; |
7674 | #endif | 7674 | #endif |
7675 | cpu_attach_domain(sd, d.rd, i); | 7675 | cpu_attach_domain(sd, d.rd, i); |
7676 | } | 7676 | } |
7677 | 7677 | ||
7678 | d.sched_group_nodes = NULL; /* don't free this we still need it */ | 7678 | d.sched_group_nodes = NULL; /* don't free this we still need it */ |
7679 | __free_domain_allocs(&d, sa_tmpmask, cpu_map); | 7679 | __free_domain_allocs(&d, sa_tmpmask, cpu_map); |
7680 | return 0; | 7680 | return 0; |
7681 | 7681 | ||
7682 | error: | 7682 | error: |
7683 | __free_domain_allocs(&d, alloc_state, cpu_map); | 7683 | __free_domain_allocs(&d, alloc_state, cpu_map); |
7684 | return -ENOMEM; | 7684 | return -ENOMEM; |
7685 | } | 7685 | } |
7686 | 7686 | ||
7687 | static int build_sched_domains(const struct cpumask *cpu_map) | 7687 | static int build_sched_domains(const struct cpumask *cpu_map) |
7688 | { | 7688 | { |
7689 | return __build_sched_domains(cpu_map, NULL); | 7689 | return __build_sched_domains(cpu_map, NULL); |
7690 | } | 7690 | } |
7691 | 7691 | ||
7692 | static cpumask_var_t *doms_cur; /* current sched domains */ | 7692 | static cpumask_var_t *doms_cur; /* current sched domains */ |
7693 | static int ndoms_cur; /* number of sched domains in 'doms_cur' */ | 7693 | static int ndoms_cur; /* number of sched domains in 'doms_cur' */ |
7694 | static struct sched_domain_attr *dattr_cur; | 7694 | static struct sched_domain_attr *dattr_cur; |
7695 | /* attribues of custom domains in 'doms_cur' */ | 7695 | /* attribues of custom domains in 'doms_cur' */ |
7696 | 7696 | ||
7697 | /* | 7697 | /* |
7698 | * Special case: If a kmalloc of a doms_cur partition (array of | 7698 | * Special case: If a kmalloc of a doms_cur partition (array of |
7699 | * cpumask) fails, then fallback to a single sched domain, | 7699 | * cpumask) fails, then fallback to a single sched domain, |
7700 | * as determined by the single cpumask fallback_doms. | 7700 | * as determined by the single cpumask fallback_doms. |
7701 | */ | 7701 | */ |
7702 | static cpumask_var_t fallback_doms; | 7702 | static cpumask_var_t fallback_doms; |
7703 | 7703 | ||
7704 | /* | 7704 | /* |
7705 | * arch_update_cpu_topology lets virtualized architectures update the | 7705 | * arch_update_cpu_topology lets virtualized architectures update the |
7706 | * cpu core maps. It is supposed to return 1 if the topology changed | 7706 | * cpu core maps. It is supposed to return 1 if the topology changed |
7707 | * or 0 if it stayed the same. | 7707 | * or 0 if it stayed the same. |
7708 | */ | 7708 | */ |
7709 | int __attribute__((weak)) arch_update_cpu_topology(void) | 7709 | int __attribute__((weak)) arch_update_cpu_topology(void) |
7710 | { | 7710 | { |
7711 | return 0; | 7711 | return 0; |
7712 | } | 7712 | } |
7713 | 7713 | ||
7714 | cpumask_var_t *alloc_sched_domains(unsigned int ndoms) | 7714 | cpumask_var_t *alloc_sched_domains(unsigned int ndoms) |
7715 | { | 7715 | { |
7716 | int i; | 7716 | int i; |
7717 | cpumask_var_t *doms; | 7717 | cpumask_var_t *doms; |
7718 | 7718 | ||
7719 | doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); | 7719 | doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); |
7720 | if (!doms) | 7720 | if (!doms) |
7721 | return NULL; | 7721 | return NULL; |
7722 | for (i = 0; i < ndoms; i++) { | 7722 | for (i = 0; i < ndoms; i++) { |
7723 | if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { | 7723 | if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { |
7724 | free_sched_domains(doms, i); | 7724 | free_sched_domains(doms, i); |
7725 | return NULL; | 7725 | return NULL; |
7726 | } | 7726 | } |
7727 | } | 7727 | } |
7728 | return doms; | 7728 | return doms; |
7729 | } | 7729 | } |
7730 | 7730 | ||
7731 | void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) | 7731 | void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) |
7732 | { | 7732 | { |
7733 | unsigned int i; | 7733 | unsigned int i; |
7734 | for (i = 0; i < ndoms; i++) | 7734 | for (i = 0; i < ndoms; i++) |
7735 | free_cpumask_var(doms[i]); | 7735 | free_cpumask_var(doms[i]); |
7736 | kfree(doms); | 7736 | kfree(doms); |
7737 | } | 7737 | } |
7738 | 7738 | ||
7739 | /* | 7739 | /* |
7740 | * Set up scheduler domains and groups. Callers must hold the hotplug lock. | 7740 | * Set up scheduler domains and groups. Callers must hold the hotplug lock. |
7741 | * For now this just excludes isolated cpus, but could be used to | 7741 | * For now this just excludes isolated cpus, but could be used to |
7742 | * exclude other special cases in the future. | 7742 | * exclude other special cases in the future. |
7743 | */ | 7743 | */ |
7744 | static int arch_init_sched_domains(const struct cpumask *cpu_map) | 7744 | static int arch_init_sched_domains(const struct cpumask *cpu_map) |
7745 | { | 7745 | { |
7746 | int err; | 7746 | int err; |
7747 | 7747 | ||
7748 | arch_update_cpu_topology(); | 7748 | arch_update_cpu_topology(); |
7749 | ndoms_cur = 1; | 7749 | ndoms_cur = 1; |
7750 | doms_cur = alloc_sched_domains(ndoms_cur); | 7750 | doms_cur = alloc_sched_domains(ndoms_cur); |
7751 | if (!doms_cur) | 7751 | if (!doms_cur) |
7752 | doms_cur = &fallback_doms; | 7752 | doms_cur = &fallback_doms; |
7753 | cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); | 7753 | cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); |
7754 | dattr_cur = NULL; | 7754 | dattr_cur = NULL; |
7755 | err = build_sched_domains(doms_cur[0]); | 7755 | err = build_sched_domains(doms_cur[0]); |
7756 | register_sched_domain_sysctl(); | 7756 | register_sched_domain_sysctl(); |
7757 | 7757 | ||
7758 | return err; | 7758 | return err; |
7759 | } | 7759 | } |
7760 | 7760 | ||
7761 | static void arch_destroy_sched_domains(const struct cpumask *cpu_map, | 7761 | static void arch_destroy_sched_domains(const struct cpumask *cpu_map, |
7762 | struct cpumask *tmpmask) | 7762 | struct cpumask *tmpmask) |
7763 | { | 7763 | { |
7764 | free_sched_groups(cpu_map, tmpmask); | 7764 | free_sched_groups(cpu_map, tmpmask); |
7765 | } | 7765 | } |
7766 | 7766 | ||
7767 | /* | 7767 | /* |
7768 | * Detach sched domains from a group of cpus specified in cpu_map | 7768 | * Detach sched domains from a group of cpus specified in cpu_map |
7769 | * These cpus will now be attached to the NULL domain | 7769 | * These cpus will now be attached to the NULL domain |
7770 | */ | 7770 | */ |
7771 | static void detach_destroy_domains(const struct cpumask *cpu_map) | 7771 | static void detach_destroy_domains(const struct cpumask *cpu_map) |
7772 | { | 7772 | { |
7773 | /* Save because hotplug lock held. */ | 7773 | /* Save because hotplug lock held. */ |
7774 | static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); | 7774 | static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); |
7775 | int i; | 7775 | int i; |
7776 | 7776 | ||
7777 | for_each_cpu(i, cpu_map) | 7777 | for_each_cpu(i, cpu_map) |
7778 | cpu_attach_domain(NULL, &def_root_domain, i); | 7778 | cpu_attach_domain(NULL, &def_root_domain, i); |
7779 | synchronize_sched(); | 7779 | synchronize_sched(); |
7780 | arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); | 7780 | arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); |
7781 | } | 7781 | } |
7782 | 7782 | ||
7783 | /* handle null as "default" */ | 7783 | /* handle null as "default" */ |
7784 | static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, | 7784 | static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, |
7785 | struct sched_domain_attr *new, int idx_new) | 7785 | struct sched_domain_attr *new, int idx_new) |
7786 | { | 7786 | { |
7787 | struct sched_domain_attr tmp; | 7787 | struct sched_domain_attr tmp; |
7788 | 7788 | ||
7789 | /* fast path */ | 7789 | /* fast path */ |
7790 | if (!new && !cur) | 7790 | if (!new && !cur) |
7791 | return 1; | 7791 | return 1; |
7792 | 7792 | ||
7793 | tmp = SD_ATTR_INIT; | 7793 | tmp = SD_ATTR_INIT; |
7794 | return !memcmp(cur ? (cur + idx_cur) : &tmp, | 7794 | return !memcmp(cur ? (cur + idx_cur) : &tmp, |
7795 | new ? (new + idx_new) : &tmp, | 7795 | new ? (new + idx_new) : &tmp, |
7796 | sizeof(struct sched_domain_attr)); | 7796 | sizeof(struct sched_domain_attr)); |
7797 | } | 7797 | } |
7798 | 7798 | ||
7799 | /* | 7799 | /* |
7800 | * Partition sched domains as specified by the 'ndoms_new' | 7800 | * Partition sched domains as specified by the 'ndoms_new' |
7801 | * cpumasks in the array doms_new[] of cpumasks. This compares | 7801 | * cpumasks in the array doms_new[] of cpumasks. This compares |
7802 | * doms_new[] to the current sched domain partitioning, doms_cur[]. | 7802 | * doms_new[] to the current sched domain partitioning, doms_cur[]. |
7803 | * It destroys each deleted domain and builds each new domain. | 7803 | * It destroys each deleted domain and builds each new domain. |
7804 | * | 7804 | * |
7805 | * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. | 7805 | * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. |
7806 | * The masks don't intersect (don't overlap.) We should setup one | 7806 | * The masks don't intersect (don't overlap.) We should setup one |
7807 | * sched domain for each mask. CPUs not in any of the cpumasks will | 7807 | * sched domain for each mask. CPUs not in any of the cpumasks will |
7808 | * not be load balanced. If the same cpumask appears both in the | 7808 | * not be load balanced. If the same cpumask appears both in the |
7809 | * current 'doms_cur' domains and in the new 'doms_new', we can leave | 7809 | * current 'doms_cur' domains and in the new 'doms_new', we can leave |
7810 | * it as it is. | 7810 | * it as it is. |
7811 | * | 7811 | * |
7812 | * The passed in 'doms_new' should be allocated using | 7812 | * The passed in 'doms_new' should be allocated using |
7813 | * alloc_sched_domains. This routine takes ownership of it and will | 7813 | * alloc_sched_domains. This routine takes ownership of it and will |
7814 | * free_sched_domains it when done with it. If the caller failed the | 7814 | * free_sched_domains it when done with it. If the caller failed the |
7815 | * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, | 7815 | * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, |
7816 | * and partition_sched_domains() will fallback to the single partition | 7816 | * and partition_sched_domains() will fallback to the single partition |
7817 | * 'fallback_doms', it also forces the domains to be rebuilt. | 7817 | * 'fallback_doms', it also forces the domains to be rebuilt. |
7818 | * | 7818 | * |
7819 | * If doms_new == NULL it will be replaced with cpu_online_mask. | 7819 | * If doms_new == NULL it will be replaced with cpu_online_mask. |
7820 | * ndoms_new == 0 is a special case for destroying existing domains, | 7820 | * ndoms_new == 0 is a special case for destroying existing domains, |
7821 | * and it will not create the default domain. | 7821 | * and it will not create the default domain. |
7822 | * | 7822 | * |
7823 | * Call with hotplug lock held | 7823 | * Call with hotplug lock held |
7824 | */ | 7824 | */ |
7825 | void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], | 7825 | void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], |
7826 | struct sched_domain_attr *dattr_new) | 7826 | struct sched_domain_attr *dattr_new) |
7827 | { | 7827 | { |
7828 | int i, j, n; | 7828 | int i, j, n; |
7829 | int new_topology; | 7829 | int new_topology; |
7830 | 7830 | ||
7831 | mutex_lock(&sched_domains_mutex); | 7831 | mutex_lock(&sched_domains_mutex); |
7832 | 7832 | ||
7833 | /* always unregister in case we don't destroy any domains */ | 7833 | /* always unregister in case we don't destroy any domains */ |
7834 | unregister_sched_domain_sysctl(); | 7834 | unregister_sched_domain_sysctl(); |
7835 | 7835 | ||
7836 | /* Let architecture update cpu core mappings. */ | 7836 | /* Let architecture update cpu core mappings. */ |
7837 | new_topology = arch_update_cpu_topology(); | 7837 | new_topology = arch_update_cpu_topology(); |
7838 | 7838 | ||
7839 | n = doms_new ? ndoms_new : 0; | 7839 | n = doms_new ? ndoms_new : 0; |
7840 | 7840 | ||
7841 | /* Destroy deleted domains */ | 7841 | /* Destroy deleted domains */ |
7842 | for (i = 0; i < ndoms_cur; i++) { | 7842 | for (i = 0; i < ndoms_cur; i++) { |
7843 | for (j = 0; j < n && !new_topology; j++) { | 7843 | for (j = 0; j < n && !new_topology; j++) { |
7844 | if (cpumask_equal(doms_cur[i], doms_new[j]) | 7844 | if (cpumask_equal(doms_cur[i], doms_new[j]) |
7845 | && dattrs_equal(dattr_cur, i, dattr_new, j)) | 7845 | && dattrs_equal(dattr_cur, i, dattr_new, j)) |
7846 | goto match1; | 7846 | goto match1; |
7847 | } | 7847 | } |
7848 | /* no match - a current sched domain not in new doms_new[] */ | 7848 | /* no match - a current sched domain not in new doms_new[] */ |
7849 | detach_destroy_domains(doms_cur[i]); | 7849 | detach_destroy_domains(doms_cur[i]); |
7850 | match1: | 7850 | match1: |
7851 | ; | 7851 | ; |
7852 | } | 7852 | } |
7853 | 7853 | ||
7854 | if (doms_new == NULL) { | 7854 | if (doms_new == NULL) { |
7855 | ndoms_cur = 0; | 7855 | ndoms_cur = 0; |
7856 | doms_new = &fallback_doms; | 7856 | doms_new = &fallback_doms; |
7857 | cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); | 7857 | cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); |
7858 | WARN_ON_ONCE(dattr_new); | 7858 | WARN_ON_ONCE(dattr_new); |
7859 | } | 7859 | } |
7860 | 7860 | ||
7861 | /* Build new domains */ | 7861 | /* Build new domains */ |
7862 | for (i = 0; i < ndoms_new; i++) { | 7862 | for (i = 0; i < ndoms_new; i++) { |
7863 | for (j = 0; j < ndoms_cur && !new_topology; j++) { | 7863 | for (j = 0; j < ndoms_cur && !new_topology; j++) { |
7864 | if (cpumask_equal(doms_new[i], doms_cur[j]) | 7864 | if (cpumask_equal(doms_new[i], doms_cur[j]) |
7865 | && dattrs_equal(dattr_new, i, dattr_cur, j)) | 7865 | && dattrs_equal(dattr_new, i, dattr_cur, j)) |
7866 | goto match2; | 7866 | goto match2; |
7867 | } | 7867 | } |
7868 | /* no match - add a new doms_new */ | 7868 | /* no match - add a new doms_new */ |
7869 | __build_sched_domains(doms_new[i], | 7869 | __build_sched_domains(doms_new[i], |
7870 | dattr_new ? dattr_new + i : NULL); | 7870 | dattr_new ? dattr_new + i : NULL); |
7871 | match2: | 7871 | match2: |
7872 | ; | 7872 | ; |
7873 | } | 7873 | } |
7874 | 7874 | ||
7875 | /* Remember the new sched domains */ | 7875 | /* Remember the new sched domains */ |
7876 | if (doms_cur != &fallback_doms) | 7876 | if (doms_cur != &fallback_doms) |
7877 | free_sched_domains(doms_cur, ndoms_cur); | 7877 | free_sched_domains(doms_cur, ndoms_cur); |
7878 | kfree(dattr_cur); /* kfree(NULL) is safe */ | 7878 | kfree(dattr_cur); /* kfree(NULL) is safe */ |
7879 | doms_cur = doms_new; | 7879 | doms_cur = doms_new; |
7880 | dattr_cur = dattr_new; | 7880 | dattr_cur = dattr_new; |
7881 | ndoms_cur = ndoms_new; | 7881 | ndoms_cur = ndoms_new; |
7882 | 7882 | ||
7883 | register_sched_domain_sysctl(); | 7883 | register_sched_domain_sysctl(); |
7884 | 7884 | ||
7885 | mutex_unlock(&sched_domains_mutex); | 7885 | mutex_unlock(&sched_domains_mutex); |
7886 | } | 7886 | } |
7887 | 7887 | ||
7888 | #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) | 7888 | #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) |
7889 | static void arch_reinit_sched_domains(void) | 7889 | static void arch_reinit_sched_domains(void) |
7890 | { | 7890 | { |
7891 | get_online_cpus(); | 7891 | get_online_cpus(); |
7892 | 7892 | ||
7893 | /* Destroy domains first to force the rebuild */ | 7893 | /* Destroy domains first to force the rebuild */ |
7894 | partition_sched_domains(0, NULL, NULL); | 7894 | partition_sched_domains(0, NULL, NULL); |
7895 | 7895 | ||
7896 | rebuild_sched_domains(); | 7896 | rebuild_sched_domains(); |
7897 | put_online_cpus(); | 7897 | put_online_cpus(); |
7898 | } | 7898 | } |
7899 | 7899 | ||
7900 | static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) | 7900 | static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) |
7901 | { | 7901 | { |
7902 | unsigned int level = 0; | 7902 | unsigned int level = 0; |
7903 | 7903 | ||
7904 | if (sscanf(buf, "%u", &level) != 1) | 7904 | if (sscanf(buf, "%u", &level) != 1) |
7905 | return -EINVAL; | 7905 | return -EINVAL; |
7906 | 7906 | ||
7907 | /* | 7907 | /* |
7908 | * level is always be positive so don't check for | 7908 | * level is always be positive so don't check for |
7909 | * level < POWERSAVINGS_BALANCE_NONE which is 0 | 7909 | * level < POWERSAVINGS_BALANCE_NONE which is 0 |
7910 | * What happens on 0 or 1 byte write, | 7910 | * What happens on 0 or 1 byte write, |
7911 | * need to check for count as well? | 7911 | * need to check for count as well? |
7912 | */ | 7912 | */ |
7913 | 7913 | ||
7914 | if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) | 7914 | if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) |
7915 | return -EINVAL; | 7915 | return -EINVAL; |
7916 | 7916 | ||
7917 | if (smt) | 7917 | if (smt) |
7918 | sched_smt_power_savings = level; | 7918 | sched_smt_power_savings = level; |
7919 | else | 7919 | else |
7920 | sched_mc_power_savings = level; | 7920 | sched_mc_power_savings = level; |
7921 | 7921 | ||
7922 | arch_reinit_sched_domains(); | 7922 | arch_reinit_sched_domains(); |
7923 | 7923 | ||
7924 | return count; | 7924 | return count; |
7925 | } | 7925 | } |
7926 | 7926 | ||
7927 | #ifdef CONFIG_SCHED_MC | 7927 | #ifdef CONFIG_SCHED_MC |
7928 | static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, | 7928 | static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, |
7929 | struct sysdev_class_attribute *attr, | 7929 | struct sysdev_class_attribute *attr, |
7930 | char *page) | 7930 | char *page) |
7931 | { | 7931 | { |
7932 | return sprintf(page, "%u\n", sched_mc_power_savings); | 7932 | return sprintf(page, "%u\n", sched_mc_power_savings); |
7933 | } | 7933 | } |
7934 | static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, | 7934 | static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, |
7935 | struct sysdev_class_attribute *attr, | 7935 | struct sysdev_class_attribute *attr, |
7936 | const char *buf, size_t count) | 7936 | const char *buf, size_t count) |
7937 | { | 7937 | { |
7938 | return sched_power_savings_store(buf, count, 0); | 7938 | return sched_power_savings_store(buf, count, 0); |
7939 | } | 7939 | } |
7940 | static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, | 7940 | static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, |
7941 | sched_mc_power_savings_show, | 7941 | sched_mc_power_savings_show, |
7942 | sched_mc_power_savings_store); | 7942 | sched_mc_power_savings_store); |
7943 | #endif | 7943 | #endif |
7944 | 7944 | ||
7945 | #ifdef CONFIG_SCHED_SMT | 7945 | #ifdef CONFIG_SCHED_SMT |
7946 | static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, | 7946 | static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, |
7947 | struct sysdev_class_attribute *attr, | 7947 | struct sysdev_class_attribute *attr, |
7948 | char *page) | 7948 | char *page) |
7949 | { | 7949 | { |
7950 | return sprintf(page, "%u\n", sched_smt_power_savings); | 7950 | return sprintf(page, "%u\n", sched_smt_power_savings); |
7951 | } | 7951 | } |
7952 | static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, | 7952 | static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, |
7953 | struct sysdev_class_attribute *attr, | 7953 | struct sysdev_class_attribute *attr, |
7954 | const char *buf, size_t count) | 7954 | const char *buf, size_t count) |
7955 | { | 7955 | { |
7956 | return sched_power_savings_store(buf, count, 1); | 7956 | return sched_power_savings_store(buf, count, 1); |
7957 | } | 7957 | } |
7958 | static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, | 7958 | static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, |
7959 | sched_smt_power_savings_show, | 7959 | sched_smt_power_savings_show, |
7960 | sched_smt_power_savings_store); | 7960 | sched_smt_power_savings_store); |
7961 | #endif | 7961 | #endif |
7962 | 7962 | ||
7963 | int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) | 7963 | int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) |
7964 | { | 7964 | { |
7965 | int err = 0; | 7965 | int err = 0; |
7966 | 7966 | ||
7967 | #ifdef CONFIG_SCHED_SMT | 7967 | #ifdef CONFIG_SCHED_SMT |
7968 | if (smt_capable()) | 7968 | if (smt_capable()) |
7969 | err = sysfs_create_file(&cls->kset.kobj, | 7969 | err = sysfs_create_file(&cls->kset.kobj, |
7970 | &attr_sched_smt_power_savings.attr); | 7970 | &attr_sched_smt_power_savings.attr); |
7971 | #endif | 7971 | #endif |
7972 | #ifdef CONFIG_SCHED_MC | 7972 | #ifdef CONFIG_SCHED_MC |
7973 | if (!err && mc_capable()) | 7973 | if (!err && mc_capable()) |
7974 | err = sysfs_create_file(&cls->kset.kobj, | 7974 | err = sysfs_create_file(&cls->kset.kobj, |
7975 | &attr_sched_mc_power_savings.attr); | 7975 | &attr_sched_mc_power_savings.attr); |
7976 | #endif | 7976 | #endif |
7977 | return err; | 7977 | return err; |
7978 | } | 7978 | } |
7979 | #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ | 7979 | #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ |
7980 | 7980 | ||
7981 | /* | 7981 | /* |
7982 | * Update cpusets according to cpu_active mask. If cpusets are | 7982 | * Update cpusets according to cpu_active mask. If cpusets are |
7983 | * disabled, cpuset_update_active_cpus() becomes a simple wrapper | 7983 | * disabled, cpuset_update_active_cpus() becomes a simple wrapper |
7984 | * around partition_sched_domains(). | 7984 | * around partition_sched_domains(). |
7985 | */ | 7985 | */ |
7986 | static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, | 7986 | static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, |
7987 | void *hcpu) | 7987 | void *hcpu) |
7988 | { | 7988 | { |
7989 | switch (action & ~CPU_TASKS_FROZEN) { | 7989 | switch (action & ~CPU_TASKS_FROZEN) { |
7990 | case CPU_ONLINE: | 7990 | case CPU_ONLINE: |
7991 | case CPU_DOWN_FAILED: | 7991 | case CPU_DOWN_FAILED: |
7992 | cpuset_update_active_cpus(); | 7992 | cpuset_update_active_cpus(); |
7993 | return NOTIFY_OK; | 7993 | return NOTIFY_OK; |
7994 | default: | 7994 | default: |
7995 | return NOTIFY_DONE; | 7995 | return NOTIFY_DONE; |
7996 | } | 7996 | } |
7997 | } | 7997 | } |
7998 | 7998 | ||
7999 | static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, | 7999 | static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, |
8000 | void *hcpu) | 8000 | void *hcpu) |
8001 | { | 8001 | { |
8002 | switch (action & ~CPU_TASKS_FROZEN) { | 8002 | switch (action & ~CPU_TASKS_FROZEN) { |
8003 | case CPU_DOWN_PREPARE: | 8003 | case CPU_DOWN_PREPARE: |
8004 | cpuset_update_active_cpus(); | 8004 | cpuset_update_active_cpus(); |
8005 | return NOTIFY_OK; | 8005 | return NOTIFY_OK; |
8006 | default: | 8006 | default: |
8007 | return NOTIFY_DONE; | 8007 | return NOTIFY_DONE; |
8008 | } | 8008 | } |
8009 | } | 8009 | } |
8010 | 8010 | ||
8011 | static int update_runtime(struct notifier_block *nfb, | 8011 | static int update_runtime(struct notifier_block *nfb, |
8012 | unsigned long action, void *hcpu) | 8012 | unsigned long action, void *hcpu) |
8013 | { | 8013 | { |
8014 | int cpu = (int)(long)hcpu; | 8014 | int cpu = (int)(long)hcpu; |
8015 | 8015 | ||
8016 | switch (action) { | 8016 | switch (action) { |
8017 | case CPU_DOWN_PREPARE: | 8017 | case CPU_DOWN_PREPARE: |
8018 | case CPU_DOWN_PREPARE_FROZEN: | 8018 | case CPU_DOWN_PREPARE_FROZEN: |
8019 | disable_runtime(cpu_rq(cpu)); | 8019 | disable_runtime(cpu_rq(cpu)); |
8020 | return NOTIFY_OK; | 8020 | return NOTIFY_OK; |
8021 | 8021 | ||
8022 | case CPU_DOWN_FAILED: | 8022 | case CPU_DOWN_FAILED: |
8023 | case CPU_DOWN_FAILED_FROZEN: | 8023 | case CPU_DOWN_FAILED_FROZEN: |
8024 | case CPU_ONLINE: | 8024 | case CPU_ONLINE: |
8025 | case CPU_ONLINE_FROZEN: | 8025 | case CPU_ONLINE_FROZEN: |
8026 | enable_runtime(cpu_rq(cpu)); | 8026 | enable_runtime(cpu_rq(cpu)); |
8027 | return NOTIFY_OK; | 8027 | return NOTIFY_OK; |
8028 | 8028 | ||
8029 | default: | 8029 | default: |
8030 | return NOTIFY_DONE; | 8030 | return NOTIFY_DONE; |
8031 | } | 8031 | } |
8032 | } | 8032 | } |
8033 | 8033 | ||
8034 | void __init sched_init_smp(void) | 8034 | void __init sched_init_smp(void) |
8035 | { | 8035 | { |
8036 | cpumask_var_t non_isolated_cpus; | 8036 | cpumask_var_t non_isolated_cpus; |
8037 | 8037 | ||
8038 | alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); | 8038 | alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); |
8039 | alloc_cpumask_var(&fallback_doms, GFP_KERNEL); | 8039 | alloc_cpumask_var(&fallback_doms, GFP_KERNEL); |
8040 | 8040 | ||
8041 | #if defined(CONFIG_NUMA) | 8041 | #if defined(CONFIG_NUMA) |
8042 | sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), | 8042 | sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), |
8043 | GFP_KERNEL); | 8043 | GFP_KERNEL); |
8044 | BUG_ON(sched_group_nodes_bycpu == NULL); | 8044 | BUG_ON(sched_group_nodes_bycpu == NULL); |
8045 | #endif | 8045 | #endif |
8046 | get_online_cpus(); | 8046 | get_online_cpus(); |
8047 | mutex_lock(&sched_domains_mutex); | 8047 | mutex_lock(&sched_domains_mutex); |
8048 | arch_init_sched_domains(cpu_active_mask); | 8048 | arch_init_sched_domains(cpu_active_mask); |
8049 | cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); | 8049 | cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); |
8050 | if (cpumask_empty(non_isolated_cpus)) | 8050 | if (cpumask_empty(non_isolated_cpus)) |
8051 | cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); | 8051 | cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); |
8052 | mutex_unlock(&sched_domains_mutex); | 8052 | mutex_unlock(&sched_domains_mutex); |
8053 | put_online_cpus(); | 8053 | put_online_cpus(); |
8054 | 8054 | ||
8055 | hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); | 8055 | hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); |
8056 | hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); | 8056 | hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); |
8057 | 8057 | ||
8058 | /* RT runtime code needs to handle some hotplug events */ | 8058 | /* RT runtime code needs to handle some hotplug events */ |
8059 | hotcpu_notifier(update_runtime, 0); | 8059 | hotcpu_notifier(update_runtime, 0); |
8060 | 8060 | ||
8061 | init_hrtick(); | 8061 | init_hrtick(); |
8062 | 8062 | ||
8063 | /* Move init over to a non-isolated CPU */ | 8063 | /* Move init over to a non-isolated CPU */ |
8064 | if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) | 8064 | if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) |
8065 | BUG(); | 8065 | BUG(); |
8066 | sched_init_granularity(); | 8066 | sched_init_granularity(); |
8067 | free_cpumask_var(non_isolated_cpus); | 8067 | free_cpumask_var(non_isolated_cpus); |
8068 | 8068 | ||
8069 | init_sched_rt_class(); | 8069 | init_sched_rt_class(); |
8070 | } | 8070 | } |
8071 | #else | 8071 | #else |
8072 | void __init sched_init_smp(void) | 8072 | void __init sched_init_smp(void) |
8073 | { | 8073 | { |
8074 | sched_init_granularity(); | 8074 | sched_init_granularity(); |
8075 | } | 8075 | } |
8076 | #endif /* CONFIG_SMP */ | 8076 | #endif /* CONFIG_SMP */ |
8077 | 8077 | ||
8078 | const_debug unsigned int sysctl_timer_migration = 1; | 8078 | const_debug unsigned int sysctl_timer_migration = 1; |
8079 | 8079 | ||
8080 | int in_sched_functions(unsigned long addr) | 8080 | int in_sched_functions(unsigned long addr) |
8081 | { | 8081 | { |
8082 | return in_lock_functions(addr) || | 8082 | return in_lock_functions(addr) || |
8083 | (addr >= (unsigned long)__sched_text_start | 8083 | (addr >= (unsigned long)__sched_text_start |
8084 | && addr < (unsigned long)__sched_text_end); | 8084 | && addr < (unsigned long)__sched_text_end); |
8085 | } | 8085 | } |
8086 | 8086 | ||
8087 | static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) | 8087 | static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) |
8088 | { | 8088 | { |
8089 | cfs_rq->tasks_timeline = RB_ROOT; | 8089 | cfs_rq->tasks_timeline = RB_ROOT; |
8090 | INIT_LIST_HEAD(&cfs_rq->tasks); | 8090 | INIT_LIST_HEAD(&cfs_rq->tasks); |
8091 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8091 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8092 | cfs_rq->rq = rq; | 8092 | cfs_rq->rq = rq; |
8093 | /* allow initial update_cfs_load() to truncate */ | 8093 | /* allow initial update_cfs_load() to truncate */ |
8094 | #ifdef CONFIG_SMP | 8094 | #ifdef CONFIG_SMP |
8095 | cfs_rq->load_stamp = 1; | 8095 | cfs_rq->load_stamp = 1; |
8096 | #endif | 8096 | #endif |
8097 | #endif | 8097 | #endif |
8098 | cfs_rq->min_vruntime = (u64)(-(1LL << 20)); | 8098 | cfs_rq->min_vruntime = (u64)(-(1LL << 20)); |
8099 | } | 8099 | } |
8100 | 8100 | ||
8101 | static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) | 8101 | static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) |
8102 | { | 8102 | { |
8103 | struct rt_prio_array *array; | 8103 | struct rt_prio_array *array; |
8104 | int i; | 8104 | int i; |
8105 | 8105 | ||
8106 | array = &rt_rq->active; | 8106 | array = &rt_rq->active; |
8107 | for (i = 0; i < MAX_RT_PRIO; i++) { | 8107 | for (i = 0; i < MAX_RT_PRIO; i++) { |
8108 | INIT_LIST_HEAD(array->queue + i); | 8108 | INIT_LIST_HEAD(array->queue + i); |
8109 | __clear_bit(i, array->bitmap); | 8109 | __clear_bit(i, array->bitmap); |
8110 | } | 8110 | } |
8111 | /* delimiter for bitsearch: */ | 8111 | /* delimiter for bitsearch: */ |
8112 | __set_bit(MAX_RT_PRIO, array->bitmap); | 8112 | __set_bit(MAX_RT_PRIO, array->bitmap); |
8113 | 8113 | ||
8114 | #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED | 8114 | #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED |
8115 | rt_rq->highest_prio.curr = MAX_RT_PRIO; | 8115 | rt_rq->highest_prio.curr = MAX_RT_PRIO; |
8116 | #ifdef CONFIG_SMP | 8116 | #ifdef CONFIG_SMP |
8117 | rt_rq->highest_prio.next = MAX_RT_PRIO; | 8117 | rt_rq->highest_prio.next = MAX_RT_PRIO; |
8118 | #endif | 8118 | #endif |
8119 | #endif | 8119 | #endif |
8120 | #ifdef CONFIG_SMP | 8120 | #ifdef CONFIG_SMP |
8121 | rt_rq->rt_nr_migratory = 0; | 8121 | rt_rq->rt_nr_migratory = 0; |
8122 | rt_rq->overloaded = 0; | 8122 | rt_rq->overloaded = 0; |
8123 | plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); | 8123 | plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); |
8124 | #endif | 8124 | #endif |
8125 | 8125 | ||
8126 | rt_rq->rt_time = 0; | 8126 | rt_rq->rt_time = 0; |
8127 | rt_rq->rt_throttled = 0; | 8127 | rt_rq->rt_throttled = 0; |
8128 | rt_rq->rt_runtime = 0; | 8128 | rt_rq->rt_runtime = 0; |
8129 | raw_spin_lock_init(&rt_rq->rt_runtime_lock); | 8129 | raw_spin_lock_init(&rt_rq->rt_runtime_lock); |
8130 | 8130 | ||
8131 | #ifdef CONFIG_RT_GROUP_SCHED | 8131 | #ifdef CONFIG_RT_GROUP_SCHED |
8132 | rt_rq->rt_nr_boosted = 0; | 8132 | rt_rq->rt_nr_boosted = 0; |
8133 | rt_rq->rq = rq; | 8133 | rt_rq->rq = rq; |
8134 | #endif | 8134 | #endif |
8135 | } | 8135 | } |
8136 | 8136 | ||
8137 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8137 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8138 | static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, | 8138 | static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, |
8139 | struct sched_entity *se, int cpu, | 8139 | struct sched_entity *se, int cpu, |
8140 | struct sched_entity *parent) | 8140 | struct sched_entity *parent) |
8141 | { | 8141 | { |
8142 | struct rq *rq = cpu_rq(cpu); | 8142 | struct rq *rq = cpu_rq(cpu); |
8143 | tg->cfs_rq[cpu] = cfs_rq; | 8143 | tg->cfs_rq[cpu] = cfs_rq; |
8144 | init_cfs_rq(cfs_rq, rq); | 8144 | init_cfs_rq(cfs_rq, rq); |
8145 | cfs_rq->tg = tg; | 8145 | cfs_rq->tg = tg; |
8146 | 8146 | ||
8147 | tg->se[cpu] = se; | 8147 | tg->se[cpu] = se; |
8148 | /* se could be NULL for root_task_group */ | 8148 | /* se could be NULL for root_task_group */ |
8149 | if (!se) | 8149 | if (!se) |
8150 | return; | 8150 | return; |
8151 | 8151 | ||
8152 | if (!parent) | 8152 | if (!parent) |
8153 | se->cfs_rq = &rq->cfs; | 8153 | se->cfs_rq = &rq->cfs; |
8154 | else | 8154 | else |
8155 | se->cfs_rq = parent->my_q; | 8155 | se->cfs_rq = parent->my_q; |
8156 | 8156 | ||
8157 | se->my_q = cfs_rq; | 8157 | se->my_q = cfs_rq; |
8158 | update_load_set(&se->load, 0); | 8158 | update_load_set(&se->load, 0); |
8159 | se->parent = parent; | 8159 | se->parent = parent; |
8160 | } | 8160 | } |
8161 | #endif | 8161 | #endif |
8162 | 8162 | ||
8163 | #ifdef CONFIG_RT_GROUP_SCHED | 8163 | #ifdef CONFIG_RT_GROUP_SCHED |
8164 | static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, | 8164 | static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, |
8165 | struct sched_rt_entity *rt_se, int cpu, | 8165 | struct sched_rt_entity *rt_se, int cpu, |
8166 | struct sched_rt_entity *parent) | 8166 | struct sched_rt_entity *parent) |
8167 | { | 8167 | { |
8168 | struct rq *rq = cpu_rq(cpu); | 8168 | struct rq *rq = cpu_rq(cpu); |
8169 | 8169 | ||
8170 | tg->rt_rq[cpu] = rt_rq; | 8170 | tg->rt_rq[cpu] = rt_rq; |
8171 | init_rt_rq(rt_rq, rq); | 8171 | init_rt_rq(rt_rq, rq); |
8172 | rt_rq->tg = tg; | 8172 | rt_rq->tg = tg; |
8173 | rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; | 8173 | rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; |
8174 | 8174 | ||
8175 | tg->rt_se[cpu] = rt_se; | 8175 | tg->rt_se[cpu] = rt_se; |
8176 | if (!rt_se) | 8176 | if (!rt_se) |
8177 | return; | 8177 | return; |
8178 | 8178 | ||
8179 | if (!parent) | 8179 | if (!parent) |
8180 | rt_se->rt_rq = &rq->rt; | 8180 | rt_se->rt_rq = &rq->rt; |
8181 | else | 8181 | else |
8182 | rt_se->rt_rq = parent->my_q; | 8182 | rt_se->rt_rq = parent->my_q; |
8183 | 8183 | ||
8184 | rt_se->my_q = rt_rq; | 8184 | rt_se->my_q = rt_rq; |
8185 | rt_se->parent = parent; | 8185 | rt_se->parent = parent; |
8186 | INIT_LIST_HEAD(&rt_se->run_list); | 8186 | INIT_LIST_HEAD(&rt_se->run_list); |
8187 | } | 8187 | } |
8188 | #endif | 8188 | #endif |
8189 | 8189 | ||
8190 | void __init sched_init(void) | 8190 | void __init sched_init(void) |
8191 | { | 8191 | { |
8192 | int i, j; | 8192 | int i, j; |
8193 | unsigned long alloc_size = 0, ptr; | 8193 | unsigned long alloc_size = 0, ptr; |
8194 | 8194 | ||
8195 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8195 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8196 | alloc_size += 2 * nr_cpu_ids * sizeof(void **); | 8196 | alloc_size += 2 * nr_cpu_ids * sizeof(void **); |
8197 | #endif | 8197 | #endif |
8198 | #ifdef CONFIG_RT_GROUP_SCHED | 8198 | #ifdef CONFIG_RT_GROUP_SCHED |
8199 | alloc_size += 2 * nr_cpu_ids * sizeof(void **); | 8199 | alloc_size += 2 * nr_cpu_ids * sizeof(void **); |
8200 | #endif | 8200 | #endif |
8201 | #ifdef CONFIG_CPUMASK_OFFSTACK | 8201 | #ifdef CONFIG_CPUMASK_OFFSTACK |
8202 | alloc_size += num_possible_cpus() * cpumask_size(); | 8202 | alloc_size += num_possible_cpus() * cpumask_size(); |
8203 | #endif | 8203 | #endif |
8204 | if (alloc_size) { | 8204 | if (alloc_size) { |
8205 | ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); | 8205 | ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); |
8206 | 8206 | ||
8207 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8207 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8208 | root_task_group.se = (struct sched_entity **)ptr; | 8208 | root_task_group.se = (struct sched_entity **)ptr; |
8209 | ptr += nr_cpu_ids * sizeof(void **); | 8209 | ptr += nr_cpu_ids * sizeof(void **); |
8210 | 8210 | ||
8211 | root_task_group.cfs_rq = (struct cfs_rq **)ptr; | 8211 | root_task_group.cfs_rq = (struct cfs_rq **)ptr; |
8212 | ptr += nr_cpu_ids * sizeof(void **); | 8212 | ptr += nr_cpu_ids * sizeof(void **); |
8213 | 8213 | ||
8214 | #endif /* CONFIG_FAIR_GROUP_SCHED */ | 8214 | #endif /* CONFIG_FAIR_GROUP_SCHED */ |
8215 | #ifdef CONFIG_RT_GROUP_SCHED | 8215 | #ifdef CONFIG_RT_GROUP_SCHED |
8216 | root_task_group.rt_se = (struct sched_rt_entity **)ptr; | 8216 | root_task_group.rt_se = (struct sched_rt_entity **)ptr; |
8217 | ptr += nr_cpu_ids * sizeof(void **); | 8217 | ptr += nr_cpu_ids * sizeof(void **); |
8218 | 8218 | ||
8219 | root_task_group.rt_rq = (struct rt_rq **)ptr; | 8219 | root_task_group.rt_rq = (struct rt_rq **)ptr; |
8220 | ptr += nr_cpu_ids * sizeof(void **); | 8220 | ptr += nr_cpu_ids * sizeof(void **); |
8221 | 8221 | ||
8222 | #endif /* CONFIG_RT_GROUP_SCHED */ | 8222 | #endif /* CONFIG_RT_GROUP_SCHED */ |
8223 | #ifdef CONFIG_CPUMASK_OFFSTACK | 8223 | #ifdef CONFIG_CPUMASK_OFFSTACK |
8224 | for_each_possible_cpu(i) { | 8224 | for_each_possible_cpu(i) { |
8225 | per_cpu(load_balance_tmpmask, i) = (void *)ptr; | 8225 | per_cpu(load_balance_tmpmask, i) = (void *)ptr; |
8226 | ptr += cpumask_size(); | 8226 | ptr += cpumask_size(); |
8227 | } | 8227 | } |
8228 | #endif /* CONFIG_CPUMASK_OFFSTACK */ | 8228 | #endif /* CONFIG_CPUMASK_OFFSTACK */ |
8229 | } | 8229 | } |
8230 | 8230 | ||
8231 | #ifdef CONFIG_SMP | 8231 | #ifdef CONFIG_SMP |
8232 | init_defrootdomain(); | 8232 | init_defrootdomain(); |
8233 | #endif | 8233 | #endif |
8234 | 8234 | ||
8235 | init_rt_bandwidth(&def_rt_bandwidth, | 8235 | init_rt_bandwidth(&def_rt_bandwidth, |
8236 | global_rt_period(), global_rt_runtime()); | 8236 | global_rt_period(), global_rt_runtime()); |
8237 | 8237 | ||
8238 | #ifdef CONFIG_RT_GROUP_SCHED | 8238 | #ifdef CONFIG_RT_GROUP_SCHED |
8239 | init_rt_bandwidth(&root_task_group.rt_bandwidth, | 8239 | init_rt_bandwidth(&root_task_group.rt_bandwidth, |
8240 | global_rt_period(), global_rt_runtime()); | 8240 | global_rt_period(), global_rt_runtime()); |
8241 | #endif /* CONFIG_RT_GROUP_SCHED */ | 8241 | #endif /* CONFIG_RT_GROUP_SCHED */ |
8242 | 8242 | ||
8243 | #ifdef CONFIG_CGROUP_SCHED | 8243 | #ifdef CONFIG_CGROUP_SCHED |
8244 | list_add(&root_task_group.list, &task_groups); | 8244 | list_add(&root_task_group.list, &task_groups); |
8245 | INIT_LIST_HEAD(&root_task_group.children); | 8245 | INIT_LIST_HEAD(&root_task_group.children); |
8246 | autogroup_init(&init_task); | 8246 | autogroup_init(&init_task); |
8247 | #endif /* CONFIG_CGROUP_SCHED */ | 8247 | #endif /* CONFIG_CGROUP_SCHED */ |
8248 | 8248 | ||
8249 | for_each_possible_cpu(i) { | 8249 | for_each_possible_cpu(i) { |
8250 | struct rq *rq; | 8250 | struct rq *rq; |
8251 | 8251 | ||
8252 | rq = cpu_rq(i); | 8252 | rq = cpu_rq(i); |
8253 | raw_spin_lock_init(&rq->lock); | 8253 | raw_spin_lock_init(&rq->lock); |
8254 | rq->nr_running = 0; | 8254 | rq->nr_running = 0; |
8255 | rq->calc_load_active = 0; | 8255 | rq->calc_load_active = 0; |
8256 | rq->calc_load_update = jiffies + LOAD_FREQ; | 8256 | rq->calc_load_update = jiffies + LOAD_FREQ; |
8257 | init_cfs_rq(&rq->cfs, rq); | 8257 | init_cfs_rq(&rq->cfs, rq); |
8258 | init_rt_rq(&rq->rt, rq); | 8258 | init_rt_rq(&rq->rt, rq); |
8259 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8259 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8260 | root_task_group.shares = root_task_group_load; | 8260 | root_task_group.shares = root_task_group_load; |
8261 | INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); | 8261 | INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); |
8262 | /* | 8262 | /* |
8263 | * How much cpu bandwidth does root_task_group get? | 8263 | * How much cpu bandwidth does root_task_group get? |
8264 | * | 8264 | * |
8265 | * In case of task-groups formed thr' the cgroup filesystem, it | 8265 | * In case of task-groups formed thr' the cgroup filesystem, it |
8266 | * gets 100% of the cpu resources in the system. This overall | 8266 | * gets 100% of the cpu resources in the system. This overall |
8267 | * system cpu resource is divided among the tasks of | 8267 | * system cpu resource is divided among the tasks of |
8268 | * root_task_group and its child task-groups in a fair manner, | 8268 | * root_task_group and its child task-groups in a fair manner, |
8269 | * based on each entity's (task or task-group's) weight | 8269 | * based on each entity's (task or task-group's) weight |
8270 | * (se->load.weight). | 8270 | * (se->load.weight). |
8271 | * | 8271 | * |
8272 | * In other words, if root_task_group has 10 tasks of weight | 8272 | * In other words, if root_task_group has 10 tasks of weight |
8273 | * 1024) and two child groups A0 and A1 (of weight 1024 each), | 8273 | * 1024) and two child groups A0 and A1 (of weight 1024 each), |
8274 | * then A0's share of the cpu resource is: | 8274 | * then A0's share of the cpu resource is: |
8275 | * | 8275 | * |
8276 | * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% | 8276 | * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% |
8277 | * | 8277 | * |
8278 | * We achieve this by letting root_task_group's tasks sit | 8278 | * We achieve this by letting root_task_group's tasks sit |
8279 | * directly in rq->cfs (i.e root_task_group->se[] = NULL). | 8279 | * directly in rq->cfs (i.e root_task_group->se[] = NULL). |
8280 | */ | 8280 | */ |
8281 | init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); | 8281 | init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); |
8282 | #endif /* CONFIG_FAIR_GROUP_SCHED */ | 8282 | #endif /* CONFIG_FAIR_GROUP_SCHED */ |
8283 | 8283 | ||
8284 | rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; | 8284 | rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; |
8285 | #ifdef CONFIG_RT_GROUP_SCHED | 8285 | #ifdef CONFIG_RT_GROUP_SCHED |
8286 | INIT_LIST_HEAD(&rq->leaf_rt_rq_list); | 8286 | INIT_LIST_HEAD(&rq->leaf_rt_rq_list); |
8287 | init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); | 8287 | init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); |
8288 | #endif | 8288 | #endif |
8289 | 8289 | ||
8290 | for (j = 0; j < CPU_LOAD_IDX_MAX; j++) | 8290 | for (j = 0; j < CPU_LOAD_IDX_MAX; j++) |
8291 | rq->cpu_load[j] = 0; | 8291 | rq->cpu_load[j] = 0; |
8292 | 8292 | ||
8293 | rq->last_load_update_tick = jiffies; | 8293 | rq->last_load_update_tick = jiffies; |
8294 | 8294 | ||
8295 | #ifdef CONFIG_SMP | 8295 | #ifdef CONFIG_SMP |
8296 | rq->sd = NULL; | 8296 | rq->sd = NULL; |
8297 | rq->rd = NULL; | 8297 | rq->rd = NULL; |
8298 | rq->cpu_power = SCHED_LOAD_SCALE; | 8298 | rq->cpu_power = SCHED_LOAD_SCALE; |
8299 | rq->post_schedule = 0; | 8299 | rq->post_schedule = 0; |
8300 | rq->active_balance = 0; | 8300 | rq->active_balance = 0; |
8301 | rq->next_balance = jiffies; | 8301 | rq->next_balance = jiffies; |
8302 | rq->push_cpu = 0; | 8302 | rq->push_cpu = 0; |
8303 | rq->cpu = i; | 8303 | rq->cpu = i; |
8304 | rq->online = 0; | 8304 | rq->online = 0; |
8305 | rq->idle_stamp = 0; | 8305 | rq->idle_stamp = 0; |
8306 | rq->avg_idle = 2*sysctl_sched_migration_cost; | 8306 | rq->avg_idle = 2*sysctl_sched_migration_cost; |
8307 | rq_attach_root(rq, &def_root_domain); | 8307 | rq_attach_root(rq, &def_root_domain); |
8308 | #ifdef CONFIG_NO_HZ | 8308 | #ifdef CONFIG_NO_HZ |
8309 | rq->nohz_balance_kick = 0; | 8309 | rq->nohz_balance_kick = 0; |
8310 | init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); | 8310 | init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); |
8311 | #endif | 8311 | #endif |
8312 | #endif | 8312 | #endif |
8313 | init_rq_hrtick(rq); | 8313 | init_rq_hrtick(rq); |
8314 | atomic_set(&rq->nr_iowait, 0); | 8314 | atomic_set(&rq->nr_iowait, 0); |
8315 | } | 8315 | } |
8316 | 8316 | ||
8317 | set_load_weight(&init_task); | 8317 | set_load_weight(&init_task); |
8318 | 8318 | ||
8319 | #ifdef CONFIG_PREEMPT_NOTIFIERS | 8319 | #ifdef CONFIG_PREEMPT_NOTIFIERS |
8320 | INIT_HLIST_HEAD(&init_task.preempt_notifiers); | 8320 | INIT_HLIST_HEAD(&init_task.preempt_notifiers); |
8321 | #endif | 8321 | #endif |
8322 | 8322 | ||
8323 | #ifdef CONFIG_SMP | 8323 | #ifdef CONFIG_SMP |
8324 | open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); | 8324 | open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); |
8325 | #endif | 8325 | #endif |
8326 | 8326 | ||
8327 | #ifdef CONFIG_RT_MUTEXES | 8327 | #ifdef CONFIG_RT_MUTEXES |
8328 | plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); | 8328 | plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); |
8329 | #endif | 8329 | #endif |
8330 | 8330 | ||
8331 | /* | 8331 | /* |
8332 | * The boot idle thread does lazy MMU switching as well: | 8332 | * The boot idle thread does lazy MMU switching as well: |
8333 | */ | 8333 | */ |
8334 | atomic_inc(&init_mm.mm_count); | 8334 | atomic_inc(&init_mm.mm_count); |
8335 | enter_lazy_tlb(&init_mm, current); | 8335 | enter_lazy_tlb(&init_mm, current); |
8336 | 8336 | ||
8337 | /* | 8337 | /* |
8338 | * Make us the idle thread. Technically, schedule() should not be | 8338 | * Make us the idle thread. Technically, schedule() should not be |
8339 | * called from this thread, however somewhere below it might be, | 8339 | * called from this thread, however somewhere below it might be, |
8340 | * but because we are the idle thread, we just pick up running again | 8340 | * but because we are the idle thread, we just pick up running again |
8341 | * when this runqueue becomes "idle". | 8341 | * when this runqueue becomes "idle". |
8342 | */ | 8342 | */ |
8343 | init_idle(current, smp_processor_id()); | 8343 | init_idle(current, smp_processor_id()); |
8344 | 8344 | ||
8345 | calc_load_update = jiffies + LOAD_FREQ; | 8345 | calc_load_update = jiffies + LOAD_FREQ; |
8346 | 8346 | ||
8347 | /* | 8347 | /* |
8348 | * During early bootup we pretend to be a normal task: | 8348 | * During early bootup we pretend to be a normal task: |
8349 | */ | 8349 | */ |
8350 | current->sched_class = &fair_sched_class; | 8350 | current->sched_class = &fair_sched_class; |
8351 | 8351 | ||
8352 | /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ | 8352 | /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ |
8353 | zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); | 8353 | zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); |
8354 | #ifdef CONFIG_SMP | 8354 | #ifdef CONFIG_SMP |
8355 | #ifdef CONFIG_NO_HZ | 8355 | #ifdef CONFIG_NO_HZ |
8356 | zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); | 8356 | zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); |
8357 | alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); | 8357 | alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); |
8358 | atomic_set(&nohz.load_balancer, nr_cpu_ids); | 8358 | atomic_set(&nohz.load_balancer, nr_cpu_ids); |
8359 | atomic_set(&nohz.first_pick_cpu, nr_cpu_ids); | 8359 | atomic_set(&nohz.first_pick_cpu, nr_cpu_ids); |
8360 | atomic_set(&nohz.second_pick_cpu, nr_cpu_ids); | 8360 | atomic_set(&nohz.second_pick_cpu, nr_cpu_ids); |
8361 | #endif | 8361 | #endif |
8362 | /* May be allocated at isolcpus cmdline parse time */ | 8362 | /* May be allocated at isolcpus cmdline parse time */ |
8363 | if (cpu_isolated_map == NULL) | 8363 | if (cpu_isolated_map == NULL) |
8364 | zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); | 8364 | zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); |
8365 | #endif /* SMP */ | 8365 | #endif /* SMP */ |
8366 | 8366 | ||
8367 | scheduler_running = 1; | 8367 | scheduler_running = 1; |
8368 | } | 8368 | } |
8369 | 8369 | ||
8370 | #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP | 8370 | #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP |
8371 | static inline int preempt_count_equals(int preempt_offset) | 8371 | static inline int preempt_count_equals(int preempt_offset) |
8372 | { | 8372 | { |
8373 | int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); | 8373 | int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); |
8374 | 8374 | ||
8375 | return (nested == preempt_offset); | 8375 | return (nested == preempt_offset); |
8376 | } | 8376 | } |
8377 | 8377 | ||
8378 | void __might_sleep(const char *file, int line, int preempt_offset) | 8378 | void __might_sleep(const char *file, int line, int preempt_offset) |
8379 | { | 8379 | { |
8380 | #ifdef in_atomic | 8380 | #ifdef in_atomic |
8381 | static unsigned long prev_jiffy; /* ratelimiting */ | 8381 | static unsigned long prev_jiffy; /* ratelimiting */ |
8382 | 8382 | ||
8383 | if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || | 8383 | if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || |
8384 | system_state != SYSTEM_RUNNING || oops_in_progress) | 8384 | system_state != SYSTEM_RUNNING || oops_in_progress) |
8385 | return; | 8385 | return; |
8386 | if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) | 8386 | if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) |
8387 | return; | 8387 | return; |
8388 | prev_jiffy = jiffies; | 8388 | prev_jiffy = jiffies; |
8389 | 8389 | ||
8390 | printk(KERN_ERR | 8390 | printk(KERN_ERR |
8391 | "BUG: sleeping function called from invalid context at %s:%d\n", | 8391 | "BUG: sleeping function called from invalid context at %s:%d\n", |
8392 | file, line); | 8392 | file, line); |
8393 | printk(KERN_ERR | 8393 | printk(KERN_ERR |
8394 | "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", | 8394 | "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", |
8395 | in_atomic(), irqs_disabled(), | 8395 | in_atomic(), irqs_disabled(), |
8396 | current->pid, current->comm); | 8396 | current->pid, current->comm); |
8397 | 8397 | ||
8398 | debug_show_held_locks(current); | 8398 | debug_show_held_locks(current); |
8399 | if (irqs_disabled()) | 8399 | if (irqs_disabled()) |
8400 | print_irqtrace_events(current); | 8400 | print_irqtrace_events(current); |
8401 | dump_stack(); | 8401 | dump_stack(); |
8402 | #endif | 8402 | #endif |
8403 | } | 8403 | } |
8404 | EXPORT_SYMBOL(__might_sleep); | 8404 | EXPORT_SYMBOL(__might_sleep); |
8405 | #endif | 8405 | #endif |
8406 | 8406 | ||
8407 | #ifdef CONFIG_MAGIC_SYSRQ | 8407 | #ifdef CONFIG_MAGIC_SYSRQ |
8408 | static void normalize_task(struct rq *rq, struct task_struct *p) | 8408 | static void normalize_task(struct rq *rq, struct task_struct *p) |
8409 | { | 8409 | { |
8410 | const struct sched_class *prev_class = p->sched_class; | 8410 | const struct sched_class *prev_class = p->sched_class; |
8411 | int old_prio = p->prio; | 8411 | int old_prio = p->prio; |
8412 | int on_rq; | 8412 | int on_rq; |
8413 | 8413 | ||
8414 | on_rq = p->on_rq; | 8414 | on_rq = p->on_rq; |
8415 | if (on_rq) | 8415 | if (on_rq) |
8416 | deactivate_task(rq, p, 0); | 8416 | deactivate_task(rq, p, 0); |
8417 | __setscheduler(rq, p, SCHED_NORMAL, 0); | 8417 | __setscheduler(rq, p, SCHED_NORMAL, 0); |
8418 | if (on_rq) { | 8418 | if (on_rq) { |
8419 | activate_task(rq, p, 0); | 8419 | activate_task(rq, p, 0); |
8420 | resched_task(rq->curr); | 8420 | resched_task(rq->curr); |
8421 | } | 8421 | } |
8422 | 8422 | ||
8423 | check_class_changed(rq, p, prev_class, old_prio); | 8423 | check_class_changed(rq, p, prev_class, old_prio); |
8424 | } | 8424 | } |
8425 | 8425 | ||
8426 | void normalize_rt_tasks(void) | 8426 | void normalize_rt_tasks(void) |
8427 | { | 8427 | { |
8428 | struct task_struct *g, *p; | 8428 | struct task_struct *g, *p; |
8429 | unsigned long flags; | 8429 | unsigned long flags; |
8430 | struct rq *rq; | 8430 | struct rq *rq; |
8431 | 8431 | ||
8432 | read_lock_irqsave(&tasklist_lock, flags); | 8432 | read_lock_irqsave(&tasklist_lock, flags); |
8433 | do_each_thread(g, p) { | 8433 | do_each_thread(g, p) { |
8434 | /* | 8434 | /* |
8435 | * Only normalize user tasks: | 8435 | * Only normalize user tasks: |
8436 | */ | 8436 | */ |
8437 | if (!p->mm) | 8437 | if (!p->mm) |
8438 | continue; | 8438 | continue; |
8439 | 8439 | ||
8440 | p->se.exec_start = 0; | 8440 | p->se.exec_start = 0; |
8441 | #ifdef CONFIG_SCHEDSTATS | 8441 | #ifdef CONFIG_SCHEDSTATS |
8442 | p->se.statistics.wait_start = 0; | 8442 | p->se.statistics.wait_start = 0; |
8443 | p->se.statistics.sleep_start = 0; | 8443 | p->se.statistics.sleep_start = 0; |
8444 | p->se.statistics.block_start = 0; | 8444 | p->se.statistics.block_start = 0; |
8445 | #endif | 8445 | #endif |
8446 | 8446 | ||
8447 | if (!rt_task(p)) { | 8447 | if (!rt_task(p)) { |
8448 | /* | 8448 | /* |
8449 | * Renice negative nice level userspace | 8449 | * Renice negative nice level userspace |
8450 | * tasks back to 0: | 8450 | * tasks back to 0: |
8451 | */ | 8451 | */ |
8452 | if (TASK_NICE(p) < 0 && p->mm) | 8452 | if (TASK_NICE(p) < 0 && p->mm) |
8453 | set_user_nice(p, 0); | 8453 | set_user_nice(p, 0); |
8454 | continue; | 8454 | continue; |
8455 | } | 8455 | } |
8456 | 8456 | ||
8457 | raw_spin_lock(&p->pi_lock); | 8457 | raw_spin_lock(&p->pi_lock); |
8458 | rq = __task_rq_lock(p); | 8458 | rq = __task_rq_lock(p); |
8459 | 8459 | ||
8460 | normalize_task(rq, p); | 8460 | normalize_task(rq, p); |
8461 | 8461 | ||
8462 | __task_rq_unlock(rq); | 8462 | __task_rq_unlock(rq); |
8463 | raw_spin_unlock(&p->pi_lock); | 8463 | raw_spin_unlock(&p->pi_lock); |
8464 | } while_each_thread(g, p); | 8464 | } while_each_thread(g, p); |
8465 | 8465 | ||
8466 | read_unlock_irqrestore(&tasklist_lock, flags); | 8466 | read_unlock_irqrestore(&tasklist_lock, flags); |
8467 | } | 8467 | } |
8468 | 8468 | ||
8469 | #endif /* CONFIG_MAGIC_SYSRQ */ | 8469 | #endif /* CONFIG_MAGIC_SYSRQ */ |
8470 | 8470 | ||
8471 | #if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) | 8471 | #if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) |
8472 | /* | 8472 | /* |
8473 | * These functions are only useful for the IA64 MCA handling, or kdb. | 8473 | * These functions are only useful for the IA64 MCA handling, or kdb. |
8474 | * | 8474 | * |
8475 | * They can only be called when the whole system has been | 8475 | * They can only be called when the whole system has been |
8476 | * stopped - every CPU needs to be quiescent, and no scheduling | 8476 | * stopped - every CPU needs to be quiescent, and no scheduling |
8477 | * activity can take place. Using them for anything else would | 8477 | * activity can take place. Using them for anything else would |
8478 | * be a serious bug, and as a result, they aren't even visible | 8478 | * be a serious bug, and as a result, they aren't even visible |
8479 | * under any other configuration. | 8479 | * under any other configuration. |
8480 | */ | 8480 | */ |
8481 | 8481 | ||
8482 | /** | 8482 | /** |
8483 | * curr_task - return the current task for a given cpu. | 8483 | * curr_task - return the current task for a given cpu. |
8484 | * @cpu: the processor in question. | 8484 | * @cpu: the processor in question. |
8485 | * | 8485 | * |
8486 | * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! | 8486 | * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! |
8487 | */ | 8487 | */ |
8488 | struct task_struct *curr_task(int cpu) | 8488 | struct task_struct *curr_task(int cpu) |
8489 | { | 8489 | { |
8490 | return cpu_curr(cpu); | 8490 | return cpu_curr(cpu); |
8491 | } | 8491 | } |
8492 | 8492 | ||
8493 | #endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ | 8493 | #endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ |
8494 | 8494 | ||
8495 | #ifdef CONFIG_IA64 | 8495 | #ifdef CONFIG_IA64 |
8496 | /** | 8496 | /** |
8497 | * set_curr_task - set the current task for a given cpu. | 8497 | * set_curr_task - set the current task for a given cpu. |
8498 | * @cpu: the processor in question. | 8498 | * @cpu: the processor in question. |
8499 | * @p: the task pointer to set. | 8499 | * @p: the task pointer to set. |
8500 | * | 8500 | * |
8501 | * Description: This function must only be used when non-maskable interrupts | 8501 | * Description: This function must only be used when non-maskable interrupts |
8502 | * are serviced on a separate stack. It allows the architecture to switch the | 8502 | * are serviced on a separate stack. It allows the architecture to switch the |
8503 | * notion of the current task on a cpu in a non-blocking manner. This function | 8503 | * notion of the current task on a cpu in a non-blocking manner. This function |
8504 | * must be called with all CPU's synchronized, and interrupts disabled, the | 8504 | * must be called with all CPU's synchronized, and interrupts disabled, the |
8505 | * and caller must save the original value of the current task (see | 8505 | * and caller must save the original value of the current task (see |
8506 | * curr_task() above) and restore that value before reenabling interrupts and | 8506 | * curr_task() above) and restore that value before reenabling interrupts and |
8507 | * re-starting the system. | 8507 | * re-starting the system. |
8508 | * | 8508 | * |
8509 | * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! | 8509 | * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! |
8510 | */ | 8510 | */ |
8511 | void set_curr_task(int cpu, struct task_struct *p) | 8511 | void set_curr_task(int cpu, struct task_struct *p) |
8512 | { | 8512 | { |
8513 | cpu_curr(cpu) = p; | 8513 | cpu_curr(cpu) = p; |
8514 | } | 8514 | } |
8515 | 8515 | ||
8516 | #endif | 8516 | #endif |
8517 | 8517 | ||
8518 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8518 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8519 | static void free_fair_sched_group(struct task_group *tg) | 8519 | static void free_fair_sched_group(struct task_group *tg) |
8520 | { | 8520 | { |
8521 | int i; | 8521 | int i; |
8522 | 8522 | ||
8523 | for_each_possible_cpu(i) { | 8523 | for_each_possible_cpu(i) { |
8524 | if (tg->cfs_rq) | 8524 | if (tg->cfs_rq) |
8525 | kfree(tg->cfs_rq[i]); | 8525 | kfree(tg->cfs_rq[i]); |
8526 | if (tg->se) | 8526 | if (tg->se) |
8527 | kfree(tg->se[i]); | 8527 | kfree(tg->se[i]); |
8528 | } | 8528 | } |
8529 | 8529 | ||
8530 | kfree(tg->cfs_rq); | 8530 | kfree(tg->cfs_rq); |
8531 | kfree(tg->se); | 8531 | kfree(tg->se); |
8532 | } | 8532 | } |
8533 | 8533 | ||
8534 | static | 8534 | static |
8535 | int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) | 8535 | int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) |
8536 | { | 8536 | { |
8537 | struct cfs_rq *cfs_rq; | 8537 | struct cfs_rq *cfs_rq; |
8538 | struct sched_entity *se; | 8538 | struct sched_entity *se; |
8539 | int i; | 8539 | int i; |
8540 | 8540 | ||
8541 | tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); | 8541 | tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); |
8542 | if (!tg->cfs_rq) | 8542 | if (!tg->cfs_rq) |
8543 | goto err; | 8543 | goto err; |
8544 | tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); | 8544 | tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); |
8545 | if (!tg->se) | 8545 | if (!tg->se) |
8546 | goto err; | 8546 | goto err; |
8547 | 8547 | ||
8548 | tg->shares = NICE_0_LOAD; | 8548 | tg->shares = NICE_0_LOAD; |
8549 | 8549 | ||
8550 | for_each_possible_cpu(i) { | 8550 | for_each_possible_cpu(i) { |
8551 | cfs_rq = kzalloc_node(sizeof(struct cfs_rq), | 8551 | cfs_rq = kzalloc_node(sizeof(struct cfs_rq), |
8552 | GFP_KERNEL, cpu_to_node(i)); | 8552 | GFP_KERNEL, cpu_to_node(i)); |
8553 | if (!cfs_rq) | 8553 | if (!cfs_rq) |
8554 | goto err; | 8554 | goto err; |
8555 | 8555 | ||
8556 | se = kzalloc_node(sizeof(struct sched_entity), | 8556 | se = kzalloc_node(sizeof(struct sched_entity), |
8557 | GFP_KERNEL, cpu_to_node(i)); | 8557 | GFP_KERNEL, cpu_to_node(i)); |
8558 | if (!se) | 8558 | if (!se) |
8559 | goto err_free_rq; | 8559 | goto err_free_rq; |
8560 | 8560 | ||
8561 | init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); | 8561 | init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); |
8562 | } | 8562 | } |
8563 | 8563 | ||
8564 | return 1; | 8564 | return 1; |
8565 | 8565 | ||
8566 | err_free_rq: | 8566 | err_free_rq: |
8567 | kfree(cfs_rq); | 8567 | kfree(cfs_rq); |
8568 | err: | 8568 | err: |
8569 | return 0; | 8569 | return 0; |
8570 | } | 8570 | } |
8571 | 8571 | ||
8572 | static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) | 8572 | static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) |
8573 | { | 8573 | { |
8574 | struct rq *rq = cpu_rq(cpu); | 8574 | struct rq *rq = cpu_rq(cpu); |
8575 | unsigned long flags; | 8575 | unsigned long flags; |
8576 | 8576 | ||
8577 | /* | 8577 | /* |
8578 | * Only empty task groups can be destroyed; so we can speculatively | 8578 | * Only empty task groups can be destroyed; so we can speculatively |
8579 | * check on_list without danger of it being re-added. | 8579 | * check on_list without danger of it being re-added. |
8580 | */ | 8580 | */ |
8581 | if (!tg->cfs_rq[cpu]->on_list) | 8581 | if (!tg->cfs_rq[cpu]->on_list) |
8582 | return; | 8582 | return; |
8583 | 8583 | ||
8584 | raw_spin_lock_irqsave(&rq->lock, flags); | 8584 | raw_spin_lock_irqsave(&rq->lock, flags); |
8585 | list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); | 8585 | list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); |
8586 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 8586 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
8587 | } | 8587 | } |
8588 | #else /* !CONFG_FAIR_GROUP_SCHED */ | 8588 | #else /* !CONFG_FAIR_GROUP_SCHED */ |
8589 | static inline void free_fair_sched_group(struct task_group *tg) | 8589 | static inline void free_fair_sched_group(struct task_group *tg) |
8590 | { | 8590 | { |
8591 | } | 8591 | } |
8592 | 8592 | ||
8593 | static inline | 8593 | static inline |
8594 | int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) | 8594 | int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) |
8595 | { | 8595 | { |
8596 | return 1; | 8596 | return 1; |
8597 | } | 8597 | } |
8598 | 8598 | ||
8599 | static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) | 8599 | static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) |
8600 | { | 8600 | { |
8601 | } | 8601 | } |
8602 | #endif /* CONFIG_FAIR_GROUP_SCHED */ | 8602 | #endif /* CONFIG_FAIR_GROUP_SCHED */ |
8603 | 8603 | ||
8604 | #ifdef CONFIG_RT_GROUP_SCHED | 8604 | #ifdef CONFIG_RT_GROUP_SCHED |
8605 | static void free_rt_sched_group(struct task_group *tg) | 8605 | static void free_rt_sched_group(struct task_group *tg) |
8606 | { | 8606 | { |
8607 | int i; | 8607 | int i; |
8608 | 8608 | ||
8609 | destroy_rt_bandwidth(&tg->rt_bandwidth); | 8609 | destroy_rt_bandwidth(&tg->rt_bandwidth); |
8610 | 8610 | ||
8611 | for_each_possible_cpu(i) { | 8611 | for_each_possible_cpu(i) { |
8612 | if (tg->rt_rq) | 8612 | if (tg->rt_rq) |
8613 | kfree(tg->rt_rq[i]); | 8613 | kfree(tg->rt_rq[i]); |
8614 | if (tg->rt_se) | 8614 | if (tg->rt_se) |
8615 | kfree(tg->rt_se[i]); | 8615 | kfree(tg->rt_se[i]); |
8616 | } | 8616 | } |
8617 | 8617 | ||
8618 | kfree(tg->rt_rq); | 8618 | kfree(tg->rt_rq); |
8619 | kfree(tg->rt_se); | 8619 | kfree(tg->rt_se); |
8620 | } | 8620 | } |
8621 | 8621 | ||
8622 | static | 8622 | static |
8623 | int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) | 8623 | int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) |
8624 | { | 8624 | { |
8625 | struct rt_rq *rt_rq; | 8625 | struct rt_rq *rt_rq; |
8626 | struct sched_rt_entity *rt_se; | 8626 | struct sched_rt_entity *rt_se; |
8627 | struct rq *rq; | 8627 | struct rq *rq; |
8628 | int i; | 8628 | int i; |
8629 | 8629 | ||
8630 | tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); | 8630 | tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); |
8631 | if (!tg->rt_rq) | 8631 | if (!tg->rt_rq) |
8632 | goto err; | 8632 | goto err; |
8633 | tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); | 8633 | tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); |
8634 | if (!tg->rt_se) | 8634 | if (!tg->rt_se) |
8635 | goto err; | 8635 | goto err; |
8636 | 8636 | ||
8637 | init_rt_bandwidth(&tg->rt_bandwidth, | 8637 | init_rt_bandwidth(&tg->rt_bandwidth, |
8638 | ktime_to_ns(def_rt_bandwidth.rt_period), 0); | 8638 | ktime_to_ns(def_rt_bandwidth.rt_period), 0); |
8639 | 8639 | ||
8640 | for_each_possible_cpu(i) { | 8640 | for_each_possible_cpu(i) { |
8641 | rq = cpu_rq(i); | 8641 | rq = cpu_rq(i); |
8642 | 8642 | ||
8643 | rt_rq = kzalloc_node(sizeof(struct rt_rq), | 8643 | rt_rq = kzalloc_node(sizeof(struct rt_rq), |
8644 | GFP_KERNEL, cpu_to_node(i)); | 8644 | GFP_KERNEL, cpu_to_node(i)); |
8645 | if (!rt_rq) | 8645 | if (!rt_rq) |
8646 | goto err; | 8646 | goto err; |
8647 | 8647 | ||
8648 | rt_se = kzalloc_node(sizeof(struct sched_rt_entity), | 8648 | rt_se = kzalloc_node(sizeof(struct sched_rt_entity), |
8649 | GFP_KERNEL, cpu_to_node(i)); | 8649 | GFP_KERNEL, cpu_to_node(i)); |
8650 | if (!rt_se) | 8650 | if (!rt_se) |
8651 | goto err_free_rq; | 8651 | goto err_free_rq; |
8652 | 8652 | ||
8653 | init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); | 8653 | init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); |
8654 | } | 8654 | } |
8655 | 8655 | ||
8656 | return 1; | 8656 | return 1; |
8657 | 8657 | ||
8658 | err_free_rq: | 8658 | err_free_rq: |
8659 | kfree(rt_rq); | 8659 | kfree(rt_rq); |
8660 | err: | 8660 | err: |
8661 | return 0; | 8661 | return 0; |
8662 | } | 8662 | } |
8663 | #else /* !CONFIG_RT_GROUP_SCHED */ | 8663 | #else /* !CONFIG_RT_GROUP_SCHED */ |
8664 | static inline void free_rt_sched_group(struct task_group *tg) | 8664 | static inline void free_rt_sched_group(struct task_group *tg) |
8665 | { | 8665 | { |
8666 | } | 8666 | } |
8667 | 8667 | ||
8668 | static inline | 8668 | static inline |
8669 | int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) | 8669 | int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) |
8670 | { | 8670 | { |
8671 | return 1; | 8671 | return 1; |
8672 | } | 8672 | } |
8673 | #endif /* CONFIG_RT_GROUP_SCHED */ | 8673 | #endif /* CONFIG_RT_GROUP_SCHED */ |
8674 | 8674 | ||
8675 | #ifdef CONFIG_CGROUP_SCHED | 8675 | #ifdef CONFIG_CGROUP_SCHED |
8676 | static void free_sched_group(struct task_group *tg) | 8676 | static void free_sched_group(struct task_group *tg) |
8677 | { | 8677 | { |
8678 | free_fair_sched_group(tg); | 8678 | free_fair_sched_group(tg); |
8679 | free_rt_sched_group(tg); | 8679 | free_rt_sched_group(tg); |
8680 | autogroup_free(tg); | 8680 | autogroup_free(tg); |
8681 | kfree(tg); | 8681 | kfree(tg); |
8682 | } | 8682 | } |
8683 | 8683 | ||
8684 | /* allocate runqueue etc for a new task group */ | 8684 | /* allocate runqueue etc for a new task group */ |
8685 | struct task_group *sched_create_group(struct task_group *parent) | 8685 | struct task_group *sched_create_group(struct task_group *parent) |
8686 | { | 8686 | { |
8687 | struct task_group *tg; | 8687 | struct task_group *tg; |
8688 | unsigned long flags; | 8688 | unsigned long flags; |
8689 | 8689 | ||
8690 | tg = kzalloc(sizeof(*tg), GFP_KERNEL); | 8690 | tg = kzalloc(sizeof(*tg), GFP_KERNEL); |
8691 | if (!tg) | 8691 | if (!tg) |
8692 | return ERR_PTR(-ENOMEM); | 8692 | return ERR_PTR(-ENOMEM); |
8693 | 8693 | ||
8694 | if (!alloc_fair_sched_group(tg, parent)) | 8694 | if (!alloc_fair_sched_group(tg, parent)) |
8695 | goto err; | 8695 | goto err; |
8696 | 8696 | ||
8697 | if (!alloc_rt_sched_group(tg, parent)) | 8697 | if (!alloc_rt_sched_group(tg, parent)) |
8698 | goto err; | 8698 | goto err; |
8699 | 8699 | ||
8700 | spin_lock_irqsave(&task_group_lock, flags); | 8700 | spin_lock_irqsave(&task_group_lock, flags); |
8701 | list_add_rcu(&tg->list, &task_groups); | 8701 | list_add_rcu(&tg->list, &task_groups); |
8702 | 8702 | ||
8703 | WARN_ON(!parent); /* root should already exist */ | 8703 | WARN_ON(!parent); /* root should already exist */ |
8704 | 8704 | ||
8705 | tg->parent = parent; | 8705 | tg->parent = parent; |
8706 | INIT_LIST_HEAD(&tg->children); | 8706 | INIT_LIST_HEAD(&tg->children); |
8707 | list_add_rcu(&tg->siblings, &parent->children); | 8707 | list_add_rcu(&tg->siblings, &parent->children); |
8708 | spin_unlock_irqrestore(&task_group_lock, flags); | 8708 | spin_unlock_irqrestore(&task_group_lock, flags); |
8709 | 8709 | ||
8710 | return tg; | 8710 | return tg; |
8711 | 8711 | ||
8712 | err: | 8712 | err: |
8713 | free_sched_group(tg); | 8713 | free_sched_group(tg); |
8714 | return ERR_PTR(-ENOMEM); | 8714 | return ERR_PTR(-ENOMEM); |
8715 | } | 8715 | } |
8716 | 8716 | ||
8717 | /* rcu callback to free various structures associated with a task group */ | 8717 | /* rcu callback to free various structures associated with a task group */ |
8718 | static void free_sched_group_rcu(struct rcu_head *rhp) | 8718 | static void free_sched_group_rcu(struct rcu_head *rhp) |
8719 | { | 8719 | { |
8720 | /* now it should be safe to free those cfs_rqs */ | 8720 | /* now it should be safe to free those cfs_rqs */ |
8721 | free_sched_group(container_of(rhp, struct task_group, rcu)); | 8721 | free_sched_group(container_of(rhp, struct task_group, rcu)); |
8722 | } | 8722 | } |
8723 | 8723 | ||
8724 | /* Destroy runqueue etc associated with a task group */ | 8724 | /* Destroy runqueue etc associated with a task group */ |
8725 | void sched_destroy_group(struct task_group *tg) | 8725 | void sched_destroy_group(struct task_group *tg) |
8726 | { | 8726 | { |
8727 | unsigned long flags; | 8727 | unsigned long flags; |
8728 | int i; | 8728 | int i; |
8729 | 8729 | ||
8730 | /* end participation in shares distribution */ | 8730 | /* end participation in shares distribution */ |
8731 | for_each_possible_cpu(i) | 8731 | for_each_possible_cpu(i) |
8732 | unregister_fair_sched_group(tg, i); | 8732 | unregister_fair_sched_group(tg, i); |
8733 | 8733 | ||
8734 | spin_lock_irqsave(&task_group_lock, flags); | 8734 | spin_lock_irqsave(&task_group_lock, flags); |
8735 | list_del_rcu(&tg->list); | 8735 | list_del_rcu(&tg->list); |
8736 | list_del_rcu(&tg->siblings); | 8736 | list_del_rcu(&tg->siblings); |
8737 | spin_unlock_irqrestore(&task_group_lock, flags); | 8737 | spin_unlock_irqrestore(&task_group_lock, flags); |
8738 | 8738 | ||
8739 | /* wait for possible concurrent references to cfs_rqs complete */ | 8739 | /* wait for possible concurrent references to cfs_rqs complete */ |
8740 | call_rcu(&tg->rcu, free_sched_group_rcu); | 8740 | call_rcu(&tg->rcu, free_sched_group_rcu); |
8741 | } | 8741 | } |
8742 | 8742 | ||
8743 | /* change task's runqueue when it moves between groups. | 8743 | /* change task's runqueue when it moves between groups. |
8744 | * The caller of this function should have put the task in its new group | 8744 | * The caller of this function should have put the task in its new group |
8745 | * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to | 8745 | * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to |
8746 | * reflect its new group. | 8746 | * reflect its new group. |
8747 | */ | 8747 | */ |
8748 | void sched_move_task(struct task_struct *tsk) | 8748 | void sched_move_task(struct task_struct *tsk) |
8749 | { | 8749 | { |
8750 | int on_rq, running; | 8750 | int on_rq, running; |
8751 | unsigned long flags; | 8751 | unsigned long flags; |
8752 | struct rq *rq; | 8752 | struct rq *rq; |
8753 | 8753 | ||
8754 | rq = task_rq_lock(tsk, &flags); | 8754 | rq = task_rq_lock(tsk, &flags); |
8755 | 8755 | ||
8756 | running = task_current(rq, tsk); | 8756 | running = task_current(rq, tsk); |
8757 | on_rq = tsk->on_rq; | 8757 | on_rq = tsk->on_rq; |
8758 | 8758 | ||
8759 | if (on_rq) | 8759 | if (on_rq) |
8760 | dequeue_task(rq, tsk, 0); | 8760 | dequeue_task(rq, tsk, 0); |
8761 | if (unlikely(running)) | 8761 | if (unlikely(running)) |
8762 | tsk->sched_class->put_prev_task(rq, tsk); | 8762 | tsk->sched_class->put_prev_task(rq, tsk); |
8763 | 8763 | ||
8764 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8764 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8765 | if (tsk->sched_class->task_move_group) | 8765 | if (tsk->sched_class->task_move_group) |
8766 | tsk->sched_class->task_move_group(tsk, on_rq); | 8766 | tsk->sched_class->task_move_group(tsk, on_rq); |
8767 | else | 8767 | else |
8768 | #endif | 8768 | #endif |
8769 | set_task_rq(tsk, task_cpu(tsk)); | 8769 | set_task_rq(tsk, task_cpu(tsk)); |
8770 | 8770 | ||
8771 | if (unlikely(running)) | 8771 | if (unlikely(running)) |
8772 | tsk->sched_class->set_curr_task(rq); | 8772 | tsk->sched_class->set_curr_task(rq); |
8773 | if (on_rq) | 8773 | if (on_rq) |
8774 | enqueue_task(rq, tsk, 0); | 8774 | enqueue_task(rq, tsk, 0); |
8775 | 8775 | ||
8776 | task_rq_unlock(rq, tsk, &flags); | 8776 | task_rq_unlock(rq, tsk, &flags); |
8777 | } | 8777 | } |
8778 | #endif /* CONFIG_CGROUP_SCHED */ | 8778 | #endif /* CONFIG_CGROUP_SCHED */ |
8779 | 8779 | ||
8780 | #ifdef CONFIG_FAIR_GROUP_SCHED | 8780 | #ifdef CONFIG_FAIR_GROUP_SCHED |
8781 | static DEFINE_MUTEX(shares_mutex); | 8781 | static DEFINE_MUTEX(shares_mutex); |
8782 | 8782 | ||
8783 | int sched_group_set_shares(struct task_group *tg, unsigned long shares) | 8783 | int sched_group_set_shares(struct task_group *tg, unsigned long shares) |
8784 | { | 8784 | { |
8785 | int i; | 8785 | int i; |
8786 | unsigned long flags; | 8786 | unsigned long flags; |
8787 | 8787 | ||
8788 | /* | 8788 | /* |
8789 | * We can't change the weight of the root cgroup. | 8789 | * We can't change the weight of the root cgroup. |
8790 | */ | 8790 | */ |
8791 | if (!tg->se[0]) | 8791 | if (!tg->se[0]) |
8792 | return -EINVAL; | 8792 | return -EINVAL; |
8793 | 8793 | ||
8794 | if (shares < MIN_SHARES) | 8794 | if (shares < MIN_SHARES) |
8795 | shares = MIN_SHARES; | 8795 | shares = MIN_SHARES; |
8796 | else if (shares > MAX_SHARES) | 8796 | else if (shares > MAX_SHARES) |
8797 | shares = MAX_SHARES; | 8797 | shares = MAX_SHARES; |
8798 | 8798 | ||
8799 | mutex_lock(&shares_mutex); | 8799 | mutex_lock(&shares_mutex); |
8800 | if (tg->shares == shares) | 8800 | if (tg->shares == shares) |
8801 | goto done; | 8801 | goto done; |
8802 | 8802 | ||
8803 | tg->shares = shares; | 8803 | tg->shares = shares; |
8804 | for_each_possible_cpu(i) { | 8804 | for_each_possible_cpu(i) { |
8805 | struct rq *rq = cpu_rq(i); | 8805 | struct rq *rq = cpu_rq(i); |
8806 | struct sched_entity *se; | 8806 | struct sched_entity *se; |
8807 | 8807 | ||
8808 | se = tg->se[i]; | 8808 | se = tg->se[i]; |
8809 | /* Propagate contribution to hierarchy */ | 8809 | /* Propagate contribution to hierarchy */ |
8810 | raw_spin_lock_irqsave(&rq->lock, flags); | 8810 | raw_spin_lock_irqsave(&rq->lock, flags); |
8811 | for_each_sched_entity(se) | 8811 | for_each_sched_entity(se) |
8812 | update_cfs_shares(group_cfs_rq(se)); | 8812 | update_cfs_shares(group_cfs_rq(se)); |
8813 | raw_spin_unlock_irqrestore(&rq->lock, flags); | 8813 | raw_spin_unlock_irqrestore(&rq->lock, flags); |
8814 | } | 8814 | } |
8815 | 8815 | ||
8816 | done: | 8816 | done: |
8817 | mutex_unlock(&shares_mutex); | 8817 | mutex_unlock(&shares_mutex); |
8818 | return 0; | 8818 | return 0; |
8819 | } | 8819 | } |
8820 | 8820 | ||
8821 | unsigned long sched_group_shares(struct task_group *tg) | 8821 | unsigned long sched_group_shares(struct task_group *tg) |
8822 | { | 8822 | { |
8823 | return tg->shares; | 8823 | return tg->shares; |
8824 | } | 8824 | } |
8825 | #endif | 8825 | #endif |
8826 | 8826 | ||
8827 | #ifdef CONFIG_RT_GROUP_SCHED | 8827 | #ifdef CONFIG_RT_GROUP_SCHED |
8828 | /* | 8828 | /* |
8829 | * Ensure that the real time constraints are schedulable. | 8829 | * Ensure that the real time constraints are schedulable. |
8830 | */ | 8830 | */ |
8831 | static DEFINE_MUTEX(rt_constraints_mutex); | 8831 | static DEFINE_MUTEX(rt_constraints_mutex); |
8832 | 8832 | ||
8833 | static unsigned long to_ratio(u64 period, u64 runtime) | 8833 | static unsigned long to_ratio(u64 period, u64 runtime) |
8834 | { | 8834 | { |
8835 | if (runtime == RUNTIME_INF) | 8835 | if (runtime == RUNTIME_INF) |
8836 | return 1ULL << 20; | 8836 | return 1ULL << 20; |
8837 | 8837 | ||
8838 | return div64_u64(runtime << 20, period); | 8838 | return div64_u64(runtime << 20, period); |
8839 | } | 8839 | } |
8840 | 8840 | ||
8841 | /* Must be called with tasklist_lock held */ | 8841 | /* Must be called with tasklist_lock held */ |
8842 | static inline int tg_has_rt_tasks(struct task_group *tg) | 8842 | static inline int tg_has_rt_tasks(struct task_group *tg) |
8843 | { | 8843 | { |
8844 | struct task_struct *g, *p; | 8844 | struct task_struct *g, *p; |
8845 | 8845 | ||
8846 | do_each_thread(g, p) { | 8846 | do_each_thread(g, p) { |
8847 | if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) | 8847 | if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) |
8848 | return 1; | 8848 | return 1; |
8849 | } while_each_thread(g, p); | 8849 | } while_each_thread(g, p); |
8850 | 8850 | ||
8851 | return 0; | 8851 | return 0; |
8852 | } | 8852 | } |
8853 | 8853 | ||
8854 | struct rt_schedulable_data { | 8854 | struct rt_schedulable_data { |
8855 | struct task_group *tg; | 8855 | struct task_group *tg; |
8856 | u64 rt_period; | 8856 | u64 rt_period; |
8857 | u64 rt_runtime; | 8857 | u64 rt_runtime; |
8858 | }; | 8858 | }; |
8859 | 8859 | ||
8860 | static int tg_schedulable(struct task_group *tg, void *data) | 8860 | static int tg_schedulable(struct task_group *tg, void *data) |
8861 | { | 8861 | { |
8862 | struct rt_schedulable_data *d = data; | 8862 | struct rt_schedulable_data *d = data; |
8863 | struct task_group *child; | 8863 | struct task_group *child; |
8864 | unsigned long total, sum = 0; | 8864 | unsigned long total, sum = 0; |
8865 | u64 period, runtime; | 8865 | u64 period, runtime; |
8866 | 8866 | ||
8867 | period = ktime_to_ns(tg->rt_bandwidth.rt_period); | 8867 | period = ktime_to_ns(tg->rt_bandwidth.rt_period); |
8868 | runtime = tg->rt_bandwidth.rt_runtime; | 8868 | runtime = tg->rt_bandwidth.rt_runtime; |
8869 | 8869 | ||
8870 | if (tg == d->tg) { | 8870 | if (tg == d->tg) { |
8871 | period = d->rt_period; | 8871 | period = d->rt_period; |
8872 | runtime = d->rt_runtime; | 8872 | runtime = d->rt_runtime; |
8873 | } | 8873 | } |
8874 | 8874 | ||
8875 | /* | 8875 | /* |
8876 | * Cannot have more runtime than the period. | 8876 | * Cannot have more runtime than the period. |
8877 | */ | 8877 | */ |
8878 | if (runtime > period && runtime != RUNTIME_INF) | 8878 | if (runtime > period && runtime != RUNTIME_INF) |
8879 | return -EINVAL; | 8879 | return -EINVAL; |
8880 | 8880 | ||
8881 | /* | 8881 | /* |
8882 | * Ensure we don't starve existing RT tasks. | 8882 | * Ensure we don't starve existing RT tasks. |
8883 | */ | 8883 | */ |
8884 | if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) | 8884 | if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) |
8885 | return -EBUSY; | 8885 | return -EBUSY; |
8886 | 8886 | ||
8887 | total = to_ratio(period, runtime); | 8887 | total = to_ratio(period, runtime); |
8888 | 8888 | ||
8889 | /* | 8889 | /* |
8890 | * Nobody can have more than the global setting allows. | 8890 | * Nobody can have more than the global setting allows. |
8891 | */ | 8891 | */ |
8892 | if (total > to_ratio(global_rt_period(), global_rt_runtime())) | 8892 | if (total > to_ratio(global_rt_period(), global_rt_runtime())) |
8893 | return -EINVAL; | 8893 | return -EINVAL; |
8894 | 8894 | ||
8895 | /* | 8895 | /* |
8896 | * The sum of our children's runtime should not exceed our own. | 8896 | * The sum of our children's runtime should not exceed our own. |
8897 | */ | 8897 | */ |
8898 | list_for_each_entry_rcu(child, &tg->children, siblings) { | 8898 | list_for_each_entry_rcu(child, &tg->children, siblings) { |
8899 | period = ktime_to_ns(child->rt_bandwidth.rt_period); | 8899 | period = ktime_to_ns(child->rt_bandwidth.rt_period); |
8900 | runtime = child->rt_bandwidth.rt_runtime; | 8900 | runtime = child->rt_bandwidth.rt_runtime; |
8901 | 8901 | ||
8902 | if (child == d->tg) { | 8902 | if (child == d->tg) { |
8903 | period = d->rt_period; | 8903 | period = d->rt_period; |
8904 | runtime = d->rt_runtime; | 8904 | runtime = d->rt_runtime; |
8905 | } | 8905 | } |
8906 | 8906 | ||
8907 | sum += to_ratio(period, runtime); | 8907 | sum += to_ratio(period, runtime); |
8908 | } | 8908 | } |
8909 | 8909 | ||
8910 | if (sum > total) | 8910 | if (sum > total) |
8911 | return -EINVAL; | 8911 | return -EINVAL; |
8912 | 8912 | ||
8913 | return 0; | 8913 | return 0; |
8914 | } | 8914 | } |
8915 | 8915 | ||
8916 | static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) | 8916 | static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) |
8917 | { | 8917 | { |
8918 | struct rt_schedulable_data data = { | 8918 | struct rt_schedulable_data data = { |
8919 | .tg = tg, | 8919 | .tg = tg, |
8920 | .rt_period = period, | 8920 | .rt_period = period, |
8921 | .rt_runtime = runtime, | 8921 | .rt_runtime = runtime, |
8922 | }; | 8922 | }; |
8923 | 8923 | ||
8924 | return walk_tg_tree(tg_schedulable, tg_nop, &data); | 8924 | return walk_tg_tree(tg_schedulable, tg_nop, &data); |
8925 | } | 8925 | } |
8926 | 8926 | ||
8927 | static int tg_set_bandwidth(struct task_group *tg, | 8927 | static int tg_set_bandwidth(struct task_group *tg, |
8928 | u64 rt_period, u64 rt_runtime) | 8928 | u64 rt_period, u64 rt_runtime) |
8929 | { | 8929 | { |
8930 | int i, err = 0; | 8930 | int i, err = 0; |
8931 | 8931 | ||
8932 | mutex_lock(&rt_constraints_mutex); | 8932 | mutex_lock(&rt_constraints_mutex); |
8933 | read_lock(&tasklist_lock); | 8933 | read_lock(&tasklist_lock); |
8934 | err = __rt_schedulable(tg, rt_period, rt_runtime); | 8934 | err = __rt_schedulable(tg, rt_period, rt_runtime); |
8935 | if (err) | 8935 | if (err) |
8936 | goto unlock; | 8936 | goto unlock; |
8937 | 8937 | ||
8938 | raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); | 8938 | raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); |
8939 | tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); | 8939 | tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); |
8940 | tg->rt_bandwidth.rt_runtime = rt_runtime; | 8940 | tg->rt_bandwidth.rt_runtime = rt_runtime; |
8941 | 8941 | ||
8942 | for_each_possible_cpu(i) { | 8942 | for_each_possible_cpu(i) { |
8943 | struct rt_rq *rt_rq = tg->rt_rq[i]; | 8943 | struct rt_rq *rt_rq = tg->rt_rq[i]; |
8944 | 8944 | ||
8945 | raw_spin_lock(&rt_rq->rt_runtime_lock); | 8945 | raw_spin_lock(&rt_rq->rt_runtime_lock); |
8946 | rt_rq->rt_runtime = rt_runtime; | 8946 | rt_rq->rt_runtime = rt_runtime; |
8947 | raw_spin_unlock(&rt_rq->rt_runtime_lock); | 8947 | raw_spin_unlock(&rt_rq->rt_runtime_lock); |
8948 | } | 8948 | } |
8949 | raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); | 8949 | raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); |
8950 | unlock: | 8950 | unlock: |
8951 | read_unlock(&tasklist_lock); | 8951 | read_unlock(&tasklist_lock); |
8952 | mutex_unlock(&rt_constraints_mutex); | 8952 | mutex_unlock(&rt_constraints_mutex); |
8953 | 8953 | ||
8954 | return err; | 8954 | return err; |
8955 | } | 8955 | } |
8956 | 8956 | ||
8957 | int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) | 8957 | int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) |
8958 | { | 8958 | { |
8959 | u64 rt_runtime, rt_period; | 8959 | u64 rt_runtime, rt_period; |
8960 | 8960 | ||
8961 | rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); | 8961 | rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); |
8962 | rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; | 8962 | rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; |
8963 | if (rt_runtime_us < 0) | 8963 | if (rt_runtime_us < 0) |
8964 | rt_runtime = RUNTIME_INF; | 8964 | rt_runtime = RUNTIME_INF; |
8965 | 8965 | ||
8966 | return tg_set_bandwidth(tg, rt_period, rt_runtime); | 8966 | return tg_set_bandwidth(tg, rt_period, rt_runtime); |
8967 | } | 8967 | } |
8968 | 8968 | ||
8969 | long sched_group_rt_runtime(struct task_group *tg) | 8969 | long sched_group_rt_runtime(struct task_group *tg) |
8970 | { | 8970 | { |
8971 | u64 rt_runtime_us; | 8971 | u64 rt_runtime_us; |
8972 | 8972 | ||
8973 | if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) | 8973 | if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) |
8974 | return -1; | 8974 | return -1; |
8975 | 8975 | ||
8976 | rt_runtime_us = tg->rt_bandwidth.rt_runtime; | 8976 | rt_runtime_us = tg->rt_bandwidth.rt_runtime; |
8977 | do_div(rt_runtime_us, NSEC_PER_USEC); | 8977 | do_div(rt_runtime_us, NSEC_PER_USEC); |
8978 | return rt_runtime_us; | 8978 | return rt_runtime_us; |
8979 | } | 8979 | } |
8980 | 8980 | ||
8981 | int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) | 8981 | int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) |
8982 | { | 8982 | { |
8983 | u64 rt_runtime, rt_period; | 8983 | u64 rt_runtime, rt_period; |
8984 | 8984 | ||
8985 | rt_period = (u64)rt_period_us * NSEC_PER_USEC; | 8985 | rt_period = (u64)rt_period_us * NSEC_PER_USEC; |
8986 | rt_runtime = tg->rt_bandwidth.rt_runtime; | 8986 | rt_runtime = tg->rt_bandwidth.rt_runtime; |
8987 | 8987 | ||
8988 | if (rt_period == 0) | 8988 | if (rt_period == 0) |
8989 | return -EINVAL; | 8989 | return -EINVAL; |
8990 | 8990 | ||
8991 | return tg_set_bandwidth(tg, rt_period, rt_runtime); | 8991 | return tg_set_bandwidth(tg, rt_period, rt_runtime); |
8992 | } | 8992 | } |
8993 | 8993 | ||
8994 | long sched_group_rt_period(struct task_group *tg) | 8994 | long sched_group_rt_period(struct task_group *tg) |
8995 | { | 8995 | { |
8996 | u64 rt_period_us; | 8996 | u64 rt_period_us; |
8997 | 8997 | ||
8998 | rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); | 8998 | rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); |
8999 | do_div(rt_period_us, NSEC_PER_USEC); | 8999 | do_div(rt_period_us, NSEC_PER_USEC); |
9000 | return rt_period_us; | 9000 | return rt_period_us; |
9001 | } | 9001 | } |
9002 | 9002 | ||
9003 | static int sched_rt_global_constraints(void) | 9003 | static int sched_rt_global_constraints(void) |
9004 | { | 9004 | { |
9005 | u64 runtime, period; | 9005 | u64 runtime, period; |
9006 | int ret = 0; | 9006 | int ret = 0; |
9007 | 9007 | ||
9008 | if (sysctl_sched_rt_period <= 0) | 9008 | if (sysctl_sched_rt_period <= 0) |
9009 | return -EINVAL; | 9009 | return -EINVAL; |
9010 | 9010 | ||
9011 | runtime = global_rt_runtime(); | 9011 | runtime = global_rt_runtime(); |
9012 | period = global_rt_period(); | 9012 | period = global_rt_period(); |
9013 | 9013 | ||
9014 | /* | 9014 | /* |
9015 | * Sanity check on the sysctl variables. | 9015 | * Sanity check on the sysctl variables. |
9016 | */ | 9016 | */ |
9017 | if (runtime > period && runtime != RUNTIME_INF) | 9017 | if (runtime > period && runtime != RUNTIME_INF) |
9018 | return -EINVAL; | 9018 | return -EINVAL; |
9019 | 9019 | ||
9020 | mutex_lock(&rt_constraints_mutex); | 9020 | mutex_lock(&rt_constraints_mutex); |
9021 | read_lock(&tasklist_lock); | 9021 | read_lock(&tasklist_lock); |
9022 | ret = __rt_schedulable(NULL, 0, 0); | 9022 | ret = __rt_schedulable(NULL, 0, 0); |
9023 | read_unlock(&tasklist_lock); | 9023 | read_unlock(&tasklist_lock); |
9024 | mutex_unlock(&rt_constraints_mutex); | 9024 | mutex_unlock(&rt_constraints_mutex); |
9025 | 9025 | ||
9026 | return ret; | 9026 | return ret; |
9027 | } | 9027 | } |
9028 | 9028 | ||
9029 | int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) | 9029 | int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) |
9030 | { | 9030 | { |
9031 | /* Don't accept realtime tasks when there is no way for them to run */ | 9031 | /* Don't accept realtime tasks when there is no way for them to run */ |
9032 | if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) | 9032 | if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) |
9033 | return 0; | 9033 | return 0; |
9034 | 9034 | ||
9035 | return 1; | 9035 | return 1; |
9036 | } | 9036 | } |
9037 | 9037 | ||
9038 | #else /* !CONFIG_RT_GROUP_SCHED */ | 9038 | #else /* !CONFIG_RT_GROUP_SCHED */ |
9039 | static int sched_rt_global_constraints(void) | 9039 | static int sched_rt_global_constraints(void) |
9040 | { | 9040 | { |
9041 | unsigned long flags; | 9041 | unsigned long flags; |
9042 | int i; | 9042 | int i; |
9043 | 9043 | ||
9044 | if (sysctl_sched_rt_period <= 0) | 9044 | if (sysctl_sched_rt_period <= 0) |
9045 | return -EINVAL; | 9045 | return -EINVAL; |
9046 | 9046 | ||
9047 | /* | 9047 | /* |
9048 | * There's always some RT tasks in the root group | 9048 | * There's always some RT tasks in the root group |
9049 | * -- migration, kstopmachine etc.. | 9049 | * -- migration, kstopmachine etc.. |
9050 | */ | 9050 | */ |
9051 | if (sysctl_sched_rt_runtime == 0) | 9051 | if (sysctl_sched_rt_runtime == 0) |
9052 | return -EBUSY; | 9052 | return -EBUSY; |
9053 | 9053 | ||
9054 | raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); | 9054 | raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); |
9055 | for_each_possible_cpu(i) { | 9055 | for_each_possible_cpu(i) { |
9056 | struct rt_rq *rt_rq = &cpu_rq(i)->rt; | 9056 | struct rt_rq *rt_rq = &cpu_rq(i)->rt; |
9057 | 9057 | ||
9058 | raw_spin_lock(&rt_rq->rt_runtime_lock); | 9058 | raw_spin_lock(&rt_rq->rt_runtime_lock); |
9059 | rt_rq->rt_runtime = global_rt_runtime(); | 9059 | rt_rq->rt_runtime = global_rt_runtime(); |
9060 | raw_spin_unlock(&rt_rq->rt_runtime_lock); | 9060 | raw_spin_unlock(&rt_rq->rt_runtime_lock); |
9061 | } | 9061 | } |
9062 | raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); | 9062 | raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); |
9063 | 9063 | ||
9064 | return 0; | 9064 | return 0; |
9065 | } | 9065 | } |
9066 | #endif /* CONFIG_RT_GROUP_SCHED */ | 9066 | #endif /* CONFIG_RT_GROUP_SCHED */ |
9067 | 9067 | ||
9068 | int sched_rt_handler(struct ctl_table *table, int write, | 9068 | int sched_rt_handler(struct ctl_table *table, int write, |
9069 | void __user *buffer, size_t *lenp, | 9069 | void __user *buffer, size_t *lenp, |
9070 | loff_t *ppos) | 9070 | loff_t *ppos) |
9071 | { | 9071 | { |
9072 | int ret; | 9072 | int ret; |
9073 | int old_period, old_runtime; | 9073 | int old_period, old_runtime; |
9074 | static DEFINE_MUTEX(mutex); | 9074 | static DEFINE_MUTEX(mutex); |
9075 | 9075 | ||
9076 | mutex_lock(&mutex); | 9076 | mutex_lock(&mutex); |
9077 | old_period = sysctl_sched_rt_period; | 9077 | old_period = sysctl_sched_rt_period; |
9078 | old_runtime = sysctl_sched_rt_runtime; | 9078 | old_runtime = sysctl_sched_rt_runtime; |
9079 | 9079 | ||
9080 | ret = proc_dointvec(table, write, buffer, lenp, ppos); | 9080 | ret = proc_dointvec(table, write, buffer, lenp, ppos); |
9081 | 9081 | ||
9082 | if (!ret && write) { | 9082 | if (!ret && write) { |
9083 | ret = sched_rt_global_constraints(); | 9083 | ret = sched_rt_global_constraints(); |
9084 | if (ret) { | 9084 | if (ret) { |
9085 | sysctl_sched_rt_period = old_period; | 9085 | sysctl_sched_rt_period = old_period; |
9086 | sysctl_sched_rt_runtime = old_runtime; | 9086 | sysctl_sched_rt_runtime = old_runtime; |
9087 | } else { | 9087 | } else { |
9088 | def_rt_bandwidth.rt_runtime = global_rt_runtime(); | 9088 | def_rt_bandwidth.rt_runtime = global_rt_runtime(); |
9089 | def_rt_bandwidth.rt_period = | 9089 | def_rt_bandwidth.rt_period = |
9090 | ns_to_ktime(global_rt_period()); | 9090 | ns_to_ktime(global_rt_period()); |
9091 | } | 9091 | } |
9092 | } | 9092 | } |
9093 | mutex_unlock(&mutex); | 9093 | mutex_unlock(&mutex); |
9094 | 9094 | ||
9095 | return ret; | 9095 | return ret; |
9096 | } | 9096 | } |
9097 | 9097 | ||
9098 | #ifdef CONFIG_CGROUP_SCHED | 9098 | #ifdef CONFIG_CGROUP_SCHED |
9099 | 9099 | ||
9100 | /* return corresponding task_group object of a cgroup */ | 9100 | /* return corresponding task_group object of a cgroup */ |
9101 | static inline struct task_group *cgroup_tg(struct cgroup *cgrp) | 9101 | static inline struct task_group *cgroup_tg(struct cgroup *cgrp) |
9102 | { | 9102 | { |
9103 | return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), | 9103 | return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), |
9104 | struct task_group, css); | 9104 | struct task_group, css); |
9105 | } | 9105 | } |
9106 | 9106 | ||
9107 | static struct cgroup_subsys_state * | 9107 | static struct cgroup_subsys_state * |
9108 | cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) | 9108 | cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) |
9109 | { | 9109 | { |
9110 | struct task_group *tg, *parent; | 9110 | struct task_group *tg, *parent; |
9111 | 9111 | ||
9112 | if (!cgrp->parent) { | 9112 | if (!cgrp->parent) { |
9113 | /* This is early initialization for the top cgroup */ | 9113 | /* This is early initialization for the top cgroup */ |
9114 | return &root_task_group.css; | 9114 | return &root_task_group.css; |
9115 | } | 9115 | } |
9116 | 9116 | ||
9117 | parent = cgroup_tg(cgrp->parent); | 9117 | parent = cgroup_tg(cgrp->parent); |
9118 | tg = sched_create_group(parent); | 9118 | tg = sched_create_group(parent); |
9119 | if (IS_ERR(tg)) | 9119 | if (IS_ERR(tg)) |
9120 | return ERR_PTR(-ENOMEM); | 9120 | return ERR_PTR(-ENOMEM); |
9121 | 9121 | ||
9122 | return &tg->css; | 9122 | return &tg->css; |
9123 | } | 9123 | } |
9124 | 9124 | ||
9125 | static void | 9125 | static void |
9126 | cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) | 9126 | cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) |
9127 | { | 9127 | { |
9128 | struct task_group *tg = cgroup_tg(cgrp); | 9128 | struct task_group *tg = cgroup_tg(cgrp); |
9129 | 9129 | ||
9130 | sched_destroy_group(tg); | 9130 | sched_destroy_group(tg); |
9131 | } | 9131 | } |
9132 | 9132 | ||
9133 | static int | 9133 | static int |
9134 | cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) | 9134 | cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) |
9135 | { | 9135 | { |
9136 | #ifdef CONFIG_RT_GROUP_SCHED | 9136 | #ifdef CONFIG_RT_GROUP_SCHED |
9137 | if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) | 9137 | if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) |
9138 | return -EINVAL; | 9138 | return -EINVAL; |
9139 | #else | 9139 | #else |
9140 | /* We don't support RT-tasks being in separate groups */ | 9140 | /* We don't support RT-tasks being in separate groups */ |
9141 | if (tsk->sched_class != &fair_sched_class) | 9141 | if (tsk->sched_class != &fair_sched_class) |
9142 | return -EINVAL; | 9142 | return -EINVAL; |
9143 | #endif | 9143 | #endif |
9144 | return 0; | 9144 | return 0; |
9145 | } | 9145 | } |
9146 | 9146 | ||
9147 | static int | 9147 | static int |
9148 | cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, | 9148 | cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, |
9149 | struct task_struct *tsk, bool threadgroup) | 9149 | struct task_struct *tsk, bool threadgroup) |
9150 | { | 9150 | { |
9151 | int retval = cpu_cgroup_can_attach_task(cgrp, tsk); | 9151 | int retval = cpu_cgroup_can_attach_task(cgrp, tsk); |
9152 | if (retval) | 9152 | if (retval) |
9153 | return retval; | 9153 | return retval; |
9154 | if (threadgroup) { | 9154 | if (threadgroup) { |
9155 | struct task_struct *c; | 9155 | struct task_struct *c; |
9156 | rcu_read_lock(); | 9156 | rcu_read_lock(); |
9157 | list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { | 9157 | list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { |
9158 | retval = cpu_cgroup_can_attach_task(cgrp, c); | 9158 | retval = cpu_cgroup_can_attach_task(cgrp, c); |
9159 | if (retval) { | 9159 | if (retval) { |
9160 | rcu_read_unlock(); | 9160 | rcu_read_unlock(); |
9161 | return retval; | 9161 | return retval; |
9162 | } | 9162 | } |
9163 | } | 9163 | } |
9164 | rcu_read_unlock(); | 9164 | rcu_read_unlock(); |
9165 | } | 9165 | } |
9166 | return 0; | 9166 | return 0; |
9167 | } | 9167 | } |
9168 | 9168 | ||
9169 | static void | 9169 | static void |
9170 | cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, | 9170 | cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, |
9171 | struct cgroup *old_cont, struct task_struct *tsk, | 9171 | struct cgroup *old_cont, struct task_struct *tsk, |
9172 | bool threadgroup) | 9172 | bool threadgroup) |
9173 | { | 9173 | { |
9174 | sched_move_task(tsk); | 9174 | sched_move_task(tsk); |
9175 | if (threadgroup) { | 9175 | if (threadgroup) { |
9176 | struct task_struct *c; | 9176 | struct task_struct *c; |
9177 | rcu_read_lock(); | 9177 | rcu_read_lock(); |
9178 | list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { | 9178 | list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { |
9179 | sched_move_task(c); | 9179 | sched_move_task(c); |
9180 | } | 9180 | } |
9181 | rcu_read_unlock(); | 9181 | rcu_read_unlock(); |
9182 | } | 9182 | } |
9183 | } | 9183 | } |
9184 | 9184 | ||
9185 | static void | 9185 | static void |
9186 | cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, | 9186 | cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, |
9187 | struct cgroup *old_cgrp, struct task_struct *task) | 9187 | struct cgroup *old_cgrp, struct task_struct *task) |
9188 | { | 9188 | { |
9189 | /* | 9189 | /* |
9190 | * cgroup_exit() is called in the copy_process() failure path. | 9190 | * cgroup_exit() is called in the copy_process() failure path. |
9191 | * Ignore this case since the task hasn't ran yet, this avoids | 9191 | * Ignore this case since the task hasn't ran yet, this avoids |
9192 | * trying to poke a half freed task state from generic code. | 9192 | * trying to poke a half freed task state from generic code. |
9193 | */ | 9193 | */ |
9194 | if (!(task->flags & PF_EXITING)) | 9194 | if (!(task->flags & PF_EXITING)) |
9195 | return; | 9195 | return; |
9196 | 9196 | ||
9197 | sched_move_task(task); | 9197 | sched_move_task(task); |
9198 | } | 9198 | } |
9199 | 9199 | ||
9200 | #ifdef CONFIG_FAIR_GROUP_SCHED | 9200 | #ifdef CONFIG_FAIR_GROUP_SCHED |
9201 | static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, | 9201 | static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, |
9202 | u64 shareval) | 9202 | u64 shareval) |
9203 | { | 9203 | { |
9204 | return sched_group_set_shares(cgroup_tg(cgrp), shareval); | 9204 | return sched_group_set_shares(cgroup_tg(cgrp), shareval); |
9205 | } | 9205 | } |
9206 | 9206 | ||
9207 | static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) | 9207 | static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) |
9208 | { | 9208 | { |
9209 | struct task_group *tg = cgroup_tg(cgrp); | 9209 | struct task_group *tg = cgroup_tg(cgrp); |
9210 | 9210 | ||
9211 | return (u64) tg->shares; | 9211 | return (u64) tg->shares; |
9212 | } | 9212 | } |
9213 | #endif /* CONFIG_FAIR_GROUP_SCHED */ | 9213 | #endif /* CONFIG_FAIR_GROUP_SCHED */ |
9214 | 9214 | ||
9215 | #ifdef CONFIG_RT_GROUP_SCHED | 9215 | #ifdef CONFIG_RT_GROUP_SCHED |
9216 | static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, | 9216 | static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, |
9217 | s64 val) | 9217 | s64 val) |
9218 | { | 9218 | { |
9219 | return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); | 9219 | return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); |
9220 | } | 9220 | } |
9221 | 9221 | ||
9222 | static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) | 9222 | static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) |
9223 | { | 9223 | { |
9224 | return sched_group_rt_runtime(cgroup_tg(cgrp)); | 9224 | return sched_group_rt_runtime(cgroup_tg(cgrp)); |
9225 | } | 9225 | } |
9226 | 9226 | ||
9227 | static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, | 9227 | static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, |
9228 | u64 rt_period_us) | 9228 | u64 rt_period_us) |
9229 | { | 9229 | { |
9230 | return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); | 9230 | return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); |
9231 | } | 9231 | } |
9232 | 9232 | ||
9233 | static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) | 9233 | static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) |
9234 | { | 9234 | { |
9235 | return sched_group_rt_period(cgroup_tg(cgrp)); | 9235 | return sched_group_rt_period(cgroup_tg(cgrp)); |
9236 | } | 9236 | } |
9237 | #endif /* CONFIG_RT_GROUP_SCHED */ | 9237 | #endif /* CONFIG_RT_GROUP_SCHED */ |
9238 | 9238 | ||
9239 | static struct cftype cpu_files[] = { | 9239 | static struct cftype cpu_files[] = { |
9240 | #ifdef CONFIG_FAIR_GROUP_SCHED | 9240 | #ifdef CONFIG_FAIR_GROUP_SCHED |
9241 | { | 9241 | { |
9242 | .name = "shares", | 9242 | .name = "shares", |
9243 | .read_u64 = cpu_shares_read_u64, | 9243 | .read_u64 = cpu_shares_read_u64, |
9244 | .write_u64 = cpu_shares_write_u64, | 9244 | .write_u64 = cpu_shares_write_u64, |
9245 | }, | 9245 | }, |
9246 | #endif | 9246 | #endif |
9247 | #ifdef CONFIG_RT_GROUP_SCHED | 9247 | #ifdef CONFIG_RT_GROUP_SCHED |
9248 | { | 9248 | { |
9249 | .name = "rt_runtime_us", | 9249 | .name = "rt_runtime_us", |
9250 | .read_s64 = cpu_rt_runtime_read, | 9250 | .read_s64 = cpu_rt_runtime_read, |
9251 | .write_s64 = cpu_rt_runtime_write, | 9251 | .write_s64 = cpu_rt_runtime_write, |
9252 | }, | 9252 | }, |
9253 | { | 9253 | { |
9254 | .name = "rt_period_us", | 9254 | .name = "rt_period_us", |
9255 | .read_u64 = cpu_rt_period_read_uint, | 9255 | .read_u64 = cpu_rt_period_read_uint, |
9256 | .write_u64 = cpu_rt_period_write_uint, | 9256 | .write_u64 = cpu_rt_period_write_uint, |
9257 | }, | 9257 | }, |
9258 | #endif | 9258 | #endif |
9259 | }; | 9259 | }; |
9260 | 9260 | ||
9261 | static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) | 9261 | static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) |
9262 | { | 9262 | { |
9263 | return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files)); | 9263 | return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files)); |
9264 | } | 9264 | } |
9265 | 9265 | ||
9266 | struct cgroup_subsys cpu_cgroup_subsys = { | 9266 | struct cgroup_subsys cpu_cgroup_subsys = { |
9267 | .name = "cpu", | 9267 | .name = "cpu", |
9268 | .create = cpu_cgroup_create, | 9268 | .create = cpu_cgroup_create, |
9269 | .destroy = cpu_cgroup_destroy, | 9269 | .destroy = cpu_cgroup_destroy, |
9270 | .can_attach = cpu_cgroup_can_attach, | 9270 | .can_attach = cpu_cgroup_can_attach, |
9271 | .attach = cpu_cgroup_attach, | 9271 | .attach = cpu_cgroup_attach, |
9272 | .exit = cpu_cgroup_exit, | 9272 | .exit = cpu_cgroup_exit, |
9273 | .populate = cpu_cgroup_populate, | 9273 | .populate = cpu_cgroup_populate, |
9274 | .subsys_id = cpu_cgroup_subsys_id, | 9274 | .subsys_id = cpu_cgroup_subsys_id, |
9275 | .early_init = 1, | 9275 | .early_init = 1, |
9276 | }; | 9276 | }; |
9277 | 9277 | ||
9278 | #endif /* CONFIG_CGROUP_SCHED */ | 9278 | #endif /* CONFIG_CGROUP_SCHED */ |
9279 | 9279 | ||
9280 | #ifdef CONFIG_CGROUP_CPUACCT | 9280 | #ifdef CONFIG_CGROUP_CPUACCT |
9281 | 9281 | ||
9282 | /* | 9282 | /* |
9283 | * CPU accounting code for task groups. | 9283 | * CPU accounting code for task groups. |
9284 | * | 9284 | * |
9285 | * Based on the work by Paul Menage (menage@google.com) and Balbir Singh | 9285 | * Based on the work by Paul Menage (menage@google.com) and Balbir Singh |
9286 | * (balbir@in.ibm.com). | 9286 | * (balbir@in.ibm.com). |
9287 | */ | 9287 | */ |
9288 | 9288 | ||
9289 | /* track cpu usage of a group of tasks and its child groups */ | 9289 | /* track cpu usage of a group of tasks and its child groups */ |
9290 | struct cpuacct { | 9290 | struct cpuacct { |
9291 | struct cgroup_subsys_state css; | 9291 | struct cgroup_subsys_state css; |
9292 | /* cpuusage holds pointer to a u64-type object on every cpu */ | 9292 | /* cpuusage holds pointer to a u64-type object on every cpu */ |
9293 | u64 __percpu *cpuusage; | 9293 | u64 __percpu *cpuusage; |
9294 | struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; | 9294 | struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; |
9295 | struct cpuacct *parent; | 9295 | struct cpuacct *parent; |
9296 | }; | 9296 | }; |
9297 | 9297 | ||
9298 | struct cgroup_subsys cpuacct_subsys; | 9298 | struct cgroup_subsys cpuacct_subsys; |
9299 | 9299 | ||
9300 | /* return cpu accounting group corresponding to this container */ | 9300 | /* return cpu accounting group corresponding to this container */ |
9301 | static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) | 9301 | static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) |
9302 | { | 9302 | { |
9303 | return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), | 9303 | return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), |
9304 | struct cpuacct, css); | 9304 | struct cpuacct, css); |
9305 | } | 9305 | } |
9306 | 9306 | ||
9307 | /* return cpu accounting group to which this task belongs */ | 9307 | /* return cpu accounting group to which this task belongs */ |
9308 | static inline struct cpuacct *task_ca(struct task_struct *tsk) | 9308 | static inline struct cpuacct *task_ca(struct task_struct *tsk) |
9309 | { | 9309 | { |
9310 | return container_of(task_subsys_state(tsk, cpuacct_subsys_id), | 9310 | return container_of(task_subsys_state(tsk, cpuacct_subsys_id), |
9311 | struct cpuacct, css); | 9311 | struct cpuacct, css); |
9312 | } | 9312 | } |
9313 | 9313 | ||
9314 | /* create a new cpu accounting group */ | 9314 | /* create a new cpu accounting group */ |
9315 | static struct cgroup_subsys_state *cpuacct_create( | 9315 | static struct cgroup_subsys_state *cpuacct_create( |
9316 | struct cgroup_subsys *ss, struct cgroup *cgrp) | 9316 | struct cgroup_subsys *ss, struct cgroup *cgrp) |
9317 | { | 9317 | { |
9318 | struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); | 9318 | struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); |
9319 | int i; | 9319 | int i; |
9320 | 9320 | ||
9321 | if (!ca) | 9321 | if (!ca) |
9322 | goto out; | 9322 | goto out; |
9323 | 9323 | ||
9324 | ca->cpuusage = alloc_percpu(u64); | 9324 | ca->cpuusage = alloc_percpu(u64); |
9325 | if (!ca->cpuusage) | 9325 | if (!ca->cpuusage) |
9326 | goto out_free_ca; | 9326 | goto out_free_ca; |
9327 | 9327 | ||
9328 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) | 9328 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) |
9329 | if (percpu_counter_init(&ca->cpustat[i], 0)) | 9329 | if (percpu_counter_init(&ca->cpustat[i], 0)) |
9330 | goto out_free_counters; | 9330 | goto out_free_counters; |
9331 | 9331 | ||
9332 | if (cgrp->parent) | 9332 | if (cgrp->parent) |
9333 | ca->parent = cgroup_ca(cgrp->parent); | 9333 | ca->parent = cgroup_ca(cgrp->parent); |
9334 | 9334 | ||
9335 | return &ca->css; | 9335 | return &ca->css; |
9336 | 9336 | ||
9337 | out_free_counters: | 9337 | out_free_counters: |
9338 | while (--i >= 0) | 9338 | while (--i >= 0) |
9339 | percpu_counter_destroy(&ca->cpustat[i]); | 9339 | percpu_counter_destroy(&ca->cpustat[i]); |
9340 | free_percpu(ca->cpuusage); | 9340 | free_percpu(ca->cpuusage); |
9341 | out_free_ca: | 9341 | out_free_ca: |
9342 | kfree(ca); | 9342 | kfree(ca); |
9343 | out: | 9343 | out: |
9344 | return ERR_PTR(-ENOMEM); | 9344 | return ERR_PTR(-ENOMEM); |
9345 | } | 9345 | } |
9346 | 9346 | ||
9347 | /* destroy an existing cpu accounting group */ | 9347 | /* destroy an existing cpu accounting group */ |
9348 | static void | 9348 | static void |
9349 | cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) | 9349 | cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) |
9350 | { | 9350 | { |
9351 | struct cpuacct *ca = cgroup_ca(cgrp); | 9351 | struct cpuacct *ca = cgroup_ca(cgrp); |
9352 | int i; | 9352 | int i; |
9353 | 9353 | ||
9354 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) | 9354 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) |
9355 | percpu_counter_destroy(&ca->cpustat[i]); | 9355 | percpu_counter_destroy(&ca->cpustat[i]); |
9356 | free_percpu(ca->cpuusage); | 9356 | free_percpu(ca->cpuusage); |
9357 | kfree(ca); | 9357 | kfree(ca); |
9358 | } | 9358 | } |
9359 | 9359 | ||
9360 | static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) | 9360 | static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) |
9361 | { | 9361 | { |
9362 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); | 9362 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); |
9363 | u64 data; | 9363 | u64 data; |
9364 | 9364 | ||
9365 | #ifndef CONFIG_64BIT | 9365 | #ifndef CONFIG_64BIT |
9366 | /* | 9366 | /* |
9367 | * Take rq->lock to make 64-bit read safe on 32-bit platforms. | 9367 | * Take rq->lock to make 64-bit read safe on 32-bit platforms. |
9368 | */ | 9368 | */ |
9369 | raw_spin_lock_irq(&cpu_rq(cpu)->lock); | 9369 | raw_spin_lock_irq(&cpu_rq(cpu)->lock); |
9370 | data = *cpuusage; | 9370 | data = *cpuusage; |
9371 | raw_spin_unlock_irq(&cpu_rq(cpu)->lock); | 9371 | raw_spin_unlock_irq(&cpu_rq(cpu)->lock); |
9372 | #else | 9372 | #else |
9373 | data = *cpuusage; | 9373 | data = *cpuusage; |
9374 | #endif | 9374 | #endif |
9375 | 9375 | ||
9376 | return data; | 9376 | return data; |
9377 | } | 9377 | } |
9378 | 9378 | ||
9379 | static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) | 9379 | static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) |
9380 | { | 9380 | { |
9381 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); | 9381 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); |
9382 | 9382 | ||
9383 | #ifndef CONFIG_64BIT | 9383 | #ifndef CONFIG_64BIT |
9384 | /* | 9384 | /* |
9385 | * Take rq->lock to make 64-bit write safe on 32-bit platforms. | 9385 | * Take rq->lock to make 64-bit write safe on 32-bit platforms. |
9386 | */ | 9386 | */ |
9387 | raw_spin_lock_irq(&cpu_rq(cpu)->lock); | 9387 | raw_spin_lock_irq(&cpu_rq(cpu)->lock); |
9388 | *cpuusage = val; | 9388 | *cpuusage = val; |
9389 | raw_spin_unlock_irq(&cpu_rq(cpu)->lock); | 9389 | raw_spin_unlock_irq(&cpu_rq(cpu)->lock); |
9390 | #else | 9390 | #else |
9391 | *cpuusage = val; | 9391 | *cpuusage = val; |
9392 | #endif | 9392 | #endif |
9393 | } | 9393 | } |
9394 | 9394 | ||
9395 | /* return total cpu usage (in nanoseconds) of a group */ | 9395 | /* return total cpu usage (in nanoseconds) of a group */ |
9396 | static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) | 9396 | static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) |
9397 | { | 9397 | { |
9398 | struct cpuacct *ca = cgroup_ca(cgrp); | 9398 | struct cpuacct *ca = cgroup_ca(cgrp); |
9399 | u64 totalcpuusage = 0; | 9399 | u64 totalcpuusage = 0; |
9400 | int i; | 9400 | int i; |
9401 | 9401 | ||
9402 | for_each_present_cpu(i) | 9402 | for_each_present_cpu(i) |
9403 | totalcpuusage += cpuacct_cpuusage_read(ca, i); | 9403 | totalcpuusage += cpuacct_cpuusage_read(ca, i); |
9404 | 9404 | ||
9405 | return totalcpuusage; | 9405 | return totalcpuusage; |
9406 | } | 9406 | } |
9407 | 9407 | ||
9408 | static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, | 9408 | static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, |
9409 | u64 reset) | 9409 | u64 reset) |
9410 | { | 9410 | { |
9411 | struct cpuacct *ca = cgroup_ca(cgrp); | 9411 | struct cpuacct *ca = cgroup_ca(cgrp); |
9412 | int err = 0; | 9412 | int err = 0; |
9413 | int i; | 9413 | int i; |
9414 | 9414 | ||
9415 | if (reset) { | 9415 | if (reset) { |
9416 | err = -EINVAL; | 9416 | err = -EINVAL; |
9417 | goto out; | 9417 | goto out; |
9418 | } | 9418 | } |
9419 | 9419 | ||
9420 | for_each_present_cpu(i) | 9420 | for_each_present_cpu(i) |
9421 | cpuacct_cpuusage_write(ca, i, 0); | 9421 | cpuacct_cpuusage_write(ca, i, 0); |
9422 | 9422 | ||
9423 | out: | 9423 | out: |
9424 | return err; | 9424 | return err; |
9425 | } | 9425 | } |
9426 | 9426 | ||
9427 | static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, | 9427 | static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, |
9428 | struct seq_file *m) | 9428 | struct seq_file *m) |
9429 | { | 9429 | { |
9430 | struct cpuacct *ca = cgroup_ca(cgroup); | 9430 | struct cpuacct *ca = cgroup_ca(cgroup); |
9431 | u64 percpu; | 9431 | u64 percpu; |
9432 | int i; | 9432 | int i; |
9433 | 9433 | ||
9434 | for_each_present_cpu(i) { | 9434 | for_each_present_cpu(i) { |
9435 | percpu = cpuacct_cpuusage_read(ca, i); | 9435 | percpu = cpuacct_cpuusage_read(ca, i); |
9436 | seq_printf(m, "%llu ", (unsigned long long) percpu); | 9436 | seq_printf(m, "%llu ", (unsigned long long) percpu); |
9437 | } | 9437 | } |
9438 | seq_printf(m, "\n"); | 9438 | seq_printf(m, "\n"); |
9439 | return 0; | 9439 | return 0; |
9440 | } | 9440 | } |
9441 | 9441 | ||
9442 | static const char *cpuacct_stat_desc[] = { | 9442 | static const char *cpuacct_stat_desc[] = { |
9443 | [CPUACCT_STAT_USER] = "user", | 9443 | [CPUACCT_STAT_USER] = "user", |
9444 | [CPUACCT_STAT_SYSTEM] = "system", | 9444 | [CPUACCT_STAT_SYSTEM] = "system", |
9445 | }; | 9445 | }; |
9446 | 9446 | ||
9447 | static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, | 9447 | static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, |
9448 | struct cgroup_map_cb *cb) | 9448 | struct cgroup_map_cb *cb) |
9449 | { | 9449 | { |
9450 | struct cpuacct *ca = cgroup_ca(cgrp); | 9450 | struct cpuacct *ca = cgroup_ca(cgrp); |
9451 | int i; | 9451 | int i; |
9452 | 9452 | ||
9453 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) { | 9453 | for (i = 0; i < CPUACCT_STAT_NSTATS; i++) { |
9454 | s64 val = percpu_counter_read(&ca->cpustat[i]); | 9454 | s64 val = percpu_counter_read(&ca->cpustat[i]); |
9455 | val = cputime64_to_clock_t(val); | 9455 | val = cputime64_to_clock_t(val); |
9456 | cb->fill(cb, cpuacct_stat_desc[i], val); | 9456 | cb->fill(cb, cpuacct_stat_desc[i], val); |
9457 | } | 9457 | } |
9458 | return 0; | 9458 | return 0; |
9459 | } | 9459 | } |
9460 | 9460 | ||
9461 | static struct cftype files[] = { | 9461 | static struct cftype files[] = { |
9462 | { | 9462 | { |
9463 | .name = "usage", | 9463 | .name = "usage", |
9464 | .read_u64 = cpuusage_read, | 9464 | .read_u64 = cpuusage_read, |
9465 | .write_u64 = cpuusage_write, | 9465 | .write_u64 = cpuusage_write, |
9466 | }, | 9466 | }, |
9467 | { | 9467 | { |
9468 | .name = "usage_percpu", | 9468 | .name = "usage_percpu", |
9469 | .read_seq_string = cpuacct_percpu_seq_read, | 9469 | .read_seq_string = cpuacct_percpu_seq_read, |
9470 | }, | 9470 | }, |
9471 | { | 9471 | { |
9472 | .name = "stat", | 9472 | .name = "stat", |
9473 | .read_map = cpuacct_stats_show, | 9473 | .read_map = cpuacct_stats_show, |
9474 | }, | 9474 | }, |
9475 | }; | 9475 | }; |
9476 | 9476 | ||
9477 | static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) | 9477 | static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) |
9478 | { | 9478 | { |
9479 | return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files)); | 9479 | return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files)); |
9480 | } | 9480 | } |
9481 | 9481 | ||
9482 | /* | 9482 | /* |
9483 | * charge this task's execution time to its accounting group. | 9483 | * charge this task's execution time to its accounting group. |
9484 | * | 9484 | * |
9485 | * called with rq->lock held. | 9485 | * called with rq->lock held. |
9486 | */ | 9486 | */ |
9487 | static void cpuacct_charge(struct task_struct *tsk, u64 cputime) | 9487 | static void cpuacct_charge(struct task_struct *tsk, u64 cputime) |
9488 | { | 9488 | { |
9489 | struct cpuacct *ca; | 9489 | struct cpuacct *ca; |
9490 | int cpu; | 9490 | int cpu; |
9491 | 9491 | ||
9492 | if (unlikely(!cpuacct_subsys.active)) | 9492 | if (unlikely(!cpuacct_subsys.active)) |
9493 | return; | 9493 | return; |
9494 | 9494 | ||
9495 | cpu = task_cpu(tsk); | 9495 | cpu = task_cpu(tsk); |
9496 | 9496 | ||
9497 | rcu_read_lock(); | 9497 | rcu_read_lock(); |
9498 | 9498 | ||
9499 | ca = task_ca(tsk); | 9499 | ca = task_ca(tsk); |
9500 | 9500 | ||
9501 | for (; ca; ca = ca->parent) { | 9501 | for (; ca; ca = ca->parent) { |
9502 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); | 9502 | u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); |
9503 | *cpuusage += cputime; | 9503 | *cpuusage += cputime; |
9504 | } | 9504 | } |
9505 | 9505 | ||
9506 | rcu_read_unlock(); | 9506 | rcu_read_unlock(); |
9507 | } | 9507 | } |
9508 | 9508 | ||
9509 | /* | 9509 | /* |
9510 | * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large | 9510 | * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large |
9511 | * in cputime_t units. As a result, cpuacct_update_stats calls | 9511 | * in cputime_t units. As a result, cpuacct_update_stats calls |
9512 | * percpu_counter_add with values large enough to always overflow the | 9512 | * percpu_counter_add with values large enough to always overflow the |
9513 | * per cpu batch limit causing bad SMP scalability. | 9513 | * per cpu batch limit causing bad SMP scalability. |
9514 | * | 9514 | * |
9515 | * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we | 9515 | * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we |
9516 | * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled | 9516 | * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled |
9517 | * and enabled. We cap it at INT_MAX which is the largest allowed batch value. | 9517 | * and enabled. We cap it at INT_MAX which is the largest allowed batch value. |
9518 | */ | 9518 | */ |
9519 | #ifdef CONFIG_SMP | 9519 | #ifdef CONFIG_SMP |
9520 | #define CPUACCT_BATCH \ | 9520 | #define CPUACCT_BATCH \ |
9521 | min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX) | 9521 | min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX) |
9522 | #else | 9522 | #else |
9523 | #define CPUACCT_BATCH 0 | 9523 | #define CPUACCT_BATCH 0 |
9524 | #endif | 9524 | #endif |
9525 | 9525 | ||
9526 | /* | 9526 | /* |
9527 | * Charge the system/user time to the task's accounting group. | 9527 | * Charge the system/user time to the task's accounting group. |
9528 | */ | 9528 | */ |
9529 | static void cpuacct_update_stats(struct task_struct *tsk, | 9529 | static void cpuacct_update_stats(struct task_struct *tsk, |
9530 | enum cpuacct_stat_index idx, cputime_t val) | 9530 | enum cpuacct_stat_index idx, cputime_t val) |
9531 | { | 9531 | { |
9532 | struct cpuacct *ca; | 9532 | struct cpuacct *ca; |
9533 | int batch = CPUACCT_BATCH; | 9533 | int batch = CPUACCT_BATCH; |
9534 | 9534 | ||
9535 | if (unlikely(!cpuacct_subsys.active)) | 9535 | if (unlikely(!cpuacct_subsys.active)) |
9536 | return; | 9536 | return; |
9537 | 9537 | ||
9538 | rcu_read_lock(); | 9538 | rcu_read_lock(); |
9539 | ca = task_ca(tsk); | 9539 | ca = task_ca(tsk); |
9540 | 9540 | ||
9541 | do { | 9541 | do { |
9542 | __percpu_counter_add(&ca->cpustat[idx], val, batch); | 9542 | __percpu_counter_add(&ca->cpustat[idx], val, batch); |
9543 | ca = ca->parent; | 9543 | ca = ca->parent; |
9544 | } while (ca); | 9544 | } while (ca); |
9545 | rcu_read_unlock(); | 9545 | rcu_read_unlock(); |
9546 | } | 9546 | } |
9547 | 9547 | ||
9548 | struct cgroup_subsys cpuacct_subsys = { | 9548 | struct cgroup_subsys cpuacct_subsys = { |
9549 | .name = "cpuacct", | 9549 | .name = "cpuacct", |
9550 | .create = cpuacct_create, | 9550 | .create = cpuacct_create, |
9551 | .destroy = cpuacct_destroy, | 9551 | .destroy = cpuacct_destroy, |
9552 | .populate = cpuacct_populate, | 9552 | .populate = cpuacct_populate, |
9553 | .subsys_id = cpuacct_subsys_id, | 9553 | .subsys_id = cpuacct_subsys_id, |
9554 | }; | 9554 | }; |
9555 | #endif /* CONFIG_CGROUP_CPUACCT */ | 9555 | #endif /* CONFIG_CGROUP_CPUACCT */ |
9556 | 9556 | ||
9557 | 9557 |