summaryrefslogtreecommitdiffhomepage
path: root/pkg/cpuid
AgeCommit message (Collapse)Author
2020-04-01Fix 386 build tagsMichael Pratt
The build tag for 32-bit x86 is 386, not i386. Updates #2298 PiperOrigin-RevId: 304206373
2020-03-30Add AMD Rome CPUID flag.Michael Pratt
This flag is set on Rome CPUs, but it is not documented. PiperOrigin-RevId: 303825532
2020-02-18cpuid: cache the maximum size of xsave stategVisor bot
perf shows that ExtendedStateSize cosumes more than 20% of cpu: 23.61% 23.61% [.] pkg/cpuid/cpuid.HostID PiperOrigin-RevId: 295813263
2020-02-10Merge pull request #1453 from xiaobo55x:cpuidgVisor bot
PiperOrigin-RevId: 294257911
2020-02-10Enable pkg/cpuid support on arm64.Haibo Xu
Fixes #1255 Signed-off-by: Haibo Xu <haibo.xu@arm.com> Change-Id: I8614e6f3ee321c2989567e4e712aa8f28cc9db14
2020-01-27Standardize on tools directory.Adin Scannell
PiperOrigin-RevId: 291745021
2020-01-16Add remaining /proc/* and /proc/sys/* filesFabricio Voznika
Except for one under /proc/sys/net/ipv4/tcp_sack. /proc/pid/* is still incomplete. Updates #1195 PiperOrigin-RevId: 290120438
2019-11-11Add more extended features.Brad Burlage
PiperOrigin-RevId: 279820435
2019-10-16Reorder BUILD license and load functions in gvisor.Kevin Krakauer
PiperOrigin-RevId: 275139066
2019-09-12Remove go_test from go_stateify and go_marshalMichael Pratt
They are no-ops, so the standard rule works fine. PiperOrigin-RevId: 268776264
2019-08-26Add support for Intel cache CPUID leafsMichael Pratt
This exposes L1, L2, etc. cache sizes, cache line size, etc. Across S/R, everything except cache line size can differ from the host. This is because cache line size is critical for correct use of CLFLUSH / CLFLUSHOPT, but as far as I know, the other cache parameters can only affect performance, not correctness. AMD uses different leafs for cache information, which are not yet supported. fail. There are no known cases of cache line size other than 64 in the fleet. PiperOrigin-RevId: 265544786
2019-06-27Fix various spelling issues in the documentationMichael Pratt
Addresses obvious typos, in the documentation only. COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gvisor/pull/443 from Pixep:fix/documentation-spelling 4d0688164eafaf0b3010e5f4824b35d1e7176d65 PiperOrigin-RevId: 255477779
2019-06-13Update canonical repository.Adin Scannell
This can be merged after: https://github.com/google/gvisor-website/pull/77 or https://github.com/google/gvisor-website/pull/78 PiperOrigin-RevId: 253132620
2019-04-29Change copyright notice to "The gVisor Authors"Michael Pratt
Based on the guidelines at https://opensource.google.com/docs/releasing/authors/. 1. $ rg -l "Google LLC" | xargs sed -i 's/Google LLC.*/The gVisor Authors./' 2. Manual fixup of "Google Inc" references. 3. Add AUTHORS file. Authors may request to be added to this file. 4. Point netstack AUTHORS to gVisor AUTHORS. Drop CONTRIBUTORS. Fixes #209 PiperOrigin-RevId: 245823212 Change-Id: I64530b24ad021a7d683137459cafc510f5ee1de9
2019-04-29Allow and document bug ids in gVisor codebase.Nicolas Lacasse
PiperOrigin-RevId: 245818639 Change-Id: I03703ef0fb9b6675955637b9fe2776204c545789
2019-04-25Perform explicit CPUID and FP state compatibility checks on restoreMichael Pratt
PiperOrigin-RevId: 245341004 Change-Id: Ic4d581039d034a8ae944b43e45e84eb2c3973657
2019-04-04Set fixed field in CPUID function 2Michael Pratt
From the SDM: "The least-significant byte in register EAX (register AL) will always return 01H. Software should ignore this value and not interpret it as an informational descriptor." Unfortunately, online docs [1] [2] (likely based on an old version of the SDM) say: "The least-significant byte in register EAX (register AL) indicates the number of times the CPUID instruction must be executed with an input value of 2 to get a complete description of the processor's caches and TLBs." dlang uses this second interpretation [3] and will loop 2^32 times if we return zero. Fix this by specifying the fixed value of one. We still don't support exposing the actual cache information, leaving all other bytes empty. A zero byte means: "Null descriptor, this byte contains no information." [1] http://www.sandpile.org/x86/cpuid.htm#level_0000_0002h [2] https://c9x.me/x86/html/file_module_x86_id_45.html [3] https://github.com/dlang/druntime/blob/424640864c2aa001731467e96f637bd3e704e481/src/core/cpuid.d#L533-L534 PiperOrigin-RevId: 242046629 Change-Id: Ic0f0a5f974b20f71391cb85645bdcd4003e5fe88
2019-03-26Automated rollback of changelist 234892473Michael Pratt
PiperOrigin-RevId: 240462667 Change-Id: I3d1c5c0d80a3badced963ae1d450c20ed8a767ed
2019-02-20Automated rollback of changelist 234680481Michael Pratt
PiperOrigin-RevId: 234892473 Change-Id: Ie568c67d299082a008a1cf9802942e5e03746501
2019-02-19Rename "perfctr_l2" to "perfctr_llc"Michael Pratt
910448bbed066ab1082b510eef1ae61bb792d854 ("perf/x86/amd/uncore: Rename cpufeatures macro for cache counters") in 4.14 changed the name. We change both the internal and cpuinfo name. As the upstream commit states, "In Family 17h, L3 is the last level cache as opposed to L2 in previous families. Avoid this name confusion ..." PiperOrigin-RevId: 234698034 Change-Id: Ibf2efd4c0b83c1a8b5bb123da65ea1d7c6acd778
2019-02-19Rename "rdt" to "rdt_a"Michael Pratt
The final merged patch in Linux 4.10, 4ab1586488cb56ed8728e54c4157cc38646874d9 ("x86/cpufeature: Add RDT CPUID feature bits") named this feature "rdt_a". Earlier patch sets had named this "rdt". PiperOrigin-RevId: 234680481 Change-Id: I0cc968201ec9a2825701405e207994a7331322b7
2019-02-13Expose XSAVES in /proc/cpuinfoMichael Pratt
Linux started doing this in b8be15d588060a03569ac85dc4a0247460988f5b ("x86/fpu/xstate: Re-enable XSAVES"), which first appeared in 4.8. PiperOrigin-RevId: 233800931 Change-Id: Icac2c2b03ccf1a91f3070431efb5152ca619fca3
2019-01-31Remove license commentsMichael Pratt
Nothing reads them and they can simply get stale. Generated with: $ sed -i "s/licenses(\(.*\)).*/licenses(\1)/" **/BUILD PiperOrigin-RevId: 231818945 Change-Id: Ibc3f9838546b7e94f13f217060d31f4ada9d4bf0
2018-10-30Clean up cpuid_parse_testMichael Pratt
Actually parse flags from cpuinfo to avoid mistakenly matching substrings in cpuinfo that happen to match a flags. Some features were only exposed in recent versions of Linux. Don't require them to appear in cpuinfo on old versions of Linux. Move PREFETCHWT1 back to parse only features. It isn't actually exposed in Linux yet. Move SDBG to shown features. It has been visible since Linux 4.3. PiperOrigin-RevId: 219381731 Change-Id: Ied7c0ee7c8a9879683e81933de56c9074b01108f
2018-10-26Add AMD-specific features to cpuid packageMichael Pratt
Extend the cpuid package to parse and emulate cpuid features that exist only on AMD and not Intel. The least straightforward part of this is that AMD duplicates several block 1 features in block 6. Thus we ignore those features when parsing block 6 and add them when emulating. PiperOrigin-RevId: 218935032 Change-Id: Id41bf1c24720b0d9b968e2c19ab5bc00a6d62bd4
2018-10-26Add block 3 features to /proc/cpuinfoMichael Pratt
Linux added these block 3 features to the end of /proc/cpuinfo in dfb4a70f20c5b3880da56ee4c9484bdb4e8f1e65. This also fixes that block 3 features were completely missing from FeatureSet.FlagsString(false) because FlagsString only prints Linux blocks regardless of the cpuinfo option. PiperOrigin-RevId: 218913816 Change-Id: I2f9c38c7c9da4b247a140877d4aca782e80684bd
2018-10-26Order feature strings by blockMichael Pratt
PiperOrigin-RevId: 218894181 Change-Id: I97d0c74175f4aa528363f768a0a85d6953ea0bfd
2018-10-19Use correct company name in copyright headerIan Gudger
PiperOrigin-RevId: 217951017 Change-Id: Ie08bf6987f98467d07457bcf35b5f1ff6e43c035
2018-08-02Automated rollback of changelist 207037226Zhaozhong Ni
PiperOrigin-RevId: 207125440 Change-Id: I6c572afb4d693ee72a0c458a988b0e96d191cd49
2018-08-01Automated rollback of changelist 207007153Michael Pratt
PiperOrigin-RevId: 207037226 Change-Id: I8b5f1a056d4f3eab17846f2e0193bb737ecb5428
2018-08-01stateify: convert all packages to use explicit mode.Zhaozhong Ni
PiperOrigin-RevId: 207007153 Change-Id: Ifedf1cc3758dc18be16647a4ece9c840c1c636c9
2018-07-27stateify: support explicit annotation mode; convert refs and stack packages.Zhaozhong Ni
We have been unnecessarily creating too many savable types implicitly. PiperOrigin-RevId: 206334201 Change-Id: Idc5a3a14bfb7ee125c4f2bb2b1c53164e46f29a8
2018-05-07Fix misspellingsIan Gudger
PiperOrigin-RevId: 195742598 Change-Id: Ibd4a8e4394e268c87700b6d1e50b4b37dfce5182
2018-04-28Check in gVisor.Googler
PiperOrigin-RevId: 194583126 Change-Id: Ica1d8821a90f74e7e745962d71801c598c652463