* Add AMD and Intel doc links
* Use 'return' only if there is no error; on error, the end-function 'return CPU_INVALID_VALUE' is used
* Add more comments about MSRs
* Simplify a lot of things
* Avoid cpu_rdmsr_range() to override cpu_rdmsr() error
* Remove int casting in cpu_msrinfo()
This is a backwards-incompatible binary change, which increases
sizeof(cpu_raw_data_t). Specifically, the cpu_raw_data_t::intel_fn4
array is increased from 4 to 8 elements, because on recent Hasells
(Crystalwell) there is a Level 4 cache, which should be encoded in
CPUID eax=4 ecx=4. However, we were only storing levels for eax=4
for ecx <= 3. Thus the raw data didn't have the relevant info.
There will be further changes to this, specifically to store
and print the level 4 cache in cpuid_tool.
- Expose intel_code_t and amd_code_t enums - they are no longer
limited to just recog_{intel,amd}.c.
- Add libcpuid_internal.h lists those enums and provides the,
cpu_ident_internal() function, which is the same as cpu_identify(),
but also has a third parameter - a internal_id_info_t structure,
which holds detection internals.
All of this is intended to be used in rdmsr, which needs to know
specifics on what CPU it is running.
Also add a comment about the upcoming version 0.2.3. A date is not
stated, as this will be done when the actual release happens (and
I will collect any further patches up to that moment). I expect the
release to be over the next weekend.
rdmsr.c:616:10: warning: comparison of 0 <= unsigned expression is always true [-Wtautological-compare]
if(0 <= val && val <= 7) { // Support 8 P-states
~ ^ ~~~
rdmsr.c:572:8: warning: variable 'val' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
if(!multiplier)
^~~~~~~~~~~
rdmsr.c:574:8: note: uninitialized use occurs here
if(val > 0) {
^~~
rdmsr.c:572:5: note: remove the 'if' if its condition is always true
if(!multiplier)
^~~~~~~~~~~~~~~
rdmsr.c:541:14: note: initialize the variable 'val' to silence this warning
uint64_t val;
^
= 0
2 warnings generated.
Tested on GhostBSD (based on FreeBSD)
It should work on DragonFlyBSD (the cpuctl driver has been ported from FreeBSD)
The situation for OpenBSD and NetBSD is not clear ; not supported
The detected intel brand code and model code (arbitrary numbers,
related to the detection algorithm) are printed at verbosiness level
2 or higher. You can see them with `cpuid_tool --all -vv` (if running
on an Intel CPU), or, generally, when decoding Intel CPU data, e.g.
`cpuid_tool --load=tests/intel/nehalem/bloomfield.test --all -vv`.
