The design of ACRN CPU performance management is to let hardware
do the autonomous frequency selection(or set to a fixed value),
and remove guest's ability to control CPU frequency.
This patch is to remove guest's ability to control CPU frequency by
removing the guests' HWP/EIST CPUIDs and blocking the related MSR
accesses. Including:
- Remove CPUID.06H:EAX[7..11] (HWP)
- Remove CPUID.01H:ECX[7] (EIST)
- Inject #GP(0) upon accesses to MSR_IA32_PM_ENABLE,
MSR_IA32_HWP_CAPABILITIES, MSR_IA32_HWP_REQUEST,
MSR_IA32_HWP_STATUS, MSR_IA32_HWP_INTERRUPT,
MSR_IA32_HWP_REQUEST_PKG
- Emulate MSR_IA32_PERF_CTL. Value written to MSR_IA32_PERF_CTL
is just stored for reading. This is like how the native
environment would behavior when EIST is disabled from BIOS.
- Emulate MSR_IA32_PERF_STATUS by filling it with base frequency
state. This is consistent with Windows, which displays current
frequency as base frequency when running in VM.
- Hide the IA32_MISC_ENABLE bit 16 (EIST enable) from guests.
This bit is dependent to CPUID.01H:ECX[7] according to SDM.
- Remove CPID.06H:ECX[0] (hardware coordination feedback)
- Inject #GP(0) upon accesses to IA32_MPERF, IA32_APERF
Also DM do not need to generate _PSS/_PPC for post-launched VMs
anymore. This is done by letting hypercall HC_PM_GET_CPU_STATE sub
command ACRN_PMCMD_GET_PX_CNT and ACRN_PMCMD_GET_PX_DATA return (-1).
Tracked-On: #8168
Signed-off-by: Wu Zhou <wu.zhou@intel.com>
Acked-by: Eddie Dong <eddie.dong@intel.com>
Reset the real_time_vcpu to 'n' if the VM is not a real-time VM.
Tracked-On: #8145
Signed-off-by: Yang,Yu-chu <yu-chu.yang@intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
HPET is used to calibrate the tsc frequency if system fails to
get the accurate frequency from CPUID 0x15. But on some platforms
(for example: the emulated ACRN on QEMU) HPET is not started
by default, which causes the failure of calibration TSC by HPET.
Tracked-On: #8113
Signed-off-by: Jian Jun Chen <jian.jun.chen@intel.com>
Reviewed-by: Zhao Yakui <yakui.zhao@intel.com>
Acked-by: Eddie Dong <eddie.dong@intel.com>
The ACRN Configurator release 3.1 following the release 3.0 logic, so
the COM2 still used for S5.
This patch modify the "The release v3.0 ACRN Configurator assigns… …"
to "The release v3.0+ ACRN Configurator assigns… …" and refine a typo
issue.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@intel.com>
The BDF of user setting should skip the slot '00', '01', '02', '1f', all
these slots should select one of the 03~1e.
This patch add an assertion to check the above policy.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@intel.com>
1. In the title "Create a new Scenario", capitalize the "N" in "new".
2. Fix the file path to the installer.
Tracked-On: #8137
Signed-off-by: Yang,Yu-chu <yu-chu.yang@intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
to avoid misleading for users, delete the description about
hypervisor relocation disabling, since it is not officially
supported by ACRN configurator now.
Tracked-On: #8133
Signed-off-by: hangliu1 <hang1.liu@linux.intel.com>
the configurator can clear its corresponding I/O port or BDF settings automatically when the VM of a vUART endpoint changes
v1-->v2: support the result working on multiple VUART Connections
Tracked-On: #8033
Signed-off-by: Chuang-Ke <chuangx.ke@intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
Now, if you use a memory address below 4G, there will be a warning,
but the build process of the hypervisor will not be interrupted.
Tracked-On: #6690
Signed-off-by: Ziheng Li <ziheng.li@intel.com>
improve the translateError function by adding a condition: if there are errors describing the same error and same paths, remove the repeat one.
Tracked-On: #8117
Signed-off-by: Chuang-Ke <chuangx.ke@intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
There is some issue when use upgrade to update some old xml version to
release_3.1, this patch modify the upgrade script to fix these issue.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@intel.com>
Because of the iteration of i as is, the condition i <= XHCI_MAX_DEVS
always results as true and thus is unnecessary.
When compiling with cflag -Werror this condition will result in a
compilation failure.
Tracked-On: #8114
Signed-off-by: Marius Rodi <marius.rodi@linutronix.de>
The current code have not check whether all cache region has "Code and
Data Prioritization", it's an issue for some platform which have only
L2 or L3 "Code and Data Prioritization" capability.
This patch add assertion to check whether all L2, L3 cache could be set
CDP_ENABLE.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@intel.com>
Restore a hidden option and its type accidentally removed by PR #8100 and #8099
Tracked-On: #8098
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Commit 2a8b80d0c ("config_tools: board_inspector: guess L3 CAT parameters
if not reported via CPUID") refactors the implementation of `--add-llc-cat`
option of the board inspector but does not update the referenced XML nodes
properly. This patch fixes a using-undefined-variable issue introduced by
that commit.
Tracked-On: #7948
Signed-off-by: Junjie Mao <junjie.mao@intel.com>
Generate config_summary.py script in misc/config-tools/scenario_config
directory. This script can extract important information from scenario
and board xml to summary it into RST format text.
Tracked-On: #8063
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
Signed-off-by: Ziheng Li <ziheng.li@intel.com>
The configurator build requires the released documentation to be
published before it normally would so it can resolve :ref: links in
tooltips. Move these :ref: links into a second xs:documentation tag so
the reference will appear in the option documentation but not in the
tooltip (and break this premature dependency in the configurator build).
Tracked-On: #8098
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Currently we have to use additional patch to change config tool python
code to enable P2SB hidden device.
This patch have add an element, user could config the P2SB device in
the scenario XML.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@linux.intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
changed-docs.sh (and the accompanying awk script) shows docs changed
between a previous release branch and the current master branch, in a format that
can be used for the releae notes (a list of :ref: items).
Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Before, the logic automatically sets RDT as y if CDP is y. when the user imports a scenario, the CDP is y and RDT is y, the view will set CDP as y and RDT as y.
After fixing, the logic won't set RDT as y if CDP is y, which means the RDT won't be changed no matter if CDP is y or n(only when import scenario) .
Tracked-On: #8087
Signed-off-by: Chuang-Ke <chuangx.ke@intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
The current code sort cpu list by string order, this is an issue when
we want to assign more then 10 vCPUs for some VM.
So this patch rewrite the sort of these list, now the cpu list order
by int type.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@linux.intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
Change ">>/dev/stderr" to ">&2"
Although it seems that the two have the same effects, the way they work is different.
The ">/dev/stderr" does an open(), it goes to the filesystem look for that file, opens and write to it. The second way, ">&2",just uses file descriptor 2.
The acrnd deamon outputs the stdin and stderr messages to journal through socket. And the socket cannot be manipulated with open methods.So acrnd cannot open the "/dev/stderr" which has redirected to a socket.
For successfully excuting the create_tap function in acrnd deamon, We change ">> /dev/stderr" to ">&2".
For the remain ">> /dev/stderr", they all follow the echo command and will not harm the launchscript functionality.
Tracked-On: #8066
Signed-off-by: Zhang Wei <wei6.zhang@intel.com>
The current elementpath of ACRN Configurator use 2.4.0 which can's
support some new python interface, this patch update it to 2.5.0 to
fix the above issue.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@linux.intel.com>
Conghui