You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The default interrupt handling priority described in Section 6.4. And with the Note below, RDSM will clear the bit corresponding to that interrupt controller selected by msdcfg.SDICN in msdeie prior to resuming execution of the supervisor domain.
Here I have a question:
When both a "non-active supervisor domain interrupt (LSDEIP)" and an "active supervisor domain interrupt (VSEI)" occur simultaneously, why is the default to prioritize handling interrupts from other domains rather than prioritizing TVM interrupts within the current active domain?
If currently in the confidential supervisor domain, TSM needs to perform a TEERET to the VMM, leaving the scheduling decision to the VMM.
When interrupts occur in multiple supervisor domains simultaneously, if each domain prioritizes handling interrupts from other domains, could this lead to a "domain scheduling storm" where no interrupt is actually processed to completion?
Looking forward to your answer, thank you!
The text was updated successfully, but these errors were encountered:
The default interrupt handling priority described in Section 6.4. And with the Note below, RDSM will clear the bit corresponding to that interrupt controller selected by msdcfg.SDICN in msdeie prior to resuming execution of the supervisor domain.
Here I have a question:
When both a "non-active supervisor domain interrupt (LSDEIP)" and an "active supervisor domain interrupt (VSEI)" occur simultaneously, why is the default to prioritize handling interrupts from other domains rather than prioritizing TVM interrupts within the current active domain?
If currently in the confidential supervisor domain, TSM needs to perform a TEERET to the VMM, leaving the scheduling decision to the VMM.
When interrupts occur in multiple supervisor domains simultaneously, if each domain prioritizes handling interrupts from other domains, could this lead to a "domain scheduling storm" where no interrupt is actually processed to completion?
Looking forward to your answer, thank you!
The text was updated successfully, but these errors were encountered: