Q2.12: Power Management Across OSs
2 likes1,484 views
This document proposes a standardized interface for collaborating on power management across operating systems on ARM devices. It suggests defining a set of APIs to handle powering down and up CPUs for idle states, hot plug, secondary boot, and CPU migration. These APIs would take parameters like the affinity level, resume address, and context ID to enable saving and restoring state across OS layers. Implementing this interface with calls like IdlePowerDown, CPUAdd, CPURemove, CPUSwitchIn, and CPUSwitchOut could facilitate collaboration between Linux, hypervisors, and trusted operating systems on power management.
Q2.12: Power Management Across OSs
- 2. 2 Introduction Firmware/ACPI is not the most popular topic in Linux: “Modern PCs are horrible. ACPI is a complete design disaster in every way. But we're kind of stuck with it. If any Intel people are listening to this and you had anything to do with ACPI, shoot yourself now, before you reproduce” “The fact that ACPI was designed by a group of monkeys high on LSD, and is some of the worst designs in the industry obviously makes running it at any point pretty damn ugly. “ “EFI is this other Intel brain-damage (the first one being ACPI). “
- 3. 3 Linux is not Alone on the Device Secure code will be present, provided by Semico or trusted OS vendor for a variety reasons: Secure boot Crypto services Secure key storage .... Global platform is a leading security standards body in mobile space Most companies in this room are members Hypervisor can also be present There is actually a work item in Linaro to cover Trustzone TrustZone kernel driver
- 4. 4 ARMv7/v8 Privilege/Exception Levels Apps Apps Apps Apps Guest OS Apps Apps Apps Apps Guest OS Hypervisor Secure AppsSecure Apps Secure OS Secure Monitor EL0 EL1 EL2 EL3 Non-Secure Secure 32-bit & 64-bit Apps Guest OS 64-bit Hypervisor Monitor Apps Apps Apps Apps Guest OS Apps Apps Apps Apps Guest OS Hypervisor Secure AppsSecure Apps Secure OS Secure Monitor PL0 PL1 PL2 Non-Secure ARMv7 ARMv8
- 5. 5 ARMv7/v8 Privilege/Exception Levels Apps Apps Apps Apps Guest OS Apps Apps Apps Apps Guest OS Hypervisor Secure AppsSecure Apps Trusted OS Secure Monitor PL0 PL1 PL2 Non-Secure ARMv7 Rich OSs Linux, Windows ... Hyp vendors OKLabs, VMWare ... TrustedOS Vendors Semicos, ...
- 6. 6 So Need Collaboration Need OSs at different privilege layers to collaborate on power OSs need to know when to save/restore their state OSs need to manage peripherals they own when entering a power state Linux Hypervisor Secure world Hotplug Secondary boot Idle Powercontroller optional bigLITTLE migration
- 7. 7 Cold Boot vs Warm Boot Linux Kernel Secure ROM Goto TrustedOS Warm boot vector Secure ROM Init check boot reason Secure Flash Boot firmware Install TrustedOS Uboot Load linux from media Trusted OS Start RichOS at Its warm boot vector Linux Kernel Secure Non-Secure
- 8. 8 Cold Boot vs Warm Boot Linux Kernel Secure ROM Goto TrustedOS Warm boot vector Secure ROM Init check boot reason Secure Flash Boot firmware Install TrustedOS Uboot Load linux from media Trusted OS Start RichOS at Its warm boot vector Linux Kernel Secure Non-Secure Linux needs to define warm boot address and inform secure side
- 9. 9 Context Idle management use of shutdown states requires context saving and restoring big.LITTLE migration models require saving context, and restoring on a different CPU Every OS layer may need to save context, and every booting CPU needs a context for every OS layer
- 10. 10 Proposal System APIs are required by Idle states Hot plug Secondary boot CPU Migration (Switching) Can be captured in a few APIs: Power down CPU for Idle -> IdlePowerDown Power up CPU for hot plug -> CPUAdd Power down a CPU for hot unplug -> CPURemove Power up the inbound CPU for migration -> CPUSwitchIn Power down the outbound CPU for migration -> CPUSwitchOut
- 11. 11 Conduit to next layer of privilege To talk across OSs you need instructions that can get you up to next level of privilege SMC provides such an interface. SMC can also be trapped at hypervisor level A virtualised guest can use the same interface
- 12. 12 Powering Down a CPU for Idle We want to capture the following semantics: What is being powered down: You can power the current CPU down If last man you can power the current cluster down How do express a return address? How do express what context to use when you restart
- 13. 13 Powering Down a CPU for Idle What is being powered down? We can use an affinity level Affinity level 0 -> current CPU Affinity Level 1 -> Current cluster Affinity Level 2 -> Current cluster of clusters / whole system CPU identification scheme in ARMv7 define three affinity levels OS managing power is responsible for tracking “last man” and synchronising entry
- 14. 14 Power Down – Resume Address & Context ID Resume address Address at which calling OS expects to be restarted Context ID Opaque value understood by calling OS which must be in R0 when OS is resumed 13 1 2 3 2
- 15. 15 Power Down IdlePowerDown Parameters Affinity level: CPU or cluster (or indeed cluster of clusters ...) Resume address and context ID Return Invalid parameters Success
- 16. 16 Power Up/Down – HotPlug Hot Plug - CPURemove Parameters Affinity level: CPU or cluster (or indeed cluster of clusters ...) OS has to track last man Hot Unplug or secondary cold boot - CPUAdd Parameters CPUID of core being powered up Resume address and context ID Return Invalid Parameters Success
- 17. 17 Migration with Power Up/Down
- 19. 19 Power Up for CPU Switching SwitchIn Secure World knows that the intent is a switch Parameters CPUID of inbound core Resume vector and contextID Return Success TryAgain Invalid parameters
- 20. 20 Power Down for Migration SwitchOut Parameters Affinity Level to power down Resume vector and contextID Must match ones used in SwitchIn Return Invalid parameters
- 21. 21 Status Standard calling conventions Secure monitor SMC Hypervisor HVC ARM will be providing sample secure code for power interface Questions ...