Re: [PATCH v6 11/11] arm64: Document Arm Confidential Compute

[Jean-Philippe Brucker]

On Fri, Oct 04, 2024 at 03:43:06PM +0100, Steven Price wrote:
> Add some documentation on Arm CCA and the requirements for running Linux
> as a Realm guest. Also update booting.rst to describe the requirement
> for RIPAS RAM.
> 
> Signed-off-by: Steven Price <steven.price@xxxxxxx>
> ---
>  Documentation/arch/arm64/arm-cca.rst | 67 ++++++++++++++++++++++++++++
>  Documentation/arch/arm64/booting.rst |  3 ++
>  Documentation/arch/arm64/index.rst   |  1 +
>  3 files changed, 71 insertions(+)
>  create mode 100644 Documentation/arch/arm64/arm-cca.rst
> 
> diff --git a/Documentation/arch/arm64/arm-cca.rst b/Documentation/arch/arm64/arm-cca.rst
> new file mode 100644
> index 000000000000..ab7f90e64c2f
> --- /dev/null
> +++ b/Documentation/arch/arm64/arm-cca.rst
> @@ -0,0 +1,67 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
> +=====================================
> +Arm Confidential Compute Architecture
> +=====================================
> +
> +Arm systems that support the Realm Management Extension (RME) contain
> +hardware to allow a VM guest to be run in a way which protects the code
> +and data of the guest from the hypervisor. It extends the older "two
> +world" model (Normal and Secure World) into four worlds: Normal, Secure,
> +Root and Realm. Linux can then also be run as a guest to a monitor
> +running in the Realm world.
> +
> +The monitor running in the Realm world is known as the Realm Management
> +Monitor (RMM) and implements the Realm Management Monitor
> +specification[1]. The monitor acts a bit like a hypervisor (e.g. it runs
> +in EL2 and manages the stage 2 page tables etc of the guests running in
> +Realm world), however much of the control is handled by a hypervisor
> +running in the Normal World. The Normal World hypervisor uses the Realm
> +Management Interface (RMI) defined by the RMM specification to request
> +the RMM to perform operations (e.g. mapping memory or executing a vCPU).
> +
> +The RMM defines an environment for guests where the address space (IPA)
> +is split into two. The lower half is protected - any memory that is
> +mapped in this half cannot be seen by the Normal World and the RMM
> +restricts what operations the Normal World can perform on this memory
> +(e.g. the Normal World cannot replace pages in this region without the
> +guest's cooperation). The upper half is shared, the Normal World is free
> +to make changes to the pages in this region, and is able to emulate MMIO
> +devices in this region too.
> +
> +A guest running in a Realm may also communicate with the RMM to request
> +changes in its environment or to perform attestation about its
> +environment. In particular it may request that areas of the protected
> +address space are transitioned between 'RAM' and 'EMPTY' (in either
> +direction). This allows a Realm guest to give up memory to be returned
> +to the Normal World, or to request new memory from the Normal World.
> +Without an explicit request from the Realm guest the RMM will otherwise
> +prevent the Normal World from making these changes.

We could mention that this interface is "RSI", so readers know what to
look for next

> +
> +Linux as a Realm Guest
> +----------------------
> +
> +To run Linux as a guest within a Realm, the following must be provided
> +either by the VMM or by a `boot loader` run in the Realm before Linux:
> +
> + * All protected RAM described to Linux (by DT or ACPI) must be marked
> +   RIPAS RAM before handing over the Linux.

"handing control over to Linux", or something like that?

> +
> + * MMIO devices must be either unprotected (e.g. emulated by the Normal
> +   World) or marked RIPAS DEV.
> +
> + * MMIO devices emulated by the Normal World and used very early in boot
> +   (specifically earlycon) must be specified in the upper half of IPA.
> +   For earlycon this can be done by specifying the address on the
> +   command line, e.g.: ``earlycon=uart,mmio,0x101000000``

This is going to be needed frequently, so maybe we should explain in a
little more detail how we come up with this value: "e.g. with an IPA size
of 33 and the base address of the emulated UART at 0x1000000,
``earlycon=uart,mmio,0x101000000``"

(Because the example IPA size is rather unintuitive and specific to the
kvmtool memory map)

Thanks,
Jean

> +
> + * Linux will use bounce buffers for communicating with unprotected
> +   devices. It will transition some protected memory to RIPAS EMPTY and
> +   expect to be able to access unprotected pages at the same IPA address
> +   but with the highest valid IPA bit set. The expectation is that the
> +   VMM will remove the physical pages from the protected mapping and
> +   provide those pages as unprotected pages.
> +
> +References
> +----------
> +[1] https://developer.arm.com/documentation/den0137/
> diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst
> index b57776a68f15..30164fb24a24 100644
> --- a/Documentation/arch/arm64/booting.rst
> +++ b/Documentation/arch/arm64/booting.rst
> @@ -41,6 +41,9 @@ to automatically locate and size all RAM, or it may use knowledge of
>  the RAM in the machine, or any other method the boot loader designer
>  sees fit.)
>  
> +For Arm Confidential Compute Realms this includes ensuring that all
> +protected RAM has a Realm IPA state (RIPAS) of "RAM".
> +
>  
>  2. Setup the device tree
>  -------------------------
> diff --git a/Documentation/arch/arm64/index.rst b/Documentation/arch/arm64/index.rst
> index 78544de0a8a9..12c243c3af20 100644
> --- a/Documentation/arch/arm64/index.rst
> +++ b/Documentation/arch/arm64/index.rst
> @@ -10,6 +10,7 @@ ARM64 Architecture
>      acpi_object_usage
>      amu
>      arm-acpi
> +    arm-cca
>      asymmetric-32bit
>      booting
>      cpu-feature-registers
> -- 
> 2.34.1
> 
>