[External] [PATCH v4 0/3] RISC-V: Detect Ssqosid extension and handle srmcfg CSR

[yunhui cui]

Hi Drew,

On Wed, Oct 8, 2025 at 2:22 PM Drew Fustini <fustini at kernel.org> wrote:
>
> This series adds support for the RISC-V Quality-of-Service Identifiers
> (Ssqosid) extension [1] which adds the srmcfg register. This CSR
> configures a hart with two identifiers: a Resource Control ID (RCID)
> and a Monitoring Counter ID (MCID). These identifiers accompany each
> request issued by the hart to shared resource controllers.
>
> Background on RISC-V QoS:
>
> The Ssqosid extension is used by the RISC-V Capacity and Bandwidth
> Controller QoS Register Interface (CBQRI) specification [2]. QoS in
> this context is concerned with shared resources on an SoC such as cache
> capacity and memory bandwidth. Intel and AMD already have QoS features
> on x86 and ARM has MPAM. There is an existing user interface in Linux:
> the resctrl virtual filesystem [3].
>
> The srmcfg CSR provides a mechanism by which a software workload (e.g.
> a process or a set of processes) can be associated with an RCID and an
> MCID. CBQRI defines operations to configure resource usage limits, in
> the form of capacity or bandwidth. CBQRI also defines operations to
> configure counters to track the resource utilization.
>
> Goal for this series:
>
> These patches are taken from the implementation of resctrl support for
> RISC-V CBQRI. Please refer to the proof-of-concept RFC [4] for details
> on the resctrl implementation. More recently, I have rebased the CBQRI
> support on mainline [5]. Big thanks to James Morse for the tireless
> work to extract resctrl from arch/x86 and make it available to all
> architectures.
>
> I think it makes sense to first focus on the detection of Ssqosid and
> handling of srmcfg when switching tasks. It has been tested against a
> QEMU branch that implements Ssqosid and CBQRI [6]. A test driver [7]
> was used to set srmcfg for the current process. This allows switch_to
> to be tested without resctrl.

Could we consider submitting the entire QoS functionality as a single
integrated patchset (indicating the upstream branch that the patchset
is based on)? This should include the content from
https://lore.kernel.org/linux-riscv/20230419111111.477118-1-dfustini@baylibre.com/


>
> [1] https://github.com/riscv/riscv-ssqosid/releases/tag/v1.0
> [2] https://github.com/riscv-non-isa/riscv-cbqri/releases/tag/v1.0
> [3] https://docs.kernel.org/filesystems/resctrl.html
> [4] https://lore.kernel.org/linux-riscv/20230419111111.477118-1-dfustini@baylibre.com/
> [5] https://git.kernel.org/pub/scm/linux/kernel/git/fustini/linux.git/log/?h=b4/cbqri
> [6] https://github.com/tt-fustini/qemu/tree/riscv-cbqri-rqsc-pptt
> [7] https://git.kernel.org/pub/scm/linux/kernel/git/fustini/linux.git/log/?h=b4/ssqosid-debug
>
> Changes in v4:
>  - Rebase on riscv/for-next as of riscv-for-linus-6.18-mw2
>  - Add Conor's Acked-by to the yaml patch
>  - Link to v3: https://lore.kernel.org/all/20250920-ssqosid-v6-17-rc5-v3-0-5093162922d8@kernel.org/
>
> Changes in v3:
>  - Fix parameter in __switch_to_srmcfg() when CONFIG_RISCV_ISA_SSQOSID
>    is not set to avoid error in clang. This does trigger checkpatch
>    warning about "Argument '__next' is not used in function-like macro"
>    but it seems that '__switch_to_srmcfg(__next)' is needed to avoid
>    the error that LKP reported. '__switch_to_srmcfg()' will trigger a
>    build error in clang.
>    https://lore.kernel.org/oe-kbuild-all/202509162355.wByessnb-lkp@intel.com/
>  - Improve description of ssqosid in extensions.xml
>  - Link to v2: https://lore.kernel.org/linux-riscv/20250915-ssqosid-v6-17-rc5-v2-0-2d4b0254dfd6@kernel.org/
>
> Changes in v2:
>  - Restore the per-cpu fix from RFC v2 that was missed in v1:
>    change DEFINE_PER_CPU to DECLARE_PER_CPU in qos.h and move
>    DEFINE_PER_CPU to qos.c
>  - Introduce a patch that adds Ssqosid to riscv/extensions.yaml
>  - Link to v1: https://lore.kernel.org/r/20250910-ssqosid-v6-17-rc5-v1-0-72cb8f144615@kernel.org
>
> Changes in v1:
>  - Rename all instances of the sqoscfg CSR to srmcfg to match the
>    ratified Ssqosid spec
>  - Link RFC v2: https://lore.kernel.org/linux-riscv/20230430-riscv-cbqri-rfc-v2-v2-0-8e3725c4a473@baylibre.com/
>
> Changes in RFC v2:
>  - change DEFINE_PER_CPU to DECLARE_PER_CPU for cpu_sqoscfg in qos.h to
>    prevent linking error about multiple definition. Move DEFINE_PER_CPU
>    for cpu_sqoscfg into qos.c
>  - renamed qos prefix in function names to sqoscfg to be less generic
>  - handle sqoscfg the same way has_vector and has_fpu are handled in the
>    vector patch series
>  - Link to RFC v1: https://lore.kernel.org/linux-riscv/20230410043646.3138446-1-dfustini@baylibre.com/
>
> Signed-off-by: Drew Fustini <fustini at kernel.org>
> ---
> Drew Fustini (3):
>       dt-bindings: riscv: Add Ssqosid extension description
>       RISC-V: Detect the Ssqosid extension
>       RISC-V: Add support for srmcfg CSR from Ssqosid ext
>
>  .../devicetree/bindings/riscv/extensions.yaml      |  6 ++++
>  MAINTAINERS                                        |  7 ++++
>  arch/riscv/Kconfig                                 | 17 +++++++++
>  arch/riscv/include/asm/csr.h                       |  8 +++++
>  arch/riscv/include/asm/hwcap.h                     |  1 +
>  arch/riscv/include/asm/processor.h                 |  3 ++
>  arch/riscv/include/asm/qos.h                       | 41 ++++++++++++++++++++++
>  arch/riscv/include/asm/switch_to.h                 |  3 ++
>  arch/riscv/kernel/Makefile                         |  2 ++
>  arch/riscv/kernel/cpufeature.c                     |  1 +
>  arch/riscv/kernel/qos/Makefile                     |  2 ++
>  arch/riscv/kernel/qos/qos.c                        |  5 +++
>  12 files changed, 96 insertions(+)
> ---
> base-commit: 68247d45c045bb7dda923cf2c8d0937ce0e16394
> change-id: 20251007-ssqosid-ddc87968b2d9
>
> Best regards,
> --
> Drew Fustini <fustini at kernel.org>
>
>

Thanks,
Yunhui