Re: [PATCH v12 1/5] riscv_cbqri: Add capacity controller core

From: Jonathan Cameron

Date: Wed Nov 18 2026 - 19:09:12 EST


On Sat, 14 Nov 2026 14:06:21 -0800
Drew Fustini <fustini@xxxxxxxxxx> wrote:

> Add the core for RISC-V CBQRI capacity controllers: the register
> layout, the capability probe, and the allocation operations that
> program a capacity block mask for an RCID and read it back.
>
> A discovery layer maps the register block and describes the controller
> in a cbqri_controller_info descriptor. riscv_cbqri_register_cc() probes
> the controller from that descriptor and adds it to the controller list,
> which stays private to the core. The core owns the controller state
> after registration, so nothing in it depends on how the controller was
> discovered. The caller keeps the register mapping alive.
>
> Tested-by: Zeng Heng <zengheng@xxxxxxxxxxxxx>
> Reviewed-by: Zeng Heng <zengheng@xxxxxxxxxxxxx>
> Co-developed-by: Adrien Ricciardi <aricciardi@xxxxxxxxxxxx>
> Signed-off-by: Adrien Ricciardi <aricciardi@xxxxxxxxxxxx>
> Signed-off-by: Drew Fustini <fustini@xxxxxxxxxx>

A couple more drive by comments.

> diff --git a/drivers/resctrl/cbqri_devices.c b/drivers/resctrl/cbqri_devices.c
> new file mode 100644
> index 000000000000..5522872f5cc1
> --- /dev/null
> +++ b/drivers/resctrl/cbqri_devices.c


> +
> +/* Read the configured CBM for closid on the AT half via READ_LIMIT. */
> +int cbqri_read_cache_config(struct cbqri_controller *ctrl, u32 closid,
> + u32 at, u32 *cbm_out)
> +{
> + int err;
> +
> + guard(mutex)(&ctrl->lock);
> +
> + err = cbqri_cc_alloc_op(ctrl, CBQRI_CC_ALLOC_CTL_OP_READ_LIMIT, closid, at, 0);
> + if (err == 0) {
> + /*
> + * resctrl exposes the CBM as a u32 and cbqri_probe_cc() rejects
> + * ncblks > 32, so the mask fits the low 32-bit word of the
> + * cc_block_mask register.
> + */
> + *cbm_out = readl(ctrl->base + CBQRI_CC_BLOCK_MASK_OFF);
> + }
> +
> + return err;
Unless this gets more complex in later patches I'd do
if (err)
return err;

/*
* resctrl exposes the CBM as a u32 and cbqri_probe_cc() rejects
* ncblks > 32, so the mask fits the low 32-bit word of the
* cc_block_mask register.
*/
*cbm_out = readl(ctrl->base + CBQRI_CC_BLOCK_MASK_OFF);

return 0;

Just to keep error handling out of line and that
comment block less indented.

> +}


> +/**
> + * riscv_cbqri_register_cc() - register a capacity controller
> + * @info: registration descriptor. info->type must be CAPACITY. The resctrl
> + * glue maps info->cache_level to the L2/L3 resource and uses
> + * info->cache_id as the domain id.
> + *
> + * The caller resolves the cache level and id from its firmware description.
> + * Domain membership is resolved per CPU at hotplug, so no cpu mask is stored.
> + *
> + * Return: 0 on success, -EEXIST when a controller for the same cache level
> + * and id is already registered, or another negative errno on failure.
> + */
> +int riscv_cbqri_register_cc(const struct cbqri_controller_info *info)
> +{
> + struct cbqri_controller *other;
> + int err;
> +
> + if (!info->addr) {
> + pr_warn("skipping controller with invalid addr=0x0\n");
> + return -EINVAL;
> + }
> +
> + if (info->type != CBQRI_CONTROLLER_TYPE_CAPACITY) {
> + pr_warn("register_cc called with non-capacity type %u\n",
> + info->type);
> + return -EINVAL;
> + }
> +
> + /*
> + * SRMCFG encodes RCID in 12 bits. Reject an out-of-range count rather
> + * than let FIELD_PREP(SRMCFG_RCID_MASK, closid) truncate it silently.
> + */
> + if (info->rcid_count > FIELD_MAX(SRMCFG_RCID_MASK) + 1) {
> + pr_warn("CC at %pa has RCID count %u beyond the 12-bit SRMCFG field, skipping\n",
> + &info->addr, info->rcid_count);
> + return -EINVAL;
> + }
> +
> + struct cbqri_controller *ctrl __free(kfree) =
> + kzalloc(sizeof(*ctrl), GFP_KERNEL);
> + if (!ctrl)
> + return -ENOMEM;
> +
> + mutex_init(&ctrl->lock);
> +
> + ctrl->base = info->base;
> + ctrl->addr = info->addr;
> + ctrl->size = info->size;
> + ctrl->type = info->type;
> + ctrl->rcid_count = info->rcid_count;
> + ctrl->cache.cache_id = info->cache_id;
> + ctrl->cache.cache_level = info->cache_level;
> +
> + err = cbqri_probe_controller(ctrl);
> + if (err)
> + return err;
> +
> + /*
> + * alloc_capable comes from the probe above and rcid_count from the
> + * discovery layer. Two RCIDs are the minimum for a useful system.
> + * resctrl reserves RCID 0 for the default group, so one RCID has
> + * nothing to allocate between, and CDP would halve it to zero.
> + * Reject fewer than two.
> + */
> + if (ctrl->alloc_capable && ctrl->rcid_count < 2) {
> + pr_warn("CC at %pa is alloc-capable but has fewer than 2 RCIDs, skipping\n",
> + &ctrl->addr);
> + return -EINVAL;
> + }
> +
> + guard(mutex)(&cbqri_controllers_lock);
> +
> + /* The resctrl glue keys its domains on cache_id, one controller each. */
> + list_for_each_entry(other, &cbqri_controllers, list) {
> + if (other->cache.cache_level == info->cache_level &&
> + other->cache.cache_id == info->cache_id) {
> + pr_warn("CC at %pa duplicates the L%u cache id %u controller at %pa, skipping\n",
> + &ctrl->addr, info->cache_level, info->cache_id,
> + &other->addr);
> + return -EEXIST;
> + }
> + }
> +
> + list_add_tail(&ctrl->list, &cbqri_controllers);
> + retain_and_null_ptr(ctrl);

Common trick for this is something like:

list_add_tail(&no_free_ptr(ctrl)->list, &cbqri_controllers);

because it couples ownership passing with stopping the autofree
magic. I'd personally only use retain_and_null_ptr() in cases where I need
to check for success of the ownership being handed off.


> + return 0;
> +}
> diff --git a/drivers/resctrl/cbqri_internal.h b/drivers/resctrl/cbqri_internal.h
> new file mode 100644
> index 000000000000..c3e39e6d30c5
> --- /dev/null
> +++ b/drivers/resctrl/cbqri_internal.h

> diff --git a/include/linux/riscv_cbqri.h b/include/linux/riscv_cbqri.h
> new file mode 100644
> index 000000000000..b0daa1a7e42f
> --- /dev/null
> +++ b/include/linux/riscv_cbqri.h
> @@ -0,0 +1,49 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Public registration API for the RISC-V Capacity and Bandwidth QoS
> + * Register Interface (CBQRI) core. Discovery layers call
> + * riscv_cbqri_register_cc() to hand a capacity controller descriptor to
> + * the core, which owns all subsequent state.
> + */
> +#ifndef _LINUX_RISCV_CBQRI_H
> +#define _LINUX_RISCV_CBQRI_H
> +
> +#include <linux/errno.h>
> +#include <linux/types.h>
> +
> +enum cbqri_controller_type {
> + CBQRI_CONTROLLER_TYPE_CAPACITY,
> +};
> +
> +/**
> + * struct cbqri_controller_info - registration descriptor
> + * @addr: MMIO base address of the controller's register interface
> + * @size: size of the MMIO region
> + * @type: controller type (capacity)
> + * @rcid_count: number of supported RCIDs
> + * @cache_id: cache id used as the resctrl domain id
> + * @cache_level: cache level (2 or 3) the controller backs
> + * @base: mapped register block, which the caller keeps mapped for
> + * the life of the system
Out of order documentation is unusual. Why?

> + */
> +struct cbqri_controller_info {
> + phys_addr_t addr;
> + phys_addr_t size;
> + void __iomem *base;
> + enum cbqri_controller_type type;
> + u32 rcid_count;
> + u32 cache_id;
> + u32 cache_level;
> +};
> +
> +#if IS_ENABLED(CONFIG_RISCV_CBQRI)
> +int riscv_cbqri_register_cc(const struct cbqri_controller_info *info);
> +#else
> +static inline int
> +riscv_cbqri_register_cc(const struct cbqri_controller_info *info)
> +{
> + return -ENODEV;
> +}
> +#endif
> +
> +#endif /* _LINUX_RISCV_CBQRI_H */
>