Message-ID: <5b9136d6-b6c0-4f24-a8d2-05d7700140a8@redhat.com>
Date: Sat, 8 Nov 2025 19:28:43 +1000
From: Gavin Shan <gshan@...hat.com>
To: Ben Horgan <ben.horgan@....com>, james.morse@....com
Cc: amitsinght@...vell.com, baisheng.gao@...soc.com,
 baolin.wang@...ux.alibaba.com, bobo.shaobowang@...wei.com,
 carl@...amperecomputing.com, catalin.marinas@....com, dakr@...nel.org,
 dave.martin@....com, david@...hat.com, dfustini@...libre.com,
 fenghuay@...dia.com, gregkh@...uxfoundation.org, guohanjun@...wei.com,
 jeremy.linton@....com, jonathan.cameron@...wei.com, kobak@...dia.com,
 lcherian@...vell.com, lenb@...nel.org, linux-acpi@...r.kernel.org,
 linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
 lpieralisi@...nel.org, peternewman@...gle.com, quic_jiles@...cinc.com,
 rafael@...nel.org, robh@...nel.org, rohit.mathew@....com,
 scott@...amperecomputing.com, sdonthineni@...dia.com, sudeep.holla@....com,
 tan.shaopeng@...itsu.com, will@...nel.org, xhao@...ux.alibaba.com,
 Shaopeng Tan <tan.shaopeng@...fujitsu.com>
Subject: Re: [PATCH 10/33] arm_mpam: Add probe/remove for mpam msc driver and
 kbuild boiler plate

Hi Ben,

On 11/7/25 10:34 PM, Ben Horgan wrote:
> From: James Morse <james.morse@....com>
> 
> Probing MPAM is convoluted. MSCs that are integrated with a CPU may
> only be accessible from those CPUs, and they may not be online.
> Touching the hardware early is pointless as MPAM can't be used until
> the system-wide common values for num_partid and num_pmg have been
> discovered.
> 

I'm not sure if below commit log is more clearer as I'm not a English
native speaker:

MPAM probing is convoluted. MSCs that are integrated to a set of CPUs
may only be accessible from those CPUs, ...

> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@...amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@...dia.com>
> Tested-by: Shaopeng Tan <tan.shaopeng@...fujitsu.com>
> Tested-by: Peter Newman <peternewman@...gle.com>
> Signed-off-by: James Morse <james.morse@....com>
> Signed-off-by: Ben Horgan <ben.horgan@....com>
> ---
> Changes since v3:
>  From Jonathan:
> Include cleanup
> Use devm_mutex_init()
> Add an ERR_CAST()
> Fenghua:
> Return zero from update_msc_accessibility()
> Additional:
> Fail probe if MSC doesn't have an MMIO interface
> ---
>   arch/arm64/Kconfig              |   1 +
>   drivers/Kconfig                 |   2 +
>   drivers/Makefile                |   1 +
>   drivers/resctrl/Kconfig         |  15 +++
>   drivers/resctrl/Makefile        |   4 +
>   drivers/resctrl/mpam_devices.c  | 194 ++++++++++++++++++++++++++++++++
>   drivers/resctrl/mpam_internal.h |  49 ++++++++
>   7 files changed, 266 insertions(+)
>   create mode 100644 drivers/resctrl/Kconfig
>   create mode 100644 drivers/resctrl/Makefile
>   create mode 100644 drivers/resctrl/mpam_devices.c
>   create mode 100644 drivers/resctrl/mpam_internal.h
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index c5e66d5d72cd..004d58cfbff8 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -2025,6 +2025,7 @@ config ARM64_TLB_RANGE
>   
>   config ARM64_MPAM
>   	bool "Enable support for MPAM"
> +	select ARM64_MPAM_DRIVER if EXPERT	# does nothing yet
>   	select ACPI_MPAM if ACPI
>   	help
>   	  Memory System Resource Partitioning and Monitoring (MPAM) is an
> diff --git a/drivers/Kconfig b/drivers/Kconfig
> index 4915a63866b0..3054b50a2f4c 100644
> --- a/drivers/Kconfig
> +++ b/drivers/Kconfig
> @@ -251,4 +251,6 @@ source "drivers/hte/Kconfig"
>   
>   source "drivers/cdx/Kconfig"
>   
> +source "drivers/resctrl/Kconfig"
> +
>   endmenu
> diff --git a/drivers/Makefile b/drivers/Makefile
> index 8e1ffa4358d5..20eb17596b89 100644
> --- a/drivers/Makefile
> +++ b/drivers/Makefile
> @@ -194,6 +194,7 @@ obj-$(CONFIG_HTE)		+= hte/
>   obj-$(CONFIG_DRM_ACCEL)		+= accel/
>   obj-$(CONFIG_CDX_BUS)		+= cdx/
>   obj-$(CONFIG_DPLL)		+= dpll/
> +obj-y				+= resctrl/
>   
>   obj-$(CONFIG_DIBS)		+= dibs/
>   obj-$(CONFIG_S390)		+= s390/
> diff --git a/drivers/resctrl/Kconfig b/drivers/resctrl/Kconfig
> new file mode 100644
> index 000000000000..ef2f3adf64a9
> --- /dev/null
> +++ b/drivers/resctrl/Kconfig
> @@ -0,0 +1,15 @@
> +menuconfig ARM64_MPAM_DRIVER
> +	bool "MPAM driver"
> +	depends on ARM64 && ARM64_MPAM && EXPERT
> +	help
> +	  Memory System Resource Partitioning and Monitoring (MPAM) driver for
> +	  System IP, e,g. caches and memory controllers.
> +
> +if ARM64_MPAM_DRIVER
> +
> +config ARM64_MPAM_DRIVER_DEBUG
> +	bool "Enable debug messages from the MPAM driver"
> +	help
> +	  Say yes here to enable debug messages from the MPAM driver.
> +
> +endif

I am asking myself why "depends on ARM64_MPAM_DRIVER" can't be used here? :-)

> diff --git a/drivers/resctrl/Makefile b/drivers/resctrl/Makefile
> new file mode 100644
> index 000000000000..898199dcf80d
> --- /dev/null
> +++ b/drivers/resctrl/Makefile
> @@ -0,0 +1,4 @@
> +obj-$(CONFIG_ARM64_MPAM_DRIVER)			+= mpam.o
> +mpam-y						+= mpam_devices.o
> +
> +ccflags-$(CONFIG_ARM64_MPAM_DRIVER_DEBUG)	+= -DDEBUG
> diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
> new file mode 100644
> index 000000000000..6c6be133d73a
> --- /dev/null
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -0,0 +1,194 @@
> +// SPDX-License-Identifier: GPL-2.0
> +// Copyright (C) 2025 Arm Ltd.
> +
> +#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__
> +
> +#include <linux/acpi.h>
> +#include <linux/arm_mpam.h>
> +#include <linux/cacheinfo.h>
> +#include <linux/cpumask.h>
> +#include <linux/device.h>
> +#include <linux/errno.h>
> +#include <linux/gfp.h>
> +#include <linux/list.h>
> +#include <linux/lockdep.h>
> +#include <linux/mutex.h>
> +#include <linux/platform_device.h>
> +#include <linux/printk.h>
> +#include <linux/srcu.h>
> +#include <linux/types.h>
> +
> +#include "mpam_internal.h"
> +
> +/*
> + * mpam_list_lock protects the SRCU lists when writing. Once the
> + * mpam_enabled key is enabled these lists are read-only,
> + * unless the error interrupt disables the driver.
> + */

s/when writing/for writing
s/are read-only/become read-only

> +static DEFINE_MUTEX(mpam_list_lock);
> +static LIST_HEAD(mpam_all_msc);
> +
> +struct srcu_struct mpam_srcu;
> +
> +/*
> + * Number of MSCs that have been probed. Once all MSC have been probed MPAM
> + * can be enabled.
> + */

s/all MSC/all MSCs  (?)

> +static atomic_t mpam_num_msc;
> +
> +/*
> + * An MSC can control traffic from a set of CPUs, but may only be accessible
> + * from a (hopefully wider) set of CPUs. The common reason for this is power
> + * management. If all the CPUs in a cluster are in PSCI:CPU_SUSPEND, the
> + * corresponding cache may also be powered off. By making accesses from
> + * one of those CPUs, we ensure this isn't the case.
> + */

s/An MSC/A MSC (?)
s/from a/from the
s/isn't the case/is the case (?)

> +static int update_msc_accessibility(struct mpam_msc *msc)
> +{
> +	u32 affinity_id;
> +	int err;
> +
> +	err = device_property_read_u32(&msc->pdev->dev, "cpu_affinity",
> +				       &affinity_id);
> +	if (err)
> +		cpumask_copy(&msc->accessibility, cpu_possible_mask);
> +	else
> +		acpi_pptt_get_cpus_from_container(affinity_id,
> +						  &msc->accessibility);
> +	return 0;
> +}
> +

{} is needed for the block spanning multiple lines.

I would validate msc->accessibility here instead of its caller
(do_mpam_msc_drv_probe()).

		if (cpumask_empty(&msc->accessibility))
			return {-EINVAL, -ENOENT};

> +static int fw_num_msc;
> +
> +static void mpam_msc_destroy(struct mpam_msc *msc)
> +{
> +	struct platform_device *pdev = msc->pdev;
> +
> +	lockdep_assert_held(&mpam_list_lock);
> +
> +	list_del_rcu(&msc->all_msc_list);
> +	platform_set_drvdata(pdev, NULL);
> +}
> +
> +static void mpam_msc_drv_remove(struct platform_device *pdev)
> +{
> +	struct mpam_msc *msc = platform_get_drvdata(pdev);
> +
> +	if (!msc)
> +		return;

'msc' is unlikely to be NULL here, so the check could be droped.

> +
> +	mutex_lock(&mpam_list_lock);
> +	mpam_msc_destroy(msc);
> +	mutex_unlock(&mpam_list_lock);
> +
> +	synchronize_srcu(&mpam_srcu);
> +}
> +
> +static struct mpam_msc *do_mpam_msc_drv_probe(struct platform_device *pdev)
> +{
> +	int err;
> +	u32 tmp;
> +	struct mpam_msc *msc;
> +	struct resource *msc_res;
> +	struct device *dev = &pdev->dev;
> +
> +	lockdep_assert_held(&mpam_list_lock);
> +
> +	msc = devm_kzalloc(&pdev->dev, sizeof(*msc), GFP_KERNEL);
> +	if (!msc)
> +		return ERR_PTR(-ENOMEM);
> +
> +	err = devm_mutex_init(dev, &msc->probe_lock);
> +	if (err)
> +		return ERR_PTR(err);
> +	err = devm_mutex_init(dev, &msc->part_sel_lock);
> +	if (err)
> +		return ERR_PTR(err);
> +	msc->id = pdev->id;
> +	msc->pdev = pdev;
> +	INIT_LIST_HEAD_RCU(&msc->all_msc_list);
> +	INIT_LIST_HEAD_RCU(&msc->ris);
> +
> +	err = update_msc_accessibility(msc);
> +	if (err)
> +		return ERR_PTR(err);
> +	if (cpumask_empty(&msc->accessibility)) {
> +		dev_err_once(dev, "MSC is not accessible from any CPU!");
> +		return ERR_PTR(-EINVAL);
> +	}
> +

As suggested above, this check would be done inside update_msc_accessibility().

> +	if (device_property_read_u32(&pdev->dev, "pcc-channel", &tmp))
> +		msc->iface = MPAM_IFACE_MMIO;
> +	else
> +		msc->iface = MPAM_IFACE_PCC;
> +
> +	if (msc->iface == MPAM_IFACE_MMIO) {
> +		void __iomem *io;
> +
> +		io = devm_platform_get_and_ioremap_resource(pdev, 0,
> +							    &msc_res);
> +		if (IS_ERR(io)) {
> +			dev_err_once(dev, "Failed to map MSC base address\n");
> +			return ERR_CAST(io);
> +		}
> +		msc->mapped_hwpage_sz = msc_res->end - msc_res->start;
> +		msc->mapped_hwpage = io;
> +	} else {
> +		return ERR_PTR(-ENOENT);

Would be:
		return ERR_PTR(-EINVAL);

> +	}
> +
> +	list_add_rcu(&msc->all_msc_list, &mpam_all_msc);
> +	platform_set_drvdata(pdev, msc);
> +
> +	return msc;
> +}
> +
> +static int mpam_msc_drv_probe(struct platform_device *pdev)
> +{
> +	int err;
> +	struct mpam_msc *msc = NULL;
> +	void *plat_data = pdev->dev.platform_data;
> +
> +	mutex_lock(&mpam_list_lock);
> +	msc = do_mpam_msc_drv_probe(pdev);
> +	mutex_unlock(&mpam_list_lock);
> +	if (!IS_ERR(msc)) {
> +		/* Create RIS entries described by firmware */
> +		err = acpi_mpam_parse_resources(msc, plat_data);
> +		if (err)
> +			mpam_msc_drv_remove(pdev);
> +	} else {
> +		err = PTR_ERR(msc);
> +	}
> +
> +	if (!err && atomic_add_return(1, &mpam_num_msc) == fw_num_msc)
> +		pr_info("Discovered all MSC\n");

s/all MSC/all MSCs

> +
> +	return err;
> +}
> +
> +static struct platform_driver mpam_msc_driver = {
> +	.driver = {
> +		.name = "mpam_msc",
> +	},
> +	.probe = mpam_msc_drv_probe,
> +	.remove = mpam_msc_drv_remove,
> +};
> +
> +static int __init mpam_msc_driver_init(void)
> +{
> +	if (!system_supports_mpam())
> +		return -EOPNOTSUPP;
> +
> +	init_srcu_struct(&mpam_srcu);
> +
> +	fw_num_msc = acpi_mpam_count_msc();
> +
> +	if (fw_num_msc <= 0) {
> +		pr_err("No MSC devices found in firmware\n");
> +		return -EINVAL;
> +	}
> +
> +	return platform_driver_register(&mpam_msc_driver);
> +}
> +subsys_initcall(mpam_msc_driver_init);
> diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h
> new file mode 100644
> index 000000000000..540066903eca
> --- /dev/null
> +++ b/drivers/resctrl/mpam_internal.h
> @@ -0,0 +1,49 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +// Copyright (C) 2025 Arm Ltd.
> +
> +#ifndef MPAM_INTERNAL_H
> +#define MPAM_INTERNAL_H
> +
> +#include <linux/arm_mpam.h>
> +#include <linux/cpumask.h>
> +#include <linux/io.h>
> +#include <linux/mutex.h>
> +#include <linux/types.h>
> +
> +struct platform_device;
> +
> +struct mpam_msc {
> +	/* member of mpam_all_msc */
> +	struct list_head	all_msc_list;
> +
> +	int			id;
> +	struct platform_device	*pdev;
> +
> +	/* Not modified after mpam_is_enabled() becomes true */
> +	enum mpam_msc_iface	iface;
> +	u32			nrdy_usec;
> +	cpumask_t		accessibility;
> +
> +	/*
> +	 * probe_lock is only taken during discovery. After discovery these
> +	 * properties become read-only and the lists are protected by SRCU.
> +	 */
> +	struct mutex		probe_lock;
> +	unsigned long		ris_idxs;
> +	u32			ris_max;
> +
> +	/* mpam_msc_ris of this component */
> +	struct list_head	ris;
> +
> +	/*
> +	 * part_sel_lock protects access to the MSC hardware registers that are
> +	 * affected by MPAMCFG_PART_SEL. (including the ID registers that vary
> +	 * by RIS).
> +	 * If needed, take msc->probe_lock first.
> +	 */
> +	struct mutex		part_sel_lock;
> +
> +	void __iomem		*mapped_hwpage;
> +	size_t			mapped_hwpage_sz;
> +};
> +#endif /* MPAM_INTERNAL_H */

Thanks,
Gavin

Powered by blists - more mailing lists