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.

Start with driver probe/remove and mapping the MSC.

CC: Carl Worth <carl@os.amperecomputing.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Signed-off-by: James Morse <james.morse@arm.com>
---
Changes since v2:
 * Comment in Kconfig about why EXPERT.
 * Dropped duplicate depends.
 * Fixed duplicate return statement.
 * Restructured driver probe to have a do_ function to allow breaks to be
   return instead...
 * Removed resctrl.h include, added spinlock.h
 * Removed stray DT function prototype
 * Removed stray PCC variables in struct mpam_msc.
 * Used ccflags not cflags for debug define.
 * Moved srcu header include to internal.h
 * Moved mpam_msc_destroy() into this patch.

Changes since v1:
 * Avoid selecting driver on other architectrues.
 * Removed PCC support stub.
 * Use for_each_available_child_of_node_scoped() and of_property_read_reg()
 * Clarified a comment.
 * Stopped using mpam_num_msc as an id,a and made it atomic.
 * Size of -1 returned from cache_of_calculate_id()
 * Renamed some struct members.
 * Made a bunch of pr_err() dev_err_ocne().
 * Used more cleanup magic.
 * Inlined a print message.
 * Fixed error propagation from mpam_dt_parse_resources().
 * Moved cache accessibility checks earlier.
 * Change cleanup macro to use IS_ERR_OR_NULL().

Changes since RFC:
 * Check for status=broken DT devices.
 * Moved all the files around.
 * Made Kconfig symbols depend on EXPERT
---
 arch/arm64/Kconfig              |   1 +
 drivers/Kconfig                 |   2 +
 drivers/Makefile                |   1 +
 drivers/acpi/arm64/mpam.c       |   7 ++
 drivers/resctrl/Kconfig         |  13 +++
 drivers/resctrl/Makefile        |   4 +
 drivers/resctrl/mpam_devices.c  | 190 ++++++++++++++++++++++++++++++++
 drivers/resctrl/mpam_internal.h |  52 +++++++++
 include/linux/acpi.h            |   2 +-
 9 files changed, 271 insertions(+), 1 deletion(-)
 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/acpi/arm64/mpam.c b/drivers/acpi/arm64/mpam.c
index 59712397025d..51c6f5fd4a5e 100644
--- a/drivers/acpi/arm64/mpam.c
+++ b/drivers/acpi/arm64/mpam.c
@@ -337,6 +337,13 @@ static int __init acpi_mpam_parse(void)
 	return 0;
 }
 
+/**
+ * acpi_mpam_count_msc() - Count the number of MSC described by firmware.
+ *
+ * Returns the number of of MSC, or zero for an error.
+ *
+ * This can be called before or in parallel with acpi_mpam_parse().
+ */
 int acpi_mpam_count_msc(void)
 {
 	struct acpi_table_header *table __free(acpi_table) = acpi_get_table_ret(ACPI_SIG_MPAM, 0);
diff --git a/drivers/resctrl/Kconfig b/drivers/resctrl/Kconfig
new file mode 100644
index 000000000000..58c83b5c8bfd
--- /dev/null
+++ b/drivers/resctrl/Kconfig
@@ -0,0 +1,13 @@
+menuconfig ARM64_MPAM_DRIVER
+	bool "MPAM driver"
+	depends on ARM64 && ARM64_MPAM && EXPERT
+	help
+	  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
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..d18eeec95f79
--- /dev/null
+++ b/drivers/resctrl/mpam_devices.c
@@ -0,0 +1,190 @@
+// 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/cpu.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/slab.h>
+#include <linux/spinlock.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.
+ */
+static DEFINE_MUTEX(mpam_list_lock);
+static LIST_HEAD(mpam_all_msc);
+
+static struct srcu_struct mpam_srcu;
+
+/*
+ * Number of MSCs that have been probed. Once all MSC have been probed MPAM
+ * can be enabled.
+ */
+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.
+ */
+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 err;
+}
+
+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;
+
+	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);
+
+	mutex_init(&msc->probe_lock);
+	mutex_init(&msc->part_sel_lock);
+	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);
+	}
+
+	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 (void *)io;
+		}
+		msc->mapped_hwpage_sz = msc_res->end - msc_res->start;
+		msc->mapped_hwpage = io;
+	}
+
+	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");
+
+	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..6ac75f3613c3
--- /dev/null
+++ b/drivers/resctrl/mpam_internal.h
@@ -0,0 +1,52 @@
+/* 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/mailbox_client.h>
+#include <linux/mutex.h>
+#include <linux/sizes.h>
+#include <linux/spinlock.h>
+#include <linux/srcu.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 */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 9d66421f68ff..70f075b397ce 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -231,7 +231,7 @@ static inline struct acpi_table_header *acpi_get_table_ret(char *signature, u32
 		return ERR_PTR(-ENOENT);
 	return table;
 }
-DEFINE_FREE(acpi_table, struct acpi_table_header *, if (!IS_ERR(_T)) acpi_put_table(_T))
+DEFINE_FREE(acpi_table, struct acpi_table_header *, if (!IS_ERR_OR_NULL(_T)) acpi_put_table(_T))
 
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
 int __init_or_acpilib acpi_table_parse_entries(char *id,
-- 
2.39.5

…
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -0,0 +1,190 @@
…
> +static void mpam_msc_drv_remove(struct platform_device *pdev)
> +{
…
> +	mutex_lock(&mpam_list_lock);
> +	mpam_msc_destroy(msc);
> +	mutex_unlock(&mpam_list_lock);
> +
> +	synchronize_srcu(&mpam_srcu);
> +}
…

Under which circumstances would you become interested to apply a statement
like “guard(mutex)(&mpam_list_lock);”?
https://elixir.bootlin.com/linux/v6.18-rc4/source/include/linux/mutex.h#L228

Regards,
Markus

On Fri, 17 Oct 2025 18:56:23 +0000
James Morse <james.morse@arm.com> wrote:

> 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.
> 
> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@os.amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
> Signed-off-by: James Morse <james.morse@arm.com>

Trying not to replicate comments too much...

A few things inline but others found bigger stuff to fix.
> diff --git a/drivers/resctrl/Kconfig b/drivers/resctrl/Kconfig
> new file mode 100644
> index 000000000000..58c83b5c8bfd
> --- /dev/null
> +++ b/drivers/resctrl/Kconfig
> @@ -0,0 +1,13 @@
> +menuconfig ARM64_MPAM_DRIVER
> +	bool "MPAM driver"
> +	depends on ARM64 && ARM64_MPAM && EXPERT
> +	help
> +	  MPAM driver for System IP, e,g. caches and memory controllers.

Bit minimal for help text :)

> +
> +if ARM64_MPAM_DRIVER

I'd add a blank line here.

> +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

> diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
> new file mode 100644
> index 000000000000..d18eeec95f79
> --- /dev/null
> +++ b/drivers/resctrl/mpam_devices.c

> +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);
> +
> +	mutex_init(&msc->probe_lock);
Maybe worth
	err = devm_mutex_init(&msc->probe_lock);
	if (err)
		return err;
to enable the mutex debugging if anyone wants it.  I've stopped trying
to analyze whether that is useful or not, now it is easy to add to drivers
already doing devm.

> +	mutex_init(&msc->part_sel_lock);
> +	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);
> +	}
> +
> +	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 (void *)io;

ERR_CAST() is there to make this stuff more obvious

> +		}
> +		msc->mapped_hwpage_sz = msc_res->end - msc_res->start;
> +		msc->mapped_hwpage = io;
> +	}
> +
> +	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");
> +
> +	return err;
> +}

> diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h
> new file mode 100644
> index 000000000000..6ac75f3613c3
> --- /dev/null
> +++ b/drivers/resctrl/mpam_internal.h
> @@ -0,0 +1,52 @@
> +/* 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/mailbox_client.h>
> +#include <linux/mutex.h>
> +#include <linux/sizes.h>
> +#include <linux/spinlock.h>
> +#include <linux/srcu.h>

Includes need another look.

Should be seeing the list header for starters and
mailbox_client.h doesn't make sense yet.  Some of the
others may need pushing to the patches where they are
first used or pushing down into the c files that need them.

> +
> +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 */

Hi, James,

On 10/17/25 11:56, James Morse wrote:
> 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.
> 
> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@os.amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
> Signed-off-by: James Morse <james.morse@arm.com>
[SNIP]> +/*
> + * 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.
> + */
> +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 err;

The error is handled and there is no need to return the error to caller.
Returning the error causes probe failure and the mpam_msc driver cannot 
be installed.

s/return err;/return 0;/

> +}
> +
> +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;
> +
> +	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);
> +
> +	mutex_init(&msc->probe_lock);
> +	mutex_init(&msc->part_sel_lock);
> +	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);

The returned error causes probe failure and the driver cannot be 
installed. Return 0 will make the probe succeed.

There is no probe failure in mpam/snapshot/v6.18-rc1 because its 
returned err=0.

[SNIP]

Thanks.

-Fenghua

On 10/21/25 7:29 PM, Fenghua Yu wrote:
> Hi, James,
> 
> On 10/17/25 11:56, James Morse wrote:
>> 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.
>>
>> Start with driver probe/remove and mapping the MSC.
>>
>> CC: Carl Worth <carl@os.amperecomputing.com>
>> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
>> Signed-off-by: James Morse <james.morse@arm.com>
> [SNIP]> +/*
>> + * 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.
>> + */
>> +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 err;
> 
> The error is handled and there is no need to return the error to caller.
> Returning the error causes probe failure and the mpam_msc driver cannot be 
> installed.

Ack. I see the probe failure too.

e.g.

[    7.118297] mpam_msc mpam_msc.183: probe with driver mpam_msc failed with 
error -22
[    7.118383] mpam_msc mpam_msc.370: probe with driver mpam_msc failed with 
error -22
[   10.208127]     # Subtest: mpam_devices_test_suite
[   10.208129]     # module: mpam
[   10.208215]     ok 1 test_mpam_reset_msc_bitmap
[   10.208275] mpam:__props_mismatch: __props_mismatch took the min cmax_wd
[   10.208285] mpam:__props_mismatch: cleared cpor_part
[   10.208287] mpam:__props_mismatch: cleared mbw_part
[   10.208294] mpam:__props_mismatch: took the min bwa_wd
[   10.208296] mpam:__props_mismatch: __props_mismatch took the min cmax_wd
[   10.208310] mpam:__props_mismatch: __props_mismatch took the min cmax_wd
[   10.208345]     ok 2 test_mpam_enable_merge_features
[   10.208411] # mpam_devices_test_suite: pass:3 fail:0 skip:0 total:3
[   10.208413] ok 1 mpam_devices_test_suite

> 
> s/return err;/return 0;/

Yes, this resolve the probe failure.

Tested-by: Tushar Dave <tdave@nvidia.com>

> 
>> +}
>> +
>> +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;
>> +
>> +    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);
>> +
>> +    mutex_init(&msc->probe_lock);
>> +    mutex_init(&msc->part_sel_lock);
>> +    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);
> 
> The returned error causes probe failure and the driver cannot be installed. 
> Return 0 will make the probe succeed.
> 
> There is no probe failure in mpam/snapshot/v6.18-rc1 because its returned err=0.
> 
> [SNIP]
> 
> Thanks.
> 
> -Fenghua
> 

Hi James,

On 10/17/25 19:56, James Morse wrote:
> 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.
> 
> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@os.amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
> Signed-off-by: James Morse <james.morse@arm.com>
> ---
> Changes since v2:
>  * Comment in Kconfig about why EXPERT.
>  * Dropped duplicate depends.
>  * Fixed duplicate return statement.
>  * Restructured driver probe to have a do_ function to allow breaks to be
>    return instead...
>  * Removed resctrl.h include, added spinlock.h
>  * Removed stray DT function prototype
>  * Removed stray PCC variables in struct mpam_msc.
>  * Used ccflags not cflags for debug define.
>  * Moved srcu header include to internal.h
>  * Moved mpam_msc_destroy() into this patch.
> 
> Changes since v1:
>  * Avoid selecting driver on other architectrues.
>  * Removed PCC support stub.
>  * Use for_each_available_child_of_node_scoped() and of_property_read_reg()
>  * Clarified a comment.
>  * Stopped using mpam_num_msc as an id,a and made it atomic.
>  * Size of -1 returned from cache_of_calculate_id()
>  * Renamed some struct members.
>  * Made a bunch of pr_err() dev_err_ocne().
>  * Used more cleanup magic.
>  * Inlined a print message.
>  * Fixed error propagation from mpam_dt_parse_resources().
>  * Moved cache accessibility checks earlier.
>  * Change cleanup macro to use IS_ERR_OR_NULL().
> 
> Changes since RFC:
>  * Check for status=broken DT devices.
>  * Moved all the files around.
>  * Made Kconfig symbols depend on EXPERT
> ---
>  arch/arm64/Kconfig              |   1 +
>  drivers/Kconfig                 |   2 +
>  drivers/Makefile                |   1 +
>  drivers/acpi/arm64/mpam.c       |   7 ++
>  drivers/resctrl/Kconfig         |  13 +++
>  drivers/resctrl/Makefile        |   4 +
>  drivers/resctrl/mpam_devices.c  | 190 ++++++++++++++++++++++++++++++++
>  drivers/resctrl/mpam_internal.h |  52 +++++++++
>  include/linux/acpi.h            |   2 +-
>  9 files changed, 271 insertions(+), 1 deletion(-)
>  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

If ARM64_MPAM is selected without selecting EXPERT then ACPI_MPAM is
selected but not ACPI_MPAM. When the whole series is applied this
configuration does not build as the mpam acpi code calls mpam_ris_create().

Thanks,

Ben

Hi James,

On 10/17/25 19:56, James Morse wrote:
> 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.
> 
> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@os.amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
> Signed-off-by: James Morse <james.morse@arm.com>
> ---
> Changes since v2:
>  * Comment in Kconfig about why EXPERT.
>  * Dropped duplicate depends.
>  * Fixed duplicate return statement.
>  * Restructured driver probe to have a do_ function to allow breaks to be
>    return instead...
>  * Removed resctrl.h include, added spinlock.h
>  * Removed stray DT function prototype
>  * Removed stray PCC variables in struct mpam_msc.
>  * Used ccflags not cflags for debug define.
>  * Moved srcu header include to internal.h
>  * Moved mpam_msc_destroy() into this patch.
> 
> Changes since v1:
>  * Avoid selecting driver on other architectrues.
>  * Removed PCC support stub.
>  * Use for_each_available_child_of_node_scoped() and of_property_read_reg()
>  * Clarified a comment.
>  * Stopped using mpam_num_msc as an id,a and made it atomic.
>  * Size of -1 returned from cache_of_calculate_id()
>  * Renamed some struct members.
>  * Made a bunch of pr_err() dev_err_ocne().
>  * Used more cleanup magic.
>  * Inlined a print message.
>  * Fixed error propagation from mpam_dt_parse_resources().
>  * Moved cache accessibility checks earlier.
>  * Change cleanup macro to use IS_ERR_OR_NULL().
> 
> Changes since RFC:
>  * Check for status=broken DT devices.
>  * Moved all the files around.
>  * Made Kconfig symbols depend on EXPERT
> ---
>  arch/arm64/Kconfig              |   1 +
>  drivers/Kconfig                 |   2 +
>  drivers/Makefile                |   1 +
>  drivers/acpi/arm64/mpam.c       |   7 ++
>  drivers/resctrl/Kconfig         |  13 +++
>  drivers/resctrl/Makefile        |   4 +
>  drivers/resctrl/mpam_devices.c  | 190 ++++++++++++++++++++++++++++++++
>  drivers/resctrl/mpam_internal.h |  52 +++++++++
>  include/linux/acpi.h            |   2 +-
>  9 files changed, 271 insertions(+), 1 deletion(-)
>  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
> 
[snip]
> +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);
> +
> +	mutex_init(&msc->probe_lock);
> +	mutex_init(&msc->part_sel_lock);
> +	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);
> +	}
> +
> +	if (device_property_read_u32(&pdev->dev, "pcc-channel", &tmp))
> +		msc->iface = MPAM_IFACE_MMIO;
> +	else
> +		msc->iface = MPAM_IFACE_PCC;

As there is no PCC support in this series should this return
ERR_PTR(-ENOTSUPP) when the firmware doesn't advertise a MMIO interface?

> +
> +	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 (void *)io;
> +		}
> +		msc->mapped_hwpage_sz = msc_res->end - msc_res->start;
> +		msc->mapped_hwpage = io;
> +	}
> +
> +	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");
> +
> +	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);
-- 
Thanks,

Ben

Hi James,

On 10/17/25 19:56, James Morse wrote:
> 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.
> 
> Start with driver probe/remove and mapping the MSC.
> 
> CC: Carl Worth <carl@os.amperecomputing.com>
> Tested-by: Fenghua Yu <fenghuay@nvidia.com>
> Signed-off-by: James Morse <james.morse@arm.com>
> ---
> Changes since v2:
>  * Comment in Kconfig about why EXPERT.
>  * Dropped duplicate depends.
>  * Fixed duplicate return statement.
>  * Restructured driver probe to have a do_ function to allow breaks to be
>    return instead...
>  * Removed resctrl.h include, added spinlock.h
>  * Removed stray DT function prototype
>  * Removed stray PCC variables in struct mpam_msc.
>  * Used ccflags not cflags for debug define.
>  * Moved srcu header include to internal.h
>  * Moved mpam_msc_destroy() into this patch.
> 
> Changes since v1:
>  * Avoid selecting driver on other architectrues.
>  * Removed PCC support stub.
>  * Use for_each_available_child_of_node_scoped() and of_property_read_reg()
>  * Clarified a comment.
>  * Stopped using mpam_num_msc as an id,a and made it atomic.
>  * Size of -1 returned from cache_of_calculate_id()
>  * Renamed some struct members.
>  * Made a bunch of pr_err() dev_err_ocne().
>  * Used more cleanup magic.
>  * Inlined a print message.
>  * Fixed error propagation from mpam_dt_parse_resources().
>  * Moved cache accessibility checks earlier.
>  * Change cleanup macro to use IS_ERR_OR_NULL().
> 
> Changes since RFC:
>  * Check for status=broken DT devices.
>  * Moved all the files around.
>  * Made Kconfig symbols depend on EXPERT
> ---
>  arch/arm64/Kconfig              |   1 +
>  drivers/Kconfig                 |   2 +
>  drivers/Makefile                |   1 +
>  drivers/acpi/arm64/mpam.c       |   7 ++
>  drivers/resctrl/Kconfig         |  13 +++
>  drivers/resctrl/Makefile        |   4 +
>  drivers/resctrl/mpam_devices.c  | 190 ++++++++++++++++++++++++++++++++
>  drivers/resctrl/mpam_internal.h |  52 +++++++++
>  include/linux/acpi.h            |   2 +-
>  9 files changed, 271 insertions(+), 1 deletion(-)
>  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/acpi/arm64/mpam.c b/drivers/acpi/arm64/mpam.c
> index 59712397025d..51c6f5fd4a5e 100644
> --- a/drivers/acpi/arm64/mpam.c
> +++ b/drivers/acpi/arm64/mpam.c
> @@ -337,6 +337,13 @@ static int __init acpi_mpam_parse(void)
>  	return 0;
>  }
>  
> +/**
> + * acpi_mpam_count_msc() - Count the number of MSC described by firmware.
> + *
> + * Returns the number of of MSC, or zero for an error.
> + *
> + * This can be called before or in parallel with acpi_mpam_parse().
> + */

This comment can be added in the patch where you add the function,
acpi_mpam_count_msc().

>  int acpi_mpam_count_msc(void)
>  {
>  	struct acpi_table_header *table __free(acpi_table) = acpi_get_table_ret(ACPI_SIG_MPAM, 0);
[...]
> diff --git a/include/linux/acpi.h b/include/linux/acpi.h
> index 9d66421f68ff..70f075b397ce 100644
> --- a/include/linux/acpi.h
> +++ b/include/linux/acpi.h
> @@ -231,7 +231,7 @@ static inline struct acpi_table_header *acpi_get_table_ret(char *signature, u32
>  		return ERR_PTR(-ENOENT);
>  	return table;
>  }
> -DEFINE_FREE(acpi_table, struct acpi_table_header *, if (!IS_ERR(_T)) acpi_put_table(_T))
> +DEFINE_FREE(acpi_table, struct acpi_table_header *, if (!IS_ERR_OR_NULL(_T)) acpi_put_table(_T))

Ah, you did make this change. Just ended up in the wrong patch.

>  
>  int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
>  int __init_or_acpilib acpi_table_parse_entries(char *id,

-- 
Thanks,

Ben