26.04_linux-nvidia-bos: Please pull MPAM 26.04 linux nvidia bos.glue.others.cpu less.hardlimit

Documentation/arch/arm64/index.rst

@@ -23,6 +23,7 @@ ARM64 Architecture
     memory
     memory-tagging-extension
     mops
+    mpam
     perf
     pointer-authentication
     ptdump

Documentation/arch/arm64/mpam.rst

@@ -0,0 +1,72 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====
+MPAM
+====
+
+What is MPAM
+============
+MPAM (Memory Partitioning and Monitoring) is a feature in the CPUs and memory
+system components such as the caches or memory controllers that allow memory
+traffic to be labelled, partitioned and monitored.
+
+Traffic is labelled by the CPU, based on the control or monitor group the
+current task is assigned to using resctrl.  Partitioning policy can be set
+using the schemata file in resctrl, and monitor values read via resctrl.
+See Documentation/filesystems/resctrl.rst for more details.
+
+This allows tasks that share memory system resources, such as caches, to be
+isolated from each other according to the partitioning policy (so called noisy
+neighbours).
+
+Supported Platforms
+===================
+Use of this feature requires CPU support, support in the memory system
+components, and a description from firmware of where the MPAM device controls
+are in the MMIO address space. (e.g. the 'MPAM' ACPI table).
+
+The MMIO device that provides MPAM controls/monitors for a memory system
+component is called a memory system component. (MSC).
+
+Because the user interface to MPAM is via resctrl, only MPAM features that are
+compatible with resctrl can be exposed to user-space.
+
+MSC are considered as a group based on the topology. MSC that correspond with
+the L3 cache are considered together, it is not possible to mix MSC between L2
+and L3 to 'cover' a resctrl schema.
+
+The supported features are:
+
+* Cache portion bitmap controls (CPOR) on the L2 or L3 caches.  To expose
+  CPOR at L2 or L3, every CPU must have a corresponding CPU cache at this
+  level that also supports the feature.  Mismatched big/little platforms are
+  not supported as resctrl's controls would then also depend on task
+  placement.
+
+* Memory bandwidth maximum controls (MBW_MAX) on or after the L3 cache.
+  resctrl uses the L3 cache-id to identify where the memory bandwidth
+  control is applied. For this reason the platform must have an L3 cache
+  with cache-id's supplied by firmware. (It doesn't need to support MPAM.)
+
+  To be exported as the 'MB' schema, the topology of the group of MSC chosen
+  must match the topology of the L3 cache so that the cache-id's can be
+  repainted. For example: Platforms with Memory bandwidth maximum controls
+  on CPU-less NUMA nodes cannot expose the 'MB' schema to resctrl as these
+  nodes do not have a corresponding L3 cache. If the memory bandwidth
+  control is on the memory rather than the L3 then there must be a single
+  global L3 as otherwise it is unknown which L3 the traffic came from. There
+  must be no caches between the L3 and the memory so that the two ends of
+  the path have equivalent traffic.
+
+  When the MPAM driver finds multiple groups of MSC it can use for the 'MB'
+  schema, it prefers the group closest to the L3 cache.
+
+* Cache Storage Usage (CSU) counters can expose the 'llc_occupancy' provided
+  there is at least one CSU monitor on each MSC that makes up the L3 group.
+  Exposing CSU counters from other caches or devices is not supported.
+
+Reporting Bugs
+==============
+If you are not seeing the counters or controls you expect please share the
+debug messages produced when enabling dynamic debug and booting with:
+dyndbg="file mpam_resctrl.c +pl"

Documentation/arch/arm64/silicon-errata.rst

@@ -214,6 +214,9 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | SI L1           | #4311569        | ARM64_ERRATUM_4311569       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | CMN-650         | #3642720        | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
 +----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_843419        |
@@ -247,6 +250,12 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | T241 GICv3/4.x  | T241-FABRIC-4   | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | T241 MPAM       | T241-MPAM-1     | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | T241 MPAM       | T241-MPAM-4     | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | T241 MPAM       | T241-MPAM-6     | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+

Documentation/filesystems/resctrl.rst

@@ -215,6 +215,14 @@ related to allocation:
 			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
 			0=00ff;1=000f
 
+		An ID of "*" configures all domains with the provided CBM.
+
+		Example on a system that does not require a minimum number of consecutive bits in the mask::
+
+			# echo "*=0" > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=0;1=0
+
 		When CDP is enabled "io_alloc_cbm" associated with the CDP_DATA and CDP_CODE
 		resources may reflect the same values. For example, values read from and
 		written to /sys/fs/resctrl/info/L3DATA/io_alloc_cbm may be reflected by
@@ -228,18 +236,30 @@ with respect to allocation:
 		user can request.
 
 "bandwidth_gran":
-		The granularity in which the memory bandwidth
+		The approximate granularity in which the memory bandwidth
 		percentage is allocated. The allocated
 		b/w percentage is rounded off to the next
-		control step available on the hardware. The
-		available bandwidth control steps are:
-		min_bandwidth + N * bandwidth_gran.
+		control step available on the hardware. The available
+		steps are at least as small as this value.
 
 "delay_linear":
 		Indicates if the delay scale is linear or
 		non-linear. This field is purely informational
 		only.
 
+"max_lim":
+		Read-only. On ARM MPAM systems where MBA exposes MBW_MAX, this
+		file contains a single decimal integer: the
+		``MPAMF_MBW_IDR.MAX_LIM`` field [1:0] (values ``0``–``3``) as probed for the MBA resource.
+		The file appears only when the platform supports MBA MBW_MAX and
+		the MAX_LIM value is available; otherwise it is not listed.
+
+		The Arm MPAM architecture defines the meaning of each MAX_LIM
+		encoding. In this kernel, when ``max_lim`` reads ``0``, the
+		driver treats the ``HARDLIM`` bit of ``MPAMCFG_MBW_MAX`` as
+		read/write and an optional ``MB_HLIM`` line may appear in
+		``schemata``. When ``max_lim`` is nonzero, ``MB_HLIM`` is omitted.
+
 "thread_throttle_mode":
 		Indicator on Intel systems of how tasks running on threads
 		of a physical core are throttled in cases where they
@@ -956,6 +976,27 @@ Memory bandwidth domain is L3 cache.
 
 	MB:<cache_id0>=bw_MiBps0;<cache_id1>=bw_MiBps1;...
 
+MBW maximum hard limit (ARM MPAM)
+---------------------------------
+On some ARM systems, resctrl memory bandwidth allocation uses MPAM
+maximum bandwidth (MBW_MAX). When ``max_lim`` reads ``0`` (see ``max_lim``
+under the ``MB`` allocation ``info`` directory), an additional schemata
+line selects the ``HARDLIM`` bit for ``MPAMCFG_MBW_MAX`` independently of
+the numeric limit on the ``MB`` line.
+
+The line uses the same cache/domain indices as ``MB``. Each value must
+be ``0`` or ``1``: ``0`` clears HARDLIM (soft-limit behaviour for the
+max), ``1`` sets HARDLIM (hard limit). When ``max_lim`` is nonzero or
+``MB_HLIM`` is not supported for the platform, the line is omitted from
+``schemata``.
+
+Format:
+::
+
+	MB_HLIM:<cache_id0>=0|1;<cache_id1>=0|1;...
+
+The corresponding ``schema_format`` entry under ``info`` is ``mb_hlim``.
+
 Slow Memory Bandwidth Allocation (SMBA)
 ---------------------------------------
 AMD hardware supports Slow Memory Bandwidth Allocation (SMBA).

MAINTAINERS

@@ -22198,11 +22198,13 @@ F:	tools/testing/selftests/net/rds/
 RDT - RESOURCE ALLOCATION
 M:	Tony Luck <tony.luck@intel.com>
 M:	Reinette Chatre <reinette.chatre@intel.com>
+M:	x86@kernel.org
 R:	Dave Martin <Dave.Martin@arm.com>
 R:	James Morse <james.morse@arm.com>
 R:	Babu Moger <babu.moger@amd.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
+P:	Documentation/process/maintainer-tip.rst
 F:	Documentation/filesystems/resctrl.rst
 F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/

arch/arm64/Kconfig

@@ -2047,8 +2047,8 @@ 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
+	select ARM64_MPAM_DRIVER
+	select ARCH_HAS_CPU_RESCTRL
 	help
 	  Memory System Resource Partitioning and Monitoring (MPAM) is an
 	  optional extension to the Arm architecture that allows each
@@ -2070,6 +2070,8 @@ config ARM64_MPAM
 
 	  MPAM is exposed to user-space via the resctrl pseudo filesystem.
 
+	  This option enables the extra context switch code.
+
 endmenu # "ARMv8.4 architectural features"
 
 menu "ARMv8.5 architectural features"

arch/arm64/include/asm/el2_setup.h

@@ -513,7 +513,8 @@
 	check_override id_aa64pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT, .Linit_mpam_\@, .Lskip_mpam_\@, x1, x2
 
 .Linit_mpam_\@:
-	msr_s	SYS_MPAM2_EL2, xzr		// use the default partition
+	mov	x0, #MPAM2_EL2_EnMPAMSM_MASK
+	msr_s	SYS_MPAM2_EL2, x0		// use the default partition,
 						// and disable lower traps
 	mrs_s	x0, SYS_MPAMIDR_EL1
 	tbz	x0, #MPAMIDR_EL1_HAS_HCR_SHIFT, .Lskip_mpam_\@  // skip if no MPAMHCR reg

arch/arm64/include/asm/mpam.h

@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2025 Arm Ltd. */
+
+#ifndef __ASM__MPAM_H
+#define __ASM__MPAM_H
+
+#include <linux/arm_mpam.h>
+#include <linux/bitfield.h>
+#include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+
+#include <asm/sysreg.h>
+
+DECLARE_STATIC_KEY_FALSE(mpam_enabled);
+DECLARE_PER_CPU(u64, arm64_mpam_default);
+DECLARE_PER_CPU(u64, arm64_mpam_current);
+
+/*
+ * The value of the MPAM0_EL1 sysreg when a task is in resctrl's default group.
+ * This is used by the context switch code to use the resctrl CPU property
+ * instead. The value is modified when CDP is enabled/disabled by mounting
+ * the resctrl filesystem.
+ */
+extern u64 arm64_mpam_global_default;
+
+#ifdef CONFIG_ARM64_MPAM
+static inline u64 __mpam_regval(u16 partid_d, u16 partid_i, u8 pmg_d, u8 pmg_i)
+{
+	return FIELD_PREP(MPAM0_EL1_PARTID_D, partid_d) |
+	       FIELD_PREP(MPAM0_EL1_PARTID_I, partid_i) |
+	       FIELD_PREP(MPAM0_EL1_PMG_D, pmg_d) |
+	       FIELD_PREP(MPAM0_EL1_PMG_I, pmg_i);
+}
+
+static inline void mpam_set_cpu_defaults(int cpu, u16 partid_d, u16 partid_i,
+					 u8 pmg_d, u8 pmg_i)
+{
+	u64 default_val = __mpam_regval(partid_d, partid_i, pmg_d, pmg_i);
+
+	WRITE_ONCE(per_cpu(arm64_mpam_default, cpu), default_val);
+}
+
+/*
+ * The resctrl filesystem writes to the partid/pmg values for threads and CPUs,
+ * which may race with reads in mpam_thread_switch(). Ensure only one of the old
+ * or new values are used. Particular care should be taken with the pmg field as
+ * mpam_thread_switch() may read a partid and pmg that don't match, causing this
+ * value to be stored with cache allocations, despite being considered 'free' by
+ * resctrl.
+ */
+static inline u64 mpam_get_regval(struct task_struct *tsk)
+{
+	return READ_ONCE(task_thread_info(tsk)->mpam_partid_pmg);
+}
+
+static inline void mpam_set_task_partid_pmg(struct task_struct *tsk,
+					    u16 partid_d, u16 partid_i,
+					    u8 pmg_d, u8 pmg_i)
+{
+	u64 regval = __mpam_regval(partid_d, partid_i, pmg_d, pmg_i);
+
+	WRITE_ONCE(task_thread_info(tsk)->mpam_partid_pmg, regval);
+}
+
+static inline void mpam_thread_switch(struct task_struct *tsk)
+{
+	u64 oldregval;
+	int cpu = smp_processor_id();
+	u64 regval = mpam_get_regval(tsk);
+
+	if (!static_branch_likely(&mpam_enabled))
+		return;
+
+	if (regval == READ_ONCE(arm64_mpam_global_default))
+		regval = READ_ONCE(per_cpu(arm64_mpam_default, cpu));
+
+	oldregval = READ_ONCE(per_cpu(arm64_mpam_current, cpu));
+	if (oldregval == regval)
+		return;
+
+	write_sysreg_s(regval | MPAM1_EL1_MPAMEN, SYS_MPAM1_EL1);
+	if (system_supports_sme())
+		write_sysreg_s(regval & (MPAMSM_EL1_PARTID_D | MPAMSM_EL1_PMG_D), SYS_MPAMSM_EL1);
+	isb();
+
+	/* Synchronising the EL0 write is left until the ERET to EL0 */
+	write_sysreg_s(regval, SYS_MPAM0_EL1);
+
+	WRITE_ONCE(per_cpu(arm64_mpam_current, cpu), regval);
+}
+#else
+static inline void mpam_thread_switch(struct task_struct *tsk) {}
+#endif /* CONFIG_ARM64_MPAM */
+
+#endif /* __ASM__MPAM_H */

arch/arm64/include/asm/resctrl.h

@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/arm_mpam.h>

arch/arm64/include/asm/thread_info.h

@@ -41,6 +41,9 @@ struct thread_info {
 #ifdef CONFIG_SHADOW_CALL_STACK
 	void			*scs_base;
 	void			*scs_sp;
+#endif
+#ifdef CONFIG_ARM64_MPAM
+	u64			mpam_partid_pmg;
 #endif
 	u32			cpu;
 };

arch/arm64/kernel/Makefile

@@ -68,6 +68,7 @@ obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 obj-$(CONFIG_VMCORE_INFO)		+= vmcore_info.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
+obj-$(CONFIG_ARM64_MPAM)		+= mpam.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o

arch/arm64/kernel/cpufeature.c

@@ -86,6 +86,7 @@
 #include <asm/kvm_host.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
+#include <asm/mpam.h>
 #include <asm/mte.h>
 #include <asm/hypervisor.h>
 #include <asm/processor.h>
@@ -2501,13 +2502,19 @@ test_has_mpam(const struct arm64_cpu_capabilities *entry, int scope)
 static void
 cpu_enable_mpam(const struct arm64_cpu_capabilities *entry)
 {
-	/*
-	 * Access by the kernel (at EL1) should use the reserved PARTID
-	 * which is configured unrestricted. This avoids priority-inversion
-	 * where latency sensitive tasks have to wait for a task that has
-	 * been throttled to release the lock.
-	 */
-	write_sysreg_s(0, SYS_MPAM1_EL1);
+	int cpu = smp_processor_id();
+	u64 regval = 0;
+
+	if (IS_ENABLED(CONFIG_ARM64_MPAM) && static_branch_likely(&mpam_enabled))
+		regval = READ_ONCE(per_cpu(arm64_mpam_current, cpu));
+
+	write_sysreg_s(regval | MPAM1_EL1_MPAMEN, SYS_MPAM1_EL1);
+	if (cpus_have_cap(ARM64_SME))
+		write_sysreg_s(regval & (MPAMSM_EL1_PARTID_D | MPAMSM_EL1_PMG_D), SYS_MPAMSM_EL1);
+	isb();
+
+	/* Synchronising the EL0 write is left until the ERET to EL0 */
+	write_sysreg_s(regval, SYS_MPAM0_EL1);
 }
 
 static bool