[linux-nvidia-6.17] Backport MPAM fixes and support for CPU-less NUMA nodes

Documentation/admin-guide/kernel-parameters.txt

@@ -6174,8 +6174,14 @@
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
 			mba, smba, bmec, abmc.
+			mba, smba, bmec, abmc, sdciae, energy[:guid],
+			perf[:guid].
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
+			To turn off all energy telemetry monitoring and ensure that
+			perf telemetry monitoring associated with guid 0x12345
+			is enabled use:
+				rdt=!energy,perf:0x12345
 
 	reboot=		[KNL]
 			Format (x86 or x86_64):

Documentation/filesystems/resctrl.rst

@@ -167,13 +167,12 @@ with respect to allocation:
 			bandwidth percentages are directly applied to
 			the threads running on the core
 
-If RDT monitoring is available there will be an "L3_MON" directory
+If L3 monitoring is available there will be an "L3_MON" directory
 with the following files:
 
 "num_rmids":
-		The number of RMIDs available. This is the
-		upper bound for how many "CTRL_MON" + "MON"
-		groups can be created.
+		The number of RMIDs supported by hardware for
+		L3 monitoring events.
 
 "mon_features":
 		Lists the monitoring events if
@@ -399,6 +398,24 @@ with the following files:
 		bytes) at which a previously used LLC_occupancy
 		counter can be considered for re-use.
 
+If telemetry monitoring is available there will be a "PERF_PKG_MON" directory
+with the following files:
+
+"num_rmids":
+		The number of RMIDs for telemetry monitoring events.
+
+		On Intel resctrl will not enable telemetry events if the number of
+		RMIDs that can be tracked concurrently is lower than the total number
+		of RMIDs supported. Telemetry events can be force-enabled with the
+		"rdt=" kernel parameter, but this may reduce the number of
+		monitoring groups that can be created.
+
+"mon_features":
+		Lists the telemetry monitoring events that are enabled on this system.
+
+The upper bound for how many "CTRL_MON" + "MON" can be created
+is the smaller of the L3_MON and PERF_PKG_MON "num_rmids" values.
+
 Finally, in the top level of the "info" directory there is a file
 named "last_cmd_status". This is reset with every "command" issued
 via the file system (making new directories or writing to any of the
@@ -504,15 +521,40 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
-	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
-	files provide a read out of the current value of the event for
-	all tasks in the group. In CTRL_MON groups these files provide
-	the sum for all tasks in the CTRL_MON group and all tasks in
+	This contains directories for each monitor domain.
+
+	If L3 monitoring is enabled, there will be a "mon_L3_XX" directory for
+	each instance of an L3 cache. Each directory contains files for the enabled
+	L3 events (e.g. "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes").
+
+	If telemetry monitoring is enabled, there will be a "mon_PERF_PKG_YY"
+	directory for each physical processor package. Each directory contains
+	files for the enabled telemetry events (e.g. "core_energy". "activity",
+	"uops_retired", etc.)
+
+	The info/`*`/mon_features files provide the full list of enabled
+	event/file names.
+
+	"core energy" reports a floating point number for the energy (in Joules)
+	consumed by cores (registers, arithmetic units, TLB and L1/L2 caches)
+	during execution of instructions summed across all logical CPUs on a
+	package for the current monitoring group.
+
+	"activity" also reports a floating point value (in Farads).  This provides
+	an estimate of work done independent of the frequency that the CPUs used
+	for execution.
+
+	Note that "core energy" and "activity" only measure energy/activity in the
+	"core" of the CPU (arithmetic units, TLB, L1 and L2 caches, etc.). They
+	do not include L3 cache, memory, I/O devices etc.
+
+	All other events report decimal integer values.
+
+	In a MON group these files provide a read out of the current value of
+	the event for all tasks in the group. In CTRL_MON groups these files
+	provide the sum for all tasks in the CTRL_MON group and all tasks in
 	MON groups. Please see example section for more details on usage.
+
 	On systems with Sub-NUMA Cluster (SNC) enabled there are extra
 	directories for each node (located within the "mon_L3_XX" directory
 	for the L3 cache they occupy). These are named "mon_sub_L3_YY"

arch/x86/Kconfig

@@ -525,6 +525,19 @@ config X86_CPU_RESCTRL
 
 	  Say N if unsure.
 
+config X86_CPU_RESCTRL_INTEL_AET
+	bool "Intel Application Energy Telemetry"
+	depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y
+	help
+	  Enable per-RMID telemetry events in resctrl.
+
+	  Intel feature that collects per-RMID execution data
+	  about energy consumption, measure of frequency independent
+	  activity and other performance metrics. Data is aggregated
+	  per package.
+
+	  Say N if unsure.
+
 config X86_FRED
 	bool "Flexible Return and Event Delivery"
 	depends on X86_64

arch/x86/include/asm/resctrl.h

@@ -198,15 +198,6 @@ static inline bool resctrl_arch_mon_can_overflow(void)
 
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
-static inline bool resctrl_arch_get_mb_uses_numa_nid(void)
-{
-	return false;
-}
-
-static inline int resctrl_arch_set_mb_uses_numa_nid(bool enabled)
-{
-	return -EOPNOTSUPP;
-}
 #else
 
 static inline void resctrl_arch_sched_in(struct task_struct *tsk) {}

arch/x86/kernel/cpu/resctrl/Makefile

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= core.o rdtgroup.o monitor.o
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= ctrlmondata.o
+obj-$(CONFIG_X86_CPU_RESCTRL_INTEL_AET)	+= intel_aet.o
 obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
 
 # To allow define_trace.h's recursive include: