[Intel][6.6] Backport AET support for Intel platforms

Documentation/admin-guide/kernel-parameters.txt

@@ -5483,9 +5483,13 @@
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba, smba, bmec.
+			mba, smba, bmec, 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/arch/x86/index.rst

@@ -31,7 +31,6 @@ x86-specific Documentation
    pti
    mds
    microcode
-   resctrl
    tsx_async_abort
    buslock
    usb-legacy-support

Documentation/filesystems/index.rst

@@ -109,6 +109,7 @@ Documentation for filesystem implementations.
    qnx6
    ramfs-rootfs-initramfs
    relay
+   resctrl
    romfs
    smb/index
    spufs/index

Documentation/arch/x86/resctrl.rst → Documentation/filesystems/resctrl.rst

@@ -1,9 +1,9 @@
 .. SPDX-License-Identifier: GPL-2.0
 .. include:: <isonum.txt>
 
-===========================================
-User Interface for Resource Control feature
-===========================================
+=====================================================
+User Interface for Resource Control feature (resctrl)
+=====================================================
 
 :Copyright: |copy| 2016 Intel Corporation
 :Authors: - Fenghua Yu <fenghua.yu@intel.com>
@@ -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
@@ -261,6 +260,24 @@ 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
@@ -366,20 +383,51 @@ 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"
 	where "YY" is the node number.
 
+	When the 'mbm_event' counter assignment mode is enabled, reading
+	an MBM event of a MON group returns 'Unassigned' if no hardware
+	counter is assigned to it. For CTRL_MON groups, 'Unassigned' is
+	returned if the MBM event does not have an assigned counter in the
+	CTRL_MON group nor in any of its associated MON groups.
+
 "mon_hw_id":
 	Available only with debug option. The identifier used by hardware
 	for the monitor group. On x86 this is the RMID.

MAINTAINERS

@@ -18108,9 +18108,11 @@ M:	Fenghua Yu <fenghua.yu@intel.com>
 M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	Documentation/arch/x86/resctrl*
+F:	Documentation/filesystems/resctrl.rst
 F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/
+F:	fs/resctrl/
+F:	include/linux/resctrl*.h
 F:	tools/testing/selftests/resctrl/
 
 READ-COPY UPDATE (RCU)

arch/Kconfig

@@ -1333,6 +1333,14 @@ config STRICT_MODULE_RWX
 config ARCH_HAS_PHYS_TO_DMA
 	bool
 
+config ARCH_HAS_CPU_RESCTRL
+	bool
+	help
+	  An architecture selects this option to indicate that the necessary
+	  hooks are provided to support the common memory system usage
+	  monitoring and control interfaces provided by the 'resctrl'
+	  filesystem (see RESCTRL_FS).
+
 config HAVE_ARCH_COMPILER_H
 	bool
 	help

arch/x86/Kconfig

@@ -482,8 +482,10 @@ config GOLDFISH
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
-	select KERNFS
-	select PROC_CPU_RESCTRL		if PROC_FS
+	depends on MISC_FILESYSTEMS
+	select ARCH_HAS_CPU_RESCTRL
+	select RESCTRL_FS
+	select RESCTRL_FS_PSEUDO_LOCK
 	help
 	  Enable x86 CPU resource control support.
 
@@ -500,6 +502,19 @@ 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.
+
 if X86_32
 config X86_BIGSMP
 	bool "Support for big SMP systems with more than 8 CPUs"

arch/x86/events/intel/uncore_snbep.c

@@ -6605,6 +6605,32 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct uncore_event_desc gnr_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x01,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0,  "event=0x05,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1,  "event=0x06,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type gnr_uncore_imc = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "imc",
+	.fixed_ctr_bits		= 48,
+	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
+	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
+	.event_descs		= gnr_uncore_imc_events,
+};
+
 static struct intel_uncore_type gnr_uncore_pciex8 = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "pciex8",
@@ -6652,7 +6678,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	NULL,
 	&spr_uncore_pcu,
 	&gnr_uncore_ubox,
-	&spr_uncore_imc,
+	&gnr_uncore_imc,
 	NULL,
 	&gnr_uncore_upi,
 	NULL,

arch/x86/include/asm/cpufeatures.h

@@ -485,6 +485,7 @@
 #define X86_FEATURE_TSA_L1_NO          (21*32+12) /* "" AMD CPU not vulnerable to TSA-L1 */
 #define X86_FEATURE_CLEAR_CPU_BUF_VM   (21*32+13) /* "" Clear CPU buffers using VERW before VMRUN */
 #define X86_FEATURE_IBPB_EXIT_TO_USER  (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
+#define X86_FEATURE_ABMC		(21*32+15) /* Assignable Bandwidth Monitoring Counters */
 
 /*
  * BUG word(s)

arch/x86/include/asm/msr-index.h

@@ -1234,6 +1234,8 @@
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
 #define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_L3_QOS_ABMC_CFG	0xc00003fd
+#define MSR_IA32_L3_QOS_EXT_CFG		0xc00003ff
 #define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
 /* MSR_IA32_VMX_MISC bits */

arch/x86/include/asm/resctrl.h

@@ -4,8 +4,10 @@
 
 #ifdef CONFIG_X86_CPU_RESCTRL
 
-#include <linux/sched.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/resctrl_types.h>
+#include <linux/sched.h>
 
 /*
  * This value can never be a valid CLOSID, and is used when mapping a
@@ -96,8 +98,8 @@ static inline void resctrl_arch_disable_mon(void)
 static inline void __resctrl_sched_in(struct task_struct *tsk)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
-	u32 closid = state->default_closid;
-	u32 rmid = state->default_rmid;
+	u32 closid = READ_ONCE(state->default_closid);
+	u32 rmid = READ_ONCE(state->default_rmid);
 	u32 tmp;
 
 	/*
@@ -132,6 +134,13 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid,
+							    u32 rmid)
+{
+	WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid);
+	WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid);
+}
+
 static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
 						u32 closid, u32 rmid)
 {
@@ -150,7 +159,7 @@ static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
 	return READ_ONCE(tsk->rmid) == rmid;
 }
 
-static inline void resctrl_sched_in(struct task_struct *tsk)
+static inline void resctrl_arch_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
@@ -169,20 +178,22 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
 
 /* x86 can always read an rmid, nothing needs allocating */
 struct rdt_resource;
-static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r,
+					       enum resctrl_event_id evtid)
 {
 	might_sleep();
 	return NULL;
-};
+}
 
-static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
-					     void *ctx) { };
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r,
+					     enum resctrl_event_id evtid,
+					     void *ctx) { }
 
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
 
-static inline void resctrl_sched_in(struct task_struct *tsk) {}
+static inline void resctrl_arch_sched_in(struct task_struct *tsk) {}
 static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
 
 #endif /* CONFIG_X86_CPU_RESCTRL */

arch/x86/kernel/cpu/resctrl/Makefile

@@ -1,4 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+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:
 CFLAGS_pseudo_lock.o = -I$(src)