Merge: Update resctrl to upstream 6.17

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1683

Description:
Updates for the resctrl file system to work on multiple arches,
which facilitates future development.

JIRA: https://issues.redhat.com/browse/RHEL-122044

Build Info: 69320879

Tested: Successful platform test results on Intel (intel-birchstream-gnr-cwf-ap-02) system.

Signed-off-by: Steve Best <sbest@redhat.com>

Approved-by: Phil Auld <pauld@redhat.com>
Approved-by: Tony Camuso <tcamuso@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

Documentation/arch/x86/index.rst

@@ -32,7 +32,6 @@ x86-specific Documentation
    pti
    mds
    microcode
-   resctrl
    tsx_async_abort
    buslock
    usb-legacy-support

Documentation/filesystems/index.rst

@@ -112,6 +112,7 @@ Documentation for filesystem implementations.
    qnx6
    ramfs-rootfs-initramfs
    relay
+   resctrl
    romfs
    smb/index
    spufs/index

Documentation/arch/x86/resctrl.rst Documentation/filesystems/resctrl.rstDocumentation/arch/x86/resctrl.rst renamed to Documentation/filesystems/resctrl.rst

@@ -384,6 +384,16 @@ When monitoring is enabled all MON groups will also contain:
 	Available only with debug option. The identifier used by hardware
 	for the monitor group. On x86 this is the RMID.
 
+When the "mba_MBps" mount option is used all CTRL_MON groups will also contain:
+
+"mba_MBps_event":
+	Reading this file shows which memory bandwidth event is used
+	as input to the software feedback loop that keeps memory bandwidth
+	below the value specified in the schemata file. Writing the
+	name of one of the supported memory bandwidth events found in
+	/sys/fs/resctrl/info/L3_MON/mon_features changes the input
+	event.
+
 Resource allocation rules
 -------------------------
 

MAINTAINERS

@@ -19540,9 +19540,11 @@ 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

@@ -1517,6 +1517,14 @@ 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

@@ -502,8 +502,10 @@ config X86_MPPARSE
 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.
 

arch/x86/include/asm/paravirt.h

@@ -180,13 +180,6 @@ static inline void halt(void)
 	PVOP_VCALL0(irq.halt);
 }
 
-extern noinstr void pv_native_wbinvd(void);
-
-static __always_inline void wbinvd(void)
-{
-	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN);
-}
-
 static inline u64 paravirt_read_msr(unsigned msr)
 {
 	return PVOP_CALL1(u64, cpu.read_msr, msr);

arch/x86/include/asm/paravirt_types.h

@@ -86,8 +86,6 @@ struct pv_cpu_ops {
 	void (*update_io_bitmap)(void);
 #endif
 
-	void (*wbinvd)(void);
-
 	/* cpuid emulation, mostly so that caps bits can be disabled */
 	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
 		      unsigned int *ecx, unsigned int *edx);

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
@@ -40,6 +42,7 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
+extern unsigned int rdt_mon_features;
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
@@ -79,6 +82,21 @@ static inline void resctrl_arch_disable_mon(void)
 	static_branch_dec_cpuslocked(&rdt_enable_key);
 }
 
+static inline bool resctrl_arch_is_llc_occupancy_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_total_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_local_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
@@ -96,8 +114,8 @@ 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 +150,13 @@ 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 +175,7 @@ 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 +194,22 @@ 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/include/asm/special_insns.h

@@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru)
 }
 #endif
 
-static __always_inline void native_wbinvd(void)
+static __always_inline void wbinvd(void)
 {
 	asm volatile("wbinvd": : :"memory");
 }
@@ -167,12 +167,6 @@ static inline void __write_cr4(unsigned long x)
 {
 	native_write_cr4(x);
 }
-
-static __always_inline void wbinvd(void)
-{
-	native_wbinvd();
-}
-
 #endif /* CONFIG_PARAVIRT_XXL */
 
 static __always_inline void clflush(volatile void *__p)