[PW_SID:1104229] riscv: add Ssqosid and CBQRI resctrl support

Documentation/devicetree/bindings/riscv/extensions.yaml

@@ -232,6 +232,12 @@ properties:
             ratified at commit d70011dde6c2 ("Update to ratified state")
             of riscv-j-extension.
 
+        - const: ssqosid
+          description: |
+            The standard Ssqosid extension for Quality of Service ID is
+            ratified as v1.0 in commit d9c616497fde ("Merge pull
+            request #7 from ved-rivos/Ratified") of riscv-ssqosid.
+
         - const: ssstateen
           description: |
             The standard Ssstateen extension for supervisor-mode view of the

MAINTAINERS

@@ -23017,6 +23017,21 @@ F:	drivers/perf/riscv_pmu.c
 F:	drivers/perf/riscv_pmu_legacy.c
 F:	drivers/perf/riscv_pmu_sbi.c
 
+RISC-V QOS RESCTRL SUPPORT
+M:	Drew Fustini <fustini@kernel.org>
+R:	yunhui cui <cuiyunhui@bytedance.com>
+L:	linux-riscv@lists.infradead.org
+S:	Supported
+F:	arch/riscv/include/asm/qos.h
+F:	arch/riscv/include/asm/resctrl.h
+F:	arch/riscv/kernel/qos.c
+F:	drivers/acpi/riscv/rqsc.c
+F:	drivers/acpi/riscv/rqsc.h
+F:	drivers/resctrl/cbqri_devices.c
+F:	drivers/resctrl/cbqri_internal.h
+F:	drivers/resctrl/cbqri_resctrl.c
+F:	include/linux/riscv_cbqri.h
+
 RISC-V RPMI AND MPXY DRIVERS
 M:	Rahul Pathak <rahul@summations.net>
 M:	Anup Patel <anup@brainfault.org>

arch/riscv/Kconfig

@@ -591,6 +591,26 @@ config RISCV_ISA_SVNAPOT
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_SSQOSID
+	bool "Ssqosid extension support for supervisor mode Quality of Service ID"
+	depends on 64BIT
+	default n
+	select ARCH_HAS_CPU_RESCTRL
+	select RISCV_CBQRI_DRIVER
+	help
+	  Adds support for the Ssqosid ISA extension (Supervisor-mode
+	  Quality of Service ID).
+
+	  Ssqosid defines the srmcfg CSR which allows the system to tag the
+	  running process with an RCID (Resource Control ID) and MCID
+	  (Monitoring Counter ID). The RCID is used to determine resource
+	  allocation. The MCID is used to track resource usage in event
+	  counters.
+
+	  For example, a cache controller may use the RCID to apply a
+	  cache partitioning scheme and use the MCID to track how much
+	  cache a process, or a group of processes, is using.
+
 config RISCV_ISA_SVPBMT
 	bool "Svpbmt extension support for supervisor mode page-based memory types"
 	depends on 64BIT && MMU

arch/riscv/include/asm/acpi.h

@@ -67,6 +67,16 @@ int acpi_get_riscv_isa(struct acpi_table_header *table,
 
 void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
 			     u32 *cboz_size, u32 *cbop_size);
+
+#ifdef CONFIG_RISCV_CBQRI_DRIVER
+int __init acpi_parse_rqsc(struct acpi_table_header *table);
+#else
+static inline int acpi_parse_rqsc(struct acpi_table_header *table)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_RISCV_CBQRI_DRIVER */
+
 #else
 static inline void acpi_init_rintc_map(void) { }
 static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)

arch/riscv/include/asm/csr.h

@@ -84,6 +84,10 @@
 #define SATP_ASID_MASK	_AC(0xFFFF, UL)
 #endif
 
+/* SRMCFG fields */
+#define SRMCFG_RCID_MASK	GENMASK(11, 0)
+#define SRMCFG_MCID_MASK	GENMASK(27, 16)
+
 /* Exception cause high bit - is an interrupt if set */
 #define CAUSE_IRQ_FLAG		(_AC(1, UL) << (__riscv_xlen - 1))
 
@@ -328,6 +332,7 @@
 #define CSR_STVAL		0x143
 #define CSR_SIP			0x144
 #define CSR_SATP		0x180
+#define CSR_SRMCFG		0x181
 
 #define CSR_STIMECMP		0x14D
 #define CSR_STIMECMPH		0x15D

arch/riscv/include/asm/hwcap.h

@@ -112,6 +112,7 @@
 #define RISCV_ISA_EXT_ZCLSD		103
 #define RISCV_ISA_EXT_ZICFILP		104
 #define RISCV_ISA_EXT_ZICFISS		105
+#define RISCV_ISA_EXT_SSQOSID		106
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 

arch/riscv/include/asm/processor.h

@@ -123,6 +123,9 @@ struct thread_struct {
 	/* A forced icache flush is not needed if migrating to the previous cpu. */
 	unsigned int prev_cpu;
 #endif
+#ifdef CONFIG_RISCV_ISA_SSQOSID
+	u32 srmcfg;
+#endif
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */

arch/riscv/include/asm/qos.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_QOS_H
+#define _ASM_RISCV_QOS_H
+
+#include <linux/percpu-defs.h>
+
+#ifdef CONFIG_RISCV_ISA_SSQOSID
+
+#include <linux/bitfield.h>
+#include <linux/cpufeature.h>
+#include <linux/sched.h>
+
+#include <asm/csr.h>
+#include <asm/fence.h>
+#include <asm/hwcap.h>
+
+/* cached value of srmcfg csr for each cpu */
+DECLARE_PER_CPU(u32, cpu_srmcfg);
+
+/* default srmcfg value for each cpu, set via resctrl cpu assignment */
+DECLARE_PER_CPU(u32, cpu_srmcfg_default);
+
+static inline void __switch_to_srmcfg(struct task_struct *next)
+{
+	u32 thread_srmcfg, default_srmcfg;
+
+	thread_srmcfg = READ_ONCE(next->thread.srmcfg);
+	default_srmcfg = __this_cpu_read(cpu_srmcfg_default);
+
+	/*
+	 * RCID and MCID inherit from cpu_srmcfg_default independently.
+	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are both 0,
+	 * so a per-field zero means "no task assignment for this
+	 * dimension" and the CPU default supplies that field. Matches
+	 * x86 RDT's __resctrl_sched_in() per-field logic. The fully
+	 * unassigned (thread.srmcfg == 0) and fully assigned (both
+	 * fields non-zero) cases short-circuit the field math.
+	 */
+	if (thread_srmcfg == 0) {
+		thread_srmcfg = default_srmcfg;
+	} else {
+		u32 rcid = FIELD_GET(SRMCFG_RCID_MASK, thread_srmcfg);
+		u32 mcid = FIELD_GET(SRMCFG_MCID_MASK, thread_srmcfg);
+
+		if (rcid == 0 || mcid == 0) {
+			if (rcid == 0)
+				rcid = FIELD_GET(SRMCFG_RCID_MASK, default_srmcfg);
+			if (mcid == 0)
+				mcid = FIELD_GET(SRMCFG_MCID_MASK, default_srmcfg);
+			thread_srmcfg = FIELD_PREP(SRMCFG_RCID_MASK, rcid) |
+					FIELD_PREP(SRMCFG_MCID_MASK, mcid);
+		}
+	}
+
+	if (thread_srmcfg != __this_cpu_read(cpu_srmcfg)) {
+		/*
+		 * Drain stores from the outgoing task before the CSR write
+		 * so they retain the previous RCID/MCID tag at the cache
+		 * interconnect.
+		 */
+		RISCV_FENCE(rw, o);
+
+		__this_cpu_write(cpu_srmcfg, thread_srmcfg);
+		csr_write(CSR_SRMCFG, thread_srmcfg);
+		/*
+		 * Order the csrw before the new task's loads/stores so they
+		 * pick up the new tag. Zicsr 6.1.1 makes CSR writes weakly
+		 * ordered (device-output) vs memory ops. Ssqosid v1.0 is
+		 * silent so honor the general CSR rule.
+		 */
+		RISCV_FENCE(o, rw);
+	}
+}
+
+static __always_inline bool has_srmcfg(void)
+{
+	return riscv_has_extension_unlikely(RISCV_ISA_EXT_SSQOSID);
+}
+
+#else /* ! CONFIG_RISCV_ISA_SSQOSID  */
+
+struct task_struct;
+static __always_inline bool has_srmcfg(void) { return false; }
+static inline void __switch_to_srmcfg(struct task_struct *next) { }
+
+#endif /* CONFIG_RISCV_ISA_SSQOSID */
+#endif /* _ASM_RISCV_QOS_H */

arch/riscv/include/asm/resctrl.h

@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_RISCV_RESCTRL_H
+#define _ASM_RISCV_RESCTRL_H
+
+#include <linux/resctrl_types.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+
+#include <asm/qos.h>
+
+struct rdt_resource;
+
+/*
+ * Sentinel "no CLOSID assigned" used by resctrl_arch_rmid_idx_decode().
+ * fs/resctrl treats this opaquely. CBQRI uses MCID directly as the linear
+ * rmid index, so closid is unused on decode.
+ */
+#define RISCV_RESCTRL_EMPTY_CLOSID	((u32)~0)
+
+/*
+ * Terminology mapping between x86 (Intel RDT/AMD QoS) and RISC-V:
+ *
+ *  CLOSID on x86 is RCID on RISC-V
+ *    RMID on x86 is MCID on RISC-V
+ *     CDP on x86 is AT (access type) on RISC-V
+ *
+ * Each fast-path arch entry point below is the RISC-V realization of the
+ * generic contract documented in <linux/resctrl.h>. Comments here describe
+ * only the RISC-V-specific behavior (srmcfg encoding, CBQRI controller
+ * lookup, MCID-as-index policy).
+ */
+
+/**
+ * resctrl_arch_alloc_capable() - any CBQRI controller exposes resctrl alloc
+ *
+ * Returns true once at least one CBQRI controller has successfully probed for
+ * a resctrl-exposed allocation feature (cache capacity or memory bandwidth).
+ * Only meaningful after cbqri_resctrl_setup() runs at late_initcall.
+ */
+bool resctrl_arch_alloc_capable(void);
+
+/**
+ * resctrl_arch_mon_capable() - any CBQRI controller exposes resctrl monitoring
+ *
+ * Returns true once at least one CBQRI controller has successfully probed a
+ * monitoring event wired through resctrl (L3 occupancy or L3 mbm_total_bytes).
+ */
+bool resctrl_arch_mon_capable(void);
+
+/**
+ * resctrl_arch_rmid_idx_encode() - encode (RCID, MCID) into a linear index
+ * @closid: RCID (resource control id)
+ * @rmid:   MCID (monitoring counter id)
+ *
+ * RISC-V uses MCID directly as the linear index into per-RMID arrays
+ * managed by fs/resctrl, since CBQRI controllers admit any MCID for any
+ * RCID. closid is unused here. CDP is encoded via the AT field on each
+ * CBQRI op rather than via the index.
+ */
+u32  resctrl_arch_rmid_idx_encode(u32 closid, u32 rmid);
+
+/**
+ * resctrl_arch_rmid_idx_decode() - inverse of resctrl_arch_rmid_idx_encode()
+ * @idx:    linear index
+ * @closid: out: always RISCV_RESCTRL_EMPTY_CLOSID
+ * @rmid:   out: the MCID that @idx encodes
+ */
+void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid);
+
+/**
+ * resctrl_arch_set_cpu_default_closid_rmid() - install per-CPU srmcfg default
+ * @cpu:    CPU number
+ * @closid: RCID to use when no task is matched
+ * @rmid:   MCID to use when no task is matched
+ *
+ * Sets the per-CPU cpu_srmcfg_default so __switch_to_srmcfg() can fall back
+ * to the CPU's default RCID/MCID for default-group tasks (those whose
+ * thread.srmcfg encodes to 0, i.e. closid == RESCTRL_RESERVED_CLOSID and
+ * rmid == RESCTRL_RESERVED_RMID). Implements resctrl allocation rule 2
+ * ("CPU default") on RISC-V.
+ */
+void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid, u32 rmid);
+
+/**
+ * resctrl_arch_sched_in() - context-switch hook to install task RCID/MCID
+ * @tsk: the task being scheduled in
+ *
+ * Called from finish_task_switch() to write tsk->thread.srmcfg into the
+ * srmcfg CSR. Tasks tagged with RISCV_RESCTRL_EMPTY_CLOSID inherit the
+ * per-CPU default set via resctrl_arch_set_cpu_default_closid_rmid().
+ */
+void resctrl_arch_sched_in(struct task_struct *tsk);
+
+/**
+ * resctrl_arch_set_closid_rmid() - tag a task with an RCID/MCID
+ * @tsk:    task to tag
+ * @closid: RCID to install
+ * @rmid:   MCID to install
+ *
+ * Updates tsk->thread.srmcfg with the encoded (RCID, MCID) pair. The new
+ * value takes effect on the next resctrl_arch_sched_in() for this task.
+ */
+void resctrl_arch_set_closid_rmid(struct task_struct *tsk, u32 closid, u32 rmid);
+
+/**
+ * resctrl_arch_match_closid() - test whether a task carries a given RCID
+ * @tsk:    task
+ * @closid: RCID
+ */
+bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid);
+
+/**
+ * resctrl_arch_match_rmid() - test whether a task carries a given (RCID, MCID)
+ * @tsk:    task
+ * @closid: RCID
+ * @rmid:   MCID
+ */
+bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 closid, u32 rmid);
+
+/**
+ * resctrl_arch_mon_ctx_alloc() - allocate per-monitor-event arch context
+ * @r:     resctrl resource being monitored
+ * @evtid: which monitor event needs context
+ *
+ * Returns an opaque pointer that resctrl_arch_rmid_read() can use to find the
+ * CBQRI controller backing this event. CBQRI's BC bandwidth context is
+ * keyed off the resource's L3 monitoring domain rather than per-event state,
+ * so this implementation returns NULL.
+ */
+void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, enum resctrl_event_id evtid);
+
+/**
+ * resctrl_arch_mon_ctx_free() - release context returned by mon_ctx_alloc()
+ * @r:            resctrl resource
+ * @evtid:        monitor event id
+ * @arch_mon_ctx: pointer returned by resctrl_arch_mon_ctx_alloc()
+ */
+void resctrl_arch_mon_ctx_free(struct rdt_resource *r, enum resctrl_event_id evtid,
+			       void *arch_mon_ctx);
+
+static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
+{
+	return val;
+}
+
+/* Not needed for RISC-V */
+static inline void resctrl_arch_enable_mon(void) { }
+static inline void resctrl_arch_disable_mon(void) { }
+static inline void resctrl_arch_enable_alloc(void) { }
+static inline void resctrl_arch_disable_alloc(void) { }
+
+#endif /* _ASM_RISCV_RESCTRL_H */

arch/riscv/include/asm/switch_to.h

@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
+#include <asm/qos.h>
 
 #ifdef CONFIG_FPU
 extern void __fstate_save(struct task_struct *save_to);
@@ -119,6 +120,8 @@ do {							\
 		__switch_to_fpu(__prev, __next);	\
 	if (has_vector() || has_xtheadvector())		\
 		__switch_to_vector(__prev, __next);	\
+	if (has_srmcfg())				\
+		__switch_to_srmcfg(__next);		\
 	if (switch_to_should_flush_icache(__next))	\
 		local_flush_icache_all();		\
 	__switch_to_envcfg(__next);			\

arch/riscv/kernel/Makefile

@@ -128,3 +128,5 @@ obj-$(CONFIG_ACPI_NUMA)	+= acpi_numa.o
 
 obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o
 obj-$(CONFIG_RISCV_USER_CFI) += usercfi.o
+
+obj-$(CONFIG_RISCV_ISA_SSQOSID) += qos.o

arch/riscv/kernel/cpufeature.c

@@ -582,6 +582,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
 	__RISCV_ISA_EXT_SUPERSET(ssnpm, RISCV_ISA_EXT_SSNPM, riscv_xlinuxenvcfg_exts),
+	__RISCV_ISA_EXT_DATA(ssqosid, RISCV_ISA_EXT_SSQOSID),
 	__RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
 	__RISCV_ISA_EXT_DATA(svade, RISCV_ISA_EXT_SVADE),
 	__RISCV_ISA_EXT_DATA_VALIDATE(svadu, RISCV_ISA_EXT_SVADU, riscv_ext_svadu_validate),