Merge patch series "Support Andes PMU extension"

palmer-dabbelt · palmer-dabbelt · commit a13a806dfb8a · 2024-03-12T07:13:21.000-07:00
Yu Chien Peter Lin <peterlin@andestech.com> says: This patch series introduces the Andes PMU extension, which serves the same purpose as Sscofpmf and Smcntrpmf. Its non-standard local interrupt is assigned to bit 18 in the custom S-mode local interrupt enable and pending registers (slie/slip), while the interrupt cause is (256 + 18). * b4-shazam-merge: riscv: andes: Support specifying symbolic firmware and hardware raw events riscv: dts: renesas: Add Andes PMU extension for r9a07g043f dt-bindings: riscv: Add Andes PMU extension description perf: RISC-V: Introduce Andes PMU to support perf event sampling perf: RISC-V: Eliminate redundant interrupt enable/disable operations riscv: dts: renesas: r9a07g043f: Update compatible string to use Andes INTC dt-bindings: riscv: Add Andes interrupt controller compatible string riscv: errata: Rename defines for Andes Link: https://lore.kernel.org/r/20240222083946.3977135-1-peterlin@andestech.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -106,7 +106,11 @@ properties:
         const: 1
 
       compatible:
-        const: riscv,cpu-intc
+        oneOf:
+          - items:
+              - const: andestech,cpu-intc
+              - const: riscv,cpu-intc
+          - const: riscv,cpu-intc
 
       interrupt-controller: true
 
diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -477,5 +477,12 @@ properties:
             latency, as ratified in commit 56ed795 ("Update
             riscv-crypto-spec-vector.adoc") of riscv-crypto.
 
+        - const: xandespmu
+          description:
+            The Andes Technology performance monitor extension for counter overflow
+            and privilege mode filtering. For more details, see Counter Related
+            Registers in the AX45MP datasheet.
+            https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf
+
 additionalProperties: true
 ...
diff --git a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi
@@ -27,7 +27,7 @@
 			riscv,isa-base = "rv64i";
 			riscv,isa-extensions = "i", "m", "a", "f", "d", "c",
 					       "zicntr", "zicsr", "zifencei",
-					       "zihpm";
+					       "zihpm", "xandespmu";
 			mmu-type = "riscv,sv39";
 			i-cache-size = <0x8000>;
 			i-cache-line-size = <0x40>;
@@ -39,7 +39,7 @@
 
 			cpu0_intc: interrupt-controller {
 				#interrupt-cells = <1>;
-				compatible = "riscv,cpu-intc";
+				compatible = "andestech,cpu-intc", "riscv,cpu-intc";
 				interrupt-controller;
 			};
 		};
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
@@ -18,9 +18,9 @@
 #include <asm/sbi.h>
 #include <asm/vendorid_list.h>
 
-#define ANDESTECH_AX45MP_MARCHID	0x8000000000008a45UL
-#define ANDESTECH_AX45MP_MIMPID		0x500UL
-#define ANDESTECH_SBI_EXT_ANDES		0x0900031E
+#define ANDES_AX45MP_MARCHID		0x8000000000008a45UL
+#define ANDES_AX45MP_MIMPID		0x500UL
+#define ANDES_SBI_EXT_ANDES		0x0900031E
 
 #define ANDES_SBI_EXT_IOCP_SW_WORKAROUND	1
 
@@ -32,7 +32,7 @@ static long ax45mp_iocp_sw_workaround(void)
 	 * ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI EXT checks if the IOCP is missing and
 	 * cache is controllable only then CMO will be applied to the platform.
 	 */
-	ret = sbi_ecall(ANDESTECH_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND,
+	ret = sbi_ecall(ANDES_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND,
 			0, 0, 0, 0, 0, 0);
 
 	return ret.error ? 0 : ret.value;
@@ -50,7 +50,7 @@ static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigne
 
 	done = true;
 
-	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
+	if (arch_id != ANDES_AX45MP_MARCHID || impid != ANDES_AX45MP_MIMPID)
 		return;
 
 	if (!ax45mp_iocp_sw_workaround())
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
@@ -12,8 +12,8 @@
 #include <asm/vendorid_list.h>
 
 #ifdef CONFIG_ERRATA_ANDES
-#define ERRATA_ANDESTECH_NO_IOCP	0
-#define ERRATA_ANDESTECH_NUMBER		1
+#define ERRATA_ANDES_NO_IOCP 0
+#define ERRATA_ANDES_NUMBER 1
 #endif
 
 #ifdef CONFIG_ERRATA_SIFIVE
@@ -112,15 +112,6 @@ asm volatile(ALTERNATIVE(						\
 #define THEAD_C9XX_RV_IRQ_PMU			17
 #define THEAD_C9XX_CSR_SCOUNTEROF		0x5c5
 
-#define ALT_SBI_PMU_OVERFLOW(__ovl)					\
-asm volatile(ALTERNATIVE(						\
-	"csrr %0, " __stringify(CSR_SSCOUNTOVF),			\
-	"csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF),		\
-		THEAD_VENDOR_ID, ERRATA_THEAD_PMU,			\
-		CONFIG_ERRATA_THEAD_PMU)				\
-	: "=r" (__ovl) :						\
-	: "memory")
-
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
@@ -80,6 +80,7 @@
 #define RISCV_ISA_EXT_ZFA		71
 #define RISCV_ISA_EXT_ZTSO		72
 #define RISCV_ISA_EXT_ZACAS		73
+#define RISCV_ISA_EXT_XANDESPMU		74
 
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
@@ -5,7 +5,7 @@
 #ifndef ASM_VENDOR_LIST_H
 #define ASM_VENDOR_LIST_H
 
-#define ANDESTECH_VENDOR_ID	0x31e
+#define ANDES_VENDOR_ID		0x31e
 #define SIFIVE_VENDOR_ID	0x489
 #define THEAD_VENDOR_ID		0x5b7
 
diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
@@ -43,7 +43,7 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info
 
 	switch (cpu_mfr_info->vendor_id) {
 #ifdef CONFIG_ERRATA_ANDES
-	case ANDESTECH_VENDOR_ID:
+	case ANDES_VENDOR_ID:
 		cpu_mfr_info->patch_func = andes_errata_patch_func;
 		break;
 #endif
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
@@ -307,6 +307,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_EXT_XANDESPMU),
 };
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
@@ -86,6 +86,20 @@ config RISCV_PMU_SBI
 	  full perf feature support i.e. counter overflow, privilege mode
 	  filtering, counter configuration.
 
+config ANDES_CUSTOM_PMU
+	bool "Andes custom PMU support"
+	depends on ARCH_RENESAS && RISCV_ALTERNATIVE && RISCV_PMU_SBI
+	default y
+	help
+	  The Andes cores implement the PMU overflow extension very
+	  similar to the standard Sscofpmf and Smcntrpmf extension.
+
+	  This will patch the overflow and pending CSRs and handle the
+	  non-standard behaviour via the regular SBI PMU driver and
+	  interface.
+
+	  If you don't know what to do here, say "Y".
+
 config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
@@ -19,11 +19,33 @@
 #include <linux/of.h>
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
+#include <linux/soc/andes/irq.h>
 
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
 #include <asm/cpufeature.h>
 
+#define ALT_SBI_PMU_OVERFLOW(__ovl)					\
+asm volatile(ALTERNATIVE_2(						\
+	"csrr %0, " __stringify(CSR_SSCOUNTOVF),			\
+	"csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF),		\
+		THEAD_VENDOR_ID, ERRATA_THEAD_PMU,			\
+		CONFIG_ERRATA_THEAD_PMU,				\
+	"csrr %0, " __stringify(ANDES_CSR_SCOUNTEROF),			\
+		0, RISCV_ISA_EXT_XANDESPMU,				\
+		CONFIG_ANDES_CUSTOM_PMU)				\
+	: "=r" (__ovl) :						\
+	: "memory")
+
+#define ALT_SBI_PMU_OVF_CLEAR_PENDING(__irq_mask)			\
+asm volatile(ALTERNATIVE(						\
+	"csrc " __stringify(CSR_IP) ", %0\n\t",				\
+	"csrc " __stringify(ANDES_CSR_SLIP) ", %0\n\t",			\
+		0, RISCV_ISA_EXT_XANDESPMU,				\
+		CONFIG_ANDES_CUSTOM_PMU)				\
+	: : "r"(__irq_mask)						\
+	: "memory")
+
 #define SYSCTL_NO_USER_ACCESS	0
 #define SYSCTL_USER_ACCESS	1
 #define SYSCTL_LEGACY		2
@@ -61,6 +83,7 @@ static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS;
 static union sbi_pmu_ctr_info *pmu_ctr_list;
 static bool riscv_pmu_use_irq;
 static unsigned int riscv_pmu_irq_num;
+static unsigned int riscv_pmu_irq_mask;
 static unsigned int riscv_pmu_irq;
 
 /* Cache the available counters in a bitmask */
@@ -694,7 +717,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 
 	event = cpu_hw_evt->events[fidx];
 	if (!event) {
-		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		return IRQ_NONE;
 	}
 
@@ -708,7 +731,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	 * Overflow interrupt pending bit should only be cleared after stopping
 	 * all the counters to avoid any race condition.
 	 */
-	csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+	ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 
 	/* No overflow bit is set */
 	if (!overflow)
@@ -780,8 +803,7 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 
 	if (riscv_pmu_use_irq) {
 		cpu_hw_evt->irq = riscv_pmu_irq;
-		csr_clear(CSR_IP, BIT(riscv_pmu_irq_num));
-		csr_set(CSR_IE, BIT(riscv_pmu_irq_num));
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE);
 	}
 
@@ -792,7 +814,6 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	if (riscv_pmu_use_irq) {
 		disable_percpu_irq(riscv_pmu_irq);
-		csr_clear(CSR_IE, BIT(riscv_pmu_irq_num));
 	}
 
 	/* Disable all counters access for user mode now */
@@ -816,8 +837,14 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		   riscv_cached_mimpid(0) == 0) {
 		riscv_pmu_irq_num = THEAD_C9XX_RV_IRQ_PMU;
 		riscv_pmu_use_irq = true;
+	} else if (riscv_isa_extension_available(NULL, XANDESPMU) &&
+		   IS_ENABLED(CONFIG_ANDES_CUSTOM_PMU)) {
+		riscv_pmu_irq_num = ANDES_SLI_CAUSE_BASE + ANDES_RV_IRQ_PMOVI;
+		riscv_pmu_use_irq = true;
 	}
 
+	riscv_pmu_irq_mask = BIT(riscv_pmu_irq_num % BITS_PER_LONG);
+
 	if (!riscv_pmu_use_irq)
 		return -EOPNOTSUPP;
 
diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json
@@ -0,0 +1,68 @@
+[
+  {
+    "ArchStdEvent": "FW_MISALIGNED_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_MISALIGNED_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_LOAD"
+  },
+  {
+    "ArchStdEvent": "FW_ACCESS_STORE"
+  },
+  {
+    "ArchStdEvent": "FW_ILLEGAL_INSN"
+  },
+  {
+    "ArchStdEvent": "FW_SET_TIMER"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_IPI_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_FENCE_I_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT"
+  },
+  {
+    "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/instructions.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/instructions.json
diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/memory.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/memory.json
diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/microarch.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/microarch.json
diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv
