perf: RISC-V: Introduce Andes PMU to support perf event sampling

Assign riscv_pmu_irq_num the value of (256 + 18) for the custome PMU
and add SSCOUNTOVF and SIP alternatives to ALT_SBI_PMU_OVERFLOW()
and ALT_SBI_PMU_OVF_CLEAR_PENDING() macros, respectively.

To make use of Andes PMU extension, "xandespmu" needs to be appended
to the riscv,isa-extensions for each cpu node in device-tree, and
make sure CONFIG_ANDES_CUSTOM_PMU is enabled.

Signed-off-by: Yu Chien Peter Lin <peterlin@andestech.com>
Reviewed-by: Charles Ci-Jyun Wu <dminus@andestech.com>
Reviewed-by: Leo Yu-Chi Liang <ycliang@andestech.com>
Co-developed-by: Locus Wei-Han Chen <locus84@andestech.com>
Signed-off-by: Locus Wei-Han Chen <locus84@andestech.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/r/20240222083946.3977135-8-peterlin@andestech.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: lyctw

arch/riscv/include/asm/errata_list.h

@@ -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

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

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);

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

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)
@@ -780,7 +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));
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE);
 	}
 
@@ -814,8 +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;