riscv_pmu_sbi: add support for PMU variant on T-Head C9xx cores

The PMU on T-Head C9xx cores is quite similar to the SSCOFPMF extension
but not completely identical, so this series adds a T-Head PMU errata
that handlen the differences.

* 'riscv-pmu' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/palmer/linux:
  drivers/perf: riscv_pmu_sbi: add support for PMU variant on T-Head C9xx cores
  RISC-V: Cache SBI vendor values

arch/riscv/Kconfig.erratas

@@ -66,4 +66,17 @@ config ERRATA_THEAD_CMO
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD_PMU
+	bool "Apply T-Head PMU errata"
+	depends on ERRATA_THEAD && RISCV_PMU_SBI
+	default y
+	help
+	  The T-Head C9xx cores implement a PMU overflow extension very
+	  similar to the core SSCOFPMF extension.
+
+	  This will apply the overflow errata to handle the non-standard
+	  behaviour via the regular SBI PMU driver and interface.
+
+	  If you don't know what to do here, say "Y".
+
 endmenu # "CPU errata selection"

arch/riscv/errata/thead/errata.c

@@ -47,6 +47,22 @@ static bool errata_probe_cmo(unsigned int stage,
 	return true;
 }
 
+static bool errata_probe_pmu(unsigned int stage,
+			     unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PMU))
+		return false;
+
+	/* target-c9xx cores report arch_id and impid as 0 */
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	return true;
+}
+
 static u32 thead_errata_probe(unsigned int stage,
 			      unsigned long archid, unsigned long impid)
 {
@@ -58,6 +74,9 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_cmo(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
 
+	if (errata_probe_pmu(stage, archid, impid))
+		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
+
 	return cpu_req_errata;
 }
 

arch/riscv/include/asm/errata_list.h

@@ -6,6 +6,7 @@
 #define ASM_ERRATA_LIST_H
 
 #include <asm/alternative.h>
+#include <asm/csr.h>
 #include <asm/vendorid_list.h>
 
 #ifdef CONFIG_ERRATA_SIFIVE
@@ -17,7 +18,8 @@
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_PBMT 0
 #define	ERRATA_THEAD_CMO 1
-#define	ERRATA_THEAD_NUMBER 2
+#define	ERRATA_THEAD_PMU 2
+#define	ERRATA_THEAD_NUMBER 3
 #endif
 
 #define	CPUFEATURE_SVPBMT 0
@@ -142,6 +144,18 @@ asm volatile(ALTERNATIVE_2(						\
 	    "r"((unsigned long)(_start) + (_size))			\
 	: "a0")
 
+#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/sbi.h

@@ -327,4 +327,9 @@ int sbi_err_map_linux_errno(int err);
 static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
 static inline void sbi_init(void) {}
 #endif /* CONFIG_RISCV_SBI */
+
+unsigned long riscv_cached_mvendorid(unsigned int cpu_id);
+unsigned long riscv_cached_marchid(unsigned int cpu_id);
+unsigned long riscv_cached_mimpid(unsigned int cpu_id);
+
 #endif /* _ASM_RISCV_SBI_H */

arch/riscv/kernel/cpu.c

@@ -70,8 +70,6 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 	return -1;
 }
 
-#ifdef CONFIG_PROC_FS
-
 struct riscv_cpuinfo {
 	unsigned long mvendorid;
 	unsigned long marchid;
@@ -79,6 +77,30 @@ struct riscv_cpuinfo {
 };
 static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 
+unsigned long riscv_cached_mvendorid(unsigned int cpu_id)
+{
+	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
+
+	return ci->mvendorid;
+}
+EXPORT_SYMBOL(riscv_cached_mvendorid);
+
+unsigned long riscv_cached_marchid(unsigned int cpu_id)
+{
+	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
+
+	return ci->marchid;
+}
+EXPORT_SYMBOL(riscv_cached_marchid);
+
+unsigned long riscv_cached_mimpid(unsigned int cpu_id)
+{
+	struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id);
+
+	return ci->mimpid;
+}
+EXPORT_SYMBOL(riscv_cached_mimpid);
+
 static int riscv_cpuinfo_starting(unsigned int cpu)
 {
 	struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo);
@@ -113,7 +135,9 @@ static int __init riscv_cpuinfo_init(void)
 
 	return 0;
 }
-device_initcall(riscv_cpuinfo_init);
+arch_initcall(riscv_cpuinfo_init);
+
+#ifdef CONFIG_PROC_FS
 
 #define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \
 	{							\

drivers/perf/riscv_pmu_sbi.c

@@ -20,6 +20,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
 
+#include <asm/errata_list.h>
 #include <asm/sbi.h>
 #include <asm/hwcap.h>
 
@@ -47,6 +48,8 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = {
  * per_cpu in case of harts with different pmu counters
  */
 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;
 
 struct sbi_pmu_event_data {
@@ -580,7 +583,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS);
 	event = cpu_hw_evt->events[fidx];
 	if (!event) {
-		csr_clear(CSR_SIP, SIP_LCOFIP);
+		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
 		return IRQ_NONE;
 	}
 
@@ -588,13 +591,13 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	pmu_sbi_stop_hw_ctrs(pmu);
 
 	/* Overflow status register should only be read after counter are stopped */
-	overflow = csr_read(CSR_SSCOUNTOVF);
+	ALT_SBI_PMU_OVERFLOW(overflow);
 
 	/*
 	 * Overflow interrupt pending bit should only be cleared after stopping
 	 * all the counters to avoid any race condition.
 	 */
-	csr_clear(CSR_SIP, SIP_LCOFIP);
+	csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
 
 	/* No overflow bit is set */
 	if (!overflow)
@@ -661,10 +664,10 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 	/* Stop all the counters so that they can be enabled from perf */
 	pmu_sbi_stop_all(pmu);
 
-	if (riscv_isa_extension_available(NULL, SSCOFPMF)) {
+	if (riscv_pmu_use_irq) {
 		cpu_hw_evt->irq = riscv_pmu_irq;
-		csr_clear(CSR_IP, BIT(RV_IRQ_PMU));
-		csr_set(CSR_IE, BIT(RV_IRQ_PMU));
+		csr_clear(CSR_IP, BIT(riscv_pmu_irq_num));
+		csr_set(CSR_IE, BIT(riscv_pmu_irq_num));
 		enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE);
 	}
 
@@ -673,9 +676,9 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 
 static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	if (riscv_isa_extension_available(NULL, SSCOFPMF)) {
+	if (riscv_pmu_use_irq) {
 		disable_percpu_irq(riscv_pmu_irq);
-		csr_clear(CSR_IE, BIT(RV_IRQ_PMU));
+		csr_clear(CSR_IE, BIT(riscv_pmu_irq_num));
 	}
 
 	/* Disable all counters access for user mode now */
@@ -691,7 +694,18 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 	struct device_node *cpu, *child;
 	struct irq_domain *domain = NULL;
 
-	if (!riscv_isa_extension_available(NULL, SSCOFPMF))
+	if (riscv_isa_extension_available(NULL, SSCOFPMF)) {
+		riscv_pmu_irq_num = RV_IRQ_PMU;
+		riscv_pmu_use_irq = true;
+	} else if (IS_ENABLED(CONFIG_ERRATA_THEAD_PMU) &&
+		   riscv_cached_mvendorid(0) == THEAD_VENDOR_ID &&
+		   riscv_cached_marchid(0) == 0 &&
+		   riscv_cached_mimpid(0) == 0) {
+		riscv_pmu_irq_num = THEAD_C9XX_RV_IRQ_PMU;
+		riscv_pmu_use_irq = true;
+	}
+
+	if (!riscv_pmu_use_irq)
 		return -EOPNOTSUPP;
 
 	for_each_of_cpu_node(cpu) {
@@ -713,7 +727,7 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		return -ENODEV;
 	}
 
-	riscv_pmu_irq = irq_create_mapping(domain, RV_IRQ_PMU);
+	riscv_pmu_irq = irq_create_mapping(domain, riscv_pmu_irq_num);
 	if (!riscv_pmu_irq) {
 		pr_err("Failed to map PMU interrupt for node\n");
 		return -ENODEV;