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

With the T-HEAD C9XX cores being designed before or during the ratification
to the SSCOFPMF extension, it implements functionality very similar but
not equal to it.

It implements overflow handling and also some privilege-mode filtering.
While SSCOFPMF supports this for all modes, the C9XX only implements the
filtering for M-mode and S-mode but not user-mode.

So add some adaptions to allow the C9XX to still handle
its PMU through the regular SBI PMU interface instead of defining new
interfaces or drivers.

To work properly, this requires a matching change in SBI, though the actual
interface between kernel and SBI does not change.

The main differences are a the overflow CSR and irq number.

As the reading of the overflow-csr is in the hot-path during irq handling,
use an errata and alternatives to not introduce new conditionals there.

Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/all/20221011231841.2951264-2-heiko@sntech.de/
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

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

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;