RISC-V: Treat IPIs as normal Linux IRQs

Currently, the RISC-V kernel provides arch specific hooks (i.e.
struct riscv_ipi_ops) to register IPI handling methods. The stats
gathering of IPIs is also arch specific in the RISC-V kernel.

Other architectures (such as ARM, ARM64, and MIPS) have moved away
from custom arch specific IPI handling methods. Currently, these
architectures have Linux irqchip drivers providing a range of Linux
IRQ numbers to be used as IPIs and IPI triggering is done using
generic IPI APIs. This approach allows architectures to treat IPIs
as normal Linux IRQs and IPI stats gathering is done by the generic
Linux IRQ subsystem.

We extend the RISC-V IPI handling as-per above approach so that arch
specific IPI handling methods (struct riscv_ipi_ops) can be removed
and the IPI handling is done through the Linux IRQ subsystem.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230328035223.1480939-4-apatel@ventanamicro.com

Author: avpatel

arch/riscv/Kconfig

@@ -63,6 +63,8 @@ config RISCV
 	select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IOREMAP if MMU
+	select GENERIC_IRQ_IPI if SMP
+	select GENERIC_IRQ_IPI_MUX if SMP
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL

arch/riscv/include/asm/sbi.h

@@ -271,8 +271,7 @@ long sbi_get_marchid(void);
 long sbi_get_mimpid(void);
 void sbi_set_timer(uint64_t stime_value);
 void sbi_shutdown(void);
-void sbi_clear_ipi(void);
-int sbi_send_ipi(const struct cpumask *cpu_mask);
+void sbi_send_ipi(unsigned int cpu);
 int sbi_remote_fence_i(const struct cpumask *cpu_mask);
 int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
 			   unsigned long start,
@@ -335,4 +334,10 @@ 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);
 
+#if IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_RISCV_SBI)
+void sbi_ipi_init(void);
+#else
+static inline void sbi_ipi_init(void) { }
+#endif
+
 #endif /* _ASM_RISCV_SBI_H */

arch/riscv/include/asm/smp.h

@@ -15,11 +15,6 @@
 struct seq_file;
 extern unsigned long boot_cpu_hartid;
 
-struct riscv_ipi_ops {
-	void (*ipi_inject)(const struct cpumask *target);
-	void (*ipi_clear)(void);
-};
-
 #ifdef CONFIG_SMP
 /*
  * Mapping between linux logical cpu index and hartid.
@@ -33,9 +28,6 @@ void show_ipi_stats(struct seq_file *p, int prec);
 /* SMP initialization hook for setup_arch */
 void __init setup_smp(void);
 
-/* Called from C code, this handles an IPI. */
-void handle_IPI(struct pt_regs *regs);
-
 /* Hook for the generic smp_call_function_many() routine. */
 void arch_send_call_function_ipi_mask(struct cpumask *mask);
 
@@ -44,11 +36,17 @@ void arch_send_call_function_single_ipi(int cpu);
 
 int riscv_hartid_to_cpuid(unsigned long hartid);
 
-/* Set custom IPI operations */
-void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops);
+/* Enable IPI for CPU hotplug */
+void riscv_ipi_enable(void);
+
+/* Disable IPI for CPU hotplug */
+void riscv_ipi_disable(void);
 
-/* Clear IPI for current CPU */
-void riscv_clear_ipi(void);
+/* Check if IPI interrupt numbers are available */
+bool riscv_ipi_have_virq_range(void);
+
+/* Set the IPI interrupt numbers for arch (called by irqchip drivers) */
+void riscv_ipi_set_virq_range(int virq, int nr);
 
 /* Check other CPUs stop or not */
 bool smp_crash_stop_failed(void);
@@ -85,11 +83,20 @@ static inline unsigned long cpuid_to_hartid_map(int cpu)
 	return boot_cpu_hartid;
 }
 
-static inline void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
+static inline void riscv_ipi_enable(void)
 {
 }
 
-static inline void riscv_clear_ipi(void)
+static inline void riscv_ipi_disable(void)
+{
+}
+
+static inline bool riscv_ipi_have_virq_range(void)
+{
+	return false;
+}
+
+static inline void riscv_ipi_set_virq_range(int virq, int nr)
 {
 }
 

arch/riscv/kernel/Makefile

@@ -74,6 +74,7 @@ obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 obj-$(CONFIG_RISCV_SBI)		+= sbi.o
 ifeq ($(CONFIG_RISCV_SBI), y)
+obj-$(CONFIG_SMP)		+= sbi-ipi.o
 obj-$(CONFIG_SMP) += cpu_ops_sbi.o
 endif
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o

arch/riscv/kernel/cpu-hotplug.c

@@ -13,7 +13,7 @@
 #include <asm/irq.h>
 #include <asm/cpu_ops.h>
 #include <asm/numa.h>
-#include <asm/sbi.h>
+#include <asm/smp.h>
 
 bool cpu_has_hotplug(unsigned int cpu)
 {
@@ -43,6 +43,7 @@ int __cpu_disable(void)
 	remove_cpu_topology(cpu);
 	numa_remove_cpu(cpu);
 	set_cpu_online(cpu, false);
+	riscv_ipi_disable();
 	irq_migrate_all_off_this_cpu();
 
 	return ret;

arch/riscv/kernel/irq.c

@@ -10,7 +10,7 @@
 #include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
-#include <asm/smp.h>
+#include <asm/sbi.h>
 
 static struct fwnode_handle *(*__get_intc_node)(void);
 
@@ -39,4 +39,5 @@ void __init init_IRQ(void)
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
+	sbi_ipi_init();
 }

arch/riscv/kernel/sbi-ipi.c

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Multiplex several IPIs over a single HW IPI.
+ *
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "riscv: " fmt
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <asm/sbi.h>
+
+static int sbi_ipi_virq;
+
+static void sbi_ipi_handle(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
+
+	csr_clear(CSR_IP, IE_SIE);
+	ipi_mux_process();
+
+	chained_irq_exit(chip, desc);
+}
+
+static int sbi_ipi_starting_cpu(unsigned int cpu)
+{
+	enable_percpu_irq(sbi_ipi_virq, irq_get_trigger_type(sbi_ipi_virq));
+	return 0;
+}
+
+void __init sbi_ipi_init(void)
+{
+	int virq;
+	struct irq_domain *domain;
+
+	if (riscv_ipi_have_virq_range())
+		return;
+
+	domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(),
+					  DOMAIN_BUS_ANY);
+	if (!domain) {
+		pr_err("unable to find INTC IRQ domain\n");
+		return;
+	}
+
+	sbi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT);
+	if (!sbi_ipi_virq) {
+		pr_err("unable to create INTC IRQ mapping\n");
+		return;
+	}
+
+	virq = ipi_mux_create(BITS_PER_BYTE, sbi_send_ipi);
+	if (virq <= 0) {
+		pr_err("unable to create muxed IPIs\n");
+		irq_dispose_mapping(sbi_ipi_virq);
+		return;
+	}
+
+	irq_set_chained_handler(sbi_ipi_virq, sbi_ipi_handle);
+
+	/*
+	 * Don't disable IPI when CPU goes offline because
+	 * the masking/unmasking of virtual IPIs is done
+	 * via generic IPI-Mux
+	 */
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+			  "irqchip/sbi-ipi:starting",
+			  sbi_ipi_starting_cpu, NULL);
+
+	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
+	pr_info("providing IPIs using SBI IPI extension\n");
+}

arch/riscv/kernel/sbi.c

@@ -17,7 +17,7 @@ unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
 EXPORT_SYMBOL(sbi_spec_version);
 
 static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init;
-static int (*__sbi_send_ipi)(const struct cpumask *cpu_mask) __ro_after_init;
+static void (*__sbi_send_ipi)(unsigned int cpu) __ro_after_init;
 static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask,
 			   unsigned long start, unsigned long size,
 			   unsigned long arg4, unsigned long arg5) __ro_after_init;
@@ -130,17 +130,6 @@ void sbi_shutdown(void)
 }
 EXPORT_SYMBOL(sbi_shutdown);
 
-/**
- * sbi_clear_ipi() - Clear any pending IPIs for the calling hart.
- *
- * Return: None
- */
-void sbi_clear_ipi(void)
-{
-	sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0);
-}
-EXPORT_SYMBOL(sbi_clear_ipi);
-
 /**
  * __sbi_set_timer_v01() - Program the timer for next timer event.
  * @stime_value: The value after which next timer event should fire.
@@ -157,17 +146,12 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
 #endif
 }
 
-static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
+static void __sbi_send_ipi_v01(unsigned int cpu)
 {
-	unsigned long hart_mask;
-
-	if (!cpu_mask || cpumask_empty(cpu_mask))
-		cpu_mask = cpu_online_mask;
-	hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
-
+	unsigned long hart_mask =
+		__sbi_v01_cpumask_to_hartmask(cpumask_of(cpu));
 	sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask),
 		  0, 0, 0, 0, 0);
-	return 0;
 }
 
 static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
@@ -216,12 +200,10 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
 		sbi_major_version(), sbi_minor_version());
 }
 
-static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
+static void __sbi_send_ipi_v01(unsigned int cpu)
 {
 	pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
 		sbi_major_version(), sbi_minor_version());
-
-	return 0;
 }
 
 static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
@@ -248,55 +230,18 @@ static void __sbi_set_timer_v02(uint64_t stime_value)
 #endif
 }
 
-static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask)
+static void __sbi_send_ipi_v02(unsigned int cpu)
 {
-	unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0;
-	struct sbiret ret = {0};
 	int result;
+	struct sbiret ret = {0};
 
-	if (!cpu_mask || cpumask_empty(cpu_mask))
-		cpu_mask = cpu_online_mask;
-
-	for_each_cpu(cpuid, cpu_mask) {
-		hartid = cpuid_to_hartid_map(cpuid);
-		if (hmask) {
-			if (hartid + BITS_PER_LONG <= htop ||
-			    hbase + BITS_PER_LONG <= hartid) {
-				ret = sbi_ecall(SBI_EXT_IPI,
-						SBI_EXT_IPI_SEND_IPI, hmask,
-						hbase, 0, 0, 0, 0);
-				if (ret.error)
-					goto ecall_failed;
-				hmask = 0;
-			} else if (hartid < hbase) {
-				/* shift the mask to fit lower hartid */
-				hmask <<= hbase - hartid;
-				hbase = hartid;
-			}
-		}
-		if (!hmask) {
-			hbase = hartid;
-			htop = hartid;
-		} else if (hartid > htop) {
-			htop = hartid;
-		}
-		hmask |= BIT(hartid - hbase);
-	}
-
-	if (hmask) {
-		ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
-				hmask, hbase, 0, 0, 0, 0);
-		if (ret.error)
-			goto ecall_failed;
+	ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
+			1UL, cpuid_to_hartid_map(cpu), 0, 0, 0, 0);
+	if (ret.error) {
+		result = sbi_err_map_linux_errno(ret.error);
+		pr_err("%s: hbase = [%lu] failed (error [%d])\n",
+			__func__, cpuid_to_hartid_map(cpu), result);
 	}
-
-	return 0;
-
-ecall_failed:
-	result = sbi_err_map_linux_errno(ret.error);
-	pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
-	       __func__, hbase, hmask, result);
-	return result;
 }
 
 static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask,
@@ -410,13 +355,11 @@ void sbi_set_timer(uint64_t stime_value)
 
 /**
  * sbi_send_ipi() - Send an IPI to any hart.
- * @cpu_mask: A cpu mask containing all the target harts.
- *
- * Return: 0 on success, appropriate linux error code otherwise.
+ * @cpu: Logical id of the target CPU.
  */
-int sbi_send_ipi(const struct cpumask *cpu_mask)
+void sbi_send_ipi(unsigned int cpu)
 {
-	return __sbi_send_ipi(cpu_mask);
+	__sbi_send_ipi(cpu);
 }
 EXPORT_SYMBOL(sbi_send_ipi);
 
@@ -641,21 +584,6 @@ long sbi_get_mimpid(void)
 }
 EXPORT_SYMBOL_GPL(sbi_get_mimpid);
 
-static void sbi_send_cpumask_ipi(const struct cpumask *target)
-{
-	sbi_send_ipi(target);
-}
-
-static void sbi_ipi_clear(void)
-{
-	csr_clear(CSR_IP, IE_SIE);
-}
-
-static const struct riscv_ipi_ops sbi_ipi_ops = {
-	.ipi_inject = sbi_send_cpumask_ipi,
-	.ipi_clear = sbi_ipi_clear
-};
-
 void __init sbi_init(void)
 {
 	int ret;
@@ -702,6 +630,4 @@ void __init sbi_init(void)
 		__sbi_send_ipi	= __sbi_send_ipi_v01;
 		__sbi_rfence	= __sbi_rfence_v01;
 	}
-
-	riscv_set_ipi_ops(&sbi_ipi_ops);
 }