Merge branch irq/riscv-ipi into irq/irqchip-next

* irq/riscv-ipi:
  : .
  : RISC-V IPI rework from Anup Patel:
  :
  : "This series aims to improve IPI support in Linux RISC-V in following ways:
  :  1) Treat IPIs as normal per-CPU interrupts instead of having custom RISC-V
  :     specific hooks. This also makes Linux RISC-V IPI support aligned with
  :     other architectures.
  :  2) Remote TLB flushes and icache flushes should prefer local IPIs instead
  :     of SBI calls whenever we have specialized hardware (such as RISC-V AIA
  :     IMSIC and RISC-V SWI) which allows S-mode software to directly inject
  :     IPIs without any assistance from M-mode runtime firmware."
  : .
  irqchip/riscv-intc: Add empty irq_eoi() for chained irq handlers
  RISC-V: Use IPIs for remote icache flush when possible
  RISC-V: Use IPIs for remote TLB flush when possible
  RISC-V: Allow marking IPIs as suitable for remote FENCEs
  RISC-V: Treat IPIs as normal Linux IRQs
  irqchip/riscv-intc: Allow drivers to directly discover INTC hwnode
  RISC-V: Clear SIP bit only when using SBI IPI operations
Signed-off-by: Marc Zyngier <maz@kernel.org>

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/irq.h

@@ -12,6 +12,10 @@
 
 #include <asm-generic/irq.h>
 
+void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void));
+
+struct fwnode_handle *riscv_get_intc_hwnode(void);
+
 extern void __init init_IRQ(void);
 
 #endif /* _ASM_RISCV_IRQ_H */

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

@@ -15,12 +15,10 @@
 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
+
+#include <linux/jump_label.h>
+
 /*
  * Mapping between linux logical cpu index and hartid.
  */
@@ -33,9 +31,6 @@ 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 +39,22 @@ 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, bool use_for_rfence);
+
+/* Check if we can use IPIs for remote FENCEs */
+DECLARE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
+#define riscv_use_ipi_for_rfence() \
+	static_branch_unlikely(&riscv_ipi_for_rfence)
 
 /* Check other CPUs stop or not */
 bool smp_crash_stop_failed(void);
@@ -85,14 +91,29 @@ 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_ipi_disable(void)
 {
 }
 
-static inline void riscv_clear_ipi(void)
+static inline bool riscv_ipi_have_virq_range(void)
+{
+	return false;
+}
+
+static inline void riscv_ipi_set_virq_range(int virq, int nr,
+					    bool use_for_rfence)
 {
 }
 
+static inline bool riscv_use_ipi_for_rfence(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)

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

@@ -7,8 +7,26 @@
 
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
+#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);
+
+void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void))
+{
+	__get_intc_node = fn;
+}
+
+struct fwnode_handle *riscv_get_intc_hwnode(void)
+{
+	if (__get_intc_node)
+		return __get_intc_node();
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
@@ -21,4 +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

+// 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, false);
+	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);
 
@@ -641,15 +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 const struct riscv_ipi_ops sbi_ipi_ops = {
-	.ipi_inject = sbi_send_cpumask_ipi
-};
-
 void __init sbi_init(void)
 {
 	int ret;
@@ -696,6 +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);
 }

arch/riscv/kernel/smp.c

@@ -13,14 +13,15 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/kexec.h>
+#include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/delay.h>
+#include <linux/irq.h>
 #include <linux/irq_work.h>
 
-#include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
@@ -44,11 +45,10 @@ void __init smp_setup_processor_id(void)
 	cpuid_to_hartid_map(0) = boot_cpu_hartid;
 }
 
-/* A collection of single bit ipi messages.  */
-static struct {
-	unsigned long stats[IPI_MAX] ____cacheline_aligned;
-	unsigned long bits ____cacheline_aligned;
-} ipi_data[NR_CPUS] __cacheline_aligned;
+static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev);
+static int ipi_virq_base __ro_after_init;
+static int nr_ipi __ro_after_init = IPI_MAX;
+static struct irq_desc *ipi_desc[IPI_MAX] __read_mostly;
 
 int riscv_hartid_to_cpuid(unsigned long hartid)
 {
@@ -100,48 +100,14 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 }
 #endif
 
-static const struct riscv_ipi_ops *ipi_ops __ro_after_init;
-
-void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
-{
-	ipi_ops = ops;
-}
-EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
-
-void riscv_clear_ipi(void)
-{
-	if (ipi_ops && ipi_ops->ipi_clear)
-		ipi_ops->ipi_clear();
-
-	csr_clear(CSR_IP, IE_SIE);
-}
-EXPORT_SYMBOL_GPL(riscv_clear_ipi);
-
 static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
 {
-	int cpu;
-
-	smp_mb__before_atomic();
-	for_each_cpu(cpu, mask)
-		set_bit(op, &ipi_data[cpu].bits);
-	smp_mb__after_atomic();
-
-	if (ipi_ops && ipi_ops->ipi_inject)
-		ipi_ops->ipi_inject(mask);
-	else
-		pr_warn("SMP: IPI inject method not available\n");
+	__ipi_send_mask(ipi_desc[op], mask);
 }
 
 static void send_ipi_single(int cpu, enum ipi_message_type op)
 {
-	smp_mb__before_atomic();
-	set_bit(op, &ipi_data[cpu].bits);
-	smp_mb__after_atomic();
-
-	if (ipi_ops && ipi_ops->ipi_inject)
-		ipi_ops->ipi_inject(cpumask_of(cpu));
-	else
-		pr_warn("SMP: IPI inject method not available\n");
+	__ipi_send_mask(ipi_desc[op], cpumask_of(cpu));
 }
 
 #ifdef CONFIG_IRQ_WORK
@@ -151,59 +117,98 @@ void arch_irq_work_raise(void)
 }
 #endif
 
-void handle_IPI(struct pt_regs *regs)
+static irqreturn_t handle_IPI(int irq, void *data)
 {
-	unsigned int cpu = smp_processor_id();
-	unsigned long *pending_ipis = &ipi_data[cpu].bits;
-	unsigned long *stats = ipi_data[cpu].stats;
+	int ipi = irq - ipi_virq_base;
+
+	switch (ipi) {
+	case IPI_RESCHEDULE:
+		scheduler_ipi();
+		break;
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
+	case IPI_CPU_STOP:
+		ipi_stop();
+		break;
+	case IPI_CPU_CRASH_STOP:
+		ipi_cpu_crash_stop(smp_processor_id(), get_irq_regs());
+		break;
+	case IPI_IRQ_WORK:
+		irq_work_run();
+		break;
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	case IPI_TIMER:
+		tick_receive_broadcast();
+		break;
+#endif
+	default:
+		pr_warn("CPU%d: unhandled IPI%d\n", smp_processor_id(), ipi);
+		break;
+	}
 
-	riscv_clear_ipi();
+	return IRQ_HANDLED;
+}
 
-	while (true) {
-		unsigned long ops;
+void riscv_ipi_enable(void)
+{
+	int i;
 
-		/* Order bit clearing and data access. */
-		mb();
+	if (WARN_ON_ONCE(!ipi_virq_base))
+		return;
 
-		ops = xchg(pending_ipis, 0);
-		if (ops == 0)
-			return;
+	for (i = 0; i < nr_ipi; i++)
+		enable_percpu_irq(ipi_virq_base + i, 0);
+}
 
-		if (ops & (1 << IPI_RESCHEDULE)) {
-			stats[IPI_RESCHEDULE]++;
-			scheduler_ipi();
-		}
+void riscv_ipi_disable(void)
+{
+	int i;
 
-		if (ops & (1 << IPI_CALL_FUNC)) {
-			stats[IPI_CALL_FUNC]++;
-			generic_smp_call_function_interrupt();
-		}
+	if (WARN_ON_ONCE(!ipi_virq_base))
+		return;
 
-		if (ops & (1 << IPI_CPU_STOP)) {
-			stats[IPI_CPU_STOP]++;
-			ipi_stop();
-		}
+	for (i = 0; i < nr_ipi; i++)
+		disable_percpu_irq(ipi_virq_base + i);
+}
 
-		if (ops & (1 << IPI_CPU_CRASH_STOP)) {
-			ipi_cpu_crash_stop(cpu, get_irq_regs());
-		}
+bool riscv_ipi_have_virq_range(void)
+{
+	return (ipi_virq_base) ? true : false;
+}
 
-		if (ops & (1 << IPI_IRQ_WORK)) {
-			stats[IPI_IRQ_WORK]++;
-			irq_work_run();
-		}
+DEFINE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
+EXPORT_SYMBOL_GPL(riscv_ipi_for_rfence);
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-		if (ops & (1 << IPI_TIMER)) {
-			stats[IPI_TIMER]++;
-			tick_receive_broadcast();
-		}
-#endif
-		BUG_ON((ops >> IPI_MAX) != 0);
+void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence)
+{
+	int i, err;
+
+	if (WARN_ON(ipi_virq_base))
+		return;
+
+	WARN_ON(nr < IPI_MAX);
+	nr_ipi = min(nr, IPI_MAX);
+	ipi_virq_base = virq;
 
-		/* Order data access and bit testing. */
-		mb();
+	/* Request IPIs */
+	for (i = 0; i < nr_ipi; i++) {
+		err = request_percpu_irq(ipi_virq_base + i, handle_IPI,
+					 "IPI", &ipi_dummy_dev);
+		WARN_ON(err);
+
+		ipi_desc[i] = irq_to_desc(ipi_virq_base + i);
+		irq_set_status_flags(ipi_virq_base + i, IRQ_HIDDEN);
 	}
+
+	/* Enabled IPIs for boot CPU immediately */
+	riscv_ipi_enable();
+
+	/* Update RFENCE static key */
+	if (use_for_rfence)
+		static_branch_enable(&riscv_ipi_for_rfence);
+	else
+		static_branch_disable(&riscv_ipi_for_rfence);
 }
 
 static const char * const ipi_names[] = {
@@ -223,7 +228,7 @@ void show_ipi_stats(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]);
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 		seq_printf(p, " %s\n", ipi_names[i]);
 	}
 }

arch/riscv/kernel/smpboot.c

@@ -30,7 +30,6 @@
 #include <asm/numa.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
-#include <asm/sbi.h>
 #include <asm/smp.h>
 
 #include "head.h"
@@ -158,12 +157,12 @@ asmlinkage __visible void smp_callin(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int curr_cpuid = smp_processor_id();
 
-	riscv_clear_ipi();
-
 	/* All kernel threads share the same mm context.  */
 	mmgrab(mm);
 	current->active_mm = mm;
 
+	riscv_ipi_enable();
+
 	store_cpu_topology(curr_cpuid);
 	notify_cpu_starting(curr_cpuid);
 	numa_add_cpu(curr_cpuid);

arch/riscv/mm/cacheflush.c

@@ -19,7 +19,7 @@ void flush_icache_all(void)
 {
 	local_flush_icache_all();
 
-	if (IS_ENABLED(CONFIG_RISCV_SBI))
+	if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
 		sbi_remote_fence_i(NULL);
 	else
 		on_each_cpu(ipi_remote_fence_i, NULL, 1);
@@ -67,7 +67,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 * with flush_icache_deferred().
 		 */
 		smp_mb();
-	} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
+	} else if (IS_ENABLED(CONFIG_RISCV_SBI) &&
+		   !riscv_use_ipi_for_rfence()) {
 		sbi_remote_fence_i(&others);
 	} else {
 		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);

arch/riscv/mm/tlbflush.c

@@ -23,14 +23,62 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
 			: "memory");
 }
 
+static inline void local_flush_tlb_range(unsigned long start,
+		unsigned long size, unsigned long stride)
+{
+	if (size <= stride)
+		local_flush_tlb_page(start);
+	else
+		local_flush_tlb_all();
+}
+
+static inline void local_flush_tlb_range_asid(unsigned long start,
+		unsigned long size, unsigned long stride, unsigned long asid)
+{
+	if (size <= stride)
+		local_flush_tlb_page_asid(start, asid);
+	else
+		local_flush_tlb_all_asid(asid);
+}
+
+static void __ipi_flush_tlb_all(void *info)
+{
+	local_flush_tlb_all();
+}
+
 void flush_tlb_all(void)
 {
-	sbi_remote_sfence_vma(NULL, 0, -1);
+	if (riscv_use_ipi_for_rfence())
+		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
+	else
+		sbi_remote_sfence_vma(NULL, 0, -1);
+}
+
+struct flush_tlb_range_data {
+	unsigned long asid;
+	unsigned long start;
+	unsigned long size;
+	unsigned long stride;
+};
+
+static void __ipi_flush_tlb_range_asid(void *info)
+{
+	struct flush_tlb_range_data *d = info;
+
+	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
+}
+
+static void __ipi_flush_tlb_range(void *info)
+{
+	struct flush_tlb_range_data *d = info;
+
+	local_flush_tlb_range(d->start, d->size, d->stride);
 }
 
-static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
-				  unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
+			      unsigned long size, unsigned long stride)
 {
+	struct flush_tlb_range_data ftd;
 	struct cpumask *cmask = mm_cpumask(mm);
 	unsigned int cpuid;
 	bool broadcast;
@@ -45,19 +93,34 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
 
 		if (broadcast) {
-			sbi_remote_sfence_vma_asid(cmask, start, size, asid);
-		} else if (size <= stride) {
-			local_flush_tlb_page_asid(start, asid);
+			if (riscv_use_ipi_for_rfence()) {
+				ftd.asid = asid;
+				ftd.start = start;
+				ftd.size = size;
+				ftd.stride = stride;
+				on_each_cpu_mask(cmask,
+						 __ipi_flush_tlb_range_asid,
+						 &ftd, 1);
+			} else
+				sbi_remote_sfence_vma_asid(cmask,
+							   start, size, asid);
 		} else {
-			local_flush_tlb_all_asid(asid);
+			local_flush_tlb_range_asid(start, size, stride, asid);
 		}
 	} else {
 		if (broadcast) {
-			sbi_remote_sfence_vma(cmask, start, size);
-		} else if (size <= stride) {
-			local_flush_tlb_page(start);
+			if (riscv_use_ipi_for_rfence()) {
+				ftd.asid = 0;
+				ftd.start = start;
+				ftd.size = size;
+				ftd.stride = stride;
+				on_each_cpu_mask(cmask,
+						 __ipi_flush_tlb_range,
+						 &ftd, 1);
+			} else
+				sbi_remote_sfence_vma(cmask, start, size);
 		} else {
-			local_flush_tlb_all();
+			local_flush_tlb_range(start, size, stride);
 		}
 	}
 
@@ -66,23 +129,23 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__sbi_tlb_flush_range(mm, 0, -1, PAGE_SIZE);
+	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+	__flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__sbi_tlb_flush_range(vma->vm_mm, start, end - start, PMD_SIZE);
+	__flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
 }
 #endif

drivers/clocksource/timer-clint.c

@@ -17,6 +17,9 @@
 #include <linux/sched_clock.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/smp.h>
 #include <linux/timex.h>
@@ -31,6 +34,7 @@
 
 /* CLINT manages IPI and Timer for RISC-V M-mode  */
 static u32 __iomem *clint_ipi_base;
+static unsigned int clint_ipi_irq;
 static u64 __iomem *clint_timer_cmp;
 static u64 __iomem *clint_timer_val;
 static unsigned long clint_timer_freq;
@@ -41,12 +45,10 @@ u64 __iomem *clint_time_val;
 EXPORT_SYMBOL(clint_time_val);
 #endif
 
-static void clint_send_ipi(const struct cpumask *target)
+#ifdef CONFIG_SMP
+static void clint_send_ipi(unsigned int cpu)
 {
-	unsigned int cpu;
-
-	for_each_cpu(cpu, target)
-		writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu));
+	writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu));
 }
 
 static void clint_clear_ipi(void)
@@ -54,10 +56,18 @@ static void clint_clear_ipi(void)
 	writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id()));
 }
 
-static struct riscv_ipi_ops clint_ipi_ops = {
-	.ipi_inject = clint_send_ipi,
-	.ipi_clear = clint_clear_ipi,
-};
+static void clint_ipi_interrupt(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
+
+	clint_clear_ipi();
+	ipi_mux_process();
+
+	chained_irq_exit(chip, desc);
+}
+#endif
 
 #ifdef CONFIG_64BIT
 #define clint_get_cycles()	readq_relaxed(clint_timer_val)
@@ -125,12 +135,19 @@ static int clint_timer_starting_cpu(unsigned int cpu)
 
 	enable_percpu_irq(clint_timer_irq,
 			  irq_get_trigger_type(clint_timer_irq));
+	enable_percpu_irq(clint_ipi_irq,
+			  irq_get_trigger_type(clint_ipi_irq));
 	return 0;
 }
 
 static int clint_timer_dying_cpu(unsigned int cpu)
 {
 	disable_percpu_irq(clint_timer_irq);
+	/*
+	 * Don't disable IPI when CPU goes offline because
+	 * the masking/unmasking of virtual IPIs is done
+	 * via generic IPI-Mux
+	 */
 	return 0;
 }
 
@@ -170,6 +187,12 @@ static int __init clint_timer_init_dt(struct device_node *np)
 			return -ENODEV;
 		}
 
+		/* Find parent irq domain and map ipi irq */
+		if (!clint_ipi_irq &&
+		    oirq.args[0] == RV_IRQ_SOFT &&
+		    irq_find_host(oirq.np))
+			clint_ipi_irq = irq_of_parse_and_map(np, i);
+
 		/* Find parent irq domain and map timer irq */
 		if (!clint_timer_irq &&
 		    oirq.args[0] == RV_IRQ_TIMER &&
@@ -177,9 +200,9 @@ static int __init clint_timer_init_dt(struct device_node *np)
 			clint_timer_irq = irq_of_parse_and_map(np, i);
 	}
 
-	/* If CLINT timer irq not found then fail */
-	if (!clint_timer_irq) {
-		pr_err("%pOFP: timer irq not found\n", np);
+	/* If CLINT ipi or timer irq not found then fail */
+	if (!clint_ipi_irq || !clint_timer_irq) {
+		pr_err("%pOFP: ipi/timer irq not found\n", np);
 		return -ENODEV;
 	}
 
@@ -219,6 +242,19 @@ static int __init clint_timer_init_dt(struct device_node *np)
 		goto fail_iounmap;
 	}
 
+#ifdef CONFIG_SMP
+	rc = ipi_mux_create(BITS_PER_BYTE, clint_send_ipi);
+	if (rc <= 0) {
+		pr_err("unable to create muxed IPIs\n");
+		rc = (rc < 0) ? rc : -ENODEV;
+		goto fail_free_irq;
+	}
+
+	irq_set_chained_handler(clint_ipi_irq, clint_ipi_interrupt);
+	riscv_ipi_set_virq_range(rc, BITS_PER_BYTE, true);
+	clint_clear_ipi();
+#endif
+
 	rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING,
 				"clockevents/clint/timer:starting",
 				clint_timer_starting_cpu,
@@ -228,13 +264,10 @@ static int __init clint_timer_init_dt(struct device_node *np)
 		goto fail_free_irq;
 	}
 
-	riscv_set_ipi_ops(&clint_ipi_ops);
-	clint_clear_ipi();
-
 	return 0;
 
 fail_free_irq:
-	free_irq(clint_timer_irq, &clint_clock_event);
+	free_percpu_irq(clint_timer_irq, &clint_clock_event);
 fail_iounmap:
 	iounmap(base);
 	return rc;

drivers/irqchip/Kconfig

@@ -537,6 +537,7 @@ config TI_PRUSS_INTC
 config RISCV_INTC
 	bool
 	depends on RISCV
+	select IRQ_DOMAIN_HIERARCHY
 
 config SIFIVE_PLIC
 	bool

drivers/irqchip/irq-riscv-intc.c

@@ -26,20 +26,7 @@ static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
 	if (unlikely(cause >= BITS_PER_LONG))
 		panic("unexpected interrupt cause");
 
-	switch (cause) {
-#ifdef CONFIG_SMP
-	case RV_IRQ_SOFT:
-		/*
-		 * We only use software interrupts to pass IPIs, so if a
-		 * non-SMP system gets one, then we don't know what to do.
-		 */
-		handle_IPI(regs);
-		break;
-#endif
-	default:
-		generic_handle_domain_irq(intc_domain, cause);
-		break;
-	}
+	generic_handle_domain_irq(intc_domain, cause);
 }
 
 /*
@@ -59,22 +46,27 @@ static void riscv_intc_irq_unmask(struct irq_data *d)
 	csr_set(CSR_IE, BIT(d->hwirq));
 }
 
-static int riscv_intc_cpu_starting(unsigned int cpu)
-{
-	csr_set(CSR_IE, BIT(RV_IRQ_SOFT));
-	return 0;
-}
-
-static int riscv_intc_cpu_dying(unsigned int cpu)
+static void riscv_intc_irq_eoi(struct irq_data *d)
 {
-	csr_clear(CSR_IE, BIT(RV_IRQ_SOFT));
-	return 0;
+	/*
+	 * The RISC-V INTC driver uses handle_percpu_devid_irq() flow
+	 * for the per-HART local interrupts and child irqchip drivers
+	 * (such as PLIC, SBI IPI, CLINT, APLIC, IMSIC, etc) implement
+	 * chained handlers for the per-HART local interrupts.
+	 *
+	 * In the absence of irq_eoi(), the chained_irq_enter() and
+	 * chained_irq_exit() functions (used by child irqchip drivers)
+	 * will do unnecessary mask/unmask of per-HART local interrupts
+	 * at the time of handling interrupts. To avoid this, we provide
+	 * an empty irq_eoi() callback for RISC-V INTC irqchip.
+	 */
 }
 
 static struct irq_chip riscv_intc_chip = {
 	.name = "RISC-V INTC",
 	.irq_mask = riscv_intc_irq_mask,
 	.irq_unmask = riscv_intc_irq_unmask,
+	.irq_eoi = riscv_intc_irq_eoi,
 };
 
 static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq,
@@ -87,11 +79,39 @@ static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
+static int riscv_intc_domain_alloc(struct irq_domain *domain,
+				   unsigned int virq, unsigned int nr_irqs,
+				   void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_fwspec *fwspec = arg;
+
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = riscv_intc_domain_map(domain, virq + i, hwirq + i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static const struct irq_domain_ops riscv_intc_domain_ops = {
 	.map	= riscv_intc_domain_map,
 	.xlate	= irq_domain_xlate_onecell,
+	.alloc	= riscv_intc_domain_alloc
 };
 
+static struct fwnode_handle *riscv_intc_hwnode(void)
+{
+	return intc_domain->fwnode;
+}
+
 static int __init riscv_intc_init(struct device_node *node,
 				  struct device_node *parent)
 {
@@ -126,10 +146,7 @@ static int __init riscv_intc_init(struct device_node *node,
 		return rc;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_STARTING,
-			  "irqchip/riscv/intc:starting",
-			  riscv_intc_cpu_starting,
-			  riscv_intc_cpu_dying);
+	riscv_set_intc_hwnode_fn(riscv_intc_hwnode);
 
 	pr_info("%d local interrupts mapped\n", BITS_PER_LONG);