Merge remote-tracking branch 'origin/irq/ipi-as-irq' into irq/irqchip-next

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm/Kconfig

@@ -49,6 +49,7 @@ config ARM
 	select GENERIC_ARCH_TOPOLOGY if ARM_CPU_TOPOLOGY
 	select GENERIC_ATOMIC64 if CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_IRQ_IPI if SMP
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP

arch/arm/include/asm/hardirq.h

@@ -6,29 +6,12 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-/* number of IPIS _not_ including IPI_CPU_BACKTRACE */
-#define NR_IPI	7
-
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_SMP
-	unsigned int ipi_irqs[NR_IPI];
-#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
-#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
-
-#ifdef CONFIG_SMP
-u64 smp_irq_stat_cpu(unsigned int cpu);
-#else
-#define smp_irq_stat_cpu(cpu)	0
-#endif
-
-#define arch_irq_stat_cpu	smp_irq_stat_cpu
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 #endif /* __ASM_HARDIRQ_H */

arch/arm/include/asm/smp.h

@@ -39,11 +39,10 @@ void handle_IPI(int ipinr, struct pt_regs *regs);
  */
 extern void smp_init_cpus(void);
 
-
 /*
- * Provide a function to raise an IPI cross call on CPUs in callmap.
+ * Register IPI interrupts with the arch SMP code
  */
-extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
+extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
 
 /*
  * Called from platform specific assembly code, this is the

arch/arm/kernel/irq.c

@@ -18,7 +18,6 @@
  *  IRQ's are in fact implemented a bit like signal handlers for the kernel.
  *  Naturally it's not a 1:1 relation, but there are similarities.
  */
-#include <linux/kernel_stat.h>
 #include <linux/signal.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>

arch/arm/kernel/smp.c

@@ -26,6 +26,7 @@
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
 #include <linux/irq_work.h>
+#include <linux/kernel_stat.h>
 
 #include <linux/atomic.h>
 #include <asm/bugs.h>
@@ -65,18 +66,27 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
+	NR_IPI,
 	/*
 	 * CPU_BACKTRACE is special and not included in NR_IPI
 	 * or tracable with trace_ipi_*
 	 */
-	IPI_CPU_BACKTRACE,
+	IPI_CPU_BACKTRACE = NR_IPI,
 	/*
 	 * SGI8-15 can be reserved by secure firmware, and thus may
 	 * not be usable by the kernel. Please keep the above limited
 	 * to at most 8 entries.
 	 */
+	MAX_IPI
 };
 
+static int ipi_irq_base __read_mostly;
+static int nr_ipi __read_mostly = NR_IPI;
+static struct irq_desc *ipi_desc[MAX_IPI] __read_mostly;
+
+static void ipi_setup(int cpu);
+static void ipi_teardown(int cpu);
+
 static DECLARE_COMPLETION(cpu_running);
 
 static struct smp_operations smp_ops __ro_after_init;
@@ -247,6 +257,7 @@ int __cpu_disable(void)
 	 * and we must not schedule until we're ready to give up the cpu.
 	 */
 	set_cpu_online(cpu, false);
+	ipi_teardown(cpu);
 
 	/*
 	 * OK - migrate IRQs away from this CPU
@@ -422,6 +433,8 @@ asmlinkage void secondary_start_kernel(void)
 
 	notify_cpu_starting(cpu);
 
+	ipi_setup(cpu);
+
 	calibrate_delay();
 
 	smp_store_cpu_info(cpu);
@@ -500,14 +513,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	if (!__smp_cross_call)
-		__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 #define S(x,s)	[x] = s
 	S(IPI_WAKEUP, "CPU wakeup interrupts"),
@@ -519,38 +524,23 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_COMPLETION, "completion interrupts"),
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
 
 void show_ipi_list(struct seq_file *p, int prec)
 {
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
+		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}
 }
 
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
-
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
-}
-
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	smp_cross_call(mask, IPI_CALL_FUNC);
@@ -627,15 +617,12 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 	handle_IPI(ipinr, regs);
 }
 
-void handle_IPI(int ipinr, struct pt_regs *regs)
+static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
-	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	if ((unsigned)ipinr < NR_IPI) {
+	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
-		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
-	}
 
 	switch (ipinr) {
 	case IPI_WAKEUP:
@@ -643,9 +630,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
-		irq_enter();
 		tick_receive_broadcast();
-		irq_exit();
 		break;
 #endif
 
@@ -654,36 +639,26 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_CALL_FUNC:
-		irq_enter();
 		generic_smp_call_function_interrupt();
-		irq_exit();
 		break;
 
 	case IPI_CPU_STOP:
-		irq_enter();
 		ipi_cpu_stop(cpu);
-		irq_exit();
 		break;
 
 #ifdef CONFIG_IRQ_WORK
 	case IPI_IRQ_WORK:
-		irq_enter();
 		irq_work_run();
-		irq_exit();
 		break;
 #endif
 
 	case IPI_COMPLETION:
-		irq_enter();
 		ipi_complete(cpu);
-		irq_exit();
 		break;
 
 	case IPI_CPU_BACKTRACE:
 		printk_nmi_enter();
-		irq_enter();
-		nmi_cpu_backtrace(regs);
-		irq_exit();
+		nmi_cpu_backtrace(get_irq_regs());
 		printk_nmi_exit();
 		break;
 
@@ -695,9 +670,78 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+}
+
+/* Legacy version, should go away once all irqchips have been converted */
+void handle_IPI(int ipinr, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	irq_enter();
+	do_handle_IPI(ipinr);
+	irq_exit();
+
 	set_irq_regs(old_regs);
 }
 
+static irqreturn_t ipi_handler(int irq, void *data)
+{
+	do_handle_IPI(irq - ipi_irq_base);
+	return IRQ_HANDLED;
+}
+
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
+{
+	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
+}
+
+static void ipi_setup(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		enable_percpu_irq(ipi_irq_base + i, 0);
+}
+
+static void ipi_teardown(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		disable_percpu_irq(ipi_irq_base + i);
+}
+
+void __init set_smp_ipi_range(int ipi_base, int n)
+{
+	int i;
+
+	WARN_ON(n < MAX_IPI);
+	nr_ipi = min(n, MAX_IPI);
+
+	for (i = 0; i < nr_ipi; i++) {
+		int err;
+
+		err = request_percpu_irq(ipi_base + i, ipi_handler,
+					 "IPI", &irq_stat);
+		WARN_ON(err);
+
+		ipi_desc[i] = irq_to_desc(ipi_base + i);
+		irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
+	}
+
+	ipi_irq_base = ipi_base;
+
+	/* Setup the boot CPU immediately */
+	ipi_setup(smp_processor_id());
+}
+
 void smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
@@ -805,7 +849,7 @@ core_initcall(register_cpufreq_notifier);
 
 static void raise_nmi(cpumask_t *mask)
 {
-	__smp_cross_call(mask, IPI_CPU_BACKTRACE);
+	__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
 }
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)

arch/arm64/Kconfig

@@ -106,6 +106,7 @@ config ARM64
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_IPI
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW

arch/arm64/include/asm/hardirq.h

@@ -13,21 +13,12 @@
 #include <asm/kvm_arm.h>
 #include <asm/sysreg.h>
 
-#define NR_IPI	7
-
 typedef struct {
 	unsigned int __softirq_pending;
-	unsigned int ipi_irqs[NR_IPI];
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
-#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
-
-u64 smp_irq_stat_cpu(unsigned int cpu);
-#define arch_irq_stat_cpu	smp_irq_stat_cpu
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 struct nmi_ctx {

arch/arm64/include/asm/irq_work.h

@@ -2,11 +2,9 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-#include <asm/smp.h>
-
 static inline bool arch_irq_work_has_interrupt(void)
 {
-	return !!__smp_cross_call;
+	return true;
 }
 
 #endif /* __ASM_IRQ_WORK_H */

arch/arm64/include/asm/smp.h

@@ -55,16 +55,6 @@ static inline void set_cpu_logical_map(int cpu, u64 hwid)
 
 struct seq_file;
 
-/*
- * generate IPI list text
- */
-extern void show_ipi_list(struct seq_file *p, int prec);
-
-/*
- * Called from C code, this handles an IPI.
- */
-extern void handle_IPI(int ipinr, struct pt_regs *regs);
-
 /*
  * Discover the set of possible CPUs and determine their
  * SMP operations.
@@ -72,11 +62,9 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs);
 extern void smp_init_cpus(void);
 
 /*
- * Provide a function to raise an IPI cross call on CPUs in callmap.
+ * Register IPI interrupts with the arch SMP code
  */
-extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
-
-extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
 
 /*
  * Called from the secondary holding pen, this is the secondary CPU entry point.

arch/arm64/kernel/irq.c

@@ -10,10 +10,10 @@
  * Copyright (C) 2012 ARM Ltd.
  */
 
-#include <linux/kernel_stat.h>
 #include <linux/irq.h>
 #include <linux/memory.h>
 #include <linux/smp.h>
+#include <linux/hardirq.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/kprobes.h>
@@ -22,20 +22,11 @@
 #include <asm/daifflags.h>
 #include <asm/vmap_stack.h>
 
-unsigned long irq_err_count;
-
 /* Only access this in an NMI enter/exit */
 DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
 
 DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
-int arch_show_interrupts(struct seq_file *p, int prec)
-{
-	show_ipi_list(p, prec);
-	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
-	return 0;
-}
-
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {

arch/arm64/kernel/smp.c

@@ -30,6 +30,7 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/kernel_stat.h>
 #include <linux/kexec.h>
 #include <linux/kvm_host.h>
 
@@ -72,9 +73,17 @@ enum ipi_msg_type {
 	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP
+	IPI_WAKEUP,
+	NR_IPI
 };
 
+static int ipi_irq_base __read_mostly;
+static int nr_ipi __read_mostly = NR_IPI;
+static struct irq_desc *ipi_desc[NR_IPI] __read_mostly;
+
+static void ipi_setup(int cpu);
+static void ipi_teardown(int cpu);
+
 #ifdef CONFIG_HOTPLUG_CPU
 static int op_cpu_kill(unsigned int cpu);
 #else
@@ -237,6 +246,8 @@ asmlinkage notrace void secondary_start_kernel(void)
 	 */
 	notify_cpu_starting(cpu);
 
+	ipi_setup(cpu);
+
 	store_cpu_topology(cpu);
 	numa_add_cpu(cpu);
 
@@ -302,6 +313,7 @@ int __cpu_disable(void)
 	 * and we must not schedule until we're ready to give up the cpu.
 	 */
 	set_cpu_online(cpu, false);
+	ipi_teardown(cpu);
 
 	/*
 	 * OK - migrate IRQs away from this CPU
@@ -772,13 +784,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 #define S(x,s)	[x] = s
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
@@ -790,35 +795,25 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
 
-void show_ipi_list(struct seq_file *p, int prec)
+unsigned long irq_err_count;
+
+int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
+		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
-}
 
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
-
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
+	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
+	return 0;
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -841,8 +836,7 @@ void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	if (__smp_cross_call)
-		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+	smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
 }
 #endif
 
@@ -890,15 +884,12 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 /*
  * Main handler for inter-processor interrupts
  */
-void handle_IPI(int ipinr, struct pt_regs *regs)
+static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
-	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	if ((unsigned)ipinr < NR_IPI) {
+	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
-		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
-	}
 
 	switch (ipinr) {
 	case IPI_RESCHEDULE:
@@ -906,21 +897,16 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_CALL_FUNC:
-		irq_enter();
 		generic_smp_call_function_interrupt();
-		irq_exit();
 		break;
 
 	case IPI_CPU_STOP:
-		irq_enter();
 		local_cpu_stop();
-		irq_exit();
 		break;
 
 	case IPI_CPU_CRASH_STOP:
 		if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
-			irq_enter();
-			ipi_cpu_crash_stop(cpu, regs);
+			ipi_cpu_crash_stop(cpu, get_irq_regs());
 
 			unreachable();
 		}
@@ -928,17 +914,13 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
-		irq_enter();
 		tick_receive_broadcast();
-		irq_exit();
 		break;
 #endif
 
 #ifdef CONFIG_IRQ_WORK
 	case IPI_IRQ_WORK:
-		irq_enter();
 		irq_work_run();
-		irq_exit();
 		break;
 #endif
 
@@ -957,7 +939,64 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
-	set_irq_regs(old_regs);
+}
+
+static irqreturn_t ipi_handler(int irq, void *data)
+{
+	do_handle_IPI(irq - ipi_irq_base);
+	return IRQ_HANDLED;
+}
+
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
+{
+	trace_ipi_raise(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
+}
+
+static void ipi_setup(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		enable_percpu_irq(ipi_irq_base + i, 0);
+}
+
+static void ipi_teardown(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		disable_percpu_irq(ipi_irq_base + i);
+}
+
+void __init set_smp_ipi_range(int ipi_base, int n)
+{
+	int i;
+
+	WARN_ON(n < NR_IPI);
+	nr_ipi = min(n, NR_IPI);
+
+	for (i = 0; i < nr_ipi; i++) {
+		int err;
+
+		err = request_percpu_irq(ipi_base + i, ipi_handler,
+					 "IPI", &cpu_number);
+		WARN_ON(err);
+
+		ipi_desc[i] = irq_to_desc(ipi_base + i);
+		irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
+	}
+
+	ipi_irq_base = ipi_base;
+
+	/* Setup the boot CPU immediately */
+	ipi_setup(smp_processor_id());
 }
 
 void smp_send_reschedule(int cpu)

drivers/irqchip/irq-armada-370-xp.c

@@ -310,7 +310,134 @@ static inline int armada_370_xp_msi_init(struct device_node *node,
 }
 #endif
 
+static void armada_xp_mpic_perf_init(void)
+{
+	unsigned long cpuid = cpu_logical_map(smp_processor_id());
+
+	/* Enable Performance Counter Overflow interrupts */
+	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
+	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
+}
+
 #ifdef CONFIG_SMP
+static struct irq_domain *ipi_domain;
+
+static void armada_370_xp_ipi_mask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg &= ~BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_unmask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg |= BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_send_mask(struct irq_data *d,
+					const struct cpumask *mask)
+{
+	unsigned long map = 0;
+	int cpu;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
+	/* submit softirq */
+	writel((map << 8) | d->hwirq, main_int_base +
+		ARMADA_370_XP_SW_TRIG_INT_OFFS);
+}
+
+static void armada_370_xp_ipi_eoi(struct irq_data *d)
+{
+	writel(~BIT(d->hwirq), per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+}
+
+static struct irq_chip ipi_irqchip = {
+	.name		= "IPI",
+	.irq_mask	= armada_370_xp_ipi_mask,
+	.irq_unmask	= armada_370_xp_ipi_unmask,
+	.irq_eoi	= armada_370_xp_ipi_eoi,
+	.ipi_send_mask	= armada_370_xp_ipi_send_mask,
+};
+
+static int armada_370_xp_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &ipi_irqchip,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void armada_370_xp_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= armada_370_xp_ipi_alloc,
+	.free	= armada_370_xp_ipi_free,
+};
+
+static void ipi_resume(void)
+{
+	int i;
+
+	for (i = 0; i < IPI_DOORBELL_END; i++) {
+		int irq;
+
+		irq = irq_find_mapping(ipi_domain, i);
+		if (irq <= 0)
+			continue;
+		if (irq_percpu_is_enabled(irq)) {
+			struct irq_data *d;
+			d = irq_domain_get_irq_data(ipi_domain, irq);
+			armada_370_xp_ipi_unmask(d);
+		}
+	}
+}
+
+static __init void armada_xp_ipi_init(struct device_node *node)
+{
+	int base_ipi;
+
+	ipi_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+					      IPI_DOORBELL_END,
+					      &ipi_domain_ops, NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, IPI_DOORBELL_END,
+					   NUMA_NO_NODE, NULL, false, NULL);
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, IPI_DOORBELL_END);
+}
+
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 static int armada_xp_set_affinity(struct irq_data *d,
@@ -334,43 +461,6 @@ static int armada_xp_set_affinity(struct irq_data *d,
 
 	return IRQ_SET_MASK_OK;
 }
-#endif
-
-static struct irq_chip armada_370_xp_irq_chip = {
-	.name		= "MPIC",
-	.irq_mask       = armada_370_xp_irq_mask,
-	.irq_mask_ack   = armada_370_xp_irq_mask,
-	.irq_unmask     = armada_370_xp_irq_unmask,
-#ifdef CONFIG_SMP
-	.irq_set_affinity = armada_xp_set_affinity,
-#endif
-	.flags		= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
-};
-
-static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
-				      unsigned int virq, irq_hw_number_t hw)
-{
-	armada_370_xp_irq_mask(irq_get_irq_data(virq));
-	if (!is_percpu_irq(hw))
-		writel(hw, per_cpu_int_base +
-			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-	else
-		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
-	irq_set_status_flags(virq, IRQ_LEVEL);
-
-	if (is_percpu_irq(hw)) {
-		irq_set_percpu_devid(virq);
-		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
-					handle_percpu_devid_irq);
-	} else {
-		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
-					handle_level_irq);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq)));
-	}
-	irq_set_probe(virq);
-
-	return 0;
-}
 
 static void armada_xp_mpic_smp_cpu_init(void)
 {
@@ -383,48 +473,16 @@ static void armada_xp_mpic_smp_cpu_init(void)
 	for (i = 0; i < nr_irqs; i++)
 		writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
 
+	/* Disable all IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+
 	/* Clear pending IPIs */
 	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
-	/* Enable first 8 IPIs */
-	writel(IPI_DOORBELL_MASK, per_cpu_int_base +
-		ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
-
 	/* Unmask IPI interrupt */
 	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 }
 
-static void armada_xp_mpic_perf_init(void)
-{
-	unsigned long cpuid = cpu_logical_map(smp_processor_id());
-
-	/* Enable Performance Counter Overflow interrupts */
-	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
-	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
-}
-
-#ifdef CONFIG_SMP
-static void armada_mpic_send_doorbell(const struct cpumask *mask,
-				      unsigned int irq)
-{
-	int cpu;
-	unsigned long map = 0;
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= 1 << cpu_logical_map(cpu);
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
-	 */
-	dsb();
-
-	/* submit softirq */
-	writel((map << 8) | irq, main_int_base +
-		ARMADA_370_XP_SW_TRIG_INT_OFFS);
-}
-
 static void armada_xp_mpic_reenable_percpu(void)
 {
 	unsigned int irq;
@@ -445,6 +503,8 @@ static void armada_xp_mpic_reenable_percpu(void)
 
 		armada_370_xp_irq_unmask(data);
 	}
+
+	ipi_resume();
 }
 
 static int armada_xp_mpic_starting_cpu(unsigned int cpu)
@@ -462,7 +522,46 @@ static int mpic_cascaded_starting_cpu(unsigned int cpu)
 	enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
 	return 0;
 }
+#else
+static void armada_xp_mpic_smp_cpu_init(void) {}
+static void ipi_resume(void) {}
+#endif
+
+static struct irq_chip armada_370_xp_irq_chip = {
+	.name		= "MPIC",
+	.irq_mask       = armada_370_xp_irq_mask,
+	.irq_mask_ack   = armada_370_xp_irq_mask,
+	.irq_unmask     = armada_370_xp_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = armada_xp_set_affinity,
 #endif
+	.flags		= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
+				      unsigned int virq, irq_hw_number_t hw)
+{
+	armada_370_xp_irq_mask(irq_get_irq_data(virq));
+	if (!is_percpu_irq(hw))
+		writel(hw, per_cpu_int_base +
+			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+	else
+		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
+	irq_set_status_flags(virq, IRQ_LEVEL);
+
+	if (is_percpu_irq(hw)) {
+		irq_set_percpu_devid(virq);
+		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
+					handle_percpu_devid_irq);
+	} else {
+		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
+					handle_level_irq);
+		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq)));
+	}
+	irq_set_probe(virq);
+
+	return 0;
+}
 
 static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
@@ -562,22 +661,15 @@ armada_370_xp_handle_irq(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 		/* IPI Handling */
 		if (irqnr == 0) {
-			u32 ipimask, ipinr;
+			unsigned long ipimask;
+			int ipi;
 
 			ipimask = readl_relaxed(per_cpu_int_base +
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& IPI_DOORBELL_MASK;
 
-			writel(~ipimask, per_cpu_int_base +
-				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
-
-			/* Handle all pending doorbells */
-			for (ipinr = IPI_DOORBELL_START;
-			     ipinr < IPI_DOORBELL_END; ipinr++) {
-				if (ipimask & (0x1 << ipinr))
-					handle_IPI(ipinr, regs);
-			}
-			continue;
+			for_each_set_bit(ipi, &ipimask, IPI_DOORBELL_END)
+				handle_domain_irq(ipi_domain, ipi, regs);
 		}
 #endif
 
@@ -636,6 +728,8 @@ static void armada_370_xp_mpic_resume(void)
 		writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 	if (doorbell_mask_reg & PCI_MSI_DOORBELL_MASK)
 		writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+
+	ipi_resume();
 }
 
 static struct syscore_ops armada_370_xp_mpic_syscore_ops = {
@@ -691,7 +785,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 		irq_set_default_host(armada_370_xp_mpic_domain);
 		set_handle_irq(armada_370_xp_handle_irq);
 #ifdef CONFIG_SMP
-		set_smp_cross_call(armada_mpic_send_doorbell);
+		armada_xp_ipi_init(node);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);

drivers/irqchip/irq-bcm2836.c

@@ -10,6 +10,7 @@
 #include <linux/of_irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/irq-bcm2836.h>
 
 #include <asm/exception.h>
@@ -89,12 +90,24 @@ static struct irq_chip bcm2836_arm_irqchip_gpu = {
 	.irq_unmask	= bcm2836_arm_irqchip_unmask_gpu_irq,
 };
 
+static void bcm2836_arm_irqchip_dummy_op(struct irq_data *d)
+{
+}
+
+static struct irq_chip bcm2836_arm_irqchip_dummy = {
+	.name		= "bcm2836-dummy",
+	.irq_eoi	= bcm2836_arm_irqchip_dummy_op,
+};
+
 static int bcm2836_map(struct irq_domain *d, unsigned int irq,
 		       irq_hw_number_t hw)
 {
 	struct irq_chip *chip;
 
 	switch (hw) {
+	case LOCAL_IRQ_MAILBOX0:
+		chip = &bcm2836_arm_irqchip_dummy;
+		break;
 	case LOCAL_IRQ_CNTPSIRQ:
 	case LOCAL_IRQ_CNTPNSIRQ:
 	case LOCAL_IRQ_CNTHPIRQ:
@@ -127,17 +140,7 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs)
 	u32 stat;
 
 	stat = readl_relaxed(intc.base + LOCAL_IRQ_PENDING0 + 4 * cpu);
-	if (stat & BIT(LOCAL_IRQ_MAILBOX0)) {
-#ifdef CONFIG_SMP
-		void __iomem *mailbox0 = (intc.base +
-					  LOCAL_MAILBOX0_CLR0 + 16 * cpu);
-		u32 mbox_val = readl(mailbox0);
-		u32 ipi = ffs(mbox_val) - 1;
-
-		writel(1 << ipi, mailbox0);
-		handle_IPI(ipi, regs);
-#endif
-	} else if (stat) {
+	if (stat) {
 		u32 hwirq = ffs(stat) - 1;
 
 		handle_domain_irq(intc.domain, hwirq, regs);
@@ -145,8 +148,35 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_SMP
-static void bcm2836_arm_irqchip_send_ipi(const struct cpumask *mask,
-					 unsigned int ipi)
+static struct irq_domain *ipi_domain;
+
+static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int cpu = smp_processor_id();
+	u32 mbox_val;
+
+	chained_irq_enter(chip, desc);
+
+	mbox_val = readl_relaxed(intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+	if (mbox_val) {
+		int hwirq = ffs(mbox_val) - 1;
+		generic_handle_irq(irq_find_mapping(ipi_domain, hwirq));
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void bcm2836_arm_irqchip_ipi_eoi(struct irq_data *d)
+{
+	int cpu = smp_processor_id();
+
+	writel_relaxed(BIT(d->hwirq),
+		       intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+}
+
+static void bcm2836_arm_irqchip_ipi_send_mask(struct irq_data *d,
+					      const struct cpumask *mask)
 {
 	int cpu;
 	void __iomem *mailbox0_base = intc.base + LOCAL_MAILBOX0_SET0;
@@ -157,11 +187,47 @@ static void bcm2836_arm_irqchip_send_ipi(const struct cpumask *mask,
 	 */
 	smp_wmb();
 
-	for_each_cpu(cpu, mask)	{
-		writel(1 << ipi, mailbox0_base + 16 * cpu);
+	for_each_cpu(cpu, mask)
+		writel_relaxed(BIT(d->hwirq), mailbox0_base + 16 * cpu);
+}
+
+static struct irq_chip bcm2836_arm_irqchip_ipi = {
+	.name		= "IPI",
+	.irq_mask	= bcm2836_arm_irqchip_dummy_op,
+	.irq_unmask	= bcm2836_arm_irqchip_dummy_op,
+	.irq_eoi	= bcm2836_arm_irqchip_ipi_eoi,
+	.ipi_send_mask	= bcm2836_arm_irqchip_ipi_send_mask,
+};
+
+static int bcm2836_arm_irqchip_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &bcm2836_arm_irqchip_ipi,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
 	}
+
+	return 0;
 }
 
+static void bcm2836_arm_irqchip_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= bcm2836_arm_irqchip_ipi_alloc,
+	.free	= bcm2836_arm_irqchip_ipi_free,
+};
+
 static int bcm2836_cpu_starting(unsigned int cpu)
 {
 	bcm2836_arm_irqchip_unmask_per_cpu_irq(LOCAL_MAILBOX_INT_CONTROL0, 0,
@@ -175,25 +241,58 @@ static int bcm2836_cpu_dying(unsigned int cpu)
 					     cpu);
 	return 0;
 }
-#endif
 
-static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
-	.xlate = irq_domain_xlate_onetwocell,
-	.map = bcm2836_map,
-};
+#define BITS_PER_MBOX	32
 
-static void
-bcm2836_arm_irqchip_smp_init(void)
+static void bcm2836_arm_irqchip_smp_init(void)
 {
-#ifdef CONFIG_SMP
+	struct irq_fwspec ipi_fwspec = {
+		.fwnode		= intc.domain->fwnode,
+		.param_count	= 1,
+		.param		= {
+			[0]	= LOCAL_IRQ_MAILBOX0,
+		},
+	};
+	int base_ipi, mux_irq;
+
+	mux_irq = irq_create_fwspec_mapping(&ipi_fwspec);
+	if (WARN_ON(mux_irq <= 0))
+		return;
+
+	ipi_domain = irq_domain_create_linear(intc.domain->fwnode,
+					      BITS_PER_MBOX, &ipi_domain_ops,
+					      NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	ipi_domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE;
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, BITS_PER_MBOX,
+					   NUMA_NO_NODE, NULL,
+					   false, NULL);
+
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, BITS_PER_MBOX);
+
+	irq_set_chained_handler_and_data(mux_irq,
+					 bcm2836_arm_irqchip_handle_ipi, NULL);
+
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
 			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
-
-	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
-#endif
 }
+#else
+#define bcm2836_arm_irqchip_smp_init()	do { } while(0)
+#endif
+
+static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
+	.xlate = irq_domain_xlate_onetwocell,
+	.map = bcm2836_map,
+};
 
 /*
  * The LOCAL_IRQ_CNT* timer firings are based off of the external
@@ -232,6 +331,8 @@ static int __init bcm2836_arm_irqchip_l1_intc_of_init(struct device_node *node,
 	if (!intc.domain)
 		panic("%pOF: unable to create IRQ domain\n", node);
 
+	irq_domain_update_bus_token(intc.domain, DOMAIN_BUS_WIRED);
+
 	bcm2836_arm_irqchip_smp_init();
 
 	set_handle_irq(bcm2836_arm_irqchip_handle_irq);

drivers/irqchip/irq-gic-common.c

@@ -152,9 +152,6 @@ void gic_cpu_config(void __iomem *base, int nr, void (*sync_access)(void))
 		writel_relaxed(GICD_INT_DEF_PRI_X4,
 					base + GIC_DIST_PRI + i * 4 / 4);
 
-	/* Ensure all SGI interrupts are now enabled */
-	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
-
 	if (sync_access)
 		sync_access();
 }

drivers/irqchip/irq-gic-v3.c

@@ -36,6 +36,8 @@
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
 
+#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
+
 struct redist_region {
 	void __iomem		*redist_base;
 	phys_addr_t		phys_base;
@@ -113,6 +115,7 @@ static DEFINE_PER_CPU(bool, has_rss);
 #define DEFAULT_PMR_VALUE	0xf0
 
 enum gic_intid_range {
+	SGI_RANGE,
 	PPI_RANGE,
 	SPI_RANGE,
 	EPPI_RANGE,
@@ -124,6 +127,8 @@ enum gic_intid_range {
 static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq)
 {
 	switch (hwirq) {
+	case 0 ... 15:
+		return SGI_RANGE;
 	case 16 ... 31:
 		return PPI_RANGE;
 	case 32 ... 1019:
@@ -149,15 +154,22 @@ static inline unsigned int gic_irq(struct irq_data *d)
 	return d->hwirq;
 }
 
-static inline int gic_irq_in_rdist(struct irq_data *d)
+static inline bool gic_irq_in_rdist(struct irq_data *d)
 {
-	enum gic_intid_range range = get_intid_range(d);
-	return range == PPI_RANGE || range == EPPI_RANGE;
+	switch (get_intid_range(d)) {
+	case SGI_RANGE:
+	case PPI_RANGE:
+	case EPPI_RANGE:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static inline void __iomem *gic_dist_base(struct irq_data *d)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		/* SGI+PPI -> SGI_base for this CPU */
@@ -254,6 +266,7 @@ static void gic_enable_redist(bool enable)
 static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case SPI_RANGE:
 		*index = d->hwirq;
@@ -373,7 +386,7 @@ static int gic_irq_set_irqchip_state(struct irq_data *d,
 {
 	u32 reg;
 
-	if (d->hwirq >= 8192) /* PPI/SPI only */
+	if (d->hwirq >= 8192) /* SGI/PPI/SPI only */
 		return -EINVAL;
 
 	switch (which) {
@@ -540,12 +553,12 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	u32 offset, index;
 	int ret;
 
-	/* Interrupt configuration for SGIs can't be changed */
-	if (irq < 16)
-		return -EINVAL;
-
 	range = get_intid_range(d);
 
+	/* Interrupt configuration for SGIs can't be changed */
+	if (range == SGI_RANGE)
+		return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0;
+
 	/* SPIs have restrictions on the supported types */
 	if ((range == SPI_RANGE || range == ESPI_RANGE) &&
 	    type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
@@ -573,6 +586,9 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 
 static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
+	if (get_intid_range(d) == SGI_RANGE)
+		return -EINVAL;
+
 	if (vcpu)
 		irqd_set_forwarded_to_vcpu(d);
 	else
@@ -647,38 +663,14 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 	if ((irqnr >= 1020 && irqnr <= 1023))
 		return;
 
-	/* Treat anything but SGIs in a uniform way */
-	if (likely(irqnr > 15)) {
-		int err;
-
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_eoir(irqnr);
-		else
-			isb();
-
-		err = handle_domain_irq(gic_data.domain, irqnr, regs);
-		if (err) {
-			WARN_ONCE(true, "Unexpected interrupt received!\n");
-			gic_deactivate_unhandled(irqnr);
-		}
-		return;
-	}
-	if (irqnr < 16) {
+	if (static_branch_likely(&supports_deactivate_key))
 		gic_write_eoir(irqnr);
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_dir(irqnr);
-#ifdef CONFIG_SMP
-		/*
-		 * Unlike GICv2, we don't need an smp_rmb() here.
-		 * The control dependency from gic_read_iar to
-		 * the ISB in gic_write_eoir is enough to ensure
-		 * that any shared data read by handle_IPI will
-		 * be read after the ACK.
-		 */
-		handle_IPI(irqnr, regs);
-#else
-		WARN_ONCE(true, "Unexpected SGI received!\n");
-#endif
+	else
+		isb();
+
+	if (handle_domain_irq(gic_data.domain, irqnr, regs)) {
+		WARN_ONCE(true, "Unexpected interrupt received!\n");
+		gic_deactivate_unhandled(irqnr);
 	}
 }
 
@@ -1132,11 +1124,11 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
 	gic_write_sgi1r(val);
 }
 
-static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
 {
 	int cpu;
 
-	if (WARN_ON(irq >= 16))
+	if (WARN_ON(d->hwirq >= 16))
 		return;
 
 	/*
@@ -1150,7 +1142,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 		u16 tlist;
 
 		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
-		gic_send_sgi(cluster_id, tlist, irq);
+		gic_send_sgi(cluster_id, tlist, d->hwirq);
 	}
 
 	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
@@ -1159,10 +1151,24 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 static void __init gic_smp_init(void)
 {
-	set_smp_cross_call(gic_raise_softirq);
+	struct irq_fwspec sgi_fwspec = {
+		.fwnode		= gic_data.fwnode,
+		.param_count	= 1,
+	};
+	int base_sgi;
+
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
+
+	/* Register all 8 non-secure SGIs */
+	base_sgi = __irq_domain_alloc_irqs(gic_data.domain, -1, 8,
+					   NUMA_NO_NODE, &sgi_fwspec,
+					   false, NULL);
+	if (WARN_ON(base_sgi <= 0))
+		return;
+
+	set_smp_ipi_range(base_sgi, 8);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
@@ -1211,6 +1217,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 }
 #else
 #define gic_set_affinity	NULL
+#define gic_ipi_send_mask	NULL
 #define gic_smp_init()		do { } while(0)
 #endif
 
@@ -1253,6 +1260,7 @@ static struct irq_chip gic_chip = {
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,
@@ -1270,6 +1278,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,
@@ -1284,6 +1293,13 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		chip = &gic_eoimode1_chip;
 
 	switch (__get_intid_range(hw)) {
+	case SGI_RANGE:
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(d, irq, hw, chip, d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+		break;
+
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		irq_set_percpu_devid(irq);
@@ -1313,13 +1329,17 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
-
 static int gic_irq_domain_translate(struct irq_domain *d,
 				    struct irq_fwspec *fwspec,
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
+	if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
+		*hwirq = fwspec->param[0];
+		*type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
+
 	if (is_of_node(fwspec->fwnode)) {
 		if (fwspec->param_count < 3)
 			return -EINVAL;
@@ -1676,9 +1696,9 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	gic_update_rdist_properties();
 
-	gic_smp_init();
 	gic_dist_init();
 	gic_cpu_init();
+	gic_smp_init();
 	gic_cpu_pm_init();
 
 	if (gic_dist_supports_lpis()) {

drivers/irqchip/irq-hip04.c

@@ -171,6 +171,29 @@ static int hip04_irq_set_affinity(struct irq_data *d,
 
 	return IRQ_SET_MASK_OK;
 }
+
+static void hip04_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
+{
+	int cpu;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= hip04_cpu_map[cpu];
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before they observe us issuing the IPI.
+	 */
+	dmb(ishst);
+
+	/* this always happens on GIC0 */
+	writel_relaxed(map << 8 | d->hwirq, hip04_data.dist_base + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
 #endif
 
 static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)
@@ -182,19 +205,9 @@ static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr <= HIP04_MAX_IRQS)) {
+		if (irqnr <= HIP04_MAX_IRQS)
 			handle_domain_irq(hip04_data.domain, irqnr, regs);
-			continue;
-		}
-		if (irqnr < 16) {
-			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-#ifdef CONFIG_SMP
-			handle_IPI(irqnr, regs);
-#endif
-			continue;
-		}
-		break;
-	} while (1);
+	} while (irqnr > HIP04_MAX_IRQS);
 }
 
 static struct irq_chip hip04_irq_chip = {
@@ -205,6 +218,7 @@ static struct irq_chip hip04_irq_chip = {
 	.irq_set_type		= hip04_irq_set_type,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= hip04_irq_set_affinity,
+	.ipi_send_mask		= hip04_ipi_send_mask,
 #endif
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
@@ -279,39 +293,17 @@ static void hip04_irq_cpu_init(struct hip04_irq_data *intc)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
-#ifdef CONFIG_SMP
-static void hip04_raise_softirq(const struct cpumask *mask, unsigned int irq)
-{
-	int cpu;
-	unsigned long flags, map = 0;
-
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= hip04_cpu_map[cpu];
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before they observe us issuing the IPI.
-	 */
-	dmb(ishst);
-
-	/* this always happens on GIC0 */
-	writel_relaxed(map << 8 | irq, hip04_data.dist_base + GIC_DIST_SOFTINT);
-
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
-}
-#endif
-
 static int hip04_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
-	if (hw < 32) {
+	if (hw < 16) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &hip04_irq_chip,
+					 handle_percpu_devid_fasteoi_ipi);
+	} else if (hw < 32) {
 		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_percpu_devid_irq);
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_fasteoi_irq);
@@ -328,10 +320,13 @@ static int hip04_irq_domain_xlate(struct irq_domain *d,
 				  unsigned long *out_hwirq,
 				  unsigned int *out_type)
 {
-	unsigned long ret = 0;
-
 	if (irq_domain_get_of_node(d) != controller)
 		return -EINVAL;
+	if (intsize == 1 && intspec[0] < 16) {
+		*out_hwirq = intspec[0];
+		*out_type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
 	if (intsize < 3)
 		return -EINVAL;
 
@@ -344,7 +339,7 @@ static int hip04_irq_domain_xlate(struct irq_domain *d,
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
 
-	return ret;
+	return 0;
 }
 
 static int hip04_irq_starting_cpu(unsigned int cpu)
@@ -361,7 +356,6 @@ static const struct irq_domain_ops hip04_irq_domain_ops = {
 static int __init
 hip04_of_init(struct device_node *node, struct device_node *parent)
 {
-	irq_hw_number_t hwirq_base = 16;
 	int nr_irqs, irq_base, i;
 
 	if (WARN_ON(!node))
@@ -390,24 +384,21 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 		nr_irqs = HIP04_MAX_IRQS;
 	hip04_data.nr_irqs = nr_irqs;
 
-	nr_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-
-	irq_base = irq_alloc_descs(-1, hwirq_base, nr_irqs, numa_node_id());
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, numa_node_id());
 	if (irq_base < 0) {
 		pr_err("failed to allocate IRQ numbers\n");
 		return -EINVAL;
 	}
 
 	hip04_data.domain = irq_domain_add_legacy(node, nr_irqs, irq_base,
-						  hwirq_base,
+						  0,
 						  &hip04_irq_domain_ops,
 						  &hip04_data);
-
 	if (WARN_ON(!hip04_data.domain))
 		return -EINVAL;
 
 #ifdef CONFIG_SMP
-	set_smp_cross_call(hip04_raise_softirq);
+	set_smp_ipi_range(irq_base, 16);
 #endif
 	set_handle_irq(hip04_handle_irq);
 

include/linux/irq.h

@@ -71,6 +71,7 @@ enum irqchip_irq_state;
  *				  it from the spurious interrupt detection
  *				  mechanism and from core side polling.
  * IRQ_DISABLE_UNLAZY		- Disable lazy irq disable
+ * IRQ_HIDDEN			- Don't show up in /proc/interrupts
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -97,13 +98,14 @@ enum {
 	IRQ_PER_CPU_DEVID	= (1 << 17),
 	IRQ_IS_POLLED		= (1 << 18),
 	IRQ_DISABLE_UNLAZY	= (1 << 19),
+	IRQ_HIDDEN		= (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
@@ -634,6 +636,7 @@ static inline int irq_set_parent(int irq, int parent_irq)
  */
 extern void handle_level_irq(struct irq_desc *desc);
 extern void handle_fasteoi_irq(struct irq_desc *desc);
+extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);

kernel/irq/chip.c

@@ -944,6 +944,33 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
+ *				     dev ids
+ * @desc:	the interrupt description structure for this irq
+ *
+ * The biggest difference with the IRQ version is that the interrupt is
+ * EOIed early, as the IPI could result in a context switch, and we need to
+ * make sure the IPI can fire again. We also assume that the arch code has
+ * registered an action. If not, we are positively doomed.
+ */
+void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	unsigned int irq = irq_desc_get_irq(desc);
+	irqreturn_t res;
+
+	__kstat_incr_irqs_this_cpu(desc);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+	trace_irq_handler_exit(irq, action, res);
+}
+
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids

kernel/irq/debugfs.c

@@ -136,6 +136,7 @@ static const struct irq_bit_descr irqdesc_states[] = {
 	BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID),
 	BIT_MASK_DESCR(_IRQ_IS_POLLED),
 	BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY),
+	BIT_MASK_DESCR(_IRQ_HIDDEN),
 };
 
 static const struct irq_bit_descr irqdesc_istates[] = {

kernel/irq/proc.c

@@ -485,7 +485,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	rcu_read_lock();
 	desc = irq_to_desc(i);
-	if (!desc)
+	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
 	if (desc->kstat_irqs)

kernel/irq/settings.h

@@ -17,6 +17,7 @@ enum {
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQ_DISABLE_UNLAZY	= IRQ_DISABLE_UNLAZY,
+	_IRQ_HIDDEN		= IRQ_HIDDEN,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -31,6 +32,7 @@ enum {
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #define IRQ_IS_POLLED		GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY	GOT_YOU_MORON
+#define IRQ_HIDDEN		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -167,3 +169,8 @@ static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc)
 {
 	desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY;
 }
+
+static inline bool irq_settings_is_hidden(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_HIDDEN;
+}