[RFC PATCH v2 26/31] kvx: Add multi-processor (SMP) support

[Yann Sionneau <ysionneau@kalray.eu>]

Coolidge v1 SoC has 5 clusters of 17 kvx cores:
 - 16 application cores aka PE
 - 1 privileged core, the Resource Manager, aka RM.

Linux can run in SMP config on the 16 cores of a Cluster.

Memory coherency between all cores is guarenteed by the L2 cache.

Co-developed-by: Clement Leger <clement@clement-leger.fr>
Signed-off-by: Clement Leger <clement@clement-leger.fr>
Co-developed-by: Julian Vetter <jvetter@kalray.eu>
Signed-off-by: Julian Vetter <jvetter@kalray.eu>
Co-developed-by: Julien Hascoet <jhascoet@kalray.eu>
Signed-off-by: Julien Hascoet <jhascoet@kalray.eu>
Co-developed-by: Louis Morhet <lmorhet@kalray.eu>
Signed-off-by: Louis Morhet <lmorhet@kalray.eu>
Co-developed-by: Luc Michel <lmichel@kalray.eu>
Signed-off-by: Luc Michel <lmichel@kalray.eu>
Co-developed-by: Marius Gligor <mgligor@kalray.eu>
Signed-off-by: Marius Gligor <mgligor@kalray.eu>
Co-developed-by: Yann Sionneau <ysionneau@kalray.eu>
Signed-off-by: Yann Sionneau <ysionneau@kalray.eu>
---

Notes:
    V1 -> V2:
     - removed L2 cache driver
     - removed ipi and pwr-ctrl driver (splitted in their own patch)

 arch/kvx/include/asm/smp.h |  42 ++++++++++++
 arch/kvx/kernel/smp.c      | 110 ++++++++++++++++++++++++++++++++
 arch/kvx/kernel/smpboot.c  | 127 +++++++++++++++++++++++++++++++++++++
 include/linux/cpuhotplug.h |   2 +
 4 files changed, 281 insertions(+)
 create mode 100644 arch/kvx/include/asm/smp.h
 create mode 100644 arch/kvx/kernel/smp.c
 create mode 100644 arch/kvx/kernel/smpboot.c

diff --git a/arch/kvx/include/asm/smp.h b/arch/kvx/include/asm/smp.h
new file mode 100644
index 000000000000..e4fd4d001b2c
--- /dev/null
+++ b/arch/kvx/include/asm/smp.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017-2023 Kalray Inc.
+ * Author(s): Clement Leger
+ */
+
+#ifndef _ASM_KVX_SMP_H
+#define _ASM_KVX_SMP_H
+
+#include <linux/cpumask.h>
+#include <linux/irqreturn.h>
+
+#include <asm/sfr.h>
+
+#ifdef CONFIG_SMP
+
+/* Hook for the generic smp_call_function_many() routine. */
+void arch_send_call_function_ipi_mask(struct cpumask *mask);
+
+/* Hook for the generic smp_call_function_single() routine. */
+void arch_send_call_function_single_ipi(int cpu);
+
+void __init setup_processor(void);
+
+void smp_init_cpus(void);
+
+irqreturn_t ipi_call_interrupt(int irq, void *dev_id);
+
+#define raw_smp_processor_id() ((int) \
+	((kvx_sfr_get(PCR) & KVX_SFR_PCR_PID_MASK) \
+					>> KVX_SFR_PCR_PID_SHIFT))
+
+#define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vunmap(start, end)		do { } while (0)
+
+#else
+
+void smp_init_cpus(void) {}
+
+#endif /* CONFIG_SMP */
+
+#endif
diff --git a/arch/kvx/kernel/smp.c b/arch/kvx/kernel/smp.c
new file mode 100644
index 000000000000..ed4c35a8c4bc
--- /dev/null
+++ b/arch/kvx/kernel/smp.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2023 Kalray Inc.
+ * Author(s): Clement Leger
+ */
+
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/of_irq.h>
+#include <linux/cpumask.h>
+#include <linux/irq_work.h>
+#include <linux/mm_types.h>
+#include <linux/interrupt.h>
+
+#include <asm/ipi.h>
+#include <asm/tlbflush.h>
+
+enum ipi_message_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_IRQ_WORK,
+	IPI_MAX
+};
+
+/* A collection of single bit ipi messages.  */
+static struct {
+	unsigned long bits ____cacheline_aligned;
+} ipi_data[NR_CPUS] __cacheline_aligned;
+
+static void send_ipi_message(const struct cpumask *mask,
+			     enum ipi_message_type operation)
+{
+	unsigned long flags;
+	int cpu;
+
+	/* Set operation that must be done by receiver */
+	for_each_cpu(cpu, mask)
+		set_bit(operation, &ipi_data[cpu].bits);
+
+	/* Commit the write before sending IPI */
+	smp_wmb();
+
+	local_irq_save(flags);
+
+	kvx_ipi_send(mask);
+
+	local_irq_restore(flags);
+}
+
+void arch_send_call_function_ipi_mask(struct cpumask *mask)
+{
+	send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	send_ipi_message(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
+static void ipi_stop(void *unused)
+{
+	local_cpu_stop();
+}
+
+void smp_send_stop(void)
+{
+	struct cpumask targets;
+
+	cpumask_copy(&targets, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &targets);
+
+	smp_call_function_many(&targets, ipi_stop, NULL, 0);
+}
+
+void smp_send_reschedule(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
+{
+	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
+
+	while (true) {
+		unsigned long ops = xchg(pending_ipis, 0);
+
+		if (ops == 0)
+			return IRQ_HANDLED;
+
+		if (ops & (1 << IPI_RESCHEDULE))
+			scheduler_ipi();
+
+		if (ops & (1 << IPI_CALL_FUNC))
+			generic_smp_call_function_interrupt();
+
+		if (ops & (1 << IPI_IRQ_WORK))
+			irq_work_run();
+
+		BUG_ON((ops >> IPI_MAX) != 0);
+	}
+
+	return IRQ_HANDLED;
+}
diff --git a/arch/kvx/kernel/smpboot.c b/arch/kvx/kernel/smpboot.c
new file mode 100644
index 000000000000..987a6f014163
--- /dev/null
+++ b/arch/kvx/kernel/smpboot.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2023 Kalray Inc.
+ * Author(s): Clement Leger
+ *            Julian Vetter
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/sched/mm.h>
+#include <linux/mm_types.h>
+#include <linux/of_platform.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/pwr_ctrl.h>
+#include <asm/tlbflush.h>
+#include <asm/ipi.h>
+
+void *__cpu_up_stack_pointer[NR_CPUS];
+void *__cpu_up_task_pointer[NR_CPUS];
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	__cpu_up_stack_pointer[cpu] = task_stack_page(tidle) + THREAD_SIZE;
+	__cpu_up_task_pointer[cpu] = tidle;
+	/* We need to be sure writes are committed */
+	smp_mb();
+
+	kvx_pwr_ctrl_cpu_poweron(cpu);
+	while (!cpu_online(cpu))
+		cpu_relax();
+
+	return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+void __init smp_init_cpus(void)
+{
+	struct cpumask cpumask;
+	struct device_node *cpu;
+	const __be32 *reg;
+	u32 cpu_num;
+	unsigned int nr_cpus = 0;
+
+	cpumask_clear(&cpumask);
+
+	for_each_of_cpu_node(cpu) {
+		if (!of_device_is_available(cpu))
+			continue;
+
+		reg = of_get_property(cpu, "reg", NULL);
+		if (!reg)
+			continue;
+
+		cpu_num = be32_to_cpup(reg);
+		if (cpu_num >= nr_cpu_ids)
+			continue;
+
+		nr_cpus++;
+		cpumask_set_cpu(cpu_num, &cpumask);
+	}
+
+	pr_info("%d possible cpus\n", nr_cpus);
+	init_cpu_possible(&cpumask);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	if (num_present_cpus() <= 1)
+		init_cpu_present(cpu_possible_mask);
+}
+
+int __init setup_smp(void)
+{
+	int ret;
+
+	ret = kvx_pwr_ctrl_probe();
+	if (ret)
+		panic("Failed to probe power controller !");
+
+	ret = kvx_ipi_ctrl_probe(ipi_call_interrupt);
+	if (ret)
+		panic("Failed to probe IPI controller !");
+
+	return 0;
+}
+
+early_initcall(setup_smp);
+
+/*
+ * C entry point for a secondary processor.
+ */
+void __init start_kernel_secondary(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	setup_processor();
+	kvx_mmu_early_setup();
+
+	/* All kernel threads share the same mm context.  */
+	mmgrab(mm);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+	trace_hardirqs_off();
+
+	local_flush_tlb_all();
+
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index f61447913db9..f5a484547b15 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -152,6 +152,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_RISCV_STARTING,
 	CPUHP_AP_IRQ_LOONGARCH_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+	CPUHP_AP_IRQ_KVX_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_MICROCODE_LOADER,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
@@ -189,6 +190,7 @@ enum cpuhp_state {
 	CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_STARTING,
 	CPUHP_AP_KVM_ARM_TIMER_STARTING,
+	CPUHP_AP_KVX_TIMER_STARTING,
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
-- 
2.37.2