xtensa: add SMP support

This is largely based on SMP code from the xtensa-2.6.29-smp tree by
Piet Delaney, Marc Gauthier, Joe Taylor, Christian Zankel (and possibly
other Tensilica folks).

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Chris Zankel <chris@zankel.net>

1 files changed, 465 insertions, 0 deletions

diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
new file mode 100644
index 000000000000..46bdd142a07d
--- /dev/null
+++ b/arch/xtensa/kernel/smp.c
@@ -0,0 +1,465 @@
+/*
+ * Xtensa SMP support functions.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2008 - 2013 Tensilica Inc.
+ *
+ * Chris Zankel <chris@zankel.net>
+ * Joe Taylor <joe@tensilica.com>
+ * Pete Delaney <piet@tensilica.com
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/seq_file.h>
+#include <linux/smp.h>
+#include <linux/thread_info.h>
+
+#include <asm/cacheflush.h>
+#include <asm/kdebug.h>
+#include <asm/mmu_context.h>
+#include <asm/mxregs.h>
+#include <asm/platform.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+#ifdef CONFIG_SMP
+# if XCHAL_HAVE_S32C1I == 0
+#  error "The S32C1I option is required for SMP."
+# endif
+#endif
+
+/* IPI (Inter Process Interrupt) */
+
+#define IPI_IRQ	0
+
+static irqreturn_t ipi_interrupt(int irq, void *dev_id);
+static struct irqaction ipi_irqaction = {
+	.handler =	ipi_interrupt,
+	.flags =	IRQF_PERCPU,
+	.name =		"ipi",
+};
+
+void ipi_init(void)
+{
+	unsigned irq = irq_create_mapping(NULL, IPI_IRQ);
+	setup_irq(irq, &ipi_irqaction);
+}
+
+static inline unsigned int get_core_count(void)
+{
+	/* Bits 18..21 of SYSCFGID contain the core count minus 1. */
+	unsigned int syscfgid = get_er(SYSCFGID);
+	return ((syscfgid >> 18) & 0xf) + 1;
+}
+
+static inline int get_core_id(void)
+{
+	/* Bits 0...18 of SYSCFGID contain the core id  */
+	unsigned int core_id = get_er(SYSCFGID);
+	return core_id & 0x3fff;
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	unsigned i;
+
+	for (i = 0; i < max_cpus; ++i)
+		set_cpu_present(i, true);
+}
+
+void __init smp_init_cpus(void)
+{
+	unsigned i;
+	unsigned int ncpus = get_core_count();
+	unsigned int core_id = get_core_id();
+
+	pr_info("%s: Core Count = %d\n", __func__, ncpus);
+	pr_info("%s: Core Id = %d\n", __func__, core_id);
+
+	for (i = 0; i < ncpus; ++i)
+		set_cpu_possible(i, true);
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
+	unsigned int cpu = smp_processor_id();
+	BUG_ON(cpu != 0);
+	cpu_asid_cache(cpu) = ASID_USER_FIRST;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+static int boot_secondary_processors = 1; /* Set with xt-gdb via .xt-gdb */
+static DECLARE_COMPLETION(cpu_running);
+
+void __init secondary_start_kernel(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	init_mmu();
+
+#ifdef CONFIG_DEBUG_KERNEL
+	if (boot_secondary_processors == 0) {
+		pr_debug("%s: boot_secondary_processors:%d; Hanging cpu:%d\n",
+			__func__, boot_secondary_processors, cpu);
+		for (;;)
+			__asm__ __volatile__ ("waiti " __stringify(LOCKLEVEL));
+	}
+
+	pr_debug("%s: boot_secondary_processors:%d; Booting cpu:%d\n",
+		__func__, boot_secondary_processors, cpu);
+#endif
+	/* Init EXCSAVE1 */
+
+	secondary_trap_init();
+
+	/* All kernel threads share the same mm context. */
+
+	atomic_inc(&mm->mm_users);
+	atomic_inc(&mm->mm_count);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+	enter_lazy_tlb(mm, current);
+
+	preempt_disable();
+	trace_hardirqs_off();
+
+	calibrate_delay();
+
+	notify_cpu_starting(cpu);
+
+	secondary_init_irq();
+	local_timer_setup(cpu);
+
+	local_irq_enable();
+
+	set_cpu_online(cpu, true);
+	complete(&cpu_running);
+
+	cpu_startup_entry(CPUHP_ONLINE);
+}
+
+static void mx_cpu_start(void *p)
+{
+	unsigned cpu = (unsigned)p;
+	unsigned long run_stall_mask = get_er(MPSCORE);
+
+	set_er(run_stall_mask & ~(1u << cpu), MPSCORE);
+	pr_debug("%s: cpu: %d, run_stall_mask: %lx ---> %lx\n",
+			__func__, cpu, run_stall_mask, get_er(MPSCORE));
+}
+
+static void mx_cpu_stop(void *p)
+{
+	unsigned cpu = (unsigned)p;
+	unsigned long run_stall_mask = get_er(MPSCORE);
+
+	set_er(run_stall_mask | (1u << cpu), MPSCORE);
+	pr_debug("%s: cpu: %d, run_stall_mask: %lx ---> %lx\n",
+			__func__, cpu, run_stall_mask, get_er(MPSCORE));
+}
+
+unsigned long cpu_start_ccount;
+
+static int boot_secondary(unsigned int cpu, struct task_struct *ts)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+	unsigned long ccount;
+	int i;
+
+	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
+
+	for (i = 0; i < 2; ++i) {
+		do
+			ccount = get_ccount();
+		while (!ccount);
+
+		cpu_start_ccount = ccount;
+
+		while (time_before(jiffies, timeout)) {
+			mb();
+			if (!cpu_start_ccount)
+				break;
+		}
+
+		if (cpu_start_ccount) {
+			smp_call_function_single(0, mx_cpu_stop,
+					(void *)cpu, 1);
+			cpu_start_ccount = 0;
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+	int ret = 0;
+
+	if (cpu_asid_cache(cpu) == 0)
+		cpu_asid_cache(cpu) = ASID_USER_FIRST;
+
+	start_info.stack = (unsigned long)task_pt_regs(idle);
+	wmb();
+
+	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
+			__func__, cpu, idle, start_info.stack);
+
+	ret = boot_secondary(cpu, idle);
+	if (ret == 0) {
+		wait_for_completion_timeout(&cpu_running,
+				msecs_to_jiffies(1000));
+		if (!cpu_online(cpu))
+			ret = -EIO;
+	}
+
+	if (ret)
+		pr_err("CPU %u failed to boot\n", cpu);
+
+	return ret;
+}
+
+enum ipi_msg_type {
+	IPI_RESCHEDULE = 0,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+	IPI_MAX
+};
+
+static const struct {
+	const char *short_text;
+	const char *long_text;
+} ipi_text[] = {
+	{ .short_text = "RES", .long_text = "Rescheduling interrupts" },
+	{ .short_text = "CAL", .long_text = "Function call interrupts" },
+	{ .short_text = "DIE", .long_text = "CPU shutdown interrupts" },
+};
+
+struct ipi_data {
+	unsigned long ipi_count[IPI_MAX];
+};
+
+static DEFINE_PER_CPU(struct ipi_data, ipi_data);
+
+static void send_ipi_message(const struct cpumask *callmask,
+		enum ipi_msg_type msg_id)
+{
+	int index;
+	unsigned long mask = 0;
+
+	for_each_cpu(index, callmask)
+		if (index != smp_processor_id())
+			mask |= 1 << index;
+
+	set_er(mask, MIPISET(msg_id));
+}
+
+void arch_send_call_function_ipi_mask(const 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);
+}
+
+void smp_send_reschedule(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+void smp_send_stop(void)
+{
+	struct cpumask targets;
+
+	cpumask_copy(&targets, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &targets);
+	send_ipi_message(&targets, IPI_CPU_STOP);
+}
+
+static void ipi_cpu_stop(unsigned int cpu)
+{
+	set_cpu_online(cpu, false);
+	machine_halt();
+}
+
+irqreturn_t ipi_interrupt(int irq, void *dev_id)
+{
+	unsigned int cpu = smp_processor_id();
+	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
+	unsigned int msg;
+	unsigned i;
+
+	msg = get_er(MIPICAUSE(cpu));
+	for (i = 0; i < IPI_MAX; i++)
+		if (msg & (1 << i)) {
+			set_er(1 << i, MIPICAUSE(cpu));
+			++ipi->ipi_count[i];
+		}
+
+	if (msg & (1 << IPI_RESCHEDULE))
+		scheduler_ipi();
+	if (msg & (1 << IPI_CALL_FUNC))
+		generic_smp_call_function_interrupt();
+	if (msg & (1 << IPI_CPU_STOP))
+		ipi_cpu_stop(cpu);
+
+	return IRQ_HANDLED;
+}
+
+void show_ipi_list(struct seq_file *p, int prec)
+{
+	unsigned int cpu;
+	unsigned i;
+
+	for (i = 0; i < IPI_MAX; ++i) {
+		seq_printf(p, "%*s:", prec, ipi_text[i].short_text);
+		for_each_online_cpu(cpu)
+			seq_printf(p, " %10lu",
+					per_cpu(ipi_data, cpu).ipi_count[i]);
+		seq_printf(p, "   %s\n", ipi_text[i].long_text);
+	}
+}
+
+int setup_profiling_timer(unsigned int multiplier)
+{
+	pr_debug("setup_profiling_timer %d\n", multiplier);
+	return 0;
+}
+
+/* TLB flush functions */
+
+struct flush_data {
+	struct vm_area_struct *vma;
+	unsigned long addr1;
+	unsigned long addr2;
+};
+
+static void ipi_flush_tlb_all(void *arg)
+{
+	local_flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
+
+static void ipi_flush_tlb_mm(void *arg)
+{
+	local_flush_tlb_mm(arg);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	on_each_cpu(ipi_flush_tlb_mm, mm, 1);
+}
+
+static void ipi_flush_tlb_page(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_tlb_page(fd->vma, fd->addr1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = addr,
+	};
+	on_each_cpu(ipi_flush_tlb_page, &fd, 1);
+}
+
+static void ipi_flush_tlb_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_tlb_range(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_tlb_range, &fd, 1);
+}
+
+/* Cache flush functions */
+
+static void ipi_flush_cache_all(void *arg)
+{
+	local_flush_cache_all();
+}
+
+void flush_cache_all(void)
+{
+	on_each_cpu(ipi_flush_cache_all, NULL, 1);
+}
+
+static void ipi_flush_cache_page(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_cache_page(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_cache_page(struct vm_area_struct *vma,
+		     unsigned long address, unsigned long pfn)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = address,
+		.addr2 = pfn,
+	};
+	on_each_cpu(ipi_flush_cache_page, &fd, 1);
+}
+
+static void ipi_flush_cache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_cache_range(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_cache_range(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_cache_range, &fd, 1);
+}
+
+static void ipi_flush_icache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_icache_range(fd->addr1, fd->addr2);
+}
+
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_icache_range, &fd, 1);
+}