RISC-V: Use Linux logical CPU number instead of hartid

Setup the cpu_logical_map during boot. Moreover, every SBI call
and PLIC context are based on the physical hartid. Use the logical
CPU to hartid mapping to pass correct hartid to respective functions.
Signed-off-by: NAtish Patra <atish.patra@wdc.com>
Reviewed-by: NAnup Patel <anup@brainfault.org>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NPalmer Dabbelt <palmer@sifive.com>

arch/riscv/include/asm/tlbflush.h

@@ -16,6 +16,7 @@
 #define _ASM_RISCV_TLBFLUSH_H
 
 #include <linux/mm_types.h>
+#include <asm/smp.h>
 
 /*
  * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
@@ -49,13 +50,22 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 
 #include <asm/sbi.h>
 
+static inline void remote_sfence_vma(struct cpumask *cmask, unsigned long start,
+				     unsigned long size)
+{
+	struct cpumask hmask;
+
+	cpumask_clear(&hmask);
+	riscv_cpuid_to_hartid_mask(cmask, &hmask);
+	sbi_remote_sfence_vma(hmask.bits, start, size);
+}
+
 #define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
 #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
 #define flush_tlb_range(vma, start, end) \
-	sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \
-			      start, (end) - (start))
+	remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start))
 #define flush_tlb_mm(mm) \
-	sbi_remote_sfence_vma(mm_cpumask(mm)->bits, 0, -1)
+	remote_sfence_vma(mm_cpumask(mm), 0, -1)
 
 #endif /* CONFIG_SMP */
 

arch/riscv/kernel/cpu.c

@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/of.h>
+#include <asm/smp.h>
 
 /*
  * Returns the hart ID of the given device tree node, or -1 if the device tree
@@ -138,11 +139,12 @@ static void c_stop(struct seq_file *m, void *v)
 
 static int c_show(struct seq_file *m, void *v)
 {
-	unsigned long hart_id = (unsigned long)v - 1;
-	struct device_node *node = of_get_cpu_node(hart_id, NULL);
+	unsigned long cpu_id = (unsigned long)v - 1;
+	struct device_node *node = of_get_cpu_node(cpuid_to_hartid_map(cpu_id),
+						   NULL);
 	const char *compat, *isa, *mmu;
 
-	seq_printf(m, "hart\t: %lu\n", hart_id);
+	seq_printf(m, "hart\t: %lu\n", cpu_id);
 	if (!of_property_read_string(node, "riscv,isa", &isa))
 		print_isa(m, isa);
 	if (!of_property_read_string(node, "mmu-type", &mmu))

arch/riscv/kernel/head.S

@@ -47,6 +47,8 @@ ENTRY(_start)
 	/* Save hart ID and DTB physical address */
 	mv s0, a0
 	mv s1, a1
+	la a2, boot_cpu_hartid
+	REG_S a0, (a2)
 
 	/* Initialize page tables and relocate to virtual addresses */
 	la sp, init_thread_union + THREAD_SIZE
@@ -55,7 +57,7 @@ ENTRY(_start)
 
 	/* Restore C environment */
 	la tp, init_task
-	sw s0, TASK_TI_CPU(tp)
+	sw zero, TASK_TI_CPU(tp)
 
 	la sp, init_thread_union
 	li a0, ASM_THREAD_SIZE

arch/riscv/kernel/setup.c

@@ -81,11 +81,17 @@ EXPORT_SYMBOL(empty_zero_page);
 
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
+unsigned long boot_cpu_hartid;
 
 unsigned long __cpuid_to_hartid_map[NR_CPUS] = {
 	[0 ... NR_CPUS-1] = INVALID_HARTID
 };
 
+void __init smp_setup_processor_id(void)
+{
+	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+}
+
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {

arch/riscv/kernel/smp.c

@@ -97,14 +97,18 @@ void riscv_software_interrupt(void)
 static void
 send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {
-	int i;
+	int cpuid, hartid;
+	struct cpumask hartid_mask;
 
+	cpumask_clear(&hartid_mask);
 	mb();
-	for_each_cpu(i, to_whom)
-		set_bit(operation, &ipi_data[i].bits);
-
+	for_each_cpu(cpuid, to_whom) {
+		set_bit(operation, &ipi_data[cpuid].bits);
+		hartid = cpuid_to_hartid_map(cpuid);
+		cpumask_set_cpu(hartid, &hartid_mask);
+	}
 	mb();
-	sbi_send_ipi(cpumask_bits(to_whom));
+	sbi_send_ipi(cpumask_bits(&hartid_mask));
 }
 
 void arch_send_call_function_ipi_mask(struct cpumask *mask)
@@ -146,7 +150,7 @@ void smp_send_reschedule(int cpu)
 void flush_icache_mm(struct mm_struct *mm, bool local)
 {
 	unsigned int cpu;
-	cpumask_t others, *mask;
+	cpumask_t others, hmask, *mask;
 
 	preempt_disable();
 
@@ -164,9 +168,11 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 	 */
 	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
 	local |= cpumask_empty(&others);
-	if (mm != current->active_mm || !local)
-		sbi_remote_fence_i(others.bits);
-	else {
+	if (mm != current->active_mm || !local) {
+		cpumask_clear(&hmask);
+		riscv_cpuid_to_hartid_mask(&others, &hmask);
+		sbi_remote_fence_i(hmask.bits);
+	} else {
 		/*
 		 * It's assumed that at least one strongly ordered operation is
 		 * performed on this hart between setting a hart's cpumask bit

arch/riscv/kernel/smpboot.c

@@ -53,17 +53,23 @@ void __init setup_smp(void)
 	struct device_node *dn = NULL;
 	int hart;
 	bool found_boot_cpu = false;
+	int cpuid = 1;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
 		hart = riscv_of_processor_hartid(dn);
-		if (hart >= 0) {
-			set_cpu_possible(hart, true);
-			set_cpu_present(hart, true);
-			if (hart == smp_processor_id()) {
-				BUG_ON(found_boot_cpu);
-				found_boot_cpu = true;
-			}
+		if (hart < 0)
+			continue;
+
+		if (hart == cpuid_to_hartid_map(0)) {
+			BUG_ON(found_boot_cpu);
+			found_boot_cpu = 1;
+			continue;
 		}
+
+		cpuid_to_hartid_map(cpuid) = hart;
+		set_cpu_possible(cpuid, true);
+		set_cpu_present(cpuid, true);
+		cpuid++;
 	}
 
 	BUG_ON(!found_boot_cpu);
@@ -71,6 +77,7 @@ void __init setup_smp(void)
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
+	int hartid = cpuid_to_hartid_map(cpu);
 	tidle->thread_info.cpu = cpu;
 
 	/*
@@ -81,9 +88,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 * the spinning harts that they can continue the boot process.
 	 */
 	smp_mb();
-	WRITE_ONCE(__cpu_up_stack_pointer[cpu],
+	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
 		  task_stack_page(tidle) + THREAD_SIZE);
-	WRITE_ONCE(__cpu_up_task_pointer[cpu], tidle);
+	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
 
 	while (!cpu_online(cpu))
 		cpu_relax();

drivers/clocksource/riscv_timer.c

@@ -8,6 +8,7 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
+#include <asm/smp.h>
 #include <asm/sbi.h>
 
 /*
@@ -84,13 +85,16 @@ void riscv_timer_interrupt(void)
 
 static int __init riscv_timer_init_dt(struct device_node *n)
 {
-	int cpu_id = riscv_of_processor_hartid(n), error;
+	int cpuid, hartid, error;
 	struct clocksource *cs;
 
-	if (cpu_id != smp_processor_id())
+	hartid = riscv_of_processor_hartid(n);
+	cpuid = riscv_hartid_to_cpuid(hartid);
+
+	if (cpuid != smp_processor_id())
 		return 0;
 
-	cs = per_cpu_ptr(&riscv_clocksource, cpu_id);
+	cs = per_cpu_ptr(&riscv_clocksource, cpuid);
 	clocksource_register_hz(cs, riscv_timebase);
 
 	error = cpuhp_setup_state(CPUHP_AP_RISCV_TIMER_STARTING,
@@ -98,7 +102,7 @@ static int __init riscv_timer_init_dt(struct device_node *n)
 			 riscv_timer_starting_cpu, riscv_timer_dying_cpu);
 	if (error)
 		pr_err("RISCV timer register failed [%d] for cpu = [%d]\n",
-		       error, cpu_id);
+		       error, cpuid);
 	return error;
 }
 

drivers/irqchip/irq-sifive-plic.c

@@ -15,6 +15,7 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
+#include <asm/smp.h>
 
 /*
  * This driver implements a version of the RISC-V PLIC with the actual layout
@@ -218,7 +219,7 @@ static int __init plic_init(struct device_node *node,
 		struct of_phandle_args parent;
 		struct plic_handler *handler;
 		irq_hw_number_t hwirq;
-		int cpu;
+		int cpu, hartid;
 
 		if (of_irq_parse_one(node, i, &parent)) {
 			pr_err("failed to parse parent for context %d.\n", i);
@@ -229,12 +230,13 @@ static int __init plic_init(struct device_node *node,
 		if (parent.args[0] == -1)
 			continue;
 
-		cpu = plic_find_hart_id(parent.np);
-		if (cpu < 0) {
+		hartid = plic_find_hart_id(parent.np);
+		if (hartid < 0) {
 			pr_warn("failed to parse hart ID for context %d.\n", i);
 			continue;
 		}
 
+		cpu = riscv_hartid_to_cpuid(hartid);
 		handler = per_cpu_ptr(&plic_handlers, cpu);
 		handler->present = true;
 		handler->ctxid = i;