RISC-V: Avoid using per cpu array for ordered booting

Currently both order booting and spinwait approach uses a per cpu
array to update stack & task pointer. This approach will not work for the
following cases.
1. If NR_CPUs are configured to be less than highest hart id.
2. A platform has sparse hartid.

This issue can be fixed for ordered booting as the booting cpu brings up
one cpu at a time using SBI HSM extension which has opaque parameter
that is unused until now.

Introduce a common secondary boot data structure that can store the stack
and task pointer. Secondary harts will use this data while booting up
to setup the sp & tp.

Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/include/asm/cpu_ops_sbi.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 by Rivos Inc.
+ */
+#ifndef __ASM_CPU_OPS_SBI_H
+#define __ASM_CPU_OPS_SBI_H
+
+#ifndef __ASSEMBLY__
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+/**
+ * struct sbi_hart_boot_data - Hart specific boot used during booting and
+ *			       cpu hotplug.
+ * @task_ptr: A pointer to the hart specific tp
+ * @stack_ptr: A pointer to the hart specific sp
+ */
+struct sbi_hart_boot_data {
+	void *task_ptr;
+	void *stack_ptr;
+};
+#endif
+
+#endif /* ifndef __ASM_CPU_OPS_SBI_H */

arch/riscv/kernel/asm-offsets.c

@@ -12,6 +12,7 @@
 #include <asm/kvm_host.h>
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
+#include <asm/cpu_ops_sbi.h>
 
 void asm_offsets(void);
 
@@ -468,4 +469,6 @@ void asm_offsets(void)
 	DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
 
 	OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
+	OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr);
+	OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
 }

arch/riscv/kernel/cpu_ops_sbi.c

@@ -7,13 +7,22 @@
 
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched/task_stack.h>
 #include <asm/cpu_ops.h>
+#include <asm/cpu_ops_sbi.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
 extern char secondary_start_sbi[];
 const struct cpu_operations cpu_ops_sbi;
 
+/*
+ * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
+ * be invoked from multiple threads in parallel. Define a per cpu data
+ * to handle that.
+ */
+DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
 {
@@ -55,14 +64,19 @@ static int sbi_hsm_hart_get_status(unsigned long hartid)
 
 static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
-	int rc;
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	int hartid = cpuid_to_hartid_map(cpuid);
+	unsigned long hsm_data;
+	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
 
-	cpu_update_secondary_bootdata(cpuid, tidle);
+	/* Make sure tidle is updated */
-	rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
+	smp_mb();
-
+	bdata->task_ptr = tidle;
-	return rc;
+	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	/* Make sure boot data is updated */
+	smp_mb();
+	hsm_data = __pa(bdata);
+	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
 static int sbi_cpu_prepare(unsigned int cpuid)

arch/riscv/kernel/head.S

@@ -11,6 +11,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
+#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include "efi-header.S"
@@ -168,15 +169,15 @@ secondary_start_sbi:
 	la a3, .Lsecondary_park
 	csrw CSR_TVEC, a3
 
-	slli a3, a0, LGREG
+	/* a0 contains the hartid & a1 contains boot data */
-	la a4, __cpu_up_stack_pointer
+	li a2, SBI_HART_BOOT_TASK_PTR_OFFSET
-	XIP_FIXUP_OFFSET a4
+	XIP_FIXUP_OFFSET a2
-	la a5, __cpu_up_task_pointer
+	add a2, a2, a1
-	XIP_FIXUP_OFFSET a5
+	REG_L tp, (a2)
-	add a4, a3, a4
+	li a3, SBI_HART_BOOT_STACK_PTR_OFFSET
-	add a5, a3, a5
+	XIP_FIXUP_OFFSET a3
-	REG_L sp, (a4)
+	add a3, a3, a1
-	REG_L tp, (a5)
+	REG_L sp, (a3)
 
 .Lsecondary_start_common: