LoongArch: Add process management

Add process management support for LoongArch, including: thread info
definition, context switch and process tracing.

Reviewed-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

1 files changed, 260 insertions, 0 deletions

diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
new file mode 100644
index 000000000000..54020223068f
--- /dev/null
+++ b/arch/loongarch/kernel/process.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 1994 - 1999, 2000 by Ralf Baechle and others.
+ * Copyright (C) 2005, 2006 by Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2004 Thiemo Seufer
+ * Copyright (C) 2013  Imagination Technologies Ltd.
+ */
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/export.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/personality.h>
+#include <linux/sys.h>
+#include <linux/completion.h>
+#include <linux/kallsyms.h>
+#include <linux/random.h>
+#include <linux/prctl.h>
+#include <linux/nmi.h>
+
+#include <asm/asm.h>
+#include <asm/bootinfo.h>
+#include <asm/cpu.h>
+#include <asm/elf.h>
+#include <asm/fpu.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/loongarch.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/reg.h>
+#include <asm/vdso.h>
+
+/*
+ * Idle related variables and functions
+ */
+
+unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
+
+void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
+{
+	unsigned long crmd;
+	unsigned long prmd;
+	unsigned long euen;
+
+	/* New thread loses kernel privileges. */
+	crmd = regs->csr_crmd & ~(PLV_MASK);
+	crmd |= PLV_USER;
+	regs->csr_crmd = crmd;
+
+	prmd = regs->csr_prmd & ~(PLV_MASK);
+	prmd |= PLV_USER;
+	regs->csr_prmd = prmd;
+
+	euen = regs->csr_euen & ~(CSR_EUEN_FPEN);
+	regs->csr_euen = euen;
+	lose_fpu(0);
+
+	clear_thread_flag(TIF_LSX_CTX_LIVE);
+	clear_thread_flag(TIF_LASX_CTX_LIVE);
+	clear_used_math();
+	regs->csr_era = pc;
+	regs->regs[3] = sp;
+}
+
+void exit_thread(struct task_struct *tsk)
+{
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	/*
+	 * Save any process state which is live in hardware registers to the
+	 * parent context prior to duplication. This prevents the new child
+	 * state becoming stale if the parent is preempted before copy_thread()
+	 * gets a chance to save the parent's live hardware registers to the
+	 * child context.
+	 */
+	preempt_disable();
+
+	if (is_fpu_owner())
+		save_fp(current);
+
+	preempt_enable();
+
+	if (used_math())
+		memcpy(dst, src, sizeof(struct task_struct));
+	else
+		memcpy(dst, src, offsetof(struct task_struct, thread.fpu.fpr));
+
+	return 0;
+}
+
+/*
+ * Copy architecture-specific thread state
+ */
+int copy_thread(unsigned long clone_flags, unsigned long usp,
+	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+{
+	unsigned long childksp;
+	struct pt_regs *childregs, *regs = current_pt_regs();
+
+	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
+
+	/* set up new TSS. */
+	childregs = (struct pt_regs *) childksp - 1;
+	/*  Put the stack after the struct pt_regs.  */
+	childksp = (unsigned long) childregs;
+	p->thread.csr_euen = 0;
+	p->thread.csr_crmd = csr_read32(LOONGARCH_CSR_CRMD);
+	p->thread.csr_prmd = csr_read32(LOONGARCH_CSR_PRMD);
+	p->thread.csr_ecfg = csr_read32(LOONGARCH_CSR_ECFG);
+	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+		/* kernel thread */
+		p->thread.reg23 = usp; /* fn */
+		p->thread.reg24 = kthread_arg;
+		p->thread.reg03 = childksp;
+		p->thread.reg01 = (unsigned long) ret_from_kernel_thread;
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->csr_euen = p->thread.csr_euen;
+		childregs->csr_crmd = p->thread.csr_crmd;
+		childregs->csr_prmd = p->thread.csr_prmd;
+		childregs->csr_ecfg = p->thread.csr_ecfg;
+		return 0;
+	}
+
+	/* user thread */
+	*childregs = *regs;
+	childregs->regs[4] = 0; /* Child gets zero as return value */
+	if (usp)
+		childregs->regs[3] = usp;
+
+	p->thread.reg03 = (unsigned long) childregs;
+	p->thread.reg01 = (unsigned long) ret_from_fork;
+
+	/*
+	 * New tasks lose permission to use the fpu. This accelerates context
+	 * switching for most programs since they don't use the fpu.
+	 */
+	childregs->csr_euen = 0;
+
+	clear_tsk_thread_flag(p, TIF_USEDFPU);
+	clear_tsk_thread_flag(p, TIF_USEDSIMD);
+	clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE);
+	clear_tsk_thread_flag(p, TIF_LASX_CTX_LIVE);
+
+	if (clone_flags & CLONE_SETTLS)
+		childregs->regs[2] = tls;
+
+	return 0;
+}
+
+unsigned long __get_wchan(struct task_struct *task)
+{
+	return 0;
+}
+
+unsigned long stack_top(void)
+{
+	unsigned long top = TASK_SIZE & PAGE_MASK;
+
+	/* Space for the VDSO & data page */
+	top -= PAGE_ALIGN(current->thread.vdso->size);
+	top -= PAGE_SIZE;
+
+	/* Space to randomize the VDSO base */
+	if (current->flags & PF_RANDOMIZE)
+		top -= VDSO_RANDOMIZE_SIZE;
+
+	return top;
+}
+
+/*
+ * Don't forget that the stack pointer must be aligned on a 8 bytes
+ * boundary for 32-bits ABI and 16 bytes for 64-bits ABI.
+ */
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_int() & ~PAGE_MASK;
+
+	return sp & STACK_ALIGN;
+}
+
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
+static struct cpumask backtrace_csd_busy;
+
+static void handle_backtrace(void *info)
+{
+	nmi_cpu_backtrace(get_irq_regs());
+	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
+}
+
+static void raise_backtrace(cpumask_t *mask)
+{
+	call_single_data_t *csd;
+	int cpu;
+
+	for_each_cpu(cpu, mask) {
+		/*
+		 * If we previously sent an IPI to the target CPU & it hasn't
+		 * cleared its bit in the busy cpumask then it didn't handle
+		 * our previous IPI & it's not safe for us to reuse the
+		 * call_single_data_t.
+		 */
+		if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
+			pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
+				cpu);
+			continue;
+		}
+
+		csd = &per_cpu(backtrace_csd, cpu);
+		csd->func = handle_backtrace;
+		smp_call_function_single_async(cpu, csd);
+	}
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+{
+	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
+}
+
+#ifdef CONFIG_64BIT
+void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs)
+{
+	unsigned int i;
+
+	for (i = LOONGARCH_EF_R1; i <= LOONGARCH_EF_R31; i++) {
+		uregs[i] = regs->regs[i - LOONGARCH_EF_R0];
+	}
+
+	uregs[LOONGARCH_EF_ORIG_A0] = regs->orig_a0;
+	uregs[LOONGARCH_EF_CSR_ERA] = regs->csr_era;
+	uregs[LOONGARCH_EF_CSR_BADV] = regs->csr_badvaddr;
+	uregs[LOONGARCH_EF_CSR_CRMD] = regs->csr_crmd;
+	uregs[LOONGARCH_EF_CSR_PRMD] = regs->csr_prmd;
+	uregs[LOONGARCH_EF_CSR_EUEN] = regs->csr_euen;
+	uregs[LOONGARCH_EF_CSR_ECFG] = regs->csr_ecfg;
+	uregs[LOONGARCH_EF_CSR_ESTAT] = regs->csr_estat;
+}
+#endif /* CONFIG_64BIT */