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>

5 files changed, 1003 insertions, 0 deletions

diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
new file mode 100644
index 000000000000..75c6ce0682a2
--- /dev/null
+++ b/arch/loongarch/kernel/fpu.S
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Lu Zeng <zenglu@loongson.cn>
+ *         Pei Huang <huangpei@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/asm-offsets.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+#include <asm/fpregdef.h>
+#include <asm/loongarch.h>
+#include <asm/regdef.h>
+
+#define FPU_REG_WIDTH		8
+#define LSX_REG_WIDTH		16
+#define LASX_REG_WIDTH		32
+
+	.macro	EX insn, reg, src, offs
+.ex\@:	\insn	\reg, \src, \offs
+	.section __ex_table,"a"
+	PTR	.ex\@, fault
+	.previous
+	.endm
+
+	.macro sc_save_fp base
+	EX	fst.d $f0,  \base, (0 * FPU_REG_WIDTH)
+	EX	fst.d $f1,  \base, (1 * FPU_REG_WIDTH)
+	EX	fst.d $f2,  \base, (2 * FPU_REG_WIDTH)
+	EX	fst.d $f3,  \base, (3 * FPU_REG_WIDTH)
+	EX	fst.d $f4,  \base, (4 * FPU_REG_WIDTH)
+	EX	fst.d $f5,  \base, (5 * FPU_REG_WIDTH)
+	EX	fst.d $f6,  \base, (6 * FPU_REG_WIDTH)
+	EX	fst.d $f7,  \base, (7 * FPU_REG_WIDTH)
+	EX	fst.d $f8,  \base, (8 * FPU_REG_WIDTH)
+	EX	fst.d $f9,  \base, (9 * FPU_REG_WIDTH)
+	EX	fst.d $f10, \base, (10 * FPU_REG_WIDTH)
+	EX	fst.d $f11, \base, (11 * FPU_REG_WIDTH)
+	EX	fst.d $f12, \base, (12 * FPU_REG_WIDTH)
+	EX	fst.d $f13, \base, (13 * FPU_REG_WIDTH)
+	EX	fst.d $f14, \base, (14 * FPU_REG_WIDTH)
+	EX	fst.d $f15, \base, (15 * FPU_REG_WIDTH)
+	EX	fst.d $f16, \base, (16 * FPU_REG_WIDTH)
+	EX	fst.d $f17, \base, (17 * FPU_REG_WIDTH)
+	EX	fst.d $f18, \base, (18 * FPU_REG_WIDTH)
+	EX	fst.d $f19, \base, (19 * FPU_REG_WIDTH)
+	EX	fst.d $f20, \base, (20 * FPU_REG_WIDTH)
+	EX	fst.d $f21, \base, (21 * FPU_REG_WIDTH)
+	EX	fst.d $f22, \base, (22 * FPU_REG_WIDTH)
+	EX	fst.d $f23, \base, (23 * FPU_REG_WIDTH)
+	EX	fst.d $f24, \base, (24 * FPU_REG_WIDTH)
+	EX	fst.d $f25, \base, (25 * FPU_REG_WIDTH)
+	EX	fst.d $f26, \base, (26 * FPU_REG_WIDTH)
+	EX	fst.d $f27, \base, (27 * FPU_REG_WIDTH)
+	EX	fst.d $f28, \base, (28 * FPU_REG_WIDTH)
+	EX	fst.d $f29, \base, (29 * FPU_REG_WIDTH)
+	EX	fst.d $f30, \base, (30 * FPU_REG_WIDTH)
+	EX	fst.d $f31, \base, (31 * FPU_REG_WIDTH)
+	.endm
+
+	.macro sc_restore_fp base
+	EX	fld.d $f0,  \base, (0 * FPU_REG_WIDTH)
+	EX	fld.d $f1,  \base, (1 * FPU_REG_WIDTH)
+	EX	fld.d $f2,  \base, (2 * FPU_REG_WIDTH)
+	EX	fld.d $f3,  \base, (3 * FPU_REG_WIDTH)
+	EX	fld.d $f4,  \base, (4 * FPU_REG_WIDTH)
+	EX	fld.d $f5,  \base, (5 * FPU_REG_WIDTH)
+	EX	fld.d $f6,  \base, (6 * FPU_REG_WIDTH)
+	EX	fld.d $f7,  \base, (7 * FPU_REG_WIDTH)
+	EX	fld.d $f8,  \base, (8 * FPU_REG_WIDTH)
+	EX	fld.d $f9,  \base, (9 * FPU_REG_WIDTH)
+	EX	fld.d $f10, \base, (10 * FPU_REG_WIDTH)
+	EX	fld.d $f11, \base, (11 * FPU_REG_WIDTH)
+	EX	fld.d $f12, \base, (12 * FPU_REG_WIDTH)
+	EX	fld.d $f13, \base, (13 * FPU_REG_WIDTH)
+	EX	fld.d $f14, \base, (14 * FPU_REG_WIDTH)
+	EX	fld.d $f15, \base, (15 * FPU_REG_WIDTH)
+	EX	fld.d $f16, \base, (16 * FPU_REG_WIDTH)
+	EX	fld.d $f17, \base, (17 * FPU_REG_WIDTH)
+	EX	fld.d $f18, \base, (18 * FPU_REG_WIDTH)
+	EX	fld.d $f19, \base, (19 * FPU_REG_WIDTH)
+	EX	fld.d $f20, \base, (20 * FPU_REG_WIDTH)
+	EX	fld.d $f21, \base, (21 * FPU_REG_WIDTH)
+	EX	fld.d $f22, \base, (22 * FPU_REG_WIDTH)
+	EX	fld.d $f23, \base, (23 * FPU_REG_WIDTH)
+	EX	fld.d $f24, \base, (24 * FPU_REG_WIDTH)
+	EX	fld.d $f25, \base, (25 * FPU_REG_WIDTH)
+	EX	fld.d $f26, \base, (26 * FPU_REG_WIDTH)
+	EX	fld.d $f27, \base, (27 * FPU_REG_WIDTH)
+	EX	fld.d $f28, \base, (28 * FPU_REG_WIDTH)
+	EX	fld.d $f29, \base, (29 * FPU_REG_WIDTH)
+	EX	fld.d $f30, \base, (30 * FPU_REG_WIDTH)
+	EX	fld.d $f31, \base, (31 * FPU_REG_WIDTH)
+	.endm
+
+	.macro sc_save_fcc base, tmp0, tmp1
+	movcf2gr	\tmp0, $fcc0
+	move	\tmp1, \tmp0
+	movcf2gr	\tmp0, $fcc1
+	bstrins.d	\tmp1, \tmp0, 15, 8
+	movcf2gr	\tmp0, $fcc2
+	bstrins.d	\tmp1, \tmp0, 23, 16
+	movcf2gr	\tmp0, $fcc3
+	bstrins.d	\tmp1, \tmp0, 31, 24
+	movcf2gr	\tmp0, $fcc4
+	bstrins.d	\tmp1, \tmp0, 39, 32
+	movcf2gr	\tmp0, $fcc5
+	bstrins.d	\tmp1, \tmp0, 47, 40
+	movcf2gr	\tmp0, $fcc6
+	bstrins.d	\tmp1, \tmp0, 55, 48
+	movcf2gr	\tmp0, $fcc7
+	bstrins.d	\tmp1, \tmp0, 63, 56
+	EX	st.d \tmp1, \base, 0
+	.endm
+
+	.macro sc_restore_fcc base, tmp0, tmp1
+	EX	ld.d \tmp0, \base, 0
+	bstrpick.d	\tmp1, \tmp0, 7, 0
+	movgr2cf	$fcc0, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 15, 8
+	movgr2cf	$fcc1, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 23, 16
+	movgr2cf	$fcc2, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 31, 24
+	movgr2cf	$fcc3, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 39, 32
+	movgr2cf	$fcc4, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 47, 40
+	movgr2cf	$fcc5, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 55, 48
+	movgr2cf	$fcc6, \tmp1
+	bstrpick.d	\tmp1, \tmp0, 63, 56
+	movgr2cf	$fcc7, \tmp1
+	.endm
+
+	.macro sc_save_fcsr base, tmp0
+	movfcsr2gr	\tmp0, fcsr0
+	EX	st.w \tmp0, \base, 0
+	.endm
+
+	.macro sc_restore_fcsr base, tmp0
+	EX	ld.w \tmp0, \base, 0
+	movgr2fcsr	fcsr0, \tmp0
+	.endm
+
+	.macro sc_save_vcsr base, tmp0
+	movfcsr2gr	\tmp0, vcsr16
+	EX	st.w \tmp0, \base, 0
+	.endm
+
+	.macro sc_restore_vcsr base, tmp0
+	EX	ld.w \tmp0, \base, 0
+	movgr2fcsr	vcsr16, \tmp0
+	.endm
+
+/*
+ * Save a thread's fp context.
+ */
+SYM_FUNC_START(_save_fp)
+	fpu_save_csr	a0 t1
+	fpu_save_double a0 t1			# clobbers t1
+	fpu_save_cc	a0 t1 t2		# clobbers t1, t2
+	jirl zero, ra, 0
+SYM_FUNC_END(_save_fp)
+EXPORT_SYMBOL(_save_fp)
+
+/*
+ * Restore a thread's fp context.
+ */
+SYM_FUNC_START(_restore_fp)
+	fpu_restore_double a0 t1		# clobbers t1
+	fpu_restore_csr	a0 t1
+	fpu_restore_cc	a0 t1 t2		# clobbers t1, t2
+	jirl zero, ra, 0
+SYM_FUNC_END(_restore_fp)
+
+/*
+ * Load the FPU with signalling NANS.  This bit pattern we're using has
+ * the property that no matter whether considered as single or as double
+ * precision represents signaling NANS.
+ *
+ * The value to initialize fcsr0 to comes in $a0.
+ */
+
+SYM_FUNC_START(_init_fpu)
+	li.w	t1, CSR_EUEN_FPEN
+	csrxchg	t1, t1, LOONGARCH_CSR_EUEN
+
+	movgr2fcsr	fcsr0, a0
+
+	li.w	t1, -1				# SNaN
+
+	movgr2fr.d	$f0, t1
+	movgr2fr.d	$f1, t1
+	movgr2fr.d	$f2, t1
+	movgr2fr.d	$f3, t1
+	movgr2fr.d	$f4, t1
+	movgr2fr.d	$f5, t1
+	movgr2fr.d	$f6, t1
+	movgr2fr.d	$f7, t1
+	movgr2fr.d	$f8, t1
+	movgr2fr.d	$f9, t1
+	movgr2fr.d	$f10, t1
+	movgr2fr.d	$f11, t1
+	movgr2fr.d	$f12, t1
+	movgr2fr.d	$f13, t1
+	movgr2fr.d	$f14, t1
+	movgr2fr.d	$f15, t1
+	movgr2fr.d	$f16, t1
+	movgr2fr.d	$f17, t1
+	movgr2fr.d	$f18, t1
+	movgr2fr.d	$f19, t1
+	movgr2fr.d	$f20, t1
+	movgr2fr.d	$f21, t1
+	movgr2fr.d	$f22, t1
+	movgr2fr.d	$f23, t1
+	movgr2fr.d	$f24, t1
+	movgr2fr.d	$f25, t1
+	movgr2fr.d	$f26, t1
+	movgr2fr.d	$f27, t1
+	movgr2fr.d	$f28, t1
+	movgr2fr.d	$f29, t1
+	movgr2fr.d	$f30, t1
+	movgr2fr.d	$f31, t1
+
+	jirl zero, ra, 0
+SYM_FUNC_END(_init_fpu)
+
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_save_fp_context)
+	sc_save_fcc a1 t1 t2
+	sc_save_fcsr a2 t1
+	sc_save_fp a0
+	li.w	a0, 0					# success
+	jirl zero, ra, 0
+SYM_FUNC_END(_save_fp_context)
+
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_restore_fp_context)
+	sc_restore_fp a0
+	sc_restore_fcc a1 t1 t2
+	sc_restore_fcsr a2 t1
+	li.w	a0, 0					# success
+	jirl zero, ra, 0
+SYM_FUNC_END(_restore_fp_context)
+
+SYM_FUNC_START(fault)
+	li.w	a0, -EFAULT				# failure
+	jirl zero, ra, 0
+SYM_FUNC_END(fault)
diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c
new file mode 100644
index 000000000000..1a65d0527d25
--- /dev/null
+++ b/arch/loongarch/kernel/idle.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * LoongArch idle loop support.
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <linux/cpu.h>
+#include <linux/irqflags.h>
+#include <asm/cpu.h>
+#include <asm/idle.h>
+
+void __cpuidle arch_cpu_idle(void)
+{
+	raw_local_irq_enable();
+	__arch_cpu_idle(); /* idle instruction needs irq enabled */
+}
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 */
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
new file mode 100644
index 000000000000..e6ab87948e1d
--- /dev/null
+++ b/arch/loongarch/kernel/ptrace.c
@@ -0,0 +1,431 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Hanlu Li <lihanlu@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 1992 Ross Biro
+ * Copyright (C) Linus Torvalds
+ * Copyright (C) 1994, 95, 96, 97, 98, 2000 Ralf Baechle
+ * Copyright (C) 1996 David S. Miller
+ * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
+ * Copyright (C) 1999 MIPS Technologies, Inc.
+ * Copyright (C) 2000 Ulf Carlsson
+ */
+#include <linux/kernel.h>
+#include <linux/audit.h>
+#include <linux/compiler.h>
+#include <linux/context_tracking.h>
+#include <linux/elf.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/ptrace.h>
+#include <linux/regset.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/security.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/seccomp.h>
+#include <linux/uaccess.h>
+
+#include <asm/byteorder.h>
+#include <asm/cpu.h>
+#include <asm/cpu-info.h>
+#include <asm/fpu.h>
+#include <asm/loongarch.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/reg.h>
+#include <asm/syscall.h>
+
+static void init_fp_ctx(struct task_struct *target)
+{
+	/* The target already has context */
+	if (tsk_used_math(target))
+		return;
+
+	/* Begin with data registers set to all 1s... */
+	memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr));
+	set_stopped_child_used_math(target);
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure single step bits etc are not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+	/* Don't load the watchpoint registers for the ex-child. */
+	clear_tsk_thread_flag(child, TIF_LOAD_WATCH);
+	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+}
+
+/* regset get/set implementations */
+
+static int gpr_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	int r;
+	struct pt_regs *regs = task_pt_regs(target);
+
+	r = membuf_write(&to, &regs->regs, sizeof(u64) * GPR_NUM);
+	r = membuf_write(&to, &regs->orig_a0, sizeof(u64));
+	r = membuf_write(&to, &regs->csr_era, sizeof(u64));
+	r = membuf_write(&to, &regs->csr_badvaddr, sizeof(u64));
+
+	return r;
+}
+
+static int gpr_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int err;
+	int a0_start = sizeof(u64) * GPR_NUM;
+	int era_start = a0_start + sizeof(u64);
+	int badvaddr_start = era_start + sizeof(u64);
+	struct pt_regs *regs = task_pt_regs(target);
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->regs,
+				 0, a0_start);
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->orig_a0,
+				 a0_start, a0_start + sizeof(u64));
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->csr_era,
+				 era_start, era_start + sizeof(u64));
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->csr_badvaddr,
+				 badvaddr_start, badvaddr_start + sizeof(u64));
+
+	return err;
+}
+
+
+/*
+ * Get the general floating-point registers.
+ */
+static int gfpr_get(struct task_struct *target, struct membuf *to)
+{
+	return membuf_write(to, &target->thread.fpu.fpr,
+			    sizeof(elf_fpreg_t) * NUM_FPU_REGS);
+}
+
+static int gfpr_get_simd(struct task_struct *target, struct membuf *to)
+{
+	int i, r;
+	u64 fpr_val;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
+		r = membuf_write(to, &fpr_val, sizeof(elf_fpreg_t));
+	}
+
+	return r;
+}
+
+/*
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCC and FCSR registers separately.
+ */
+static int fpr_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	int r;
+
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		r = gfpr_get(target, &to);
+	else
+		r = gfpr_get_simd(target, &to);
+
+	r = membuf_write(&to, &target->thread.fpu.fcc, sizeof(target->thread.fpu.fcc));
+	r = membuf_write(&to, &target->thread.fpu.fcsr, sizeof(target->thread.fpu.fcsr));
+
+	return r;
+}
+
+static int gfpr_set(struct task_struct *target,
+		    unsigned int *pos, unsigned int *count,
+		    const void **kbuf, const void __user **ubuf)
+{
+	return user_regset_copyin(pos, count, kbuf, ubuf,
+				  &target->thread.fpu.fpr,
+				  0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+static int gfpr_set_simd(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       const void **kbuf, const void __user **ubuf)
+{
+	int i, err;
+	u64 fpr_val;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) {
+		err = user_regset_copyin(pos, count, kbuf, ubuf,
+					 &fpr_val, i * sizeof(elf_fpreg_t),
+					 (i + 1) * sizeof(elf_fpreg_t));
+		if (err)
+			return err;
+		set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
+	}
+
+	return 0;
+}
+
+/*
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCC register separately.
+ */
+static int fpr_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	const int fcc_start = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+	const int fcc_end = fcc_start + sizeof(u64);
+	int err;
+
+	BUG_ON(count % sizeof(elf_fpreg_t));
+	if (pos + count > sizeof(elf_fpregset_t))
+		return -EIO;
+
+	init_fp_ctx(target);
+
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		err = gfpr_set(target, &pos, &count, &kbuf, &ubuf);
+	else
+		err = gfpr_set_simd(target, &pos, &count, &kbuf, &ubuf);
+	if (err)
+		return err;
+
+	if (count > 0)
+		err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.fpu.fcc,
+					  fcc_start, fcc_end);
+
+	return err;
+}
+
+static int cfg_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	int i, r;
+	u32 cfg_val;
+
+	i = 0;
+	while (to.left > 0) {
+		cfg_val = read_cpucfg(i++);
+		r = membuf_write(&to, &cfg_val, sizeof(u32));
+	}
+
+	return r;
+}
+
+/*
+ * CFG registers are read-only.
+ */
+static int cfg_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(n, r) {.name = #n, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_NAME(r0, regs[0]),
+	REG_OFFSET_NAME(r1, regs[1]),
+	REG_OFFSET_NAME(r2, regs[2]),
+	REG_OFFSET_NAME(r3, regs[3]),
+	REG_OFFSET_NAME(r4, regs[4]),
+	REG_OFFSET_NAME(r5, regs[5]),
+	REG_OFFSET_NAME(r6, regs[6]),
+	REG_OFFSET_NAME(r7, regs[7]),
+	REG_OFFSET_NAME(r8, regs[8]),
+	REG_OFFSET_NAME(r9, regs[9]),
+	REG_OFFSET_NAME(r10, regs[10]),
+	REG_OFFSET_NAME(r11, regs[11]),
+	REG_OFFSET_NAME(r12, regs[12]),
+	REG_OFFSET_NAME(r13, regs[13]),
+	REG_OFFSET_NAME(r14, regs[14]),
+	REG_OFFSET_NAME(r15, regs[15]),
+	REG_OFFSET_NAME(r16, regs[16]),
+	REG_OFFSET_NAME(r17, regs[17]),
+	REG_OFFSET_NAME(r18, regs[18]),
+	REG_OFFSET_NAME(r19, regs[19]),
+	REG_OFFSET_NAME(r20, regs[20]),
+	REG_OFFSET_NAME(r21, regs[21]),
+	REG_OFFSET_NAME(r22, regs[22]),
+	REG_OFFSET_NAME(r23, regs[23]),
+	REG_OFFSET_NAME(r24, regs[24]),
+	REG_OFFSET_NAME(r25, regs[25]),
+	REG_OFFSET_NAME(r26, regs[26]),
+	REG_OFFSET_NAME(r27, regs[27]),
+	REG_OFFSET_NAME(r28, regs[28]),
+	REG_OFFSET_NAME(r29, regs[29]),
+	REG_OFFSET_NAME(r30, regs[30]),
+	REG_OFFSET_NAME(r31, regs[31]),
+	REG_OFFSET_NAME(orig_a0, orig_a0),
+	REG_OFFSET_NAME(csr_era, csr_era),
+	REG_OFFSET_NAME(csr_badvaddr, csr_badvaddr),
+	REG_OFFSET_NAME(csr_crmd, csr_crmd),
+	REG_OFFSET_NAME(csr_prmd, csr_prmd),
+	REG_OFFSET_NAME(csr_euen, csr_euen),
+	REG_OFFSET_NAME(csr_ecfg, csr_ecfg),
+	REG_OFFSET_NAME(csr_estat, csr_estat),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:       the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+enum loongarch_regset {
+	REGSET_GPR,
+	REGSET_FPR,
+	REGSET_CPUCFG,
+};
+
+static const struct user_regset loongarch64_regsets[] = {
+	[REGSET_GPR] = {
+		.core_note_type	= NT_PRSTATUS,
+		.n		= ELF_NGREG,
+		.size		= sizeof(elf_greg_t),
+		.align		= sizeof(elf_greg_t),
+		.regset_get	= gpr_get,
+		.set		= gpr_set,
+	},
+	[REGSET_FPR] = {
+		.core_note_type	= NT_PRFPREG,
+		.n		= ELF_NFPREG,
+		.size		= sizeof(elf_fpreg_t),
+		.align		= sizeof(elf_fpreg_t),
+		.regset_get	= fpr_get,
+		.set		= fpr_set,
+	},
+	[REGSET_CPUCFG] = {
+		.core_note_type	= NT_LOONGARCH_CPUCFG,
+		.n		= 64,
+		.size		= sizeof(u32),
+		.align		= sizeof(u32),
+		.regset_get	= cfg_get,
+		.set		= cfg_set,
+	},
+};
+
+static const struct user_regset_view user_loongarch64_view = {
+	.name		= "loongarch64",
+	.e_machine	= ELF_ARCH,
+	.regsets	= loongarch64_regsets,
+	.n		= ARRAY_SIZE(loongarch64_regsets),
+};
+
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_loongarch64_view;
+}
+
+static inline int read_user(struct task_struct *target, unsigned long addr,
+			    unsigned long __user *data)
+{
+	unsigned long tmp = 0;
+
+	switch (addr) {
+	case 0 ... 31:
+		tmp = task_pt_regs(target)->regs[addr];
+		break;
+	case ARG0:
+		tmp = task_pt_regs(target)->orig_a0;
+		break;
+	case PC:
+		tmp = task_pt_regs(target)->csr_era;
+		break;
+	case BADVADDR:
+		tmp = task_pt_regs(target)->csr_badvaddr;
+		break;
+	default:
+		return -EIO;
+	}
+
+	return put_user(tmp, data);
+}
+
+static inline int write_user(struct task_struct *target, unsigned long addr,
+			    unsigned long data)
+{
+	switch (addr) {
+	case 0 ... 31:
+		task_pt_regs(target)->regs[addr] = data;
+		break;
+	case ARG0:
+		task_pt_regs(target)->orig_a0 = data;
+		break;
+	case PC:
+		task_pt_regs(target)->csr_era = data;
+		break;
+	case BADVADDR:
+		task_pt_regs(target)->csr_badvaddr = data;
+		break;
+	default:
+		return -EIO;
+	}
+
+	return 0;
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	int ret;
+	unsigned long __user *datap = (void __user *) data;
+
+	switch (request) {
+	case PTRACE_PEEKUSR:
+		ret = read_user(child, addr, datap);
+		break;
+
+	case PTRACE_POKEUSR:
+		ret = write_user(child, addr, data);
+		break;
+
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
new file mode 100644
index 000000000000..53e2fa8e580e
--- /dev/null
+++ b/arch/loongarch/kernel/switch.S
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/asm-offsets.h>
+#include <asm/loongarch.h>
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/thread_info.h>
+
+/*
+ * task_struct *__switch_to(task_struct *prev, task_struct *next,
+ *			    struct thread_info *next_ti)
+ */
+	.align	5
+SYM_FUNC_START(__switch_to)
+	csrrd	t1, LOONGARCH_CSR_PRMD
+	stptr.d	t1, a0, THREAD_CSRPRMD
+
+	cpu_save_nonscratch a0
+	stptr.d	ra, a0, THREAD_REG01
+	move	tp, a2
+	cpu_restore_nonscratch a1
+
+	li.w	t0, _THREAD_SIZE - 32
+	PTR_ADD	t0, t0, tp
+	set_saved_sp	t0, t1, t2
+
+	ldptr.d	t1, a1, THREAD_CSRPRMD
+	csrwr	t1, LOONGARCH_CSR_PRMD
+
+	jr	ra
+SYM_FUNC_END(__switch_to)