LoongArch: Add vector extensions support

Add LoongArch's vector extensions support, which including 128bit LSX
(i.e., Loongson SIMD eXtension) and 256bit LASX (i.e., Loongson Advanced
SIMD eXtension).

Linux kernel doesn't use vector itself, it only handle exceptions and
context save/restore. So it only needs a subset of these instructions:

* Vector load/store:   vld vst vldx vstx xvld xvst xvldx xvstx
* 8bit-elements move:  vpickve2gr.b xvpickve2gr.b vinsgr2vr.b xvinsgr2vr.b
* 16bit-elements move: vpickve2gr.h xvpickve2gr.h vinsgr2vr.h xvinsgr2vr.h
* 32bit-elements move: vpickve2gr.w xvpickve2gr.w vinsgr2vr.w xvinsgr2vr.w
* 64bit-elements move: vpickve2gr.d xvpickve2gr.d vinsgr2vr.d xvinsgr2vr.d
* Elements permute:    vpermi.w vpermi.d xvpermi.w xvpermi.d xvpermi.q

Introduce AS_HAS_LSX_EXTENSION and AS_HAS_LASX_EXTENSION to avoid non-
vector toolchains complains unsupported instructions.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

6 files changed, 803 insertions, 9 deletions

diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index 5adf0f736c6d..f42acc6c8df6 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -116,6 +116,18 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		c->options |= LOONGARCH_CPU_FPU;
 		elf_hwcap |= HWCAP_LOONGARCH_FPU;
 	}
+#ifdef CONFIG_CPU_HAS_LSX
+	if (config & CPUCFG2_LSX) {
+		c->options |= LOONGARCH_CPU_LSX;
+		elf_hwcap |= HWCAP_LOONGARCH_LSX;
+	}
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
+	if (config & CPUCFG2_LASX) {
+		c->options |= LOONGARCH_CPU_LASX;
+		elf_hwcap |= HWCAP_LOONGARCH_LASX;
+	}
+#endif
 	if (config & CPUCFG2_COMPLEX) {
 		c->options |= LOONGARCH_CPU_COMPLEX;
 		elf_hwcap |= HWCAP_LOONGARCH_COMPLEX;
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index ccde94140c89..f3df5f0a4509 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -145,6 +145,154 @@
 	movgr2fcsr	fcsr0, \tmp0
 	.endm
 
+	.macro sc_save_lsx base
+#ifdef CONFIG_CPU_HAS_LSX
+	EX	vst	$vr0,  \base, (0 * LSX_REG_WIDTH)
+	EX	vst	$vr1,  \base, (1 * LSX_REG_WIDTH)
+	EX	vst	$vr2,  \base, (2 * LSX_REG_WIDTH)
+	EX	vst	$vr3,  \base, (3 * LSX_REG_WIDTH)
+	EX	vst	$vr4,  \base, (4 * LSX_REG_WIDTH)
+	EX	vst	$vr5,  \base, (5 * LSX_REG_WIDTH)
+	EX	vst	$vr6,  \base, (6 * LSX_REG_WIDTH)
+	EX	vst	$vr7,  \base, (7 * LSX_REG_WIDTH)
+	EX	vst	$vr8,  \base, (8 * LSX_REG_WIDTH)
+	EX	vst	$vr9,  \base, (9 * LSX_REG_WIDTH)
+	EX	vst	$vr10, \base, (10 * LSX_REG_WIDTH)
+	EX	vst	$vr11, \base, (11 * LSX_REG_WIDTH)
+	EX	vst	$vr12, \base, (12 * LSX_REG_WIDTH)
+	EX	vst	$vr13, \base, (13 * LSX_REG_WIDTH)
+	EX	vst	$vr14, \base, (14 * LSX_REG_WIDTH)
+	EX	vst	$vr15, \base, (15 * LSX_REG_WIDTH)
+	EX	vst	$vr16, \base, (16 * LSX_REG_WIDTH)
+	EX	vst	$vr17, \base, (17 * LSX_REG_WIDTH)
+	EX	vst	$vr18, \base, (18 * LSX_REG_WIDTH)
+	EX	vst	$vr19, \base, (19 * LSX_REG_WIDTH)
+	EX	vst	$vr20, \base, (20 * LSX_REG_WIDTH)
+	EX	vst	$vr21, \base, (21 * LSX_REG_WIDTH)
+	EX	vst	$vr22, \base, (22 * LSX_REG_WIDTH)
+	EX	vst	$vr23, \base, (23 * LSX_REG_WIDTH)
+	EX	vst	$vr24, \base, (24 * LSX_REG_WIDTH)
+	EX	vst	$vr25, \base, (25 * LSX_REG_WIDTH)
+	EX	vst	$vr26, \base, (26 * LSX_REG_WIDTH)
+	EX	vst	$vr27, \base, (27 * LSX_REG_WIDTH)
+	EX	vst	$vr28, \base, (28 * LSX_REG_WIDTH)
+	EX	vst	$vr29, \base, (29 * LSX_REG_WIDTH)
+	EX	vst	$vr30, \base, (30 * LSX_REG_WIDTH)
+	EX	vst	$vr31, \base, (31 * LSX_REG_WIDTH)
+#endif
+	.endm
+
+	.macro sc_restore_lsx base
+#ifdef CONFIG_CPU_HAS_LSX
+	EX	vld	$vr0,  \base, (0 * LSX_REG_WIDTH)
+	EX	vld	$vr1,  \base, (1 * LSX_REG_WIDTH)
+	EX	vld	$vr2,  \base, (2 * LSX_REG_WIDTH)
+	EX	vld	$vr3,  \base, (3 * LSX_REG_WIDTH)
+	EX	vld	$vr4,  \base, (4 * LSX_REG_WIDTH)
+	EX	vld	$vr5,  \base, (5 * LSX_REG_WIDTH)
+	EX	vld	$vr6,  \base, (6 * LSX_REG_WIDTH)
+	EX	vld	$vr7,  \base, (7 * LSX_REG_WIDTH)
+	EX	vld	$vr8,  \base, (8 * LSX_REG_WIDTH)
+	EX	vld	$vr9,  \base, (9 * LSX_REG_WIDTH)
+	EX	vld	$vr10, \base, (10 * LSX_REG_WIDTH)
+	EX	vld	$vr11, \base, (11 * LSX_REG_WIDTH)
+	EX	vld	$vr12, \base, (12 * LSX_REG_WIDTH)
+	EX	vld	$vr13, \base, (13 * LSX_REG_WIDTH)
+	EX	vld	$vr14, \base, (14 * LSX_REG_WIDTH)
+	EX	vld	$vr15, \base, (15 * LSX_REG_WIDTH)
+	EX	vld	$vr16, \base, (16 * LSX_REG_WIDTH)
+	EX	vld	$vr17, \base, (17 * LSX_REG_WIDTH)
+	EX	vld	$vr18, \base, (18 * LSX_REG_WIDTH)
+	EX	vld	$vr19, \base, (19 * LSX_REG_WIDTH)
+	EX	vld	$vr20, \base, (20 * LSX_REG_WIDTH)
+	EX	vld	$vr21, \base, (21 * LSX_REG_WIDTH)
+	EX	vld	$vr22, \base, (22 * LSX_REG_WIDTH)
+	EX	vld	$vr23, \base, (23 * LSX_REG_WIDTH)
+	EX	vld	$vr24, \base, (24 * LSX_REG_WIDTH)
+	EX	vld	$vr25, \base, (25 * LSX_REG_WIDTH)
+	EX	vld	$vr26, \base, (26 * LSX_REG_WIDTH)
+	EX	vld	$vr27, \base, (27 * LSX_REG_WIDTH)
+	EX	vld	$vr28, \base, (28 * LSX_REG_WIDTH)
+	EX	vld	$vr29, \base, (29 * LSX_REG_WIDTH)
+	EX	vld	$vr30, \base, (30 * LSX_REG_WIDTH)
+	EX	vld	$vr31, \base, (31 * LSX_REG_WIDTH)
+#endif
+	.endm
+
+	.macro sc_save_lasx base
+#ifdef CONFIG_CPU_HAS_LASX
+	EX	xvst	$xr0,  \base, (0 * LASX_REG_WIDTH)
+	EX	xvst	$xr1,  \base, (1 * LASX_REG_WIDTH)
+	EX	xvst	$xr2,  \base, (2 * LASX_REG_WIDTH)
+	EX	xvst	$xr3,  \base, (3 * LASX_REG_WIDTH)
+	EX	xvst	$xr4,  \base, (4 * LASX_REG_WIDTH)
+	EX	xvst	$xr5,  \base, (5 * LASX_REG_WIDTH)
+	EX	xvst	$xr6,  \base, (6 * LASX_REG_WIDTH)
+	EX	xvst	$xr7,  \base, (7 * LASX_REG_WIDTH)
+	EX	xvst	$xr8,  \base, (8 * LASX_REG_WIDTH)
+	EX	xvst	$xr9,  \base, (9 * LASX_REG_WIDTH)
+	EX	xvst	$xr10, \base, (10 * LASX_REG_WIDTH)
+	EX	xvst	$xr11, \base, (11 * LASX_REG_WIDTH)
+	EX	xvst	$xr12, \base, (12 * LASX_REG_WIDTH)
+	EX	xvst	$xr13, \base, (13 * LASX_REG_WIDTH)
+	EX	xvst	$xr14, \base, (14 * LASX_REG_WIDTH)
+	EX	xvst	$xr15, \base, (15 * LASX_REG_WIDTH)
+	EX	xvst	$xr16, \base, (16 * LASX_REG_WIDTH)
+	EX	xvst	$xr17, \base, (17 * LASX_REG_WIDTH)
+	EX	xvst	$xr18, \base, (18 * LASX_REG_WIDTH)
+	EX	xvst	$xr19, \base, (19 * LASX_REG_WIDTH)
+	EX	xvst	$xr20, \base, (20 * LASX_REG_WIDTH)
+	EX	xvst	$xr21, \base, (21 * LASX_REG_WIDTH)
+	EX	xvst	$xr22, \base, (22 * LASX_REG_WIDTH)
+	EX	xvst	$xr23, \base, (23 * LASX_REG_WIDTH)
+	EX	xvst	$xr24, \base, (24 * LASX_REG_WIDTH)
+	EX	xvst	$xr25, \base, (25 * LASX_REG_WIDTH)
+	EX	xvst	$xr26, \base, (26 * LASX_REG_WIDTH)
+	EX	xvst	$xr27, \base, (27 * LASX_REG_WIDTH)
+	EX	xvst	$xr28, \base, (28 * LASX_REG_WIDTH)
+	EX	xvst	$xr29, \base, (29 * LASX_REG_WIDTH)
+	EX	xvst	$xr30, \base, (30 * LASX_REG_WIDTH)
+	EX	xvst	$xr31, \base, (31 * LASX_REG_WIDTH)
+#endif
+	.endm
+
+	.macro sc_restore_lasx base
+#ifdef CONFIG_CPU_HAS_LASX
+	EX	xvld	$xr0,  \base, (0 * LASX_REG_WIDTH)
+	EX	xvld	$xr1,  \base, (1 * LASX_REG_WIDTH)
+	EX	xvld	$xr2,  \base, (2 * LASX_REG_WIDTH)
+	EX	xvld	$xr3,  \base, (3 * LASX_REG_WIDTH)
+	EX	xvld	$xr4,  \base, (4 * LASX_REG_WIDTH)
+	EX	xvld	$xr5,  \base, (5 * LASX_REG_WIDTH)
+	EX	xvld	$xr6,  \base, (6 * LASX_REG_WIDTH)
+	EX	xvld	$xr7,  \base, (7 * LASX_REG_WIDTH)
+	EX	xvld	$xr8,  \base, (8 * LASX_REG_WIDTH)
+	EX	xvld	$xr9,  \base, (9 * LASX_REG_WIDTH)
+	EX	xvld	$xr10, \base, (10 * LASX_REG_WIDTH)
+	EX	xvld	$xr11, \base, (11 * LASX_REG_WIDTH)
+	EX	xvld	$xr12, \base, (12 * LASX_REG_WIDTH)
+	EX	xvld	$xr13, \base, (13 * LASX_REG_WIDTH)
+	EX	xvld	$xr14, \base, (14 * LASX_REG_WIDTH)
+	EX	xvld	$xr15, \base, (15 * LASX_REG_WIDTH)
+	EX	xvld	$xr16, \base, (16 * LASX_REG_WIDTH)
+	EX	xvld	$xr17, \base, (17 * LASX_REG_WIDTH)
+	EX	xvld	$xr18, \base, (18 * LASX_REG_WIDTH)
+	EX	xvld	$xr19, \base, (19 * LASX_REG_WIDTH)
+	EX	xvld	$xr20, \base, (20 * LASX_REG_WIDTH)
+	EX	xvld	$xr21, \base, (21 * LASX_REG_WIDTH)
+	EX	xvld	$xr22, \base, (22 * LASX_REG_WIDTH)
+	EX	xvld	$xr23, \base, (23 * LASX_REG_WIDTH)
+	EX	xvld	$xr24, \base, (24 * LASX_REG_WIDTH)
+	EX	xvld	$xr25, \base, (25 * LASX_REG_WIDTH)
+	EX	xvld	$xr26, \base, (26 * LASX_REG_WIDTH)
+	EX	xvld	$xr27, \base, (27 * LASX_REG_WIDTH)
+	EX	xvld	$xr28, \base, (28 * LASX_REG_WIDTH)
+	EX	xvld	$xr29, \base, (29 * LASX_REG_WIDTH)
+	EX	xvld	$xr30, \base, (30 * LASX_REG_WIDTH)
+	EX	xvld	$xr31, \base, (31 * LASX_REG_WIDTH)
+#endif
+	.endm
+
 /*
  * Save a thread's fp context.
  */
@@ -166,6 +314,76 @@ SYM_FUNC_START(_restore_fp)
 	jr			ra
 SYM_FUNC_END(_restore_fp)
 
+#ifdef CONFIG_CPU_HAS_LSX
+
+/*
+ * Save a thread's LSX vector context.
+ */
+SYM_FUNC_START(_save_lsx)
+	lsx_save_all	a0 t1 t2
+	jr	ra
+SYM_FUNC_END(_save_lsx)
+EXPORT_SYMBOL(_save_lsx)
+
+/*
+ * Restore a thread's LSX vector context.
+ */
+SYM_FUNC_START(_restore_lsx)
+	lsx_restore_all	a0 t1 t2
+	jr	ra
+SYM_FUNC_END(_restore_lsx)
+
+SYM_FUNC_START(_save_lsx_upper)
+	lsx_save_all_upper a0 t0 t1
+	jr	ra
+SYM_FUNC_END(_save_lsx_upper)
+
+SYM_FUNC_START(_restore_lsx_upper)
+	lsx_restore_all_upper a0 t0 t1
+	jr	ra
+SYM_FUNC_END(_restore_lsx_upper)
+
+SYM_FUNC_START(_init_lsx_upper)
+	lsx_init_all_upper t1
+	jr	ra
+SYM_FUNC_END(_init_lsx_upper)
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+
+/*
+ * Save a thread's LASX vector context.
+ */
+SYM_FUNC_START(_save_lasx)
+	lasx_save_all	a0 t1 t2
+	jr	ra
+SYM_FUNC_END(_save_lasx)
+EXPORT_SYMBOL(_save_lasx)
+
+/*
+ * Restore a thread's LASX vector context.
+ */
+SYM_FUNC_START(_restore_lasx)
+	lasx_restore_all a0 t1 t2
+	jr	ra
+SYM_FUNC_END(_restore_lasx)
+
+SYM_FUNC_START(_save_lasx_upper)
+	lasx_save_all_upper a0 t0 t1
+	jr	ra
+SYM_FUNC_END(_save_lasx_upper)
+
+SYM_FUNC_START(_restore_lasx_upper)
+	lasx_restore_all_upper a0 t0 t1
+	jr	ra
+SYM_FUNC_END(_restore_lasx_upper)
+
+SYM_FUNC_START(_init_lasx_upper)
+	lasx_init_all_upper t1
+	jr	ra
+SYM_FUNC_END(_init_lasx_upper)
+#endif
+
 /*
  * 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
@@ -244,6 +462,58 @@ SYM_FUNC_START(_restore_fp_context)
 	jr		ra
 SYM_FUNC_END(_restore_fp_context)
 
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_save_lsx_context)
+	sc_save_fcc a1, t0, t1
+	sc_save_fcsr a2, t0
+	sc_save_lsx a0
+	li.w	a0, 0					# success
+	jr	ra
+SYM_FUNC_END(_save_lsx_context)
+
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_restore_lsx_context)
+	sc_restore_lsx a0
+	sc_restore_fcc a1, t1, t2
+	sc_restore_fcsr a2, t1
+	li.w	a0, 0					# success
+	jr	ra
+SYM_FUNC_END(_restore_lsx_context)
+
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_save_lasx_context)
+	sc_save_fcc a1, t0, t1
+	sc_save_fcsr a2, t0
+	sc_save_lasx a0
+	li.w	a0, 0					# success
+	jr	ra
+SYM_FUNC_END(_save_lasx_context)
+
+/*
+ * a0: fpregs
+ * a1: fcc
+ * a2: fcsr
+ */
+SYM_FUNC_START(_restore_lasx_context)
+	sc_restore_lasx a0
+	sc_restore_fcc a1, t1, t2
+	sc_restore_fcsr a2, t1
+	li.w	a0, 0					# success
+	jr	ra
+SYM_FUNC_END(_restore_lasx_context)
+
 SYM_FUNC_START(fault)
 	li.w	a0, -EFAULT				# failure
 	jr	ra
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 9535a0662480..2e04eb07abb6 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -117,8 +117,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	 */
 	preempt_disable();
 
-	if (is_fpu_owner())
-		save_fp(current);
+	if (is_fpu_owner()) {
+		if (is_lasx_enabled())
+			save_lasx(current);
+		else if (is_lsx_enabled())
+			save_lsx(current);
+		else
+			save_fp(current);
+	}
 
 	preempt_enable();
 
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index 5fcffb452367..a0767c3a0f0a 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -250,6 +250,90 @@ static int cfg_set(struct task_struct *target,
 	return 0;
 }
 
+#ifdef CONFIG_CPU_HAS_LSX
+
+static void copy_pad_fprs(struct task_struct *target,
+			 const struct user_regset *regset,
+			 struct membuf *to, unsigned int live_sz)
+{
+	int i, j;
+	unsigned long long fill = ~0ull;
+	unsigned int cp_sz, pad_sz;
+
+	cp_sz = min(regset->size, live_sz);
+	pad_sz = regset->size - cp_sz;
+	WARN_ON(pad_sz % sizeof(fill));
+
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		membuf_write(to, &target->thread.fpu.fpr[i], cp_sz);
+		for (j = 0; j < (pad_sz / sizeof(fill)); j++) {
+			membuf_store(to, fill);
+		}
+	}
+}
+
+static int simd_get(struct task_struct *target,
+		    const struct user_regset *regset,
+		    struct membuf to)
+{
+	const unsigned int wr_size = NUM_FPU_REGS * regset->size;
+
+	if (!tsk_used_math(target)) {
+		/* The task hasn't used FP or LSX, fill with 0xff */
+		copy_pad_fprs(target, regset, &to, 0);
+	} else if (!test_tsk_thread_flag(target, TIF_LSX_CTX_LIVE)) {
+		/* Copy scalar FP context, fill the rest with 0xff */
+		copy_pad_fprs(target, regset, &to, 8);
+#ifdef CONFIG_CPU_HAS_LASX
+	} else if (!test_tsk_thread_flag(target, TIF_LASX_CTX_LIVE)) {
+		/* Copy LSX 128 Bit context, fill the rest with 0xff */
+		copy_pad_fprs(target, regset, &to, 16);
+#endif
+	} else if (sizeof(target->thread.fpu.fpr[0]) == regset->size) {
+		/* Trivially copy the vector registers */
+		membuf_write(&to, &target->thread.fpu.fpr, wr_size);
+	} else {
+		/* Copy as much context as possible, fill the rest with 0xff */
+		copy_pad_fprs(target, regset, &to, sizeof(target->thread.fpu.fpr[0]));
+	}
+
+	return 0;
+}
+
+static int simd_set(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    const void *kbuf, const void __user *ubuf)
+{
+	const unsigned int wr_size = NUM_FPU_REGS * regset->size;
+	unsigned int cp_sz;
+	int i, err, start;
+
+	init_fp_ctx(target);
+
+	if (sizeof(target->thread.fpu.fpr[0]) == regset->size) {
+		/* Trivially copy the vector registers */
+		err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.fpu.fpr,
+					 0, wr_size);
+	} else {
+		/* Copy as much context as possible */
+		cp_sz = min_t(unsigned int, regset->size,
+			      sizeof(target->thread.fpu.fpr[0]));
+
+		i = start = err = 0;
+		for (; i < NUM_FPU_REGS; i++, start += regset->size) {
+			err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+						  &target->thread.fpu.fpr[i],
+						  start, start + cp_sz);
+		}
+	}
+
+	return err;
+}
+
+#endif /* CONFIG_CPU_HAS_LSX */
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
 /*
@@ -708,6 +792,12 @@ enum loongarch_regset {
 	REGSET_GPR,
 	REGSET_FPR,
 	REGSET_CPUCFG,
+#ifdef CONFIG_CPU_HAS_LSX
+	REGSET_LSX,
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
+	REGSET_LASX,
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	REGSET_HW_BREAK,
 	REGSET_HW_WATCH,
@@ -739,6 +829,26 @@ static const struct user_regset loongarch64_regsets[] = {
 		.regset_get	= cfg_get,
 		.set		= cfg_set,
 	},
+#ifdef CONFIG_CPU_HAS_LSX
+	[REGSET_LSX] = {
+		.core_note_type	= NT_LOONGARCH_LSX,
+		.n		= NUM_FPU_REGS,
+		.size		= 16,
+		.align		= 16,
+		.regset_get	= simd_get,
+		.set		= simd_set,
+	},
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
+	[REGSET_LASX] = {
+		.core_note_type	= NT_LOONGARCH_LASX,
+		.n		= NUM_FPU_REGS,
+		.size		= 32,
+		.align		= 32,
+		.regset_get	= simd_get,
+		.set		= simd_set,
+	},
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	[REGSET_HW_BREAK] = {
 		.core_note_type = NT_LOONGARCH_HW_BREAK,
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 8f5b7986374b..ceb899366c0a 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -50,6 +50,14 @@ extern asmlinkage int
 _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
 extern asmlinkage int
 _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+extern asmlinkage int
+_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+extern asmlinkage int
+_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+extern asmlinkage int
+_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+extern asmlinkage int
+_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
 struct rt_sigframe {
 	struct siginfo rs_info;
@@ -65,6 +73,8 @@ struct extctx_layout {
 	unsigned long size;
 	unsigned int flags;
 	struct _ctx_layout fpu;
+	struct _ctx_layout lsx;
+	struct _ctx_layout lasx;
 	struct _ctx_layout end;
 };
 
@@ -115,6 +125,96 @@ static int copy_fpu_from_sigcontext(struct fpu_context __user *ctx)
 	return err;
 }
 
+static int copy_lsx_to_sigcontext(struct lsx_context __user *ctx)
+{
+	int i;
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 0),
+				  &regs[2*i]);
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 1),
+				  &regs[2*i+1]);
+	}
+	err |= __put_user(current->thread.fpu.fcc, fcc);
+	err |= __put_user(current->thread.fpu.fcsr, fcsr);
+
+	return err;
+}
+
+static int copy_lsx_from_sigcontext(struct lsx_context __user *ctx)
+{
+	int i;
+	int err = 0;
+	u64 fpr_val;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		err |= __get_user(fpr_val, &regs[2*i]);
+		set_fpr64(&current->thread.fpu.fpr[i], 0, fpr_val);
+		err |= __get_user(fpr_val, &regs[2*i+1]);
+		set_fpr64(&current->thread.fpu.fpr[i], 1, fpr_val);
+	}
+	err |= __get_user(current->thread.fpu.fcc, fcc);
+	err |= __get_user(current->thread.fpu.fcsr, fcsr);
+
+	return err;
+}
+
+static int copy_lasx_to_sigcontext(struct lasx_context __user *ctx)
+{
+	int i;
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 0),
+				  &regs[4*i]);
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 1),
+				  &regs[4*i+1]);
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 2),
+				  &regs[4*i+2]);
+		err |= __put_user(get_fpr64(&current->thread.fpu.fpr[i], 3),
+				  &regs[4*i+3]);
+	}
+	err |= __put_user(current->thread.fpu.fcc, fcc);
+	err |= __put_user(current->thread.fpu.fcsr, fcsr);
+
+	return err;
+}
+
+static int copy_lasx_from_sigcontext(struct lasx_context __user *ctx)
+{
+	int i;
+	int err = 0;
+	u64 fpr_val;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		err |= __get_user(fpr_val, &regs[4*i]);
+		set_fpr64(&current->thread.fpu.fpr[i], 0, fpr_val);
+		err |= __get_user(fpr_val, &regs[4*i+1]);
+		set_fpr64(&current->thread.fpu.fpr[i], 1, fpr_val);
+		err |= __get_user(fpr_val, &regs[4*i+2]);
+		set_fpr64(&current->thread.fpu.fpr[i], 2, fpr_val);
+		err |= __get_user(fpr_val, &regs[4*i+3]);
+		set_fpr64(&current->thread.fpu.fpr[i], 3, fpr_val);
+	}
+	err |= __get_user(current->thread.fpu.fcc, fcc);
+	err |= __get_user(current->thread.fpu.fcsr, fcsr);
+
+	return err;
+}
+
 /*
  * Wrappers for the assembly _{save,restore}_fp_context functions.
  */
@@ -136,6 +236,42 @@ static int restore_hw_fpu_context(struct fpu_context __user *ctx)
 	return _restore_fp_context(regs, fcc, fcsr);
 }
 
+static int save_hw_lsx_context(struct lsx_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	return _save_lsx_context(regs, fcc, fcsr);
+}
+
+static int restore_hw_lsx_context(struct lsx_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	return _restore_lsx_context(regs, fcc, fcsr);
+}
+
+static int save_hw_lasx_context(struct lasx_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	return _save_lasx_context(regs, fcc, fcsr);
+}
+
+static int restore_hw_lasx_context(struct lasx_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint64_t __user *fcc	= &ctx->fcc;
+	uint32_t __user *fcsr	= &ctx->fcsr;
+
+	return _restore_lasx_context(regs, fcc, fcsr);
+}
+
 static int fcsr_pending(unsigned int __user *fcsr)
 {
 	int err, sig = 0;
@@ -227,6 +363,162 @@ static int protected_restore_fpu_context(struct extctx_layout *extctx)
 	return err ?: sig;
 }
 
+static int protected_save_lsx_context(struct extctx_layout *extctx)
+{
+	int err = 0;
+	struct sctx_info __user *info = extctx->lsx.addr;
+	struct lsx_context __user *lsx_ctx = (struct lsx_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lsx_ctx->regs;
+	uint64_t __user *fcc	= &lsx_ctx->fcc;
+	uint32_t __user *fcsr	= &lsx_ctx->fcsr;
+
+	while (1) {
+		lock_fpu_owner();
+		if (is_lsx_enabled())
+			err = save_hw_lsx_context(lsx_ctx);
+		else {
+			if (is_fpu_owner())
+				save_fp(current);
+			err = copy_lsx_to_sigcontext(lsx_ctx);
+		}
+		unlock_fpu_owner();
+
+		err |= __put_user(LSX_CTX_MAGIC, &info->magic);
+		err |= __put_user(extctx->lsx.size, &info->size);
+
+		if (likely(!err))
+			break;
+		/* Touch the LSX context and try again */
+		err = __put_user(0, &regs[0]) |
+			__put_user(0, &regs[32*2-1]) |
+			__put_user(0, fcc) |
+			__put_user(0, fcsr);
+		if (err)
+			return err;	/* really bad sigcontext */
+	}
+
+	return err;
+}
+
+static int protected_restore_lsx_context(struct extctx_layout *extctx)
+{
+	int err = 0, sig = 0, tmp __maybe_unused;
+	struct sctx_info __user *info = extctx->lsx.addr;
+	struct lsx_context __user *lsx_ctx = (struct lsx_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lsx_ctx->regs;
+	uint64_t __user *fcc	= &lsx_ctx->fcc;
+	uint32_t __user *fcsr	= &lsx_ctx->fcsr;
+
+	err = sig = fcsr_pending(fcsr);
+	if (err < 0)
+		return err;
+
+	while (1) {
+		lock_fpu_owner();
+		if (is_lsx_enabled())
+			err = restore_hw_lsx_context(lsx_ctx);
+		else {
+			err = copy_lsx_from_sigcontext(lsx_ctx);
+			if (is_fpu_owner())
+				restore_fp(current);
+		}
+		unlock_fpu_owner();
+
+		if (likely(!err))
+			break;
+		/* Touch the LSX context and try again */
+		err = __get_user(tmp, &regs[0]) |
+			__get_user(tmp, &regs[32*2-1]) |
+			__get_user(tmp, fcc) |
+			__get_user(tmp, fcsr);
+		if (err)
+			break;	/* really bad sigcontext */
+	}
+
+	return err ?: sig;
+}
+
+static int protected_save_lasx_context(struct extctx_layout *extctx)
+{
+	int err = 0;
+	struct sctx_info __user *info = extctx->lasx.addr;
+	struct lasx_context __user *lasx_ctx =
+		(struct lasx_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lasx_ctx->regs;
+	uint64_t __user *fcc	= &lasx_ctx->fcc;
+	uint32_t __user *fcsr	= &lasx_ctx->fcsr;
+
+	while (1) {
+		lock_fpu_owner();
+		if (is_lasx_enabled())
+			err = save_hw_lasx_context(lasx_ctx);
+		else {
+			if (is_lsx_enabled())
+				save_lsx(current);
+			else if (is_fpu_owner())
+				save_fp(current);
+			err = copy_lasx_to_sigcontext(lasx_ctx);
+		}
+		unlock_fpu_owner();
+
+		err |= __put_user(LASX_CTX_MAGIC, &info->magic);
+		err |= __put_user(extctx->lasx.size, &info->size);
+
+		if (likely(!err))
+			break;
+		/* Touch the LASX context and try again */
+		err = __put_user(0, &regs[0]) |
+			__put_user(0, &regs[32*4-1]) |
+			__put_user(0, fcc) |
+			__put_user(0, fcsr);
+		if (err)
+			return err;	/* really bad sigcontext */
+	}
+
+	return err;
+}
+
+static int protected_restore_lasx_context(struct extctx_layout *extctx)
+{
+	int err = 0, sig = 0, tmp __maybe_unused;
+	struct sctx_info __user *info = extctx->lasx.addr;
+	struct lasx_context __user *lasx_ctx =
+		(struct lasx_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lasx_ctx->regs;
+	uint64_t __user *fcc	= &lasx_ctx->fcc;
+	uint32_t __user *fcsr	= &lasx_ctx->fcsr;
+
+	err = sig = fcsr_pending(fcsr);
+	if (err < 0)
+		return err;
+
+	while (1) {
+		lock_fpu_owner();
+		if (is_lasx_enabled())
+			err = restore_hw_lasx_context(lasx_ctx);
+		else {
+			err = copy_lasx_from_sigcontext(lasx_ctx);
+			if (is_lsx_enabled())
+				restore_lsx(current);
+			else if (is_fpu_owner())
+				restore_fp(current);
+		}
+		unlock_fpu_owner();
+
+		if (likely(!err))
+			break;
+		/* Touch the LASX context and try again */
+		err = __get_user(tmp, &regs[0]) |
+			__get_user(tmp, &regs[32*4-1]) |
+			__get_user(tmp, fcc) |
+			__get_user(tmp, fcsr);
+		if (err)
+			break;	/* really bad sigcontext */
+	}
+
+	return err ?: sig;
+}
+
 static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 			    struct extctx_layout *extctx)
 {
@@ -240,7 +532,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	for (i = 1; i < 32; i++)
 		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
 
-	if (extctx->fpu.addr)
+	if (extctx->lasx.addr)
+		err |= protected_save_lasx_context(extctx);
+	else if (extctx->lsx.addr)
+		err |= protected_save_lsx_context(extctx);
+	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
 	/* Set the "end" magic */
@@ -274,6 +570,20 @@ static int parse_extcontext(struct sigcontext __user *sc, struct extctx_layout *
 			extctx->fpu.addr = info;
 			break;
 
+		case LSX_CTX_MAGIC:
+			if (size < (sizeof(struct sctx_info) +
+				    sizeof(struct lsx_context)))
+				goto invalid;
+			extctx->lsx.addr = info;
+			break;
+
+		case LASX_CTX_MAGIC:
+			if (size < (sizeof(struct sctx_info) +
+				    sizeof(struct lasx_context)))
+				goto invalid;
+			extctx->lasx.addr = info;
+			break;
+
 		default:
 			goto invalid;
 		}
@@ -319,7 +629,11 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc
 	for (i = 1; i < 32; i++)
 		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);
 
-	if (extctx.fpu.addr)
+	if (extctx.lasx.addr)
+		err |= protected_restore_lasx_context(&extctx);
+	else if (extctx.lsx.addr)
+		err |= protected_restore_lsx_context(&extctx);
+	else if (extctx.fpu.addr)
 		err |= protected_restore_fpu_context(&extctx);
 
 bad:
@@ -375,7 +689,13 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon
 	extctx->size += extctx->end.size;
 
 	if (extctx->flags & SC_USED_FP) {
-		if (cpu_has_fpu)
+		if (cpu_has_lasx && thread_lasx_context_live())
+			new_sp = extframe_alloc(extctx, &extctx->lasx,
+			  sizeof(struct lasx_context), LASX_CTX_ALIGN, new_sp);
+		else if (cpu_has_lsx && thread_lsx_context_live())
+			new_sp = extframe_alloc(extctx, &extctx->lsx,
+			  sizeof(struct lsx_context), LSX_CTX_ALIGN, new_sp);
+		else if (cpu_has_fpu)
 			new_sp = extframe_alloc(extctx, &extctx->fpu,
 			  sizeof(struct fpu_context), FPU_CTX_ALIGN, new_sp);
 	}
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index e73d9bbe1658..e56df45f7202 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -852,12 +852,67 @@ static void init_restore_fp(void)
 	BUG_ON(!is_fp_enabled());
 }
 
+static void init_restore_lsx(void)
+{
+	enable_lsx();
+
+	if (!thread_lsx_context_live()) {
+		/* First time LSX context user */
+		init_restore_fp();
+		init_lsx_upper();
+		set_thread_flag(TIF_LSX_CTX_LIVE);
+	} else {
+		if (!is_simd_owner()) {
+			if (is_fpu_owner()) {
+				restore_lsx_upper(current);
+			} else {
+				__own_fpu();
+				restore_lsx(current);
+			}
+		}
+	}
+
+	set_thread_flag(TIF_USEDSIMD);
+
+	BUG_ON(!is_fp_enabled());
+	BUG_ON(!is_lsx_enabled());
+}
+
+static void init_restore_lasx(void)
+{
+	enable_lasx();
+
+	if (!thread_lasx_context_live()) {
+		/* First time LASX context user */
+		init_restore_lsx();
+		init_lasx_upper();
+		set_thread_flag(TIF_LASX_CTX_LIVE);
+	} else {
+		if (is_fpu_owner() || is_simd_owner()) {
+			init_restore_lsx();
+			restore_lasx_upper(current);
+		} else {
+			__own_fpu();
+			enable_lsx();
+			restore_lasx(current);
+		}
+	}
+
+	set_thread_flag(TIF_USEDSIMD);
+
+	BUG_ON(!is_fp_enabled());
+	BUG_ON(!is_lsx_enabled());
+	BUG_ON(!is_lasx_enabled());
+}
+
 asmlinkage void noinstr do_fpu(struct pt_regs *regs)
 {
 	irqentry_state_t state = irqentry_enter(regs);
 
 	local_irq_enable();
 	die_if_kernel("do_fpu invoked from kernel context!", regs);
+	BUG_ON(is_lsx_enabled());
+	BUG_ON(is_lasx_enabled());
 
 	preempt_disable();
 	init_restore_fp();
@@ -872,9 +927,20 @@ asmlinkage void noinstr do_lsx(struct pt_regs *regs)
 	irqentry_state_t state = irqentry_enter(regs);
 
 	local_irq_enable();
-	force_sig(SIGILL);
-	local_irq_disable();
+	if (!cpu_has_lsx) {
+		force_sig(SIGILL);
+		goto out;
+	}
+
+	die_if_kernel("do_lsx invoked from kernel context!", regs);
+	BUG_ON(is_lasx_enabled());
 
+	preempt_disable();
+	init_restore_lsx();
+	preempt_enable();
+
+out:
+	local_irq_disable();
 	irqentry_exit(regs, state);
 }
 
@@ -883,9 +949,19 @@ asmlinkage void noinstr do_lasx(struct pt_regs *regs)
 	irqentry_state_t state = irqentry_enter(regs);
 
 	local_irq_enable();
-	force_sig(SIGILL);
-	local_irq_disable();
+	if (!cpu_has_lasx) {
+		force_sig(SIGILL);
+		goto out;
+	}
+
+	die_if_kernel("do_lasx invoked from kernel context!", regs);
 
+	preempt_disable();
+	init_restore_lasx();
+	preempt_enable();
+
+out:
+	local_irq_disable();
 	irqentry_exit(regs, state);
 }