MIPS: Use WSBH/DSBH/DSHD on Loongson 3A

Signed-off-by: chenj <chenj@lemote.com>
Cc: linux-mips@linux-mips.org
Cc: chenhc@lemote.com
Patchwork: https://patchwork.linux-mips.org/patch/7542/
Patchwork: https://patchwork.linux-mips.org/patch/7550/Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/include/asm/cpu-features.h

@@ -231,6 +231,16 @@
 #define cpu_has_clo_clz	cpu_has_mips_r
 #endif
 
+/*
+ * MIPS32 R2, MIPS64 R2, Loongson 3A and Octeon have WSBH.
+ * MIPS64 R2, Loongson 3A and Octeon have WSBH, DSBH and DSHD.
+ * This indicates the availability of WSBH and in case of 64 bit CPUs also
+ * DSBH and DSHD.
+ */
+#ifndef cpu_has_wsbh
+#define cpu_has_wsbh		cpu_has_mips_r2
+#endif
+
 #ifndef cpu_has_dsp
 #define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
 #endif

arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h

@@ -57,6 +57,7 @@
 #define cpu_has_vint		0
 #define cpu_has_veic		0
 #define cpu_hwrena_impl_bits	0xc0000000
+#define cpu_has_wsbh            1
 
 #define cpu_has_rixi		(cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
 

arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h

@@ -59,4 +59,6 @@
 #define cpu_has_watch		1
 #define cpu_has_local_ebase	0
 
+#define cpu_has_wsbh		IS_ENABLED(CONFIG_CPU_LOONGSON3)
+
 #endif /* __ASM_MACH_LOONGSON_CPU_FEATURE_OVERRIDES_H */

arch/mips/include/uapi/asm/swab.h

@@ -13,12 +13,16 @@
 
 #define __SWAB_64_THRU_32__
 
-#if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
+#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
+    defined(_MIPS_ARCH_LOONGSON3A)
 
 static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -29,8 +33,11 @@ static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -46,8 +53,11 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 {
 	__asm__(
-	"	dsbh	%0, %1\n"
-	"	dshd	%0, %0"
+	"	.set	push			\n"
+	"	.set	arch=mips64r2		\n"
+	"	dsbh	%0, %1			\n"
+	"	dshd	%0, %0			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -55,5 +65,5 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 }
 #define __arch_swab64 __arch_swab64
 #endif /* __mips64 */
-#endif /* MIPS R2 or newer  */
+#endif /* MIPS R2 or newer or Loongson 3A */
 #endif /* _ASM_SWAB_H */

arch/mips/lib/csum_partial.S

@@ -277,9 +277,12 @@ LEAF(csum_partial)
 #endif
 
 	/* odd buffer alignment? */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, t7
+	.set	pop
 #else
 	beqz	t7, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff
@@ -726,9 +729,12 @@ LEAF(csum_partial)
 	addu	sum, v1
 #endif
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, odd
+	.set	pop
 #else
 	beqz	odd, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff

arch/mips/net/bpf_jit.c

@@ -1263,7 +1263,7 @@ static int build_body(struct jit_ctx *ctx)
 			emit_half_load(r_A, r_skb, off, ctx);
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 			/* This needs little endian fixup */
-			if (cpu_has_mips_r2) {
+			if (cpu_has_wsbh) {
 				/* R2 and later have the wsbh instruction */
 				emit_wsbh(r_A, r_A, ctx);
 			} else {