LoongArch: Simplify "BEQ/BNE foo, zero" with BEQZ/BNEZ

While B{EQ,NE}Z and B{EQ,NE} are different instructions, and the vastly
expanded range for branch destination does not really matter in the few
cases touched, use the B{EQ,NE}Z where possible for shorter lines and
better consistency (e.g. some places used "BEQ foo, zero", while some
used "BEQ zero, foo").
Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/include/asm/atomic.h

@@ -160,7 +160,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	move	%1, %0					\n"
 		"	blt	%0, $zero, 2f				\n"
 		"	sc.w	%1, %2					\n"
-		"	beq	$zero, %1, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
@@ -173,7 +173,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	move	%1, %0					\n"
 		"	blt	%0, $zero, 2f				\n"
 		"	sc.w	%1, %2					\n"
-		"	beq	$zero, %1, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
@@ -323,7 +323,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	move	%1, %0					\n"
 		"	blt	%0, $zero, 2f				\n"
 		"	sc.d	%1, %2					\n"
-		"	beq	%1, $zero, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
@@ -336,7 +336,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	move	%1, %0					\n"
 		"	blt	%0, $zero, 2f				\n"
 		"	sc.d	%1, %2					\n"
-		"	beq	%1, $zero, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),

arch/loongarch/include/asm/cmpxchg.h

@@ -57,7 +57,7 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 	"	bne	%0, %z3, 2f			\n"		\
 	"	move	$t0, %z4			\n"		\
 	"	" st "	$t0, %1				\n"		\
-	"	beq	$zero, $t0, 1b			\n"		\
+	"	beqz	$t0, 1b				\n"		\
 	"2:						\n"		\
 	__WEAK_LLSC_MB							\
 	: "=&r" (__ret), "=ZB"(*m)					\

arch/loongarch/include/asm/futex.h

@@ -17,7 +17,7 @@
 	"1:	ll.w	%1, %4 # __futex_atomic_op\n"		\
 	"	" insn	"				\n"	\
 	"2:	sc.w	$t0, %2				\n"	\
-	"	beq	$t0, $zero, 1b			\n"	\
+	"	beqz	$t0, 1b				\n"	\
 	"3:						\n"	\
 	"	.section .fixup,\"ax\"			\n"	\
 	"4:	li.w	%0, %6				\n"	\
@@ -84,7 +84,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
 	"	bne	%1, %z4, 3f				\n"
 	"	move	$t0, %z5				\n"
 	"2:	sc.w	$t0, %2					\n"
-	"	beq	$zero, $t0, 1b				\n"
+	"	beqz	$t0, 1b					\n"
 	"3:							\n"
 	__WEAK_LLSC_MB
 	"	.section .fixup,\"ax\"				\n"

arch/loongarch/mm/tlbex.S

@@ -80,7 +80,7 @@ vmalloc_done_load:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, zero, tlb_huge_update_load
+	bnez	t0, tlb_huge_update_load
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -100,12 +100,12 @@ smp_pgtable_change_load:
 
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, 1
-	beq	ra, zero, nopage_tlb_load
+	beqz	ra, nopage_tlb_load
 
 	ori	t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, smp_pgtable_change_load
+	beqz	t0, smp_pgtable_change_load
 #else
 	st.d	t0, t1, 0
 #endif
@@ -139,13 +139,13 @@ tlb_huge_update_load:
 #endif
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, 1
-	beq	ra, zero, nopage_tlb_load
+	beqz	ra, nopage_tlb_load
 	tlbsrch
 
 	ori	t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, tlb_huge_update_load
+	beqz	t0, tlb_huge_update_load
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0
@@ -244,7 +244,7 @@ vmalloc_done_store:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, zero, tlb_huge_update_store
+	bnez	t0, tlb_huge_update_store
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -265,12 +265,12 @@ smp_pgtable_change_store:
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
 	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bne	ra, zero, nopage_tlb_store
+	bnez	ra, nopage_tlb_store
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, smp_pgtable_change_store
+	beqz	t0, smp_pgtable_change_store
 #else
 	st.d	t0, t1, 0
 #endif
@@ -306,14 +306,14 @@ tlb_huge_update_store:
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
 	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bne	ra, zero, nopage_tlb_store
+	bnez	ra, nopage_tlb_store
 
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, tlb_huge_update_store
+	beqz	t0, tlb_huge_update_store
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0
@@ -411,7 +411,7 @@ vmalloc_done_modify:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, zero, tlb_huge_update_modify
+	bnez	t0, tlb_huge_update_modify
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -431,12 +431,12 @@ smp_pgtable_change_modify:
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
 	andi	ra, ra, 1
-	beq	ra, zero, nopage_tlb_modify
+	beqz	ra, nopage_tlb_modify
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, smp_pgtable_change_modify
+	beqz	t0, smp_pgtable_change_modify
 #else
 	st.d	t0, t1, 0
 #endif
@@ -471,14 +471,14 @@ tlb_huge_update_modify:
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
 	andi	ra, ra, 1
-	beq	ra, zero, nopage_tlb_modify
+	beqz	ra, nopage_tlb_modify
 
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, zero, tlb_huge_update_modify
+	beqz	t0, tlb_huge_update_modify
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0