Index: lib/builtins/arm/aeabi_uidivmod.S
===================================================================
--- lib/builtins/arm/aeabi_uidivmod.S
+++ lib/builtins/arm/aeabi_uidivmod.S
@@ -23,6 +23,20 @@
         .syntax unified
         .p2align 2
 DEFINE_COMPILERRT_FUNCTION(__aeabi_uidivmod)
+#if __ARM_ARCH_ISA_THUMB == 1
+        cmp     r0, r1
+        bcc     LOCAL_LABEL(case_denom_larger)
+        push    {r0, r1, lr}
+        bl      SYMBOL_NAME(__aeabi_uidiv)
+        pop     {r1, r2, r3}
+        muls    r2, r2, r0 // r2 = quot * denom
+        subs    r1, r1, r2
+        JMP     (r3)
+LOCAL_LABEL(case_denom_larger):
+        movs    r1, r0
+        movs    r0, #0
+        JMP     (lr)
+#else
         push    { lr }
         sub     sp, sp, #4
         mov     r2, sp
@@ -35,6 +49,7 @@
         ldr     r1, [sp]
         add     sp, sp, #4
         pop     { pc }
+#endif
 END_COMPILERRT_FUNCTION(__aeabi_uidivmod)
 
 NO_EXEC_STACK_DIRECTIVE
Index: lib/builtins/arm/udivsi3.S
===================================================================
--- lib/builtins/arm/udivsi3.S
+++ lib/builtins/arm/udivsi3.S
@@ -40,12 +40,26 @@
 #else
 	cmp	r1, #1
 	bcc	LOCAL_LABEL(divby0)
+#if __ARM_ARCH_ISA_THUMB == 1
+	bne LOCAL_LABEL(num_neq_denom)
+	JMP(lr)
+LOCAL_LABEL(num_neq_denom):
+#else
 	IT(eq)
 	JMPc(lr, eq)
+#endif
 	cmp	r0, r1
+#if __ARM_ARCH_ISA_THUMB == 1
+	bhs LOCAL_LABEL(num_ge_denom)
+	movs r0, #0
+	JMP(lr)
+LOCAL_LABEL(num_ge_denom):
+#else
 	ITT(cc)
 	movcc	r0, #0
 	JMPc(lr, cc)
+#endif
+
 	/*
 	 * Implement division using binary long division algorithm.
 	 *
@@ -61,6 +75,9 @@
 	 * It assumes (r0 << shift) can be computed without overflow and
 	 * that (r0 << shift) < 2 * r1. The quotient is stored in r3.
 	 */
+#if __ARM_ARCH_ISA_THUMB == 1
+#define BLOCK_SIZE 10
+#endif
 
 #  ifdef __ARM_FEATURE_CLZ
 	clz	ip, r0
@@ -82,44 +99,110 @@
 #    error THUMB mode requires CLZ or UDIV
 #    endif
 	mov	r2, r0
+#    if __ARM_ARCH_ISA_THUMB == 1
+	.p2align 2 /* adr requires aligned by 4 */
+	mov ip, r0
+	adr r0, LOCAL_LABEL(div0block)
+	adds r0, #1
+#    else
 	adr	ip, LOCAL_LABEL(div0block)
-
-	lsr	r3, r2, #16
+#    endif
+	lsrs	r3, r2, #16
 	cmp	r3, r1
+#    if __ARM_ARCH_ISA_THUMB == 1
+	blo LOCAL_LABEL(skip_16)
+	movs r2, r3
+	subs r0, r0, #(16 * BLOCK_SIZE)
+LOCAL_LABEL(skip_16):
+#    else
 	movhs	r2, r3
 	subhs	ip, ip, #(16 * 12)
+#    endif
 
-	lsr	r3, r2, #8
+	lsrs	r3, r2, #8
 	cmp	r3, r1
+#    if __ARM_ARCH_ISA_THUMB == 1
+	blo LOCAL_LABEL(skip_8)
+	movs r2, r3
+	subs r0, r0, #(8 * BLOCK_SIZE)
+LOCAL_LABEL(skip_8):
+#    else
 	movhs	r2, r3
 	subhs	ip, ip, #(8 * 12)
+#    endif
 
-	lsr	r3, r2, #4
+	lsrs	r3, r2, #4
 	cmp	r3, r1
+#    if __ARM_ARCH_ISA_THUMB == 1
+	blo LOCAL_LABEL(skip_4)
+	movs r2, r3
+	subs r0, r0, #(4 * BLOCK_SIZE)
+LOCAL_LABEL(skip_4):
+#    else
 	movhs	r2, r3
 	subhs	ip, #(4 * 12)
+#    endif
 
-	lsr	r3, r2, #2
+	lsrs	r3, r2, #2
 	cmp	r3, r1
+#    if __ARM_ARCH_ISA_THUMB == 1
+	blo LOCAL_LABEL(skip_2)
+	movs r2, r3
+	subs r0, r0, #(2 * BLOCK_SIZE)
+LOCAL_LABEL(skip_2):
+#    else
 	movhs	r2, r3
 	subhs	ip, ip, #(2 * 12)
+#    endif
 
 	/* Last block, no need to update r2 or r3. */
+#    if __ARM_ARCH_ISA_THUMB == 1
+	lsrs r3, r2, #1
+	cmp r3, r1
+	blo LOCAL_LABEL(skip_1)
+	subs r0, r0, #(1 * BLOCK_SIZE)
+LOCAL_LABEL(skip_1):
+	movs r2, r0
+	mov r0, ip
+	movs r3, #0
+	JMP (r2)
+
+	/* due to the range limit of branch in Thumb1, we have to place the
+		 block closer */
+LOCAL_LABEL(divby0):
+	movs	r0, #0
+#      ifdef __ARM_EABI__
+	bl	__aeabi_idiv0 // due to relocation limit, can't use b.
+#      endif
+	JMP(lr)
+
+#    else
 	cmp	r1, r2, lsr #1
 	subls	ip, ip, #(1 * 12)
 
-	mov	r3, #0
+	movs	r3, #0
 
 	JMP(ip)
+#    endif
 #  endif
 
 #define	IMM	#
 
+#if __ARM_ARCH_ISA_THUMB == 1
+#define block(shift) \
+	lsls r2, r1, IMM shift; \
+	cmp r0, r2 ; \
+	blo LOCAL_LABEL(block_skip_ ## shift) ; \
+	subs r0, r0, r2 ;\
+LOCAL_LABEL(block_skip_ ## shift): ;\
+	adcs r3, r3 /* this is equivalent to (r3 << 1) | Carry. Carry is set if r0 >= r2. */
+#else
 #define block(shift)                                                           \
 	cmp	r0, r1, lsl IMM shift;                                         \
 	ITT(hs);                                                               \
 	WIDE(addhs)	r3, r3, IMM (1 << shift);                              \
 	WIDE(subhs)	r0, r0, r1, lsl IMM shift
+#endif
 
 	block(31)
 	block(30)
@@ -159,6 +242,7 @@
 	JMP(lr)
 #endif /* __ARM_ARCH_EXT_IDIV__ */
 
+#if __ARM_ARCH_ISA_THUMB != 1
 LOCAL_LABEL(divby0):
 	mov	r0, #0
 #ifdef __ARM_EABI__
@@ -166,6 +250,7 @@
 #else
 	JMP(lr)
 #endif
+#endif
 
 END_COMPILERRT_FUNCTION(__udivsi3)
 
Index: lib/builtins/assembly.h
===================================================================
--- lib/builtins/assembly.h
+++ lib/builtins/assembly.h
@@ -71,7 +71,7 @@
 #define ARM_HAS_BX
 #endif
 #if !defined(__ARM_FEATURE_CLZ) &&                                             \
-    (__ARM_ARCH >= 6 || (__ARM_ARCH == 5 && !defined(__ARM_ARCH_5__)))
+    ((__ARM_ARCH >= 6 && __ARM_ARCH_PROFILE != 'M') || (__ARM_ARCH == 5 && !defined(__ARM_ARCH_5__)))
 #define __ARM_FEATURE_CLZ
 #endif