diff --git a/arch/arm/core/swap_helper.S b/arch/arm/core/swap_helper.S
index 272bc6ba93c..164393978bf 100644
--- a/arch/arm/core/swap_helper.S
+++ b/arch/arm/core/swap_helper.S
@@ -368,25 +368,30 @@ _oops:
      *
      * On SVC exeption, the stack looks like the following:
      * r0 - r1 - r2 - r3 - r12 - LR - PC - PSR
-     * r5 - r6 - call id - saved LR
      *
+     * Registers look like:
+     * r0 - arg1
+     * r1 - arg2
+     * r2 - arg3
+     * r3 - arg4
+     * r4 - arg5
+     * r5 - arg6
+     * r6 - call_id
+     * r7 - saved link register
      */
 _do_syscall:
-    ldr r1, [r0, #24]   /* grab address of PC from stack frame */
-    str r1, [r0, #44]   /* store address to use for LR after syscall */
+    ldr r7, [r0, #24]   /* grab address of PC from stack frame */
     ldr r1, =_arm_do_syscall
     str r1, [r0, #24]   /* overwrite the LR to point to _arm_do_syscall */
 
     /* validate syscall limit, only set priv mode if valid */
     ldr ip, =_SYSCALL_LIMIT
-    ldr r1, [r0, #40]
-    cmp r1, ip
+    cmp r6, ip
     blt valid_syscall_id
 
     /* bad syscall id.  Set arg0 to bad id and set call_id to SYSCALL_BAD */
-    str r1, [r0, #0]
-    ldr r1, =_SYSCALL_BAD
-    str r1, [r0, #40]
+    str r6, [r0, #0]
+    ldr r6, =_SYSCALL_BAD
 
 valid_syscall_id:
     /* set mode to privileged, r2 still contains value from CONTROL */
diff --git a/arch/arm/core/userspace.S b/arch/arm/core/userspace.S
index 2bd5fd5d602..65a80f6b0be 100644
--- a/arch/arm/core/userspace.S
+++ b/arch/arm/core/userspace.S
@@ -118,62 +118,54 @@ SECTION_FUNC(TEXT,_arm_userspace_enter)
  */
 SECTION_FUNC(TEXT, _arm_do_syscall)
     /*
-     * r0-r3 are values from pre-SVC from stack frame stored during SVC
-     * 16 bytes of storage reside on the stack:
-     * arg5, arg6, call_id, and LR from SVC frame
+     * r0-r5 contain arguments
+     * r6 contains call_id
+     * r7 contains original LR
      */
-    push {r4,r5,r6,lr}
-
-    ldr ip, =_k_syscall_table
-    ldr r4, [sp, #24]	/* load call_id from stack */
-    lsl r4, #2
-    add ip, r4
-    ldr ip, [ip]	/* load table address */
-    ldr r5, =_SYSCALL_BAD
-    lsl r5, #2		/* shift to match the shift we did on the call_id */
-    cmp r4, r5
+    ldr ip, =_SYSCALL_BAD
+    cmp r6, ip
     bne valid_syscall
 
     /* BAD SYSCALL path */
     /* fixup stack frame on unprivileged stack, adding ssf */
-    /* pop registers and lr as this is a one way jump */
-    mov r4, sp
-    str r4, [sp, #24]
-    pop {r4,r5,r6,lr}
+    mov ip, sp
+    push {r4,r5,ip,lr}
     b dispatch_syscall
 
 valid_syscall:
     /* setup priviliged stack */
-    ldr r4, =_kernel
-    ldr r4, [r4, #_kernel_offset_to_current]
-    ldr r5, [r4, #_thread_offset_to_priv_stack_start]    /* priv stack ptr */
+    push {r6}
+    ldr r6, =_kernel
+    ldr r6, [r6, #_kernel_offset_to_current]
+    ldr ip, [r6, #_thread_offset_to_priv_stack_start]    /* priv stack ptr */
     ldr r6, =CONFIG_PRIVILEGED_STACK_SIZE
-    add r5, r6
-
-    /* setup privileged stack frame */
-    /* 16 bytes: arg5, arg6, ssf, 4 bytes padding */
-    sub r5, #16
-    ldr r6, [sp, #16]
-    str r6, [r5, #0]
-    ldr r6, [sp, #20]
-    str r6, [r5, #4]
-    mov r6, sp
-    str r6, [r5, #8]	/* store ssf of unprivileged stack */
-    ldr r6, =0
-    str r6, [r5, #12]	/* store zeroed padding */
+    add ip, r6
+    pop {r6}
+    subs ip, #8
+    str sp, [ip, #0]
+    str lr, [ip, #4]
 
     /* switch to privileged stack */
-    msr PSP, r5
+    msr PSP, ip
+
+    /* push args to complete stack frame */
+    push {r4,r5}
+
 dispatch_syscall:
+    ldr ip, =_k_syscall_table
+    lsl r6, #2
+    add ip, r6
+    ldr ip, [ip]	/* load table address */
     /* execute function from dispatch table */
     blx ip
 
+    /* restore LR */
+    ldr lr, [sp,#12]
+
     /* set stack back to unprivileged stack */
     ldr ip, [sp,#8]
     msr PSP, ip
 
-    pop {r4,r5,r6,lr}
-
     /* drop privileges by setting bit 0 in CONTROL */
     mrs ip, CONTROL
     orrs ip, ip, #1
@@ -189,6 +181,6 @@ dispatch_syscall:
      * return back to original function that called SVC, add 1 to force thumb
      * mode
      */
-    ldr ip, [sp, #12]
+    mov ip, r7
     orrs ip, ip, #1
     bx ip
diff --git a/include/arch/arm/arch.h b/include/arch/arm/arch.h
index a1dde6ad752..8071513f368 100644
--- a/include/arch/arm/arch.h
+++ b/include/arch/arm/arch.h
@@ -360,19 +360,16 @@ static inline u32_t _arch_syscall_invoke6(u32_t arg1, u32_t arg2, u32_t arg3,
 	register u32_t r1 __asm__("r1") = arg2;
 	register u32_t r2 __asm__("r2") = arg3;
 	register u32_t r3 __asm__("r3") = arg4;
+	register u32_t r4 __asm__("r4") = arg5;
+	register u32_t r5 __asm__("r5") = arg6;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile("sub sp, #16\n"
-			 "str %[a5], [sp, #0]\n"
-			 "str %[a6], [sp, #4]\n"
-			 "str %[cid], [sp, #8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
 			   "r" (ret), "r" (r1), "r" (r2), "r" (r3),
-			   [a5] "r" (arg5), [a6] "r" (arg6)
-			 : "ip", "memory");
+			   "r" (r4), "r" (r5), "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }
@@ -384,18 +381,15 @@ static inline u32_t _arch_syscall_invoke5(u32_t arg1, u32_t arg2, u32_t arg3,
 	register u32_t r1 __asm__("r1") = arg2;
 	register u32_t r2 __asm__("r2") = arg3;
 	register u32_t r3 __asm__("r3") = arg4;
+	register u32_t r4 __asm__("r4") = arg5;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile("sub sp, #16\n"
-			 "str %[a5], [sp, #0]\n"
-			 "str %[cid], [sp, #8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
 			   "r" (ret), "r" (r1), "r" (r2), "r" (r3),
-			   [a5] "r" (arg5)
-			 : "ip", "memory");
+			   "r" (r4), "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }
@@ -407,16 +401,14 @@ static inline u32_t _arch_syscall_invoke4(u32_t arg1, u32_t arg2, u32_t arg3,
 	register u32_t r1 __asm__("r1") = arg2;
 	register u32_t r2 __asm__("r2") = arg3;
 	register u32_t r3 __asm__("r3") = arg4;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile("sub sp, #16\n"
-			 "str %[cid], [sp,#8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
-			   "r" (ret), "r" (r1), "r" (r2), "r" (r3)
-			 : "ip", "memory");
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			   "r" (ret), "r" (r1), "r" (r2), "r" (r3),
+			   "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }
@@ -427,16 +419,13 @@ static inline u32_t _arch_syscall_invoke3(u32_t arg1, u32_t arg2, u32_t arg3,
 	register u32_t ret __asm__("r0") = arg1;
 	register u32_t r1 __asm__("r1") = arg2;
 	register u32_t r2 __asm__("r2") = arg3;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile("sub sp, #16\n"
-			 "str %[cid], [sp,#8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
-			   "r" (ret), "r" (r1), "r" (r2)
-			 : "r3", "ip", "memory");
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			   "r" (ret), "r" (r1), "r" (r2), "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }
@@ -445,17 +434,13 @@ static inline u32_t _arch_syscall_invoke2(u32_t arg1, u32_t arg2, u32_t call_id)
 {
 	register u32_t ret __asm__("r0") = arg1;
 	register u32_t r1 __asm__("r1") = arg2;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile(
-			 "sub sp, #16\n"
-			 "str %[cid], [sp,#8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
-			   "r" (ret), "r" (r1)
-			 : "r2", "r3", "ip", "memory");
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			   "r" (ret), "r" (r1), "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }
@@ -463,34 +448,26 @@ static inline u32_t _arch_syscall_invoke2(u32_t arg1, u32_t arg2, u32_t call_id)
 static inline u32_t _arch_syscall_invoke1(u32_t arg1, u32_t call_id)
 {
 	register u32_t ret __asm__("r0") = arg1;
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile(
-			 "sub sp, #16\n"
-			 "str %[cid], [sp,#8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
-			   "r" (ret)
-			 : "r1", "r2", "r3", "ip", "memory");
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			   "r" (ret), "r" (r6)
+			 : "r7", "memory");
 	return ret;
 }
 
 static inline u32_t _arch_syscall_invoke0(u32_t call_id)
 {
 	register u32_t ret __asm__("r0");
+	register u32_t r6 __asm__("r6") = call_id;
 
-	__asm__ volatile(
-			 "sub sp, #16\n"
-			 "str %[cid], [sp,#8]\n"
-			 "svc %[svid]\n"
-			 "add sp, #16\n"
+	__asm__ volatile("svc %[svid]\n"
 			 : "=r"(ret)
-			 : [cid] "r" (call_id),
-			   [svid] "i" (_SVC_CALL_SYSTEM_CALL),
-			   "r" (ret)
-			 : "r1", "r2", "r3", "ip", "memory");
+			 : [svid] "i" (_SVC_CALL_SYSTEM_CALL),
+			   "r" (ret), "r" (r6)
+			 : "r7", "memory");
 
 	return ret;
 }