arm: add ARMv7-M version of ARMv6 mixer code

GCC cannot compile the existing assembly here on ARMv7-M,
claiming impossible constraints. It is actually possible to
compile if the input arguments (addresses and sizes) are
first moved to a high register so as not to conflict with
the use of r0-r7 in ldm/stm -- this is exactly what GCC does
for ARMv6, but it won't do it on ARMv7-M for some reason.

We can get a result similar to the ARMv6 code by manually
moving the inputs into temporaries, but the generated code
is a actually a bit smaller on ARMv7-M if the r0-r7 block is
shifted up to r3-r10. This only works since ARMv7-M supports
the 32-bit Thumb encoding -- 16-bit Thumb can't represent an
ldm/stm instruction of this type.

It's worth #ifdef'ing the code because although the ARMv7-M
version works on ARMv6 too, it spills a lot of registers on
the stack even though register use is mostly similar.

Change-Id: I9bc8b5c76e198aecfd0a0e7a2158b1c00f82c4df

firmware/asm/arm/pcm-mixer-armv6.c

@@ -78,6 +78,27 @@ static FORCE_INLINE void write_samples(void *out,
     if (LIKELY(amp == MIX_AMP_UNITY))
     {
         /* Channel is unity amplitude */
+#if defined(CPU_ARM_MICRO) && ARCH_VERSION >= 7
+        asm volatile (
+            "ands       r4, %2, #0x1f   \n"
+            "beq        2f              \n"
+        "1:                             \n"
+            "ldr        r3, [%1], #4    \n"
+            "subs       r4, r4, #4      \n"
+            "str        r3, [%0], #4    \n"
+            "bne        1b              \n"
+            "bics       %2, %2, #0x1f   \n"
+            "beq        3f              \n"
+        "2:                             \n"
+            "ldmia      %1!, { r3-r10 } \n"
+            "subs       %2, %2, #32     \n"
+            "stmia      %0!, { r3-r10 } \n"
+            "bhi        2b              \n"
+        "3:                             \n"
+            : "+lr"(out), "+lr"(src), "+r"(size)
+            :
+            : "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10");
+#else
         asm volatile (
             "ands       r1, %2, #0x1f  \n"
             "beq        2f             \n"
@@ -97,6 +118,7 @@ static FORCE_INLINE void write_samples(void *out,
             : "+r"(out), "+r"(src), "+r"(size)
             :
             : "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7");
+#endif
     }
     else
     {