SSE/MMX/ARM: Fix high frequency noise with unusual number of channels

In the assembly optimized versions of SSE, a noise could occur when the
number of channels were 3,5,6 or 7. For MMX and ARM, this could occur
when the number of channels were 3.

Signed-off-by: David Henningsson <david.henningsson@canonical.com>

src/pulsecore/svolume_arm.c

@@ -47,7 +47,10 @@ pa_volume_s16ne_arm (int16_t *samples, int32_t *volumes, unsigned channels, unsi
 {
     int32_t *ve;
 
-    channels = PA_MAX (4U, channels);
+    /* Channels must be at least 4, and always a multiple of the original number.
+     * This is also the max amount we overread the volume array, which should
+     * have enough padding. */
+    channels = channels == 3 ? 6 : PA_MAX (4U, channels);
     ve = volumes + channels;
 
     __asm__ __volatile__ (

src/pulsecore/svolume_mmx.c

@@ -100,9 +100,10 @@ pa_volume_s16ne_mmx (int16_t *samples, int32_t *volumes, unsigned channels, unsi
 {
     pa_reg_x86 channel, temp;
 
-    /* the max number of samples we process at a time, this is also the max amount
+    /* Channels must be at least 4, and always a multiple of the original number.
-     * we overread the volume array, which should have enough padding. */
+     * This is also the max amount we overread the volume array, which should
-    channels = PA_MAX (4U, channels);
+     * have enough padding. */
+    channels = channels == 3 ? 6 : PA_MAX (4U, channels);
 
     __asm__ __volatile__ (
         " xor %3, %3                    \n\t"
@@ -166,9 +167,10 @@ pa_volume_s16re_mmx (int16_t *samples, int32_t *volumes, unsigned channels, unsi
 {
     pa_reg_x86 channel, temp;
 
-    /* the max number of samples we process at a time, this is also the max amount
+    /* Channels must be at least 4, and always a multiple of the original number.
-     * we overread the volume array, which should have enough padding. */
+     * This is also the max amount we overread the volume array, which should
-    channels = PA_MAX (4U, channels);
+     * have enough padding. */
+    channels = channels == 3 ? 6 : PA_MAX (4U, channels);
 
     __asm__ __volatile__ (
         " xor %3, %3                    \n\t"

src/pulsecore/svolume_sse.c

@@ -76,14 +76,19 @@
       " por %%xmm4, "#s1"            \n\t" /* .. |  l  h |  */ \
       " por %%xmm5, "#s2"            \n\t"
 
+
+static int channel_overread_table[8] = {8,8,8,12,8,10,12,14};
+
 static void
 pa_volume_s16ne_sse2 (int16_t *samples, int32_t *volumes, unsigned channels, unsigned length)
 {
     pa_reg_x86 channel, temp;
 
-    /* the max number of samples we process at a time, this is also the max amount
+    /* Channels must be at least 8 and always a multiple of the original number.
-     * we overread the volume array, which should have enough padding. */
+     * This is also the max amount we overread the volume array, which should
-    channels = PA_MAX (8U, channels);
+     * have enough padding. */
+    if (channels < 8)
+        channels = channel_overread_table[channels];
 
     __asm__ __volatile__ (
         " xor %3, %3                    \n\t"
@@ -161,9 +166,11 @@ pa_volume_s16re_sse2 (int16_t *samples, int32_t *volumes, unsigned channels, uns
 {
     pa_reg_x86 channel, temp;
 
-    /* the max number of samples we process at a time, this is also the max amount
+    /* Channels must be at least 8 and always a multiple of the original number.
-     * we overread the volume array, which should have enough padding. */
+     * This is also the max amount we overread the volume array, which should
-    channels = PA_MAX (8U, channels);
+     * have enough padding. */
+    if (channels < 8)
+        channels = channel_overread_table[channels];
 
     __asm__ __volatile__ (
         " xor %3, %3                    \n\t"