1 files changed, 81 insertions, 128 deletions

diff --git a/sound/pci/emu10k1/emu10k1_patch.c b/sound/pci/emu10k1/emu10k1_patch.c
index 89890f2450..dbfa89435a 100644
--- a/sound/pci/emu10k1/emu10k1_patch.c
+++ b/sound/pci/emu10k1/emu10k1_patch.c
@@ -16,7 +16,7 @@
 #define BLANK_LOOP_START	4
 #define BLANK_LOOP_END		8
 #define BLANK_LOOP_SIZE		12
-#define BLANK_HEAD_SIZE		32
+#define BLANK_HEAD_SIZE		3
 
 /*
  * allocate a sample block and copy data from userspace
@@ -26,56 +26,76 @@ snd_emu10k1_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 		       struct snd_util_memhdr *hdr,
 		       const void __user *data, long count)
 {
+	u8 fill;
+	u32 xor;
+	int shift;
 	int offset;
 	int truesize, size, blocksize;
-	__maybe_unused int loopsize;
-	int loopend, sampleend;
-	unsigned int start_addr;
+	int loop_start, loop_end, loop_size, data_end, unroll;
 	struct snd_emu10k1 *emu;
 
 	emu = rec->hw;
 	if (snd_BUG_ON(!sp || !hdr))
 		return -EINVAL;
 
-	if (sp->v.size == 0) {
-		dev_dbg(emu->card->dev,
-			"emu: rom font for sample %d\n", sp->v.sample);
-		return 0;
+	if (sp->v.mode_flags & (SNDRV_SFNT_SAMPLE_BIDIR_LOOP | SNDRV_SFNT_SAMPLE_REVERSE_LOOP)) {
+		/* should instead return -ENOTSUPP; but compatibility */
+		printk(KERN_WARNING "Emu10k1 wavetable patch %d with unsupported loop feature\n",
+		       sp->v.sample);
 	}
 
-	/* recalculate address offset */
-	sp->v.end -= sp->v.start;
-	sp->v.loopstart -= sp->v.start;
-	sp->v.loopend -= sp->v.start;
-	sp->v.start = 0;
-
-	/* some samples have invalid data.  the addresses are corrected in voice info */
-	sampleend = sp->v.end;
-	if (sampleend > sp->v.size)
-		sampleend = sp->v.size;
-	loopend = sp->v.loopend;
-	if (loopend > sampleend)
-		loopend = sampleend;
-
-	/* be sure loop points start < end */
-	if (sp->v.loopstart >= sp->v.loopend)
-		swap(sp->v.loopstart, sp->v.loopend);
+	if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS) {
+		shift = 0;
+		fill = 0x80;
+		xor = (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_UNSIGNED) ? 0 : 0x80808080;
+	} else {
+		shift = 1;
+		fill = 0;
+		xor = (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_UNSIGNED) ? 0x80008000 : 0;
+	}
 
 	/* compute true data size to be loaded */
 	truesize = sp->v.size + BLANK_HEAD_SIZE;
-	loopsize = 0;
-#if 0 /* not supported */
-	if (sp->v.mode_flags & (SNDRV_SFNT_SAMPLE_BIDIR_LOOP|SNDRV_SFNT_SAMPLE_REVERSE_LOOP))
-		loopsize = sp->v.loopend - sp->v.loopstart;
-	truesize += loopsize;
-#endif
-	if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_NO_BLANK)
+	if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_NO_BLANK) {
 		truesize += BLANK_LOOP_SIZE;
+		/* if no blank loop is attached in the sample, add it */
+		if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_SINGLESHOT) {
+			sp->v.loopstart = sp->v.end + BLANK_LOOP_START;
+			sp->v.loopend = sp->v.end + BLANK_LOOP_END;
+		}
+	}
+
+	loop_start = sp->v.loopstart;
+	loop_end = sp->v.loopend;
+	loop_size = loop_end - loop_start;
+	if (!loop_size)
+		return -EINVAL;
+	data_end = sp->v.end;
+
+	/* recalculate offset */
+	sp->v.start += BLANK_HEAD_SIZE;
+	sp->v.end += BLANK_HEAD_SIZE;
+	sp->v.loopstart += BLANK_HEAD_SIZE;
+	sp->v.loopend += BLANK_HEAD_SIZE;
+
+	// Automatic pre-filling of the cache does not work in the presence
+	// of loops (*), and we don't want to fill it manually, as that is
+	// fiddly and slow. So we unroll the loop until the loop end is
+	// beyond the cache size.
+	// (*) Strictly speaking, a single iteration is supported (that's
+	// how it works when the playback engine runs), but handling this
+	// special case is not worth it.
+	unroll = 0;
+	while (sp->v.loopend < 64) {
+		truesize += loop_size;
+		sp->v.loopstart += loop_size;
+		sp->v.loopend += loop_size;
+		sp->v.end += loop_size;
+		unroll++;
+	}
 
 	/* try to allocate a memory block */
-	blocksize = truesize;
-	if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS))
-		blocksize *= 2;
+	blocksize = truesize << shift;
 	sp->block = snd_emu10k1_synth_alloc(emu, blocksize);
 	if (sp->block == NULL) {
 		dev_dbg(emu->card->dev,
@@ -88,110 +108,43 @@ snd_emu10k1_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 
 	/* write blank samples at head */
 	offset = 0;
-	size = BLANK_HEAD_SIZE;
-	if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS))
-		size *= 2;
-	if (offset + size > blocksize)
-		return -EINVAL;
-	snd_emu10k1_synth_bzero(emu, sp->block, offset, size);
-	offset += size;
-
-	/* copy start->loopend */
-	size = loopend;
-	if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS))
-		size *= 2;
-	if (offset + size > blocksize)
-		return -EINVAL;
-	if (snd_emu10k1_synth_copy_from_user(emu, sp->block, offset, data, size)) {
-		snd_emu10k1_synth_free(emu, sp->block);
-		sp->block = NULL;
-		return -EFAULT;
-	}
+	size = BLANK_HEAD_SIZE << shift;
+	snd_emu10k1_synth_memset(emu, sp->block, offset, size, fill);
 	offset += size;
-	data += size;
-
-#if 0 /* not supported yet */
-	/* handle reverse (or bidirectional) loop */
-	if (sp->v.mode_flags & (SNDRV_SFNT_SAMPLE_BIDIR_LOOP|SNDRV_SFNT_SAMPLE_REVERSE_LOOP)) {
-		/* copy loop in reverse */
-		if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS)) {
-			int woffset;
-			unsigned short *wblock = (unsigned short*)block;
-			woffset = offset / 2;
-			if (offset + loopsize * 2 > blocksize)
-				return -EINVAL;
-			for (i = 0; i < loopsize; i++)
-				wblock[woffset + i] = wblock[woffset - i -1];
-			offset += loopsize * 2;
-		} else {
-			if (offset + loopsize > blocksize)
-				return -EINVAL;
-			for (i = 0; i < loopsize; i++)
-				block[offset + i] = block[offset - i -1];
-			offset += loopsize;
-		}
 
-		/* modify loop pointers */
-		if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_BIDIR_LOOP) {
-			sp->v.loopend += loopsize;
-		} else {
-			sp->v.loopstart += loopsize;
-			sp->v.loopend += loopsize;
+	/* copy provided samples */
+	if (unroll && loop_end <= data_end) {
+		size = loop_end << shift;
+		if (snd_emu10k1_synth_copy_from_user(emu, sp->block, offset, data, size, xor))
+			goto faulty;
+		offset += size;
+
+		data += loop_start << shift;
+		while (--unroll > 0) {
+			size = loop_size << shift;
+			if (snd_emu10k1_synth_copy_from_user(emu, sp->block, offset, data, size, xor))
+				goto faulty;
+			offset += size;
 		}
-		/* add sample pointer */
-		sp->v.end += loopsize;
-	}
-#endif
 
-	/* loopend -> sample end */
-	size = sp->v.size - loopend;
-	if (size < 0)
-		return -EINVAL;
-	if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS))
-		size *= 2;
-	if (snd_emu10k1_synth_copy_from_user(emu, sp->block, offset, data, size)) {
-		snd_emu10k1_synth_free(emu, sp->block);
-		sp->block = NULL;
-		return -EFAULT;
+		size = (data_end - loop_start) << shift;
+	} else {
+		size = data_end << shift;
 	}
+	if (snd_emu10k1_synth_copy_from_user(emu, sp->block, offset, data, size, xor))
+		goto faulty;
 	offset += size;
 
 	/* clear rest of samples (if any) */
 	if (offset < blocksize)
-		snd_emu10k1_synth_bzero(emu, sp->block, offset, blocksize - offset);
-
-	if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_NO_BLANK) {
-		/* if no blank loop is attached in the sample, add it */
-		if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_SINGLESHOT) {
-			sp->v.loopstart = sp->v.end + BLANK_LOOP_START;
-			sp->v.loopend = sp->v.end + BLANK_LOOP_END;
-		}
-	}
-
-#if 0 /* not supported yet */
-	if (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_UNSIGNED) {
-		/* unsigned -> signed */
-		if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS)) {
-			unsigned short *wblock = (unsigned short*)block;
-			for (i = 0; i < truesize; i++)
-				wblock[i] ^= 0x8000;
-		} else {
-			for (i = 0; i < truesize; i++)
-				block[i] ^= 0x80;
-		}
-	}
-#endif
-
-	/* recalculate offset */
-	start_addr = BLANK_HEAD_SIZE * 2;
-	if (! (sp->v.mode_flags & SNDRV_SFNT_SAMPLE_8BITS))
-		start_addr >>= 1;
-	sp->v.start += start_addr;
-	sp->v.end += start_addr;
-	sp->v.loopstart += start_addr;
-	sp->v.loopend += start_addr;
+		snd_emu10k1_synth_memset(emu, sp->block, offset, blocksize - offset, fill);
 
 	return 0;
+
+faulty:
+	snd_emu10k1_synth_free(emu, sp->block);
+	sp->block = NULL;
+	return -EFAULT;
 }
 
 /*