viafb: 2D engine rewrite

This patch is a completly rewritten 2D engine.  The engine is no longer in
a default state but reinitialized every time to allow usage for both
framebuffers regardless of their settings.

The whole engine handling is concentrated in a big function which takes 16
parameters.  Although the number of parameters is worryingly it is good to
have a single funtion to deal with this stuff as it allows to easily
support different engines and avoids some code duplication.

On the way support for the new 2D engine in VX800 was added.  As the with
less code duplication but it is probably better to duplicate the code as
this way is easier to walk if VIA ever decides to release a new engine
which changes anything the driver touches.

The engine support for VX800 gives a notable boost in speed.  There are no
known regressions but as this patch changes paths I do neither have the
hardware nor documentation to check and has the possibility to put the
system in a critical state heavy testing is appreciated.

Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
Cc: Scott Fang <ScottFang@viatech.com.cn>
Cc: Joseph Chan <JosephChan@via.com.tw>
Cc: Harald Welte <laforge@gnumonks.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 312 insertions, 51 deletions

diff --git a/drivers/video/via/accel.c b/drivers/video/via/accel.c
index b3e7e824632..8ac02515a18 100644
--- a/drivers/video/via/accel.c
+++ b/drivers/video/via/accel.c
@@ -20,8 +20,316 @@
  */
 #include "global.h"
 
-void viafb_init_accel(void)
+static int hw_bitblt_1(void __iomem *engine, u8 op, u32 width, u32 height,
+	u8 dst_bpp, u32 dst_addr, u32 dst_pitch, u32 dst_x, u32 dst_y,
+	u32 *src_mem, u32 src_addr, u32 src_pitch, u32 src_x, u32 src_y,
+	u32 fg_color, u32 bg_color, u8 fill_rop)
 {
+	u32 ge_cmd = 0, tmp, i;
+
+	if (!op || op > 3) {
+		printk(KERN_WARNING "hw_bitblt_1: Invalid operation: %d\n", op);
+		return -EINVAL;
+	}
+
+	if (op != VIA_BITBLT_FILL && !src_mem && src_addr == dst_addr) {
+		if (src_x < dst_x) {
+			ge_cmd |= 0x00008000;
+			src_x += width - 1;
+			dst_x += width - 1;
+		}
+		if (src_y < dst_y) {
+			ge_cmd |= 0x00004000;
+			src_y += height - 1;
+			dst_y += height - 1;
+		}
+	}
+
+	if (op == VIA_BITBLT_FILL) {
+		switch (fill_rop) {
+		case 0x00: /* blackness */
+		case 0x5A: /* pattern inversion */
+		case 0xF0: /* pattern copy */
+		case 0xFF: /* whiteness */
+			break;
+		default:
+			printk(KERN_WARNING "hw_bitblt_1: Invalid fill rop: "
+				"%u\n", fill_rop);
+			return -EINVAL;
+		}
+	}
+
+	switch (dst_bpp) {
+	case 8:
+		tmp = 0x00000000;
+		break;
+	case 16:
+		tmp = 0x00000100;
+		break;
+	case 32:
+		tmp = 0x00000300;
+		break;
+	default:
+		printk(KERN_WARNING "hw_bitblt_1: Unsupported bpp %d\n",
+			dst_bpp);
+		return -EINVAL;
+	}
+	writel(tmp, engine + 0x04);
+
+	if (op != VIA_BITBLT_FILL) {
+		if (src_x & (op == VIA_BITBLT_MONO ? 0xFFFF8000 : 0xFFFFF000)
+			|| src_y & 0xFFFFF000) {
+			printk(KERN_WARNING "hw_bitblt_1: Unsupported source "
+				"x/y %d %d\n", src_x, src_y);
+			return -EINVAL;
+		}
+		tmp = src_x | (src_y << 16);
+		writel(tmp, engine + 0x08);
+	}
+
+	if (dst_x & 0xFFFFF000 || dst_y & 0xFFFFF000) {
+		printk(KERN_WARNING "hw_bitblt_1: Unsupported destination x/y "
+			"%d %d\n", dst_x, dst_y);
+		return -EINVAL;
+	}
+	tmp = dst_x | (dst_y << 16);
+	writel(tmp, engine + 0x0C);
+
+	if ((width - 1) & 0xFFFFF000 || (height - 1) & 0xFFFFF000) {
+		printk(KERN_WARNING "hw_bitblt_1: Unsupported width/height "
+			"%d %d\n", width, height);
+		return -EINVAL;
+	}
+	tmp = (width - 1) | ((height - 1) << 16);
+	writel(tmp, engine + 0x10);
+
+	if (op != VIA_BITBLT_COLOR)
+		writel(fg_color, engine + 0x18);
+
+	if (op == VIA_BITBLT_MONO)
+		writel(bg_color, engine + 0x1C);
+
+	if (op != VIA_BITBLT_FILL) {
+		tmp = src_mem ? 0 : src_addr;
+		if (dst_addr & 0xE0000007) {
+			printk(KERN_WARNING "hw_bitblt_1: Unsupported source "
+				"address %X\n", tmp);
+			return -EINVAL;
+		}
+		tmp >>= 3;
+		writel(tmp, engine + 0x30);
+	}
+
+	if (dst_addr & 0xE0000007) {
+		printk(KERN_WARNING "hw_bitblt_1: Unsupported destination "
+			"address %X\n", dst_addr);
+		return -EINVAL;
+	}
+	tmp = dst_addr >> 3;
+	writel(tmp, engine + 0x34);
+
+	if (op == VIA_BITBLT_FILL)
+		tmp = 0;
+	else
+		tmp = src_pitch;
+	if (tmp & 0xFFFFC007 || dst_pitch & 0xFFFFC007) {
+		printk(KERN_WARNING "hw_bitblt_1: Unsupported pitch %X %X\n",
+			tmp, dst_pitch);
+		return -EINVAL;
+	}
+	tmp = (tmp >> 3) | (dst_pitch << (16 - 3));
+	writel(tmp, engine + 0x38);
+
+	if (op == VIA_BITBLT_FILL)
+		ge_cmd |= fill_rop << 24 | 0x00002000 | 0x00000001;
+	else {
+		ge_cmd |= 0xCC000000; /* ROP=SRCCOPY */
+		if (src_mem)
+			ge_cmd |= 0x00000040;
+		if (op == VIA_BITBLT_MONO)
+			ge_cmd |= 0x00000002 | 0x00000100 | 0x00020000;
+		else
+			ge_cmd |= 0x00000001;
+	}
+	writel(ge_cmd, engine);
+
+	if (op == VIA_BITBLT_FILL || !src_mem)
+		return 0;
+
+	tmp = (width * height * (op == VIA_BITBLT_MONO ? 1 : (dst_bpp >> 3)) +
+		3) >> 2;
+
+	for (i = 0; i < tmp; i++)
+		writel(src_mem[i], engine + VIA_MMIO_BLTBASE);
+
+	return 0;
+}
+
+static int hw_bitblt_2(void __iomem *engine, u8 op, u32 width, u32 height,
+	u8 dst_bpp, u32 dst_addr, u32 dst_pitch, u32 dst_x, u32 dst_y,
+	u32 *src_mem, u32 src_addr, u32 src_pitch, u32 src_x, u32 src_y,
+	u32 fg_color, u32 bg_color, u8 fill_rop)
+{
+	u32 ge_cmd = 0, tmp, i;
+
+	if (!op || op > 3) {
+		printk(KERN_WARNING "hw_bitblt_2: Invalid operation: %d\n", op);
+		return -EINVAL;
+	}
+
+	if (op != VIA_BITBLT_FILL && !src_mem && src_addr == dst_addr) {
+		if (src_x < dst_x) {
+			ge_cmd |= 0x00008000;
+			src_x += width - 1;
+			dst_x += width - 1;
+		}
+		if (src_y < dst_y) {
+			ge_cmd |= 0x00004000;
+			src_y += height - 1;
+			dst_y += height - 1;
+		}
+	}
+
+	if (op == VIA_BITBLT_FILL) {
+		switch (fill_rop) {
+		case 0x00: /* blackness */
+		case 0x5A: /* pattern inversion */
+		case 0xF0: /* pattern copy */
+		case 0xFF: /* whiteness */
+			break;
+		default:
+			printk(KERN_WARNING "hw_bitblt_2: Invalid fill rop: "
+				"%u\n", fill_rop);
+			return -EINVAL;
+		}
+	}
+
+	switch (dst_bpp) {
+	case 8:
+		tmp = 0x00000000;
+		break;
+	case 16:
+		tmp = 0x00000100;
+		break;
+	case 32:
+		tmp = 0x00000300;
+		break;
+	default:
+		printk(KERN_WARNING "hw_bitblt_2: Unsupported bpp %d\n",
+			dst_bpp);
+		return -EINVAL;
+	}
+	writel(tmp, engine + 0x04);
+
+	if (op == VIA_BITBLT_FILL)
+		tmp = 0;
+	else
+		tmp = src_pitch;
+	if (tmp & 0xFFFFC007 || dst_pitch & 0xFFFFC007) {
+		printk(KERN_WARNING "hw_bitblt_2: Unsupported pitch %X %X\n",
+			tmp, dst_pitch);
+		return -EINVAL;
+	}
+	tmp = (tmp >> 3) | (dst_pitch << (16 - 3));
+	writel(tmp, engine + 0x08);
+
+	if ((width - 1) & 0xFFFFF000 || (height - 1) & 0xFFFFF000) {
+		printk(KERN_WARNING "hw_bitblt_2: Unsupported width/height "
+			"%d %d\n", width, height);
+		return -EINVAL;
+	}
+	tmp = (width - 1) | ((height - 1) << 16);
+	writel(tmp, engine + 0x0C);
+
+	if (dst_x & 0xFFFFF000 || dst_y & 0xFFFFF000) {
+		printk(KERN_WARNING "hw_bitblt_2: Unsupported destination x/y "
+			"%d %d\n", dst_x, dst_y);
+		return -EINVAL;
+	}
+	tmp = dst_x | (dst_y << 16);
+	writel(tmp, engine + 0x10);
+
+	if (dst_addr & 0xE0000007) {
+		printk(KERN_WARNING "hw_bitblt_2: Unsupported destination "
+			"address %X\n", dst_addr);
+		return -EINVAL;
+	}
+	tmp = dst_addr >> 3;
+	writel(tmp, engine + 0x14);
+
+	if (op != VIA_BITBLT_FILL) {
+		if (src_x & (op == VIA_BITBLT_MONO ? 0xFFFF8000 : 0xFFFFF000)
+			|| src_y & 0xFFFFF000) {
+			printk(KERN_WARNING "hw_bitblt_2: Unsupported source "
+				"x/y %d %d\n", src_x, src_y);
+			return -EINVAL;
+		}
+		tmp = src_x | (src_y << 16);
+		writel(tmp, engine + 0x18);
+
+		tmp = src_mem ? 0 : src_addr;
+		if (dst_addr & 0xE0000007) {
+			printk(KERN_WARNING "hw_bitblt_2: Unsupported source "
+				"address %X\n", tmp);
+			return -EINVAL;
+		}
+		tmp >>= 3;
+		writel(tmp, engine + 0x1C);
+	}
+
+	if (op != VIA_BITBLT_COLOR)
+		writel(fg_color, engine + 0x4C);
+
+	if (op == VIA_BITBLT_MONO)
+		writel(bg_color, engine + 0x50);
+
+	if (op == VIA_BITBLT_FILL)
+		ge_cmd |= fill_rop << 24 | 0x00002000 | 0x00000001;
+	else {
+		ge_cmd |= 0xCC000000; /* ROP=SRCCOPY */
+		if (src_mem)
+			ge_cmd |= 0x00000040;
+		if (op == VIA_BITBLT_MONO)
+			ge_cmd |= 0x00000002 | 0x00000100 | 0x00020000;
+		else
+			ge_cmd |= 0x00000001;
+	}
+	writel(ge_cmd, engine);
+
+	if (op == VIA_BITBLT_FILL || !src_mem)
+		return 0;
+
+	tmp = (width * height * (op == VIA_BITBLT_MONO ? 1 : (dst_bpp >> 3)) +
+		3) >> 2;
+
+	for (i = 0; i < tmp; i++)
+		writel(src_mem[i], engine + VIA_MMIO_BLTBASE);
+
+	return 0;
+}
+
+void viafb_init_accel(struct viafb_shared *shared)
+{
+	switch (shared->chip_info.gfx_chip_name) {
+	case UNICHROME_CLE266:
+	case UNICHROME_K400:
+	case UNICHROME_K800:
+	case UNICHROME_PM800:
+	case UNICHROME_CN700:
+	case UNICHROME_CX700:
+	case UNICHROME_CN750:
+	case UNICHROME_K8M890:
+	case UNICHROME_P4M890:
+	case UNICHROME_P4M900:
+		shared->hw_bitblt = hw_bitblt_1;
+		break;
+	case UNICHROME_VX800:
+		shared->hw_bitblt = hw_bitblt_2;
+		break;
+	default:
+		shared->hw_bitblt = NULL;
+	}
+
 	viaparinfo->fbmem_free -= CURSOR_SIZE;
 	viaparinfo->cursor_start = viaparinfo->fbmem_free;
 	viaparinfo->fbmem_used += CURSOR_SIZE;
@@ -30,30 +338,14 @@ void viafb_init_accel(void)
 	viaparinfo->fbmem_free -= (CURSOR_SIZE + VQ_SIZE);
 	viaparinfo->VQ_start = viaparinfo->fbmem_free;
 	viaparinfo->VQ_end = viaparinfo->VQ_start + VQ_SIZE - 1;
-	viaparinfo->fbmem_used += (CURSOR_SIZE + VQ_SIZE); }
+	viaparinfo->fbmem_used += (CURSOR_SIZE + VQ_SIZE);
+}
 
 void viafb_init_2d_engine(void)
 {
-	u32 dwVQStartAddr, dwVQEndAddr, linesize;
+	u32 dwVQStartAddr, dwVQEndAddr;
 	u32 dwVQLen, dwVQStartL, dwVQEndL, dwVQStartEndH;
 
-	/* init 2D engine regs to reset 2D engine */
-	writel(0x0, viaparinfo->io_virt + VIA_REG_GEMODE);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_SRCPOS);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_DSTPOS);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_DIMENSION);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_PATADDR);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_FGCOLOR);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_BGCOLOR);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_CLIPTL);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_CLIPBR);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_OFFSET);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_KEYCONTROL);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_SRCBASE);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_DSTBASE);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_PITCH);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_MONOPAT1);
-
 	/* Init AGP and VQ regs */
 	switch (viaparinfo->chip_info->gfx_chip_name) {
 	case UNICHROME_K8M890:
@@ -190,37 +482,6 @@ void viafb_init_2d_engine(void)
 			break;
 		}
 	}
-
-	viafb_set_2d_color_depth(viafbinfo->var.bits_per_pixel);
-
-	writel(0x0, viaparinfo->io_virt + VIA_REG_SRCBASE);
-	writel(0x0, viaparinfo->io_virt + VIA_REG_DSTBASE);
-
-	linesize = viafbinfo->var.xres * viafbinfo->var.bits_per_pixel >> 3;
-	writel(VIA_PITCH_ENABLE | (linesize >> 3) | ((linesize >> 3) << 16),
-		viaparinfo->io_virt + VIA_REG_PITCH);
-}
-
-void viafb_set_2d_color_depth(int bpp)
-{
-	u32 dwGEMode;
-
-	dwGEMode = readl(viaparinfo->io_virt + 0x04) & 0xFFFFFCFF;
-
-	switch (bpp) {
-	case 16:
-		dwGEMode |= VIA_GEM_16bpp;
-		break;
-	case 32:
-		dwGEMode |= VIA_GEM_32bpp;
-		break;
-	default:
-		dwGEMode |= VIA_GEM_8bpp;
-		break;
-	}
-
-	/* Set BPP and Pitch */
-	writel(dwGEMode, viaparinfo->io_virt + VIA_REG_GEMODE);
 }
 
 void viafb_hw_cursor_init(void)