mach64: fix image corruption due to reading accelerator registers

Reading the registers without waiting for engine idle returns
unpredictable values. These unpredictable values result in display
corruption - if atyfb_imageblit reads the content of DP_PIX_WIDTH with the
bit DP_HOST_TRIPLE_EN set (from previous invocation), the driver would
never ever clear the bit, resulting in display corruption.

We don't want to wait for idle because it would degrade performance, so
this patch modifies the driver so that it never reads accelerator
registers.

HOST_CNTL doesn't have to be read, we can just write it with
HOST_BYTE_ALIGN because no other part of the driver cares if
HOST_BYTE_ALIGN is set.

DP_PIX_WIDTH is written in the functions atyfb_copyarea and atyfb_fillrect
with the default value and in atyfb_imageblit with the value set according
to the source image data.

Signed-off-by: Mikulas Patocka <[e-mail]>
Reviewed-by: Ville Syrjälä <[e-mail]>
Cc: [e-mail]
Signed-off-by: Bartlomiej Zolnierkiewicz <[e-mail]>

drivers/video/fbdev/aty/mach64_accel.c

···
 
 	/* set host attributes */
 	wait_for_fifo(13, par);
-	aty_st_le32(HOST_CNTL, 0, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 
 	/* set pattern attributes */
 	aty_st_le32(PAT_REG0, 0, par);
···
 		rotation = rotation24bpp(dx, direction);
 	}
 
-	wait_for_fifo(4, par);
+	wait_for_fifo(5, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_SRC, FRGD_SRC_BLIT, par);
 	aty_st_le32(SRC_Y_X, (sx << 16) | sy, par);
 	aty_st_le32(SRC_HEIGHT1_WIDTH1, (width << 16) | area->height, par);
···
 		rotation = rotation24bpp(dx, DST_X_LEFT_TO_RIGHT);
 	}
 
-	wait_for_fifo(3, par);
+	wait_for_fifo(4, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_FRGD_CLR, color, par);
 	aty_st_le32(DP_SRC,
 		    BKGD_SRC_BKGD_CLR | FRGD_SRC_FRGD_CLR | MONO_SRC_ONE,
···
 {
 	struct atyfb_par *par = (struct atyfb_par *) info->par;
 	u32 src_bytes, dx = image->dx, dy = image->dy, width = image->width;
-	u32 pix_width_save, pix_width, host_cntl, rotation = 0, src, mix;
+	u32 pix_width, rotation = 0, src, mix;
 
 	if (par->asleep)
 		return;
···
 		return;
 	}
 
-	pix_width = pix_width_save = aty_ld_le32(DP_PIX_WIDTH, par);
-	host_cntl = aty_ld_le32(HOST_CNTL, par) | HOST_BYTE_ALIGN;
+	pix_width = par->crtc.dp_pix_width;
 
 	switch (image->depth) {
 	case 1:
···
 		mix = FRGD_MIX_D_XOR_S | BKGD_MIX_D;
 	}
 
-	wait_for_fifo(6, par);
-	aty_st_le32(DP_WRITE_MASK, 0xFFFFFFFF, par);
+	wait_for_fifo(5, par);
 	aty_st_le32(DP_PIX_WIDTH, pix_width, par);
 	aty_st_le32(DP_MIX, mix, par);
 	aty_st_le32(DP_SRC, src, par);
-	aty_st_le32(HOST_CNTL, host_cntl, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 	aty_st_le32(DST_CNTL, DST_Y_TOP_TO_BOTTOM | DST_X_LEFT_TO_RIGHT | rotation, par);
 
 	draw_rect(dx, dy, width, image->height, par);
···
 			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
-
-	/* restore pix_width */
-	wait_for_fifo(1, par);
-	aty_st_le32(DP_PIX_WIDTH, pix_width_save, par);
 }