drm/mgag200: Hardware cursor support

G200 cards support, at best, 16 colour palleted images for the cursor
so we do a conversion in the cursor_set function, and reject cursors
with more than 16 colours, or cursors with partial transparency. Xorg
falls back gracefully to software cursors in this case.

We can't disable/enable the cursor hardware without causing momentary
corruption around the cursor. Instead, once the cursor is on we leave
it on, and simulate turning the cursor off by moving it
offscreen. This works well.

Since we can't disable -> update -> enable the cursors, we double
buffer cursor icons, then just move the base address that points to
the old cursor, to the new. This also works well, but uses an extra
page of memory.

The cursor buffers are lazily-allocated on first cursor_set. This is
to make sure they don't take priority over any framebuffers in case of
limited memory.

Here is a representation of how the bitmap for the cursor is mapped in G200 memory :

  Each line of color cursor use 6 Slices of 8 bytes. Slices 0 to 3
  are used for the 4bpp bitmap, slice 4 for XOR mask and slice 5 for
  AND mask. Each line has the following format:

      //      Byte 0  Byte 1  Byte 2  Byte 3  Byte 4  Byte 5  Byte 6 Byte 7
      //
      // S0:  P00-01  P02-03  P04-05  P06-07  P08-09  P10-11  P12-13 P14-15
      // S1:  P16-17  P18-19  P20-21  P22-23  P24-25  P26-27  P28-29 P30-31
      // S2:  P32-33  P34-35  P36-37  P38-39  P40-41  P42-43  P44-45 P46-47
      // S3:  P48-49  P50-51  P52-53  P54-55  P56-57  P58-59  P60-61 P62-63
      // S4:  X63-56  X55-48  X47-40  X39-32  X31-24  X23-16  X15-08 X07-00
      // S5:  A63-56  A55-48  A47-40  A39-32  A31-24  A23-16  A15-08 A07-00
      //
      //       S0 to S5      = Slices 0 to 5
      //       P00 to P63    = Bitmap - pixels 0 to 63
      //       X00 to X63    = always 0 - pixels 0 to 63
      //       A00 to A63    = transparent markers - pixels 0 to 63
      //                       1 means colour, 0 means transparent

Signed-off-by: Christopher Harvey <charvey@matrox.com>
Signed-off-by: Mathieu Larouche <mathieu.larouche@matrox.com>
Acked-by: Julia Lemire <jlemire@matrox.com>
Tested-by: Julia Lemire <jlemire@matrox.com>
Signed-off-by: Dave Airlie <airlied@gmail.com>
diff --git a/drivers/gpu/drm/mgag200/Makefile b/drivers/gpu/drm/mgag200/Makefile
index 7db592e..a9a0300 100644
--- a/drivers/gpu/drm/mgag200/Makefile
+++ b/drivers/gpu/drm/mgag200/Makefile
@@ -1,5 +1,5 @@
 ccflags-y := -Iinclude/drm
-mgag200-y   := mgag200_main.o mgag200_mode.o \
+mgag200-y   := mgag200_main.o mgag200_mode.o mgag200_cursor.o \
 	mgag200_drv.o mgag200_fb.o mgag200_i2c.o mgag200_ttm.o
 
 obj-$(CONFIG_DRM_MGAG200) += mgag200.o
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
new file mode 100644
index 0000000..801731a
--- /dev/null
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -0,0 +1,275 @@
+/*
+ * Copyright 2013 Matrox Graphics
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License version 2. See the file COPYING in the main
+ * directory of this archive for more details.
+ *
+ * Author: Christopher Harvey <charvey@matrox.com>
+ */
+
+#include <drm/drmP.h>
+#include "mgag200_drv.h"
+
+static bool warn_transparent = true;
+static bool warn_palette = true;
+
+/*
+  Hide the cursor off screen. We can't disable the cursor hardware because it
+  takes too long to re-activate and causes momentary corruption
+*/
+static void mga_hide_cursor(struct mga_device *mdev)
+{
+	WREG8(MGA_CURPOSXL, 0);
+	WREG8(MGA_CURPOSXH, 0);
+	mgag200_bo_unpin(mdev->cursor.pixels_1);
+	mgag200_bo_unpin(mdev->cursor.pixels_2);
+}
+
+int mga_crtc_cursor_set(struct drm_crtc *crtc,
+			struct drm_file *file_priv,
+			uint32_t handle,
+			uint32_t width,
+			uint32_t height)
+{
+	struct drm_device *dev = (struct drm_device *)file_priv->minor->dev;
+	struct mga_device *mdev = (struct mga_device *)dev->dev_private;
+	struct mgag200_bo *pixels_1 = mdev->cursor.pixels_1;
+	struct mgag200_bo *pixels_2 = mdev->cursor.pixels_2;
+	struct mgag200_bo *pixels_current = mdev->cursor.pixels_current;
+	struct mgag200_bo *pixels_prev = mdev->cursor.pixels_prev;
+	struct drm_gem_object *obj;
+	struct mgag200_bo *bo = NULL;
+	int ret = 0;
+	unsigned int i, row, col;
+	uint32_t colour_set[16];
+	uint32_t *next_space = &colour_set[0];
+	uint32_t *palette_iter;
+	uint32_t this_colour;
+	bool found = false;
+	int colour_count = 0;
+	u64 gpu_addr;
+	u8 reg_index;
+	u8 this_row[48];
+
+	if (!pixels_1 || !pixels_2) {
+		WREG8(MGA_CURPOSXL, 0);
+		WREG8(MGA_CURPOSXH, 0);
+		return -ENOTSUPP; /* Didn't allocate space for cursors */
+	}
+
+	if ((width != 64 || height != 64) && handle) {
+		WREG8(MGA_CURPOSXL, 0);
+		WREG8(MGA_CURPOSXH, 0);
+		return -EINVAL;
+	}
+
+	BUG_ON(pixels_1 != pixels_current && pixels_1 != pixels_prev);
+	BUG_ON(pixels_2 != pixels_current && pixels_2 != pixels_prev);
+	BUG_ON(pixels_current == pixels_prev);
+
+	ret = mgag200_bo_reserve(pixels_1, true);
+	if (ret) {
+		WREG8(MGA_CURPOSXL, 0);
+		WREG8(MGA_CURPOSXH, 0);
+		return ret;
+	}
+	ret = mgag200_bo_reserve(pixels_2, true);
+	if (ret) {
+		WREG8(MGA_CURPOSXL, 0);
+		WREG8(MGA_CURPOSXH, 0);
+		mgag200_bo_unreserve(pixels_1);
+		return ret;
+	}
+
+	if (!handle) {
+		mga_hide_cursor(mdev);
+		ret = 0;
+		goto out1;
+	}
+
+	/* Move cursor buffers into VRAM if they aren't already */
+	if (!pixels_1->pin_count) {
+		ret = mgag200_bo_pin(pixels_1, TTM_PL_FLAG_VRAM,
+				     &mdev->cursor.pixels_1_gpu_addr);
+		if (ret)
+			goto out1;
+	}
+	if (!pixels_2->pin_count) {
+		ret = mgag200_bo_pin(pixels_2, TTM_PL_FLAG_VRAM,
+				     &mdev->cursor.pixels_2_gpu_addr);
+		if (ret) {
+			mgag200_bo_unpin(pixels_1);
+			goto out1;
+		}
+	}
+
+	mutex_lock(&dev->struct_mutex);
+	obj = drm_gem_object_lookup(dev, file_priv, handle);
+	if (!obj) {
+		mutex_unlock(&dev->struct_mutex);
+		ret = -ENOENT;
+		goto out1;
+	}
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	bo = gem_to_mga_bo(obj);
+	ret = mgag200_bo_reserve(bo, true);
+	if (ret) {
+		dev_err(&dev->pdev->dev, "failed to reserve user bo\n");
+		goto out1;
+	}
+	if (!bo->kmap.virtual) {
+		ret = ttm_bo_kmap(&bo->bo, 0, bo->bo.num_pages, &bo->kmap);
+		if (ret) {
+			dev_err(&dev->pdev->dev, "failed to kmap user buffer updates\n");
+			goto out2;
+		}
+	}
+
+	memset(&colour_set[0], 0, sizeof(uint32_t)*16);
+	/* width*height*4 = 16384 */
+	for (i = 0; i < 16384; i += 4) {
+		this_colour = ioread32(bo->kmap.virtual + i);
+		/* No transparency */
+		if (this_colour>>24 != 0xff &&
+			this_colour>>24 != 0x0) {
+			if (warn_transparent) {
+				dev_info(&dev->pdev->dev, "Video card doesn't support cursors with partial transparency.\n");
+				dev_info(&dev->pdev->dev, "Not enabling hardware cursor.\n");
+				warn_transparent = false; /* Only tell the user once. */
+			}
+			ret = -EINVAL;
+			goto out3;
+		}
+		/* Don't need to store transparent pixels as colours */
+		if (this_colour>>24 == 0x0)
+			continue;
+		found = false;
+		for (palette_iter = &colour_set[0]; palette_iter != next_space; palette_iter++) {
+			if (*palette_iter == this_colour) {
+				found = true;
+				break;
+			}
+		}
+		if (found)
+			continue;
+		/* We only support 4bit paletted cursors */
+		if (colour_count >= 16) {
+			if (warn_palette) {
+				dev_info(&dev->pdev->dev, "Video card only supports cursors with up to 16 colours.\n");
+				dev_info(&dev->pdev->dev, "Not enabling hardware cursor.\n");
+				warn_palette = false; /* Only tell the user once. */
+			}
+			ret = -EINVAL;
+			goto out3;
+		}
+		*next_space = this_colour;
+		next_space++;
+		colour_count++;
+	}
+
+	/* Program colours from cursor icon into palette */
+	for (i = 0; i < colour_count; i++) {
+		if (i <= 2)
+			reg_index = 0x8 + i*0x4;
+		else
+			reg_index = 0x60 + i*0x3;
+		WREG_DAC(reg_index, colour_set[i] & 0xff);
+		WREG_DAC(reg_index+1, colour_set[i]>>8 & 0xff);
+		WREG_DAC(reg_index+2, colour_set[i]>>16 & 0xff);
+		BUG_ON((colour_set[i]>>24 & 0xff) != 0xff);
+	}
+
+	/* Map up-coming buffer to write colour indices */
+	if (!pixels_prev->kmap.virtual) {
+		ret = ttm_bo_kmap(&pixels_prev->bo, 0,
+				  pixels_prev->bo.num_pages,
+				  &pixels_prev->kmap);
+		if (ret) {
+			dev_err(&dev->pdev->dev, "failed to kmap cursor updates\n");
+			goto out3;
+		}
+	}
+
+	/* now write colour indices into hardware cursor buffer */
+	for (row = 0; row < 64; row++) {
+		memset(&this_row[0], 0, 48);
+		for (col = 0; col < 64; col++) {
+			this_colour = ioread32(bo->kmap.virtual + 4*(col + 64*row));
+			/* write transparent pixels */
+			if (this_colour>>24 == 0x0) {
+				this_row[47 - col/8] |= 0x80>>(col%8);
+				continue;
+			}
+
+			/* write colour index here */
+			for (i = 0; i < colour_count; i++) {
+				if (colour_set[i] == this_colour) {
+					if (col % 2)
+						this_row[col/2] |= i<<4;
+					else
+						this_row[col/2] |= i;
+					break;
+				}
+			}
+		}
+		memcpy_toio(pixels_prev->kmap.virtual + row*48, &this_row[0], 48);
+	}
+
+	/* Program gpu address of cursor buffer */
+	if (pixels_prev == pixels_1)
+		gpu_addr = mdev->cursor.pixels_1_gpu_addr;
+	else
+		gpu_addr = mdev->cursor.pixels_2_gpu_addr;
+	WREG_DAC(MGA1064_CURSOR_BASE_ADR_LOW, (u8)((gpu_addr>>10) & 0xff));
+	WREG_DAC(MGA1064_CURSOR_BASE_ADR_HI, (u8)((gpu_addr>>18) & 0x3f));
+
+	/* Adjust cursor control register to turn on the cursor */
+	WREG_DAC(MGA1064_CURSOR_CTL, 4); /* 16-colour palletized cursor mode */
+
+	/* Now swap internal buffer pointers */
+	if (mdev->cursor.pixels_1 == mdev->cursor.pixels_prev) {
+		mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
+		mdev->cursor.pixels_current = mdev->cursor.pixels_1;
+	} else if (mdev->cursor.pixels_1 == mdev->cursor.pixels_current) {
+		mdev->cursor.pixels_prev = mdev->cursor.pixels_1;
+		mdev->cursor.pixels_current = mdev->cursor.pixels_2;
+	} else {
+		BUG();
+	}
+	ret = 0;
+
+	ttm_bo_kunmap(&pixels_prev->kmap);
+ out3:
+	ttm_bo_kunmap(&bo->kmap);
+ out2:
+	mgag200_bo_unreserve(bo);
+ out1:
+	if (ret)
+		mga_hide_cursor(mdev);
+	mgag200_bo_unreserve(pixels_1);
+	mgag200_bo_unreserve(pixels_2);
+	return ret;
+}
+
+int mga_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
+{
+	struct mga_device *mdev = (struct mga_device *)crtc->dev->dev_private;
+	/* Our origin is at (64,64) */
+	x += 64;
+	y += 64;
+
+	BUG_ON(x <= 0);
+	BUG_ON(y <= 0);
+	BUG_ON(x & ~0xffff);
+	BUG_ON(y & ~0xffff);
+
+	WREG8(MGA_CURPOSXL, x & 0xff);
+	WREG8(MGA_CURPOSXH, (x>>8) & 0xff);
+
+	WREG8(MGA_CURPOSYL, y & 0xff);
+	WREG8(MGA_CURPOSYH, (y>>8) & 0xff);
+	return 0;
+}
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index bf29b2f..364a05a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -149,6 +149,21 @@
 	struct mga_i2c_chan *i2c;
 };
 
+struct mga_cursor {
+	/*
+	   We have to have 2 buffers for the cursor to avoid occasional
+	   corruption while switching cursor icons.
+	   If either of these is NULL, then don't do hardware cursors, and
+	   fall back to software.
+	*/
+	struct mgag200_bo *pixels_1;
+	struct mgag200_bo *pixels_2;
+	u64 pixels_1_gpu_addr, pixels_2_gpu_addr;
+	/* The currently displayed icon, this points to one of pixels_1, or pixels_2 */
+	struct mgag200_bo *pixels_current;
+	/* The previously displayed icon */
+	struct mgag200_bo *pixels_prev;
+};
 
 struct mga_mc {
 	resource_size_t			vram_size;
@@ -181,6 +196,7 @@
 	struct mga_mode_info		mode_info;
 
 	struct mga_fbdev *mfbdev;
+	struct mga_cursor cursor;
 
 	bool				suspended;
 	int				num_crtc;
@@ -273,4 +289,9 @@
 int mgag200_bo_pin(struct mgag200_bo *bo, u32 pl_flag, u64 *gpu_addr);
 int mgag200_bo_unpin(struct mgag200_bo *bo);
 int mgag200_bo_push_sysram(struct mgag200_bo *bo);
+			   /* mgag200_cursor.c */
+int mga_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
+						uint32_t handle, uint32_t width, uint32_t height);
+int mga_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
+
 #endif				/* __MGAG200_DRV_H__ */
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 9905923..5189675 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -221,8 +221,27 @@
 	dev->mode_config.prefer_shadow = 1;
 
 	r = mgag200_modeset_init(mdev);
-	if (r)
+	if (r) {
 		dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r);
+		goto out;
+	}
+
+	/* Make small buffers to store a hardware cursor (double buffered icon updates) */
+	mgag200_bo_create(dev, roundup(48*64, PAGE_SIZE), 0, 0,
+					  &mdev->cursor.pixels_1);
+	mgag200_bo_create(dev, roundup(48*64, PAGE_SIZE), 0, 0,
+					  &mdev->cursor.pixels_2);
+	if (!mdev->cursor.pixels_2 || !mdev->cursor.pixels_1)
+		goto cursor_nospace;
+	mdev->cursor.pixels_current = mdev->cursor.pixels_1;
+	mdev->cursor.pixels_prev = mdev->cursor.pixels_2;
+	goto cursor_done;
+ cursor_nospace:
+	mdev->cursor.pixels_1 = NULL;
+	mdev->cursor.pixels_2 = NULL;
+	dev_warn(&dev->pdev->dev, "Could not allocate space for cursors. Not doing hardware cursors.\n");
+ cursor_done:
+
 out:
 	if (r)
 		mgag200_driver_unload(dev);
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 77b8a45..deed0bd 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1252,6 +1252,8 @@
 
 /* These provide the minimum set of functions required to handle a CRTC */
 static const struct drm_crtc_funcs mga_crtc_funcs = {
+	.cursor_set = mga_crtc_cursor_set,
+	.cursor_move = mga_crtc_cursor_move,
 	.gamma_set = mga_crtc_gamma_set,
 	.set_config = drm_crtc_helper_set_config,
 	.destroy = mga_crtc_destroy,
diff --git a/drivers/gpu/drm/mgag200/mgag200_reg.h b/drivers/gpu/drm/mgag200/mgag200_reg.h
index fb24d86..3ae442a6 100644
--- a/drivers/gpu/drm/mgag200/mgag200_reg.h
+++ b/drivers/gpu/drm/mgag200/mgag200_reg.h
@@ -235,7 +235,11 @@
 #define MGAREG_CRTCEXT_INDEX	0x1fde
 #define MGAREG_CRTCEXT_DATA	0x1fdf
 
-
+/* Cursor X and Y position */
+#define MGA_CURPOSXL 0x3c0c
+#define MGA_CURPOSXH 0x3c0d
+#define MGA_CURPOSYL 0x3c0e
+#define MGA_CURPOSYH 0x3c0f
 
 /* MGA bits for registers PCI_OPTION_REG */
 #define MGA1064_OPT_SYS_CLK_PCI   		( 0x00 << 0 )