radeonfb: accelerate imageblit and other improvements

Implement support for HW color expansion of 1bpp images, along with some
improvements to the FIFO handling and other accel operations.

The offset fixup code is now unnecessary as the fbcon core will call our
set_par upon switch back from KD_GRAPHICS before anything else happens.  I
removed it as it would slow down accel operations.

The fifo wait has been improved to avoid hitting the HW register as often,
and the various accel ops are now performing better caching of register
values.

Overall, this improve accel performances.  The imageblit acceleration does
result in a small overall regression in performances on some machines (on
the order of 5% on some x86), probably becaus the SW path provides a
better bus utilisation, but I decided to ingnore that as the performances
is still very good, and on the other hand, some machines such as some
sparc64 get a 3 fold performance improvement.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 13 insertions, 5 deletions

diff --git a/include/video/radeon.h b/include/video/radeon.h
index 1cd09cc5b16..d5dcaf154ba 100644
--- a/include/video/radeon.h
+++ b/include/video/radeon.h
@@ -525,6 +525,9 @@
 #define CRTC_DISPLAY_DIS                           (1 << 10)
 #define CRTC_CRT_ON                                (1 << 15)
 
+/* DSTCACHE_MODE bits constants */
+#define RB2D_DC_AUTOFLUSH_ENABLE                   (1 << 8)
+#define RB2D_DC_DC_DISABLE_IGNORE_PE               (1 << 17)
 
 /* DSTCACHE_CTLSTAT bit constants */
 #define RB2D_DC_FLUSH_2D                           (1 << 0)
@@ -866,15 +869,10 @@
 #define GMC_DST_16BPP_YVYU422                      0x00000c00
 #define GMC_DST_32BPP_AYUV444                      0x00000e00
 #define GMC_DST_16BPP_ARGB4444                     0x00000f00
-#define GMC_SRC_MONO                               0x00000000
-#define GMC_SRC_MONO_LBKGD                         0x00001000
-#define GMC_SRC_DSTCOLOR                           0x00003000
 #define GMC_BYTE_ORDER_MSB_TO_LSB                  0x00000000
 #define GMC_BYTE_ORDER_LSB_TO_MSB                  0x00004000
 #define GMC_DP_CONVERSION_TEMP_9300                0x00008000
 #define GMC_DP_CONVERSION_TEMP_6500                0x00000000
-#define GMC_DP_SRC_RECT                            0x02000000
-#define GMC_DP_SRC_HOST                            0x03000000
 #define GMC_DP_SRC_HOST_BYTEALIGN                  0x04000000
 #define GMC_3D_FCN_EN_CLR                          0x00000000
 #define GMC_3D_FCN_EN_SET                          0x08000000
@@ -885,6 +883,9 @@
 #define GMC_WRITE_MASK_LEAVE                       0x00000000
 #define GMC_WRITE_MASK_SET                         0x40000000
 #define GMC_CLR_CMP_CNTL_DIS                       (1 << 28)
+#define GMC_SRC_DATATYPE_MASK                      (3 << 12)
+#define GMC_SRC_DATATYPE_MONO_FG_BG                (0 << 12)
+#define GMC_SRC_DATATYPE_MONO_FG_LA                (1 << 12)
 #define GMC_SRC_DATATYPE_COLOR                     (3 << 12)
 #define ROP3_S                                     0x00cc0000
 #define ROP3_SRCCOPY                               0x00cc0000
@@ -893,6 +894,7 @@
 #define DP_SRC_SOURCE_MASK                         (7    << 24)
 #define GMC_BRUSH_NONE                             (15   <<  4)
 #define DP_SRC_SOURCE_MEMORY                       (2    << 24)
+#define DP_SRC_SOURCE_HOST_DATA                    (3    << 24)
 #define GMC_BRUSH_SOLIDCOLOR                       0x000000d0
 
 /* DP_MIX bit constants */
@@ -978,6 +980,12 @@
 #define DISP_PWR_MAN_TV_ENABLE_RST                 (1 << 25)
 #define DISP_PWR_MAN_AUTO_PWRUP_EN                 (1 << 26)
 
+/* RBBM_GUICNTL constants */
+#define RBBM_GUICNTL_HOST_DATA_SWAP_NONE           (0 << 0)
+#define RBBM_GUICNTL_HOST_DATA_SWAP_16BIT          (1 << 0)
+#define RBBM_GUICNTL_HOST_DATA_SWAP_32BIT          (2 << 0)
+#define RBBM_GUICNTL_HOST_DATA_SWAP_HDW            (3 << 0)
+
 /* masks */
 
 #define CONFIG_MEMSIZE_MASK             0x1f000000