Evergreen and later Radeons let the driver choose a macro tile layout,
within certain constraints. If we don't set the appropriate fields
correctly, the card will use a layout that doesn't normally meet the
constraints on Evergreen tiling.
For now, select 8x8 aspect 1 macrotiles, as this makes it possible to
guarantee that we meet the hardware constraints. Once macrotiling is
reliable, we can consider a better API to let us exploit the hardware
capabilities.
Signed-off-by: Simon Farnsworth <simon.farnsworth@xxxxxxxxxxxx>
---
This doesn't fix my problems with enabling macro tiling, but it does help
somewhat. I also need to fix alignment in the DDX and Mesa to avoid
misrendering, at which point I see CP lockups instead.
I'm therefore sending this, the DDX patch, and the Mesa patch out in order
to avoid getting stuck in a world where I have an 80% fix, someone else has
an 80% fix, and if only we talked, we'd have a 100% fix.
drivers/gpu/drm/radeon/atombios_crtc.c | 4 ++++
drivers/gpu/drm/radeon/evergreen_cs.c | 9 +++++++++
drivers/gpu/drm/radeon/evergreend.h | 7 +++++++
3 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 2b97262..f982975 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1113,6 +1113,10 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
else
tmp = rdev->config.evergreen.tile_config;
+ fb_format |= (EVERGREEN_GRPH_BANK_HEIGHT(EVERGREEN_ADDR_SURF_BANK_HEIGHT_8) |
+ EVERGREEN_GRPH_BANK_WIDTH(EVERGREEN_ADDR_SURF_BANK_WIDTH_8) |
+ EVERGREEN_GRPH_MACRO_TILE_ASPECT(EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_1));
+
switch ((tmp & 0xf0) >> 4) {
case 0: /* 4 banks */
fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index b53d1c6..a14a04e 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -532,6 +532,9 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx] |= (DB_BANK_WIDTH(ADDR_SURF_BANK_WIDTH_8) |
+ DB_BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+ DB_MACRO_TILE_ASPECT(ADDR_SURF_MACRO_TILE_ASPECT_1));
ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
ib[idx] |= DB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
}
@@ -736,6 +739,9 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
return -EINVAL;
}
if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+ ib[idx] |= (CB_BANK_WIDTH(ADDR_SURF_BANK_WIDTH_8) |
+ CB_BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+ CB_MACRO_TILE_ASPECT(ADDR_SURF_MACRO_TILE_ASPECT_1));
ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
ib[idx] |= CB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
}
@@ -1360,6 +1366,9 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
ib[idx+1+(i*8)+6] |= TEX_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
ib[idx+1+(i*8)+7] |= TEX_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+ ib[idx+1+(i*8)+8] |= (TEX_BANK_WIDTH(ADDR_SURF_BANK_WIDTH_8) |
+ TEX_BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+ TEX_MACRO_TILE_ASPECT(ADDR_SURF_MACRO_TILE_ASPECT_1));
}
}
texture = reloc->robj;
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index e00039e..3731e8f 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -903,6 +903,7 @@
# define DB_NUM_BANKS(x) (((x) & 0x3) << 12)
# define DB_BANK_WIDTH(x) (((x) & 0x3) << 16)
# define DB_BANK_HEIGHT(x) (((x) & 0x3) << 20)
+# define DB_MACRO_TILE_ASPECT(x) (((x) & 0x3) << 24)
#define DB_STENCIL_INFO 0x28044
#define DB_Z_READ_BASE 0x28048
#define DB_STENCIL_READ_BASE 0x2804c
@@ -978,6 +979,11 @@
# define ADDR_SURF_BANK_HEIGHT_2 1
# define ADDR_SURF_BANK_HEIGHT_4 2
# define ADDR_SURF_BANK_HEIGHT_8 3
+# define CB_MACRO_TILE_ASPECT(x) (((x) & 0x3) << 19)
+# define ADDR_SURF_MACRO_TILE_ASPECT_1 0
+# define ADDR_SURF_MACRO_TILE_ASPECT_2 1
+# define ADDR_SURF_MACRO_TILE_ASPECT_4 2
+# define ADDR_SURF_MACRO_TILE_ASPECT_8 3
#define CB_COLOR0_DIM 0x28c78
/* only CB0-7 blocks have these regs */
#define CB_COLOR0_CMASK 0x28c7c
@@ -1166,6 +1172,7 @@
#define SQ_TEX_RESOURCE_WORD6_0 0x30018
# define TEX_TILE_SPLIT(x) (((x) & 0x7) << 29)
#define SQ_TEX_RESOURCE_WORD7_0 0x3001c
+# define TEX_MACRO_TILE_ASPECT(x) (((x) & 0x3) << 6)
# define TEX_BANK_WIDTH(x) (((x) & 0x3) << 8)
# define TEX_BANK_HEIGHT(x) (((x) & 0x3) << 10)
# define TEX_NUM_BANKS(x) (((x) & 0x3) << 16)
--
1.7.6.4
_______________________________________________
dri-devel mailing list
dri-devel@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/dri-devel
