r600: increase number of ubos by one to 14

Ideally we'd support 16 (d3d11 requires 15, and mesa subtracts one for non-ubo
constants), but that's kind of impossible (it would be only doable if either
we'd somehow merge the mesa non-ubo constants with the driver constants, or
only use the driver constants with vtx fetch instead of through the kcache
mechanism - the latter probably wouldn't be too bad).
For now just do as the comment already said, place the gs ring (not really
a const buffer in any case) which is only ever referred to through vc fetch
clauses at index 16. Throw in a couple asserts for good measure to make sure
the hw limit isn't exceeded.

Tested-by: Konstantin Kharlamov <hi-angel@yandex.ru>
Reviewed-by: Dave Airlie <airlied@redhat.com>

diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
index 81b7c4a..f5b8e71 100644 (file)
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -2168,6 +2168,7 @@ static void evergreen_emit_constant_buffers(struct r600_context *rctx,
                va = rbuffer->gpu_address + cb->buffer_offset;
 
                if (!gs_ring_buffer) {
+                       assert(buffer_index < R600_MAX_HW_CONST_BUFFERS);
                        radeon_set_context_reg_flag(cs, reg_alu_constbuf_size + buffer_index * 4,
                                                    DIV_ROUND_UP(cb->buffer_size, 256), pkt_flags);
                        radeon_set_context_reg_flag(cs, reg_alu_const_cache + buffer_index * 4, va >> 8,

diff --git a/src/gallium/drivers/r600/r600_asm.c b/src/gallium/drivers/r600/r600_asm.c
index 69b2d14..d6bd561 100644 (file)
--- a/src/gallium/drivers/r600/r600_asm.c
+++ b/src/gallium/drivers/r600/r600_asm.c
@@ -1008,6 +1008,7 @@ static int r600_bytecode_alloc_inst_kcache_lines(struct r600_bytecode *bc,
                        continue;
 
                bank = alu->src[i].kc_bank;
+               assert(bank < R600_MAX_HW_CONST_BUFFERS);
                line = (sel-512)>>4;
                index_mode = alu->src[i].kc_rel ? 1 : 0; // V_SQ_CF_INDEX_0 / V_SQ_CF_INDEX_NONE
 

diff --git a/src/gallium/drivers/r600/r600_pipe.h b/src/gallium/drivers/r600/r600_pipe.h
index e042edf..cb84bc1 100644 (file)
--- a/src/gallium/drivers/r600/r600_pipe.h
+++ b/src/gallium/drivers/r600/r600_pipe.h
@@ -69,11 +69,12 @@
 #define R600_MAX_DRAW_CS_DWORDS                58
 #define R600_MAX_PFP_SYNC_ME_DWORDS    16
 
-#define R600_MAX_USER_CONST_BUFFERS 13
+#define EG_MAX_ATOMIC_BUFFERS 8
+
+#define R600_MAX_USER_CONST_BUFFERS 14
 #define R600_MAX_DRIVER_CONST_BUFFERS 3
 #define R600_MAX_CONST_BUFFERS (R600_MAX_USER_CONST_BUFFERS + R600_MAX_DRIVER_CONST_BUFFERS)
-
-#define EG_MAX_ATOMIC_BUFFERS 8
+#define R600_MAX_HW_CONST_BUFFERS 16
 
 /* start driver buffers after user buffers */
 #define R600_BUFFER_INFO_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS)
@@ -84,7 +85,8 @@
 #define R600_LDS_INFO_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 1)
 /*
  * Note GS doesn't use a constant buffer binding, just a resource index,
- * so it's fine to have it exist at index 16.
+ * so it's fine to have it exist at index 16. I.e. it's not actually
+ * a const buffer, just a buffer resource.
  */
 #define R600_GS_RING_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 2)
 /* Currently R600_MAX_CONST_BUFFERS just fits on the hw, which has a limit

diff --git a/src/gallium/drivers/r600/r600_state.c b/src/gallium/drivers/r600/r600_state.c
index 253ff57..89cf7d2 100644 (file)
--- a/src/gallium/drivers/r600/r600_state.c
+++ b/src/gallium/drivers/r600/r600_state.c
@@ -1712,6 +1712,7 @@ static void r600_emit_constant_buffers(struct r600_context *rctx,
                offset = cb->buffer_offset;
 
                if (!gs_ring_buffer) {
+                       assert(buffer_index < R600_MAX_HW_CONST_BUFFERS);
                        radeon_set_context_reg(cs, reg_alu_constbuf_size + buffer_index * 4,
                                               DIV_ROUND_UP(cb->buffer_size, 256));
                        radeon_set_context_reg(cs, reg_alu_const_cache + buffer_index * 4, offset >> 8);