gallium: add CAPs to support HW atomic counters. (v3)

This looks like an evergreen specific feature, but with atomic
counters AMD have hw specific counters they use instead of operating
on buffers directly. These are separate to the buffer atomics,
so require different limits and code paths.

I've left the CAP for atomic type extensible in case someone
else has a variant on this sort of thing (freedreno maybe?)
and needs to change it.

This adds all the CAPs required to add support for those atomic
counters, along with a related CAP for limiting the number of
output resources.

I'd like to land this and the st patch then I can start to
upstream the evergreen support for these and other GL4.x features.

v2: drop the ATOMIC_COUNTER_MODE cap, just use the return
from the HW counters. If 0 we use the current mode.
v3: fix some rebase errors (Gert Wollny)

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Tested-By: Gert Wollny <gw.fossdev@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

15 files changed, 34 insertions, 1 deletions

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_limits.h b/src/gallium/auxiliary/gallivm/lp_bld_limits.h
index ea320bb5f7b..c7755bfe1df 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_limits.h
+++ b/src/gallium/auxiliary/gallivm/lp_bld_limits.h
@@ -140,6 +140,8 @@ gallivm_get_shader_param(enum pipe_shader_cap param)
    case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
    case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
    case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       return 0;
    case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
       return 32;
diff --git a/src/gallium/auxiliary/tgsi/tgsi_exec.h b/src/gallium/auxiliary/tgsi/tgsi_exec.h
index 514c69ede30..ad920dcf168 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_exec.h
+++ b/src/gallium/auxiliary/tgsi/tgsi_exec.h
@@ -541,6 +541,8 @@ tgsi_exec_get_shader_param(enum pipe_shader_cap param)
    case PIPE_SHADER_CAP_TGSI_FMA_SUPPORTED:
    case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
    case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       return 0;
    case PIPE_SHADER_CAP_MAX_SHADER_BUFFERS:
       return PIPE_MAX_SHADER_BUFFERS;
diff --git a/src/gallium/docs/source/screen.rst b/src/gallium/docs/source/screen.rst
index 9f000596198..519728f188b 100644
--- a/src/gallium/docs/source/screen.rst
+++ b/src/gallium/docs/source/screen.rst
@@ -519,7 +519,10 @@ MOV OUT[0], CONST[0][3]  # copy vector 3 of constbuf 0
 * ``PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS``: Whether the merge registers
   TGSI pass is skipped. This might reduce code size and register pressure if
   the underlying driver has a real backend compiler.
-
+* ``PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS``: If atomic counters are separate,
+  how many HW counters are available for this stage. (0 uses SSBO atomics).
+* ``PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS``: If atomic counters are
+  separate, how many atomic counter buffers are available for this stage.
 
 .. _pipe_compute_cap:
 
diff --git a/src/gallium/drivers/etnaviv/etnaviv_screen.c b/src/gallium/drivers/etnaviv/etnaviv_screen.c
index 30beb412d9d..cea59ea4f82 100644
--- a/src/gallium/drivers/etnaviv/etnaviv_screen.c
+++ b/src/gallium/drivers/etnaviv/etnaviv_screen.c
@@ -459,6 +459,8 @@ etna_screen_get_shader_param(struct pipe_screen *pscreen,
    case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
    case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
    case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       return 0;
    }
 
diff --git a/src/gallium/drivers/freedreno/freedreno_screen.c b/src/gallium/drivers/freedreno/freedreno_screen.c
index 5bb1e20c780..673d1e5b030 100644
--- a/src/gallium/drivers/freedreno/freedreno_screen.c
+++ b/src/gallium/drivers/freedreno/freedreno_screen.c
@@ -554,6 +554,8 @@ fd_screen_get_shader_param(struct pipe_screen *pscreen,
 		return 32;
 	case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
 	case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
 		return 0;
 	case PIPE_SHADER_CAP_MAX_SHADER_BUFFERS:
 		if (is_a5xx(screen)) {
diff --git a/src/gallium/drivers/nouveau/nv30/nv30_screen.c b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
index 81733335c48..37f6cf63453 100644
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
@@ -329,6 +329,8 @@ nv30_screen_get_shader_param(struct pipe_screen *pscreen,
       case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
       case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
       case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
          return 0;
       default:
          debug_printf("unknown vertex shader param %d\n", param);
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.c b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
index c2e69f55134..d9c868cd197 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
@@ -374,6 +374,8 @@ nv50_screen_get_shader_param(struct pipe_screen *pscreen,
    case PIPE_SHADER_CAP_SUPPORTED_IRS:
    case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
    case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       return 0;
    default:
       NOUVEAU_ERR("unknown PIPE_SHADER_CAP %d\n", param);
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
index 45259c424d7..2e7b4d7afd5 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -412,6 +412,8 @@ nvc0_screen_get_shader_param(struct pipe_screen *pscreen,
    case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
    case PIPE_SHADER_CAP_INT64_ATOMICS:
    case PIPE_SHADER_CAP_FP16:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+   case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       return 0;
    case PIPE_SHADER_CAP_MAX_SHADER_BUFFERS:
       return NVC0_MAX_BUFFERS;
diff --git a/src/gallium/drivers/r300/r300_screen.c b/src/gallium/drivers/r300/r300_screen.c
index b9b2d7d8382..ac5208a0c48 100644
--- a/src/gallium/drivers/r300/r300_screen.c
+++ b/src/gallium/drivers/r300/r300_screen.c
@@ -368,6 +368,8 @@ static int r300_get_shader_param(struct pipe_screen *pscreen,
         case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
         case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
         case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+        case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+        case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
             return 0;
         case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
             return 32;
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 2381c5b7d00..0b815d4aef6 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -605,6 +605,8 @@ static int r600_get_shader_param(struct pipe_screen* pscreen,
 	case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
 	case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
 	case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
 		return 0;
 	case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
 		/* due to a bug in the shader compiler, some loops hang
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index 5fbf1b35303..6c4420c1baf 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -792,6 +792,8 @@ static int si_get_shader_param(struct pipe_screen* pscreen,
 	/* Unsupported boolean features. */
 	case PIPE_SHADER_CAP_SUBROUTINES:
 	case PIPE_SHADER_CAP_SUPPORTED_IRS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+	case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
 		return 0;
 	}
 	return 0;
diff --git a/src/gallium/drivers/svga/svga_screen.c b/src/gallium/drivers/svga/svga_screen.c
index 2a97ccb1886..8621640c849 100644
--- a/src/gallium/drivers/svga/svga_screen.c
+++ b/src/gallium/drivers/svga/svga_screen.c
@@ -540,6 +540,8 @@ vgpu9_get_shader_param(struct pipe_screen *screen,
       case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
       case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
       case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
          return 0;
       case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
          return 32;
@@ -605,6 +607,8 @@ vgpu9_get_shader_param(struct pipe_screen *screen,
       case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
       case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
       case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
          return 0;
       case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
          return 32;
diff --git a/src/gallium/drivers/vc4/vc4_screen.c b/src/gallium/drivers/vc4/vc4_screen.c
index 7f44fedee80..1a9eaad1cd9 100644
--- a/src/gallium/drivers/vc4/vc4_screen.c
+++ b/src/gallium/drivers/vc4/vc4_screen.c
@@ -451,6 +451,8 @@ vc4_screen_get_shader_param(struct pipe_screen *pscreen,
         case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
 	case PIPE_SHADER_CAP_LOWER_IF_THRESHOLD:
         case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
+        case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+        case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
                 return 0;
         default:
                 fprintf(stderr, "unknown shader param %d\n", param);
diff --git a/src/gallium/drivers/virgl/virgl_screen.c b/src/gallium/drivers/virgl/virgl_screen.c
index 1646e7ee025..725f7dbed44 100644
--- a/src/gallium/drivers/virgl/virgl_screen.c
+++ b/src/gallium/drivers/virgl/virgl_screen.c
@@ -341,6 +341,8 @@ virgl_get_shader_param(struct pipe_screen *screen,
       case PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS:
       case PIPE_SHADER_CAP_INT64_ATOMICS:
       case PIPE_SHADER_CAP_FP16:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS:
+      case PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS:
       default:
          return 0;
       }
diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h
index 5078a11f008..e4d0d63066d 100644
--- a/src/gallium/include/pipe/p_defines.h
+++ b/src/gallium/include/pipe/p_defines.h
@@ -857,6 +857,8 @@ enum pipe_shader_cap
    PIPE_SHADER_CAP_LOWER_IF_THRESHOLD,
    PIPE_SHADER_CAP_TGSI_SKIP_MERGE_REGISTERS,
    PIPE_SHADER_CAP_TGSI_LDEXP_SUPPORTED,
+   PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTERS,
+   PIPE_SHADER_CAP_MAX_HW_ATOMIC_COUNTER_BUFFERS,
 };
 
 /**