drm/amdgpu: set COMPUTE_PGM_RSRC1 for SGPR/VGPR clearing shaders

Otherwise, the SQ may skip some of the register writes, or shader waves may
be allocated where we don't expect them, so that as a result we don't actually
reset all of the register SRAMs. This can lead to spurious ECC errors later on
if a shader uses an uninitialized register.

Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index b0e591eaa71a21754e1e2246bf41df3cdd1936cf..e14263fca1c91472ead16fd5bfdceed0b11be81e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1459,10 +1459,11 @@ static const u32 sgpr_init_compute_shader[] =
 static const u32 vgpr_init_regs[] =
 {
        mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0xffffffff,
-       mmCOMPUTE_RESOURCE_LIMITS, 0,
+       mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
        mmCOMPUTE_NUM_THREAD_X, 256*4,
        mmCOMPUTE_NUM_THREAD_Y, 1,
        mmCOMPUTE_NUM_THREAD_Z, 1,
+       mmCOMPUTE_PGM_RSRC1, 0x100004f, /* VGPRS=15 (64 logical VGPRs), SGPRS=1 (16 SGPRs), BULKY=1 */
        mmCOMPUTE_PGM_RSRC2, 20,
        mmCOMPUTE_USER_DATA_0, 0xedcedc00,
        mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1479,10 +1480,11 @@ static const u32 vgpr_init_regs[] =
 static const u32 sgpr1_init_regs[] =
 {
        mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0x0f,
-       mmCOMPUTE_RESOURCE_LIMITS, 0x1000000,
+       mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
        mmCOMPUTE_NUM_THREAD_X, 256*5,
        mmCOMPUTE_NUM_THREAD_Y, 1,
        mmCOMPUTE_NUM_THREAD_Z, 1,
+       mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
        mmCOMPUTE_PGM_RSRC2, 20,
        mmCOMPUTE_USER_DATA_0, 0xedcedc00,
        mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1503,6 +1505,7 @@ static const u32 sgpr2_init_regs[] =
        mmCOMPUTE_NUM_THREAD_X, 256*5,
        mmCOMPUTE_NUM_THREAD_Y, 1,
        mmCOMPUTE_NUM_THREAD_Z, 1,
+       mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
        mmCOMPUTE_PGM_RSRC2, 20,
        mmCOMPUTE_USER_DATA_0, 0xedcedc00,
        mmCOMPUTE_USER_DATA_1, 0xedcedc01,