drm/amdkfd: disable shader message vgpr deallocation on gc 12.1

Shader messages to deallocate VGPRs prior to shader end can prevent
the trap handler from saving context, making debugging and core dumps
unreliable.

VGPR deallocations for performance gain is negligible.
GC 12.1 will NOP shader VGPR deallocation messages via HW
settings on driver boot.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Acked-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Jonathan Kim
2025-05-26 15:39:45 -04:00
committed by Alex Deucher
parent 8e0187aec6
commit cf356fe11d

View File

@@ -1362,6 +1362,11 @@ static void gfx_v12_1_xcc_init_compute_vmid(struct amdgpu_device *adev,
data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regSPI_GDBG_PER_VMID_CNTL);
data = REG_SET_FIELD(data, SPI_GDBG_PER_VMID_CNTL, TRAP_EN, 1);
WREG32_SOC15(GC, GET_INST(GC, xcc_id), regSPI_GDBG_PER_VMID_CNTL, data);
/* Disable VGPR deallocation instruction for each KFD vmid. */
data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regSQ_DEBUG);
data = REG_SET_FIELD(data, SQ_DEBUG, DISABLE_VGPR_DEALLOC, 1);
WREG32_SOC15(GC, GET_INST(GC, xcc_id), regSQ_DEBUG, data);
}
soc_v1_0_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, xcc_id));
mutex_unlock(&adev->srbm_mutex);