From 42bc87167ad6eac96ff362bea82bcfdc9730e2ec Mon Sep 17 00:00:00 2001 From: Richard Zhao Date: Mon, 13 Nov 2017 15:22:13 -0800 Subject: gpu: nvgpu: vgpu: abort the channel right after force reset it For gp10b and previous chips, RM server will issue fake mmu fault to reset the channel. And the mmu fault event will be sent to vgpu client, which will cause the client to abort the channel or tsg. But on gv11b, RM server doesn't issue fake mmu fault any more. So I need to abort it right after the force reset is finished. Jira EVLR-1671 Change-Id: I11399fda84d31086ba1d4ffde5948e409cde2a28 Signed-off-by: Richard Zhao Reviewed-on: https://git-master.nvidia.com/r/1597378 Reviewed-by: mobile promotions Tested-by: mobile promotions --- drivers/gpu/nvgpu/vgpu/fifo_vgpu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/gpu/nvgpu/vgpu/fifo_vgpu.c') diff --git a/drivers/gpu/nvgpu/vgpu/fifo_vgpu.c b/drivers/gpu/nvgpu/vgpu/fifo_vgpu.c index 66b2dbef..cc56f9f8 100644 --- a/drivers/gpu/nvgpu/vgpu/fifo_vgpu.c +++ b/drivers/gpu/nvgpu/vgpu/fifo_vgpu.c @@ -714,6 +714,8 @@ int vgpu_fifo_force_reset_ch(struct channel_gk20a *ch, p->handle = ch->virt_ctx; err = vgpu_comm_sendrecv(&msg, sizeof(msg), sizeof(msg)); WARN_ON(err || msg.ret); + if (!err) + gk20a_channel_abort(ch, false); return err ? err : msg.ret; } -- cgit v1.2.2