From e7c45478895a359bd122b359c1f29b7e64116caf Mon Sep 17 00:00:00 2001 From: Terje Bergstrom Date: Tue, 7 Nov 2017 08:43:23 -0800 Subject: gpu: nvgpu: Hard code regops max batch size We set the regops limit in common code to a hard coded value and access it in Linux code. Change the responsibility so that regops limit is set in Linux code in the GPU characteristics query to a hard coded value and just use the same hard coded value in the IOCTL limit check. JIRA NVGPU-259 Change-Id: I2f78a7ea8f1cb68a08633a2dc74b71b3b001e5c9 Signed-off-by: Terje Bergstrom Reviewed-on: https://git-master.nvidia.com/r/1593682 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Seshendra Gadagottu Reviewed-by: Peter Daifuku Reviewed-by: mobile promotions Tested-by: mobile promotions --- drivers/gpu/nvgpu/gk20a/gk20a.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/gpu/nvgpu/gk20a/gk20a.c') diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.c b/drivers/gpu/nvgpu/gk20a/gk20a.c index a9ee65d0..2d7266ce 100644 --- a/drivers/gpu/nvgpu/gk20a/gk20a.c +++ b/drivers/gpu/nvgpu/gk20a/gk20a.c @@ -488,8 +488,6 @@ int gk20a_init_gpu_characteristics(struct gk20a *g) gpu->pci_class = g->pci_class; gpu->pci_revision = g->pci_revision; - gpu->reg_ops_limit = 1024; - return 0; } -- cgit v1.2.2