From 85c323c3e89d6e1b624b839c3325ae072952e545 Mon Sep 17 00:00:00 2001 From: Debarshi Dutta Date: Wed, 8 Aug 2018 17:36:01 +0530 Subject: gpu: nvgpu: restrict devfreq during active clk_arb set requests Restrict access to devfreq when there are active set requests in the clk_arbiter. We make the following changes in the patch. 1) Add a global counter in the struct gk20a named clk_arb_global_nr which is used to track the number of active set requests in the system. 2) Anytime a set request is successfully made by the userspace, clk_arb_global_nr is incremented by 1 and during the completion of request(releasing the corresponding file handle), clk_arb_global_nr is decremented by 1. 3) gk20a_scale_target(invoked by devfreq to set the new frequency based on load) atomically checks clk_arb_global_nr. If the value = 0, the code simply continue or else if its > 0, it quits thus making devfreq requests mutually exclusive with the clk_arbiter. Bug 2061372 Change-Id: I5d19de03e45520f4ff8fccb97b1f1589d04c8ab8 Signed-off-by: Debarshi Dutta Reviewed-on: https://git-master.nvidia.com/r/1790002 Reviewed-by: mobile promotions Tested-by: mobile promotions --- drivers/gpu/nvgpu/gp10b/clk_arb_gp10b.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/gpu/nvgpu/gp10b') diff --git a/drivers/gpu/nvgpu/gp10b/clk_arb_gp10b.c b/drivers/gpu/nvgpu/gp10b/clk_arb_gp10b.c index 4dcc3ca5..78fb1261 100644 --- a/drivers/gpu/nvgpu/gp10b/clk_arb_gp10b.c +++ b/drivers/gpu/nvgpu/gp10b/clk_arb_gp10b.c @@ -215,6 +215,9 @@ int gp10b_init_clk_arbiter(struct gk20a *g) goto init_fail; } + /* This is set for the duration of the default req */ + nvgpu_atomic_inc(&g->clk_arb_global_nr); + nvgpu_clk_arb_worker_enqueue(g, &arb->update_arb_work_item); do { @@ -224,6 +227,8 @@ int gp10b_init_clk_arbiter(struct gk20a *g) nvgpu_atomic_read(&arb->req_nr) != 0, 0); } while (nvgpu_atomic_read(&arb->req_nr) == 0); + /* Once the default request is completed, reduce the usage count */ + nvgpu_atomic_dec(&g->clk_arb_global_nr); return arb->status; -- cgit v1.2.2