gpu: nvgpu: Kill pg init thread if pmu boot fails

- Created nvgpu_kill_task_pg_init() method to set
pmu state to PMU_STATE_EXIT & make thread stop,
and poll to confirm thread stopped.
- Check for PMU/SEC2 ACR secure boot completion
status & initiate pg init thread kill if ACR boot
exits with error, which fails to validate &
boot LS-PMU.
- Set pmu state to PMU_STATE_OFF after thread kill
during ACR boot failure.

Issue: pg init task blocks if PMU boot fails &
cause kernel to show message "task nvgpu_pg_init_g:2120
blocked for more than 120 seconds"

Bug 200346134

Change-Id: I5270426080dcd628ccca4df798005294c19767a0
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1582593
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 8 insertions, 2 deletions

diff --git a/drivers/gpu/nvgpu/gp106/sec2_gp106.c b/drivers/gpu/nvgpu/gp106/sec2_gp106.c
index 26ded39e..332ac794 100644
--- a/drivers/gpu/nvgpu/gp106/sec2_gp106.c
+++ b/drivers/gpu/nvgpu/gp106/sec2_gp106.c
@@ -52,20 +52,26 @@ int sec2_wait_for_halt(struct gk20a *g, unsigned int timeout)
         completion = nvgpu_flcn_wait_for_halt(&g->sec2_flcn, timeout);
         if (completion) {
                 nvgpu_err(g, "ACR boot timed out");
-                return completion;
+                goto exit;
         }
 
         g->acr.capabilities = gk20a_readl(g, psec_falcon_mailbox1_r());
         gm20b_dbg_pmu("ACR capabilities %x\n", g->acr.capabilities);
         data = gk20a_readl(g, psec_falcon_mailbox0_r());
         if (data) {
-
                 nvgpu_err(g, "ACR boot failed, err %x", data);
                 completion = -EAGAIN;
+                goto exit;
         }
 
         init_pmu_setup_hw1(g);
 
+exit:
+        if (completion) {
+                nvgpu_kill_task_pg_init(g);
+                nvgpu_pmu_state_change(g, PMU_STATE_OFF, false);
+        }
+
         return completion;
 }