gpu: nvgpu: Add ECC Support for GV11B in Linux

Implement nvgpu plumbing to allow reporting ECC errors(corrected
and uncorrected) to a L1SS service(if one exists).

This patch includes the following

1) Added code that submits ECC error reports via the Interrupt context
directly to a L1SS service in linux OS.

2) Added support for enabling/disabling the error reports via L1SS's
registration/deregistration API. Nvgpu simply invokes an empty function
until the registration is successful.

3) Added Spinlock to correctly handle concurrency for accessing the
correct Ops for submitting requests.

4) Adds error reporting for a subset of interrupts that can be verified
via external ECC injection logic. A subsequent patch will add the
API for rest of the interrupts.

5) In case of critical(uncorrected errors), change nvgpu's state to
quiesce state.

Jira L4T-1187
Bug 200700400

Change-Id: Id31f70531fba355e94e72c4f9762593e7667a11c
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2530411
Tested-by: Bibek Basu <bbasu@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit

1 files changed, 20 insertions, 2 deletions

diff --git a/drivers/gpu/nvgpu/os/linux/module.c b/drivers/gpu/nvgpu/os/linux/module.c
index 807df2ca..fdbab46d 100644
--- a/drivers/gpu/nvgpu/os/linux/module.c
+++ b/drivers/gpu/nvgpu/os/linux/module.c
@@ -1,7 +1,7 @@
 /*
  * GK20A Graphics
  *
- * Copyright (c) 2011-2020, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (c) 2011-2021, NVIDIA CORPORATION.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -49,6 +49,7 @@
 #include <nvgpu/clk_arb.h>
 #include <nvgpu/timers.h>
 #include <nvgpu/channel.h>
+#include <nvgpu/nvgpu_err.h>
 
 #include "platform_gk20a.h"
 #include "sysfs.h"
@@ -355,6 +356,10 @@ int gk20a_pm_finalize_poweron(struct device *dev)
                 gk20a_init_cde_support(l);
 #endif
 
+#ifdef CONFIG_NVGPU_SUPPORT_LINUX_ECC_ERROR_REPORTING
+        nvgpu_enable_ecc_reporting(g);
+#endif
+
         err = gk20a_sched_ctrl_init(g);
         if (err) {
                 nvgpu_err(g, "failed to init sched control");
@@ -364,9 +369,14 @@ int gk20a_pm_finalize_poweron(struct device *dev)
         g->sw_ready = true;
 
 done:
-        if (err)
+        if (err) {
                 g->power_on = false;
 
+#ifdef CONFIG_NVGPU_SUPPORT_LINUX_ECC_ERROR_REPORTING
+                nvgpu_disable_ecc_reporting(g);
+#endif
+        }
+
         nvgpu_mutex_release(&g->power_lock);
         return err;
 }
@@ -433,6 +443,10 @@ static int gk20a_pm_prepare_poweroff(struct device *dev)
         /* Stop CPU from accessing the GPU registers. */
         gk20a_lockout_registers(g);
 
+#ifdef CONFIG_NVGPU_SUPPORT_LINUX_ECC_ERROR_REPORTING
+        nvgpu_disable_ecc_reporting(g);
+#endif
+
         nvgpu_hide_usermode_for_poweroff(g);
         nvgpu_mutex_release(&g->power_lock);
         return 0;
@@ -1382,6 +1396,10 @@ static int gk20a_probe(struct platform_device *dev)
                 goto return_err;
         }
 
+#ifdef CONFIG_NVGPU_SUPPORT_LINUX_ECC_ERROR_REPORTING
+        nvgpu_init_ecc_reporting(gk20a);
+#endif
+
         gk20a->nvgpu_reboot_nb.notifier_call =
                 nvgpu_kernel_shutdown_notification;
         err = register_reboot_notifier(&gk20a->nvgpu_reboot_nb);