gpu: nvgpu: Make driver rebind work

Make the GPU bind and rebind operations work when the driver
is idle. This required two changes.

1. Reset the GPU before doing SW init for PCI GPUs. This clears
the SW state which may be stale in the case of a rebind attempt.

2. Cleanup the interrupt enable/disables. Firstly there was one
place where nvgpu would accidentally disable the stalling
interrupt twice when the stalling interrupt and non-stalling
interrupt are the same. Secondly make sure when exiting nvgpu
that the interrupt enable/disables are balanced. Leaving the
interrupt in the -1 disable state means that next time the
driver runs interrupts never quite get enabled.

Bug 1816516

Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1287643
Reviewed-on: http://git-master/r/1287649
(cherry picked from commit aa15af0aae5d0a95a8e765469be4354ab7ddd9f8)
Change-Id: I945e21c1fbb3f096834acf850616b71b2aab9ee3
Reviewed-on: http://git-master/r/1292700
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>

3 files changed, 14 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.c b/drivers/gpu/nvgpu/gk20a/gk20a.c
index 069dfc95..44786e4b 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.c
@@ -822,7 +822,8 @@ static int gk20a_pm_prepare_poweroff(struct device *dev)
          * serviced.
          */
         disable_irq(g->irq_stall);
-        disable_irq(g->irq_nonstall);
+        if (g->irq_stall != g->irq_nonstall)
+                disable_irq(g->irq_nonstall);
 
         ret |= gk20a_gr_suspend(g);
         ret |= gk20a_mm_suspend(g);
@@ -907,6 +908,15 @@ int gk20a_pm_finalize_poweron(struct device *dev)
         if (err)
                 goto done;
 
+        /*
+         * Before probing the GPU make sure the GPU's state is cleared. This is
+         * relevant for rebind operations.
+         */
+        if (g->ops.xve.reset_gpu && !g->gpu_reset_done) {
+                g->ops.xve.reset_gpu(g);
+                g->gpu_reset_done = true;
+        }
+
         if (g->ops.bios.init)
                 err = g->ops.bios.init(g);
         if (err)
diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.h b/drivers/gpu/nvgpu/gk20a/gk20a.h
index 30a3252a..ff354bc8 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.h
@@ -832,6 +832,7 @@ struct gk20a {
         void __iomem *bar1;
         void __iomem *bar1_saved;
 
+        bool gpu_reset_done;
         bool power_on;
         bool suspended;
 
diff --git a/drivers/gpu/nvgpu/pci.c b/drivers/gpu/nvgpu/pci.c
index ed681c75..88b743bc 100644
--- a/drivers/gpu/nvgpu/pci.c
+++ b/drivers/gpu/nvgpu/pci.c
@@ -400,6 +400,8 @@ static void nvgpu_pci_remove(struct pci_dev *pdev)
                 platform->remove(g->dev);
         gk20a_dbg(gpu_dbg_shutdown, "Platform remove done.\b");
 
+        enable_irq(g->irq_stall);
+
         kfree(g);
 }