nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-24 10:34:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: use railgate instead of reset_assert

Browse Source 
In gk20a_do_idle(), if can_railgate = false, we do
reset_assert() on the GPU

But asserting reset might have dependencies on
specific h/w seqeunce for ensuring proper reset

Hence avoid calling reset_assert() and directly
call platform specific unrailgate() and railgate()
APIs which take care of the correct reset sequence

Bug 200142989
Bug 200137963
Bug 1678611

Change-Id: Ide886dd88b8422ad36de52d54378b1edd9c7bbd6
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/820322
(cherry picked from commit d621ddd49da976a75c14aa7aaa37f700fb4e83f2)
Reviewed-on: http://git-master/r/822515
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
This commit is contained in:
Deepak Nibade
2015-10-20 17:15:52 +05:30
committed by Sachin Nikam
parent 0334d7e303
commit 3684ed8fd6
1 changed files with 12 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
drivers/gpu/nvgpu/gk20a/gk20a.c
View File

@@ -1854,23 +1854,23 @@ int __gk20a_do_idle(struct platform_device *pdev, bool force_reset)
} else {
/*
* Case 2 : GPU railgate is not supported or we explicitly
* do not want to do railgate
* do not want to depend on runtime PM
*
* if GPU is now idle, call prepare_poweroff() to save the
* state and then assert the reset
* state and then do explicit railgate
*
* __gk20a_do_unidle() needs to deassert reset, call
* __gk20a_do_unidle() needs to unrailgate, call
* finalize_poweron(), and then call pm_runtime_put_sync()
* to balance the GPU usage counter
*/
if (!platform->reset_assert || !platform->reset_deassert)
goto fail_drop_usage_count;
/* Save the GPU state */
gk20a_pm_prepare_poweroff(&pdev->dev);
/* assert GPU reset */
platform->reset_assert(pdev);
gk20a_pm_disable_clk(&pdev->dev);
/* railgate GPU */
platform->railgate(pdev);
udelay(10);
@@ -1915,10 +1915,12 @@ int __gk20a_do_unidle(struct platform_device *pdev)
if (g->forced_reset) {
/*
* If we did a reset (and not railgate),
* then deassert the GPU reset here first
* If we did a forced-reset/railgate
* then unrailgate the GPU here first
*/
platform->reset_deassert(pdev);
platform->unrailgate(pdev);
gk20a_pm_enable_clk(&pdev->dev);
/* restore the GPU state */
gk20a_pm_finalize_poweron(&pdev->dev);