nvidia-tegra-modules.git/include/linux/nvmap_t19x.h, branch rtss22-ae NVIDIA's kernel modules to support tegra chips (used in Jetson boards) video: tegra: nvmap: add runtime busy/idle calls 2018-04-02T05:33:00+00:00 Puneet Saxena puneets@nvidia.com 2018-03-01T10:32:31+00:00 d2c3fc38fb4afcb34503e121ccc1acda00c56dcd CVSRAM falls under cvnas cluster. nvmap_alloc/free from cvsram heap requires CV rail to be power ungated/gated. Presently CV rail is always on/not power gated as CVNAS power gating is called from driver remove and cvnas driver is statically loaded The change registers runtime cvnas busy/idle callbacks at cvsram carveout creation. It exports CVNAS power gate(nvcvnas_idle()) and CVNAS power ungate(nvcvnas_busy). The callbacks are used during nvmap_alloc/free from CVSRAM. Bug 200383595 Change-Id: I545c18ea7bcf61bb6356e2d6d05c2f4f9b1f5368 Signed-off-by: Puneet Saxena <puneets@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1666574 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Rajkumar Kasirajan <rkasirajan@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
CVSRAM falls under cvnas cluster. nvmap_alloc/free
from cvsram heap requires CV rail to be power ungated/gated.
Presently CV rail is always on/not power gated as CVNAS power
gating is called from driver remove and cvnas driver is statically loaded

The change registers runtime cvnas busy/idle callbacks at
cvsram carveout creation.
It exports CVNAS power gate(nvcvnas_idle()) and CVNAS power
ungate(nvcvnas_busy). The callbacks are used during  nvmap_alloc/free
from CVSRAM.

Bug 200383595

Change-Id: I545c18ea7bcf61bb6356e2d6d05c2f4f9b1f5368
Signed-off-by: Puneet Saxena <puneets@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1666574
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Rajkumar Kasirajan <rkasirajan@nvidia.com>
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: allow cpu access to set GoS initial value 2018-02-13T11:52:51+00:00 Pritesh Raithatha praithatha@nvidia.com 2018-02-07T11:16:11+00:00 a30d87ef00f23bda01a853d51d126c8c771a5368 -Clients are getting last used GoS value instead of reset value. -Added cpu_addr to cvdev_info for host1x to set initial value. -Cpu don't have permission to access GoS. Given permission with removing no cpu access from gosmem carveout. Bug 2045565 Change-Id: I1b816e2a7415cd04804f5c9d236d111129053b77 Signed-off-by: Pritesh Raithatha <praithatha@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1653500 Reviewed-by: Sachin Nikam <snikam@nvidia.com> GVS: Gerrit_Virtual_Submit Tested-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
-Clients are getting last used GoS value instead of reset value.
-Added cpu_addr to cvdev_info for host1x to set initial value.
-Cpu don't have permission to access GoS. Given permission with
removing no cpu access from gosmem carveout.

Bug 2045565

Change-Id: I1b816e2a7415cd04804f5c9d236d111129053b77
Signed-off-by: Pritesh Raithatha <praithatha@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1653500
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: update copyright text 2017-06-16T10:19:25+00:00 Sri Krishna chowdary schowdary@nvidia.com 2017-04-25T14:09:34+00:00 592bc947bb088720081c12639836b326e0f377e2 Update copyright text as recommended by GPLv2 bug 200302395 Change-Id: I18d720ba152df43532ef16bb7bb0e95f00f683ea Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1469581 Reviewed-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com> 
Update copyright text as recommended by GPLv2

bug 200302395

Change-Id: I18d720ba152df43532ef16bb7bb0e95f00f683ea
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1469581
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
video: tegra: nvmap: Support Gosmem initialization 2017-06-16T10:18:42+00:00 Sri Krishna chowdary schowdary@nvidia.com 2016-12-29T11:47:24+00:00 1cff492553513ed0e0b099a646a3bf2fde78929a Add support for gosmem offset_dev. This can be used for allocating the individual semaphores from GoS. Also fix the following issues 1. Use rmem->phandle to retrieve DT node of gosmem as name is not reliable. 2. alloc sgt before setting buf as it leads to NULL dereference otherwise 3. Use same API to get cv_dev_info of a particular device. This improves code coverage and also fixes the incorrect sgt mapping. bug 200209819 Change-Id: I66f83a71c4a44350fea662da22d08308099df58c Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1278215 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> 
Add support for gosmem offset_dev. This can be used for allocating
the individual semaphores from GoS.

Also fix the following issues
1. Use rmem->phandle to retrieve DT node of gosmem as name
   is not reliable.
2. alloc sgt before setting buf as it leads to NULL dereference
   otherwise
3. Use same API to get cv_dev_info of a particular device. This
   improves code coverage and also fixes the incorrect sgt mapping.

bug 200209819

Change-Id: I66f83a71c4a44350fea662da22d08308099df58c
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1278215
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
video: tegra: nvmap: Consider client coherency for cache ops 2017-06-16T10:18:42+00:00 Sri Krishna chowdary schowdary@nvidia.com 2016-10-25T15:49:05+00:00 7c96a5d9539309f3f9a93040f1f492036486690c Track the number of outstanding dma maps from non IO coherent clients of dmabuf and do cache maintenance only if the count is non zero. This patch assumes that the following sequence is followed for all clients is 1. dma_buf_map_attachment 2. cache maintenance for device 3. device does some oepration 4. cache maintenance for cpu 5. dma_buf_unmap_attachment Although this patch would work with dmabuf deferred unmapping feature, disabling deferred unmapping for non IO coherent clients will help avoid unnecessary cache maintenance. Add "nvidia,tegra194-carveouts" to compatible property of nvmap DT node to enable this feature. JIRA TMM-80 Change-Id: Ic06b4ae110b48f69705d535cbfd90a13313b170f Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1242227 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> 
Track the number of outstanding dma maps from non IO coherent
clients of dmabuf and do cache maintenance only if the count
is non zero.

This patch assumes that the following sequence is followed
for all clients is
1. dma_buf_map_attachment
2. cache maintenance for device
3. device does some oepration
4. cache maintenance for cpu
5. dma_buf_unmap_attachment

Although this patch would work with dmabuf deferred unmapping
feature, disabling deferred unmapping for non IO coherent clients
will help avoid unnecessary cache maintenance.

Add "nvidia,tegra194-carveouts" to compatible property of nvmap
DT node to enable this feature.

JIRA TMM-80

Change-Id: Ic06b4ae110b48f69705d535cbfd90a13313b170f
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1242227
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
video: tegra: nvmap: support gosmem initialization 2017-06-16T10:17:56+00:00 Sri Krishna chowdary schowdary@nvidia.com 2016-07-26T03:45:20+00:00 b93e5aefa726929278a8cac4a76dc6c9d93a8b28 Also add nvmap_gosmem_fetch_cvdev_info() so that the cv components can fetch the information they need about the grid of semaphore memory. bug 200209819 Change-Id: I8ac5384a4240d118de54fb12913b61833e66a0bc Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1190541 Reviewed-by: Prashant Gaikwad <pgaikwad@nvidia.com> GVS: Gerrit_Virtual_Submit 
Also add nvmap_gosmem_fetch_cvdev_info() so that
the cv components can fetch the information they
need about the grid of semaphore memory.

bug 200209819

Change-Id: I8ac5384a4240d118de54fb12913b61833e66a0bc
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1190541
Reviewed-by: Prashant Gaikwad <pgaikwad@nvidia.com>
GVS: Gerrit_Virtual_Submit
linux: nvmap_t19x: declare nvmap_register_cvsram_carveout 2017-06-16T10:17:56+00:00 Sri Krishna chowdary schowdary@nvidia.com 2016-06-23T04:30:56+00:00 994e15b8b45cd7c209435a266537f8acda42d44e This is needed for sanity testing cvsram carveout. bug 1763257 Change-Id: I5c22d6c9663598679f2e0d8000f3760337b05b3c Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1170006 GVS: Gerrit_Virtual_Submit Reviewed-by: Krishna Reddy <vdumpa@nvidia.com> 
This is needed for sanity testing cvsram carveout.

bug 1763257

Change-Id: I5c22d6c9663598679f2e0d8000f3760337b05b3c
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1170006
GVS: Gerrit_Virtual_Submit
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
video: tegra: nvmap: support cvsram carveout 2017-06-16T10:17:56+00:00 Sri Krishna chowdary schowdary@nvidia.com 2016-06-01T08:29:12+00:00 070123b6fdd34ce13739e22b8692e2971d3a7557 cvram carveout should not be accessed by cpu and also should not be dma mapped. bug 1763257 Change-Id: Ib8908e735165b2b5d6d7a9cc8290a28c81ce97c6 Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1156663 GVS: Gerrit_Virtual_Submit Reviewed-by: Krishna Reddy <vdumpa@nvidia.com> 
cvram carveout should not be accessed by cpu and also
should not be dma mapped.

bug 1763257

Change-Id: Ib8908e735165b2b5d6d7a9cc8290a28c81ce97c6
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/1156663
GVS: Gerrit_Virtual_Submit
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>