nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-22 09:12:24 +03:00
Code Issues Packages Projects Releases Wiki Activity
9,525 Commits 57 Branches 84 Tags
76792585b55fe634f39ea4d7d0832d3420f3761c
Commit Graph

6 Commits

Author SHA1 Message Date
Sagar Kamble
76792585b5 gpu: nvgpu: add hal to get the bar2 vm size 
On ga10b+ platforms, more VM space is needed to map various buffers
to bar2 vm. Engine method buffer is mapped for each pbdma and for
maximum supported TSGs this requires more than 32MB of space.
Also we need to consider fault buffer space and vab buffer
space requirement.

Bug 3958581

Change-Id: I9ee87119f762352ee12859b71c08a5f75b3554e0
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2872811
(cherry picked from commit 53dc53a8b4)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2881179
Reviewed-by: Ankur Kishore <ankkishore@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
 2023-04-03 07:51:45 -07:00
Vedashree Vidwans
00d1e10ff2 gpu: nvgpu: accept small_big_split in vm_init 
Currently, when unified address space is not requested, nvgpu_vm_init
splits user vm at a fixed address of 56G.
Modify nvgpu_vm_init to allow user to specify small big page vm split.

JIRA NVGPU-5302

Change-Id: I6ed33a4dc080f10a723cb9bd486f0d36c0cee0e9
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2428326
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: Sami Kiminki <skiminki@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
 2020-12-15 14:13:28 -06:00
Vedashree Vidwans
673cd507a8 gpu: nvgpu: add mm gops to get default va size 
Currently, default va aperture size, user size and kernel size are
defined as fixed macros. However, max va bits can be chip specific.
Add below mm gops API to obtain default aperture, user and/or kernel
virtual memory size.
void (*get_default_va_sizes)(u64 *aperture_size,
		u64 *user_size, u64 *kernel_size);

JIRA NVGPU-5302

Change-Id: Ie0c60ca08ecff6613ce44184153bda066803d7d9
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2414840
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
 2020-12-15 14:13:28 -06:00
Vedashree Vidwans
49c9f0c137 gpu: nvgpu: accept user vma size in vm init 
Modify nvgpu_vm_init to accept low_hole, user_reserved and
kernel_reserved. This will simplify argument limit checks and make code
more legible.

JIRA NVGPU-5302

Change-Id: I62773dd7b06264a3b6cb8896239b24c49fa69f9b
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2394901
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
 2020-12-15 14:13:28 -06:00
Philip Elcan
93ebeac3bd gpu: nvgpu: mm: fix CERT-C bugs in nvgpu.*.mm.mm 
INT-30 requires checking for overflow of arithmetic operations on
unsigned integers.
INT-31 requires bounds checking for unsigned integers cast to
smaller size.

Fix these violations by using the safe ops in nvgpu.common.mm.mm and
nvgpu.hal.mm.mm.

JIRA NVGPU-3848

Change-Id: I2751a14fb1f45d330a92040ac3c7777c52ae9199
Signed-off-by: Philip Elcan <pelcan@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2158860
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Adeel Raza <araza@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
 2019-07-23 15:49:00 -07:00
Nicolas Benech
9a4ad88f21 gpu: nvgpu: hal: split MM-related HALs based on FUSA 
This patch moves MM HALs that are guaranteed to be functionaly safe
into _fusa.c files. HALs that are not part of FUSA are not compiled
anymore when the safety profile is enabled.

Given a HAL source file:
- it may contain only FUSA code, in that case the source file is
  simply renamed with the _fusa postfix.
- it may contain only non-FUSA code, in that case the file is left
  as-is
- it may contain a mix, in that case the original file will now only
  contain non-FUSA code, and all FUSA code will be moved into a new
  source file with the _fusa postfix.

JIRA NVGPU-3690

Change-Id: I44c604aef2d72252abb7da1c0ef1210d71a0efa7
Signed-off-by: Nicolas Benech <nbenech@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2140895
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
 2019-06-27 01:36:07 -07:00