mirror of
git://nv-tegra.nvidia.com/linux-nvgpu.git
synced 2025-12-23 18:16:01 +03:00
Global context buffers were mapped on every ALLOC_OBJ_CTX call. If many channels are created sharing an address space they can exhaust the VA space by mapping same global context buffers again and again. Skip mapping the global context buffer if it is already mapped for an address space. Bug 3802863 Bug 3796293 Change-Id: I3844c211b3350aa06cabd92c415a34a83034dd43 Signed-off-by: Sagar Kamble <skamble@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2789584 (cherry picked from commit 0611ec30c6a61b7e1b07d516b74d6eddb3c6b37e) Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2789581 Reviewed-by: Scott Long <scottl@nvidia.com> Reviewed-by: Ankur Kishore <ankkishore@nvidia.com> GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>