summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/nvgpu
Commit message (Collapse)AuthorAge
* Revert "WAR: gpu: nvgpu: gp10b: disable railgate for K4.4"Deepak Nibade2016-12-27
| | | | | | | | | | | | | | This reverts commit 39a62cba57b243632be56e155813b7318e22c273. Proper fixes are merged for failing tests. Hence re-enable railgating Bug 200198908 Change-Id: Ic9693736add36e7ff77d39fed585126bb6281677 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1163167 Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Remove hard coded runlist_id mappingLakshmanan M2016-12-27
| | | | | | | | | | | | | | | From this patch onwards, runlist_id is a member of struct channel_gk20a. So removed hard coded runlist_id mapping logic. JIRA DNVGPU-25 Change-Id: Ib87d96a518a490d4167071708a76100a4d4c02dd Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1161776 GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* WAR: gpu: nvgpu: gp10b: disable railgate for K4.4Bharat Nihalani2016-12-27
| | | | | | | | | | | | This is done to mask a race issue seen where power refcount is zero during ISR or bottom half. Bug 200198908 Change-Id: I0a8ed774cd4fda9db65429b5aad03c5e001ff666 Signed-off-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-on: http://git-master/r/1162314 Reviewed-by: Juha Tukkinen <jtukkinen@nvidia.com>
* gpu: nvgpu: Enable GP10x GPMU secure bootMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | Build support & enable GPMU secure boot for GP10x JIRA DNVGPU-34 Change-Id: Id1316677ed44790aa150e0ada8ff39daf0ef1d0c Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161174 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: PMU/SEC2 reset sequence & OPS updateMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | - Enable OPS to support secure boot - PMU/SEC2 reset sequence change for GP104/GP106 JIRA DNVGPU-34 Change-Id: I583a6af1d5354649c3df9d9b4d74141d52d6ca9d Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161132 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: ACR boot on SEC2Mahantesh Kumbar2016-12-27
| | | | | | | | | | | | | ACR/SEC2 methods to support ACR boot SEC2 falcon JIRA DNVGPU-34 Change-Id: I917be1d6c61a1c1ae61a918f50228ea00492cd50 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161122 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: ACR interface update for GP104/GP106Mahantesh Kumbar2016-12-27
| | | | | | | | | | | JIRA DNVGPU-34 Change-Id: Ieb8e73451a5d73480b8d9e29e78b1a273b17d796 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161120 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* Revert "gpu: nvgpu: register to nvhost for debug dump"Krishna Reddy2016-12-27
| | | | | | | | | | | | | | | This reverts commit fe3adf3d0a72f936788b98365557783b53ecb6ed. This revert is fixing the Vulkan 1.0.1 CTS failures. Bug 200196104 Change-Id: I8cc90ac9dc3d29a08341f37e83277a0b431e2187 Signed-off-by: Krishna Reddy <vdumpa@nvidia.com> Reviewed-on: http://git-master/r/1161577 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: include matching header in mm_gp106.cKonsta Holtta2016-12-27
| | | | | | | | | | | | | Include mm_gp106.h in mm_gp106.c to bring function declarations visible and to fix a Sparse warning. Bug 200088648 Change-Id: Id76f565021de585bc02a53a01e52084ff70009c2 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1161607 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com>
* gpu: nvgpu: detect vidmem configuration from HWKonsta Holtta2016-12-27
| | | | | | | | | | | | | Read video memory size from hardware during initialization for devices that support it. JIRA DNVGPU-14 Change-Id: I84e1bca0eaac8dc204e1fb82628acc6b52c3e5cc Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1157212 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add multiple engine and runlist supportLakshmanan M2016-12-27
| | | | | | | | | | | | | | | | | | | | This CL covers the following modification, 1) Added multiple engine_info support 2) Added multiple runlist_info support 3) Initial changes for ASYNC CE support 4) Added ASYNC CE interrupt support for Pascal GPU series 5) Removed hard coded engine_id logic and made generic way 6) Code cleanup for readability JIRA DNVGPU-26 Change-Id: Ibf46a89a5308c82f01040ffa979c5014b3206f8e Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1156022 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove clockgate_delay paramSeshendra Gadagottu2016-12-27
| | | | | | | | | | | | | Removed platform data parameter clockgate_delay, since it is not really used for gpu clock gating any more. Change-Id: I4c7148c70699cb5ed24f0b034ddc92bfb4b41887 Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1159594 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gp10b: clear TEX ECC interruptAdeel Raza2016-12-27
| | | | | | | | | | | | Fix bug in clearing the TEX ECC interrupt. Bug 200206379 Change-Id: I758b55d20919173de527aeb98143851edcde4eeb Signed-off-by: Adeel Raza <araza@nvidia.com> Reviewed-on: http://git-master/r/1158806 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: map patch ctx in set_preemption_modeKonsta Holtta2016-12-27
| | | | | | | | | | | | The per-write map/unmap feature from gr_gk20a_ctx_patch_write_begin() is dropped, so call begin/end explicitly from gr_gp10b_set_preemption_mode for the commit_global_cb_manager call. Change-Id: I7bf952fffb54d4f18706e77dea015ffe4b68bcfe Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1157835 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix patch write error check in update_ctxsw_preemption_modeKonsta Holtta2016-12-27
| | | | | | | | | | | | Don't attempt to access memory if the patch context can't be mapped, but print an error message instead. Change-Id: I374dc94d13674e0bd9d081b790f7c0dac834e868 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1157828 GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add Fuse prints on PMU HaltSupriya2016-12-27
| | | | | | | | | | | | | | -Print fuse values in case of PMU halt error -and mailbox reads 0xDEADDEAD Bug 1737044 Change-Id: Icb9677ca278bd316232e07f1d92980f6deb17125 Signed-off-by: Supriya <ssharatkumar@nvidia.com> Reviewed-on: http://git-master/r/1120988 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
* gpu: nvgpu: use correct APIs for disable and preemptDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | | | | | In gr_gp10b_set_preemption_mode() and in gp10b_fifo_resetup_ramfc(), we call channel specific APIs to disable/preempt/enable channel But we do not consider TSGs in this case Hence use correct (below) APIs in above function which will handle channel or TSG internally : gk20a_disable_channel_tsg() gk20a_fifo_preempt() gk20a_enable_channel_tsg() Bug 200205041 Change-Id: I2369e79b2af3b8a91699044106293865d5f8f260 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1157192 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gp10b: set floor emc freq to bwmgrSeshendra Gadagottu2016-12-27
| | | | | | | | | | | | | | Set emc floor frequency as zero during rail-gate and set max emc frequency as floor frequency during rail-ungate. Bug 1770241 Change-Id: Ib6b6ea6c8b04518423126c3ca3600b4afac15180 Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1152848 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: init tsg HAL opsRichard Zhao2016-12-27
| | | | | | | | | | | | | Bug 1702773 Change-Id: I9b6e1d0f2f4fe979f6fab83347884bd69413ccda Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1144935 (cherry picked from commit f79eb75272879c869b137cd042312db0a5953412) Reviewed-on: http://git-master/r/1127031 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: manage gr_ctx as independent resourceRichard Zhao2016-12-27
| | | | | | | | | | | | | | | gr_ctx will managed as independent resource in RM server and vgpu can get a gr_ctx handle. Bug 1702773 Change-Id: Ifceb44b7d9a1ba03fc2a4df847f4a78ac4c4a0d4 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1144934 (cherry picked from commit 0da3101d9b59fe1f9a47ce7b70b30cb8919f35ac) Reviewed-on: http://git-master/r/1150707 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Force GPCCS priv loadTerje Bergstrom2016-12-27
| | | | | | | | | | | | Use priv load for GPCCS instead of DMA. Bug 200204675 Change-Id: Ic7ea7d9e0ef98330e0bdd7606284b8fb3c5bfec8 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1155281 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com>
* gpu: nvgpu: Fix timeout error in suspend_contextsCory Perry2016-12-27
| | | | | | | | | | | | | | | * Moving jiffy counter after preemption work to more accurately and fairly give time for preemption to complete. * Add debug information to coordinate waiting. * Check if cilp is still pending before returning the timedout error. Bug 1700310 Change-Id: Ic16bb3b11f2cd5aea9a5a85b5e0d9927732a065c Signed-off-by: Cory Perry <cperry@nvidia.com> Reviewed-on: http://git-master/r/1151907 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add device_info_data supportLakshmanan M2016-12-27
| | | | | | | | | | | | | | | | | | | Added device_info_data parsing support for pascal GPU series. This is required to identify the (Logical CE) NV_PTOP_DEVICE_INFO_TYPE_ENUM_LCE instance id. (example - CE0, CE1, CE2, CE3, ...) JIRA DNVGPU-26 Change-Id: I35c42cb1d544729e4099db1528c690dd2be025f4 Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1151605 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Ken Adams <kadams@nvidia.com>
* gpu: nvgpu: fix sparse warningDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | fix below sparse warning : $TOP/kernel-nvgpu-t18x/drivers/gpu/nvgpu/gp106/pmu_gp106.c:22:5: warning: symbol 'gp106_pmu_reset' was not declared. Should it be static? Bug 200088648 Change-Id: I86120fb6b9733f256c96764a77c6ea4bb636934a Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1154452 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Amit Sharma (SW-TEGRA) <amisharma@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Enable ELPG init for gp10bMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | set can_elpg to true to support ELPG init Bug N/A Change-Id: I9bdf264689440ef715cf34a5332d03cb60c5aef7 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1152432 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: secure boot HAL updateMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | -And also enable GPCCS load using DMA Updated/added secure boot HAL with methods required to support multiple GPU chips. JIRA DNVGPU-10 Change-Id: Id4546fa74954ba7be7c4544d74ad2b7a31b0ecec Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1151788 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gp10b: SM LRF ECC overcount WARAdeel Raza2016-12-27
| | | | | | | | | | | | | | SM LRF ECC HW overcounts errors in certain situations. Implement SW WAR to correct error counts. Bug 1752609 Bug 1761594 Change-Id: I79047d21e2e44e0fca3ece1da80f02faa4cd6c54 Signed-off-by: Adeel Raza <araza@nvidia.com> Reviewed-on: http://git-master/r/1150773 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: change kernel pathPritesh Raithatha2016-12-27
| | | | | | | | | | | | | | All kernel versions are getting moved inside $TOP/kernel folder. Changing kernel paths accordingly. Bug 200190733 Change-Id: If2f4b8fd77da6c1534558ed34763aa1e1e76cbd6 Signed-off-by: Pritesh Raithatha <praithatha@nvidia.com> Reviewed-on: http://git-master/r/1143387 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: gp10b: add PRAMIN support for mem accessorsKonsta Holtta2016-12-27
| | | | | | | | | | JIRA DNVGPU-23 Change-Id: I6f4a7018ebeb5c7928667148a52f779ca4938e47 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1148120 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add support for gp104 and gp106Terje Bergstrom2016-12-27
| | | | | | | | | | Add support for chips gp104 and gp106. Change-Id: Ied5f239bdd0ec85245bce1fb6ef51330871d0f05 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1120465 GVS: Gerrit_Virtual_Submit Reviewed-by: Ken Adams <kadams@nvidia.com>
* gpu: nvgpu: Fix SM number when more than 4 TPCsTerje Bergstrom2016-12-27
| | | | | | | | | | | Use multiplication instead of division to come up with an SM id. Change-Id: Ib185970ee99cc8c010d02ba846229e0959a5fef3 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1150599 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com>
* gpu: nvgpu: gp10b: Use gk20a version of PMU resetTerje Bergstrom2016-12-27
| | | | | | | | | Change-Id: I9b6c2e3bcae4ac43a20089e05891654654df1b54 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1150541 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
* gpu: nvgpu: Add HWPM registers to regops whitelistTerje Bergstrom2016-12-27
| | | | | | | | | | | Bug 1763653 Change-Id: Ief7ed56c29dba5836fc8435359a7c615ce53bb84 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1150717 Reviewed-by: Peter Daifuku <pdaifuku@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: hwpm broadcast register supportPeter Daifuku2016-12-27
| | | | | | | | | | | | | | | | | Add support for hwpm broadcast registers (ltc and lts) Bug 1648200 Change-Id: I2aa4e6c0991abaa94b0f58354a826f626f1d43a2 Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com> Reviewed-on: http://git-master/r/1131363 (cherry picked from commit 383d195dabed76ecc50bb2bd355d6180bcda082a) Reviewed-on: http://git-master/r/1133629 (cherry picked from commit 725d02e2690c96fbfa5f49ade550442de5961e82) Reviewed-on: http://git-master/r/1127750 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Implement engine_enum_from_typeTerje Bergstrom2016-12-27
| | | | | | | | | | | | | Implement a helper function engine_enum_from_type. This allows parsing device_info entries for LCE engine type. Pascal has logical copy engine instead of CE2, so so add definition of that. Change-Id: I71f59c308641d84ac59fd57fc37d9b627bb07a43 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1147747 Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
* gpu: nvgpu: gp10b: Program NISO sysmem flush addrTerje Bergstrom2016-12-27
| | | | | | | | | | | | Program sysmem flush address to prevent random accesses of address 0. Change-Id: Ia577106c63a80589c154af41d18b70480ed7c7d7 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1149174 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com>
* gpu: nvgpu: gp10b: Fix CWD floorsweep programmingTerje Bergstrom2016-12-27
| | | | | | | | | | | | Program CWD TPC and SM registers correctly. The old code did not work when there are more than 4 TPCs. Change-Id: I18a14a0f76d97b0962607ec0bbd71aafcd768bca Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1143075 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
* gpu: nvgpu: Remove setting op set_max_ways_evict_lastTerje Bergstrom2016-12-27
| | | | | | | | | Do not set op set_max_ways_evict_last. It gets removed from ltc_gk20a.c, and it's never called in gm20b and beyond anyway. Change-Id: Ib8851057810aa8ddf2088c9e9245e4caf469bddf Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1146882
* gpu: nvgpu: Add support for multiple PBDMAsLakshmanan M2016-12-27
| | | | | | | | | | | | | | | | Added support for multiple PBDMAs handling during fifo_pbdma_isr and gk20a_init_fifo_reset_enable_hw use case. JIRA DNVGPU-26 Change-Id: I3ce65fdeacb012551d15eed85dc61602f7dadbbb Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1145601 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: refactor gk20a_mem_{wr,rd} for vidmemKonsta Holtta2016-12-27
| | | | | | | | | | | | | | | | | To support vidmem, pass g and mem_desc to the buffer memory accessor functions. This allows the functions to select the memory access method based on the buffer aperture instead of using the cpu pointer directly (like until now). The selection and aperture support will be in another patch; this patch only refactors these accessors, but keeps the underlying functionality as-is. JIRA DNVGPU-23 Change-Id: I21d4a54827b0e2741012dfde7952c0555a583435 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1121914 GVS: Gerrit_Virtual_Submit Reviewed-by: Ken Adams <kadams@nvidia.com>
* gp10b: initialize dynamic sysfs attributesRemi Denis-Courmont2016-12-27
| | | | | | | | | | | | | All dynamically allocated sysfs attributes MUST be initialized explicitly. Otherwise lock debugging fails. Change-Id: I8f77857831221b5ceddb43f9d161c3bf4ca049d6 Signed-off-by: Remi Denis-Courmont <remid@nvidia.com> Reviewed-on: http://git-master/r/1145929 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Juha Tukkinen <jtukkinen@nvidia.com>
* gpu: nvgpu: Remove fn debug from PTE updateTerje Bergstrom2016-12-27
| | | | | | | | | | | | | | Function trace in update_gmmu_ptes_locked() cause too much spew on UART. Change-Id: I94c79be76394631cdee343b2f77e4bf0f830e0a8 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1144808 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Ken Adams <kadams@nvidia.com>
* gpu: nvgpu: add code to handle DT fuse overridesAdeel Raza2016-12-27
| | | | | | | | | | | | | | Add code for handling GP10B fuse overrides specified in the device tree. Also add specific handling for the ECC fuse override. Bug 1699676 Change-Id: Ifa07983054cd143f7f1745a6a6de36f4d4e08126 Signed-off-by: Adeel Raza <araza@nvidia.com> Reviewed-on: http://git-master/r/1140893 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: API to return preemption modesDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | Add API gr_gp10b_get_preemption_mode_flags() to return supported and default graphics/compute preemption modes on gp10b Bug 1646259 Change-Id: I291a82a911e021b605b6d1ccae9cef663cc7a01a Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1133596 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: API to set preemption modeDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Separate out new API gr_gp10b_set_ctxsw_preemption_mode() which will check requested preemption modes and take appropriate action for each preemption mode This API will also do some sanity checking for valid preemption modes and combinations Define API set_preemption_mode() for gp10b which will set the preemption modes passed as argument and then use gr_gp10b_set_ctxsw_preemption_mode() and update_ctxsw_preemption_mode() to update preemption mode Legacy path from gr_gp10b_alloc_gr_ctx() will convert flags NVGPU_ALLOC_OBJ_FLAGS_* into appropriate preemption modes and then call gr_gp10b_set_ctxsw_preemption_mode() New API set_preemption_mode() will use new flags NVGPU_GRAPHICS/COMPUTE_PREEMPTION_MODE_* and set and update ctxsw preemption mode In gr_gp10b_update_ctxsw_preemption_mode(), update graphics context to set CTA premption mode if mode NVGPU_COMPUTE_PREEMPTION_MODE_CTA is set Also, define preemption modes in nvgpu-t18x.h and use them everywhere Remove old definitions of modes from gr_gp10b.h Bug 1646259 Change-Id: Ib4dc1fb9933b15d32f0122a9e52665b69402df18 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1131806 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: adapt gk20a_mm_entry for mem_descKonsta Holtta2016-12-27
| | | | | | | | | | | | | | | | | For upcoming vidmem refactor, replace struct gk20a_mm_entry's contents identical to struct mem_desc, with a struct mem_desc member. This makes it possible to use the page table buffers like the others too. JIRA DNVGPU-23 JIRA DNVGPU-20 Change-Id: Ia82da07b5a3bb9fb14a86bcf96a46b3a3c80bf28 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1139696 GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Ken Adams <kadams@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gp10b: Add def for NISO sysmem flush addrTerje Bergstrom2016-12-27
| | | | | | | | | | | Add definition for NISO sysmem flush addr. This makes gp10b in sync with rest of chips. Change-Id: Ic3548585000602497e9d7ff271144b9ca9b2acca Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1129217 Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: gp10b: set soc memory aperture typeSeshendra Gadagottu2016-12-27
| | | | | | | | | | | | | | For gp10b, set platform data for soc memory aperture type as vidmem. Bug 1749338 Change-Id: I7961734d3ebcca4af459c7c7d49bc31f0fc8ce5d Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1129168 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Ken Adams <kadams@nvidia.com>
* gpu: nvgpu: gp10b: add delay cycles before elcgSeshendra Gadagottu2016-12-27
| | | | | | | | | | | | | | | Update prod value for gr engine delay cycles before engine clock gating. For copy engine, it was updated earlier and now it is extended to both gr and ce. Bug 1689806 Change-Id: I457ad6f9c461db89d53c57e68ad937ab5292849e Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1129922 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: suspend context support for gp10bDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | | | | | | | | | Add API gr_gp10b_suspend_contexts() to support context suspend on gp10b sequence to suspend: - disable ctxsw - loop through list of channels - if channel is ctx resident, suspend all SMs - if CILP channel, set CILP preempt pending = true - resume all SMs - otherwise, disable channel/TSG - enable ctxsw - if CILP preempt is pending, wait for it to complete Bug 200156699 Change-Id: Id9609077c283f99f420ad21c636b29f74b8eff6b Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1120334 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-11-09 02:31:39 -0500