summaryrefslogtreecommitdiffstats
path: root/drivers/gpu
Commit message (Collapse)AuthorAge
* gpu: nvgpu: round clock locallyDeepak Nibade2017-01-06
| | | | | | | | | | | | | | | | | | In gp10b_round_clk_rate(), we currently call clk_round_rate() to round the clock rate for us But since the frequency table is prepared using the frequency values supported in h/w, we can round the rate locally using the table Bug 1827281 Change-Id: I85d034326539590352badceb4164aa5d89ee8842 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1280630 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: select N'th freq from all available frequenciesDeepak Nibade2017-01-06
| | | | | | | | | | | | | | | | | | | | | | | | | We right now get min and max frequencies, and then interpolate rest of the frequencies. With this approach, we do not select exact frequencies as supported by h/w Fix this so that we query all supported frequencies using clk_round_rate() and then select every N'th frequency to keep number of frequencies under limit Use GP10B_FREQ_SELECT_STEP (currently set to 8) to configure frequency selection step Raise GP10B_MAX_SUPPORTED_FREQS to 200 since h/w supported frequencies could be in that range Bug 1827281 Change-Id: Id8678d7a0280a249e4affbba084ff2e33b6694e6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1280629 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Do not access NULL pointer devTerje Bergstrom2017-01-06
| | | | | | | | | | | | | In gk20a_busy() we check if dev is NULL and return -ENODEV if so. But before that we've already dereferenced dev by passing it to get_gk20a(). Defer call to get_gk20a() until after the NULL check. Bug 200192125 Change-Id: I943a9e96d13ff8cb4333fe20a941c8e95d159a66 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1280349 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Do not recursively #include clk.hTerje Bergstrom2017-01-06
| | | | | | | | | | | | | clk.h #includes clk_vin.h, which recursively #includes clk.h without needing anything from clk.h. Remove the #include to improve build time. Bug 200192125 Change-Id: Icab32b7e73a1eaaee8e017367d71b8ebde47c21e Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1280350 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Use perf table only if VBIOS supports itTerje Bergstrom2017-01-06
| | | | | | | | | | | | | | | | We retrieve perf table from VBIOS only if respective HAL op is implemented. Later in code we unconditionally dereference a pointer which can lead to NULL pointer access. Fix two new cases by early aborting creation of devinit tables if the perf VBIOS getter is missing. Bug 200192125 Change-Id: I30f20f1829305ecc1117c6301e26ff1b869967eb Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1280347 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Don't recursively #include ctrlvolt.hTerje Bergstrom2017-01-06
| | | | | | | | | | | | | ctrlvolt.h #includes ctrlperf.h, which recursively #includes ctrlvolt.h without needing anything from it. Remove the #include to improve built time. Bug 200192125 Change-Id: I8c917533127e6d42aae6ad1401860c1f5d110d81 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1280345 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: fix out-of-bound access on gr->map_tilesDeepak Nibade2017-01-06
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix slab-out-of-bounds issue reported by KASAN [ 28.464077] BUG: KASAN: slab-out-of-bounds in gr_gk20a_init_map_tiles+0x624/0x708 at addr ffffffc1a098ee01 ... [ 28.503241] INFO: Allocated in gr_gk20a_init_map_tiles+0x2dc/0x708 age=11 cpu=5 pid=1 out-of-bound access from below 3 stacks : [1] [ 28.782886] [<ffffffc0007d5f64>] gr_gk20a_init_map_tiles+0x624/0x708 [ 28.789228] [<ffffffc0007eadf0>] gk20a_init_gr_support+0x2d0/0xeb0 [ 28.795397] [<ffffffc00079d9c8>] gk20a_pm_finalize_poweron+0x738/0xd10 [2] [ 29.268070] [<ffffffc0007d618c>] gr_gk20a_zcull_init_hw+0x144/0x730 [ 29.274329] [<ffffffc0007d6a00>] gk20a_init_gr_setup_hw+0x288/0x1530 [ 29.280677] [<ffffffc0007eac6c>] gk20a_init_gr_support+0x14c/0xeb0 [ 29.286938] [<ffffffc00079d9c8>] gk20a_pm_finalize_poweron+0x738/0xd10 [3] [ 50.076223] [<ffffffc000d1df14>] gr_gk20a_setup_rop_mapping+0x5e4/0x2018 [ 50.082913] [<ffffffc000d2559c>] gr_gk20a_init_fs_state+0x80c/0x1028 [ 50.089259] [<ffffffc000ddcbc8>] gr_gm20b_init_fs_state+0xc8/0x960 [ 50.095430] [<ffffffc000e413f8>] gr_gp10b_init_fs_state+0x5c0/0x5d8 [ 50.101687] [<ffffffc000d2ed30>] gk20a_init_gr_setup_hw+0x1b48/0x2418 [ 50.108115] [<ffffffc000d50bc0>] gk20a_init_gr_support+0x19e0/0x1ab0 [ 50.114457] [<ffffffc000cc7af8>] gk20a_pm_finalize_poweron+0xd20/0x1558 Fix this by adding below - allocate gr->map_tiles[] with size of (num_gpc * num_tpc_per_gpc) intead of num_gpc - add new static API gr_gk20a_get_map_tile_count() which returns tile count for given index, and returns 0 for out-of-bounds access Bug 200257557 Change-Id: If572837ffb661f92a21be5ce855d0146b2609cb0 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1279411 Reviewed-by: Konsta Holtta <kholtta@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Don't recursively #include gk20a.hTerje Bergstrom2017-01-05
| | | | | | | | | | | | | | | | | gk20a.h includes pmu_gk20a.h, which #includes gpmuifboardobj.h, which recursively #includes gk20a.h without needing anything from it. Remove the #include to improve built time. gpmuifboardobj.h also includes pmu_gk20a.h, when it actually needs a definition from pmu_common.h. Change the #include to prevent another recursive #include. Bug 200192125 Change-Id: Idb8c13bceeae1a60a4efa466c07e78cb15ffa1fb Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1280348 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: free boardobj if construct hits an errVijayakumar2017-01-05
| | | | | | | | | | | | | | | | | | | During construct of some VFE/CLK boardobjs, some data is filled after a boardobj allocation is done. Free up boardobj memory if an error is encountered in the data filling. Coverity ID 490171 Coverity ID 490172 Bug 200192125 Change-Id: I20621f7f9f9e379b8dced4905cd417c2ffa905b0 Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1280700 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add GPCCLK on ioctl APIThomas Fleury2017-01-05
| | | | | | | | | | | | | | | Internally we use GPC2CLK in the arbiter, but we should expose GPCCLK on kernel API and in user space. Added GPCCLK on the ioctl API. Arbiter uses GPC2CLK to make queries, then converts to GPCCLK. Jira DNVGPU-210 Change-Id: Id0b8134d0505c1f9bfd655a08e902bdcd03ebd96 Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: http://git-master/r/1280316 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Apply default pri timeout on all SKUsDavid Nieto2017-01-05
| | | | | | | | | | | | | | | Previous patch added ability so set default PRI timeout and set it for one of the dGPU boards. Set the timeout to all known dGPU boards. Bug 200246808 Change-Id: I645ca8b4a51d61c924a9f52b1fc6e884795adf19 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1264304 Reviewed-on: http://git-master/r/1280436 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: return error on pmu_ucode_details() failureDeepak Nibade2017-01-05
| | | | | | | | | | | | | | | | | | | | | | In lsfm_discover_ucode_images(), we currently collect pmu ucode details with API pmu_ucode_details() But if this API fails, we still continue loading other firmwares In case loading of pmu firmware fails due to some reason, we should actually bail out immediately with error Also, remove unnecessary chekc (ucode_img.lsf_desc != NULL) since pmu_ucode_details() ensures that this cannot be NULL Bug 200265373 Change-Id: I68e7f9575e2a07b473ceacc528a5d172b58d6fb6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1276555 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Implement SET_RD_COALESCETerje Bergstrom2017-01-05
| | | | | | | | | | | | | Implement SW method SET_RD_COALESCE to implement correct handling of texture read coalescing. Bug 200223870 Change-Id: Icd6f987b72d78e5add4076fc550e2070eba70628 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1271303 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: remove default verbose in pbus isrDavid Nieto2017-01-04
| | | | | | | | | | | | | | And reduce pri timeout to match PCIE specs bug 200246808 Change-Id: I0225ae964b5635665fe774c43f773d0ce86650ab Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1264179 (cherry picked from commit 1c3dbf8324b7ec5d06bd0e57e7deee9a1c8e9411) Reviewed-on: http://git-master/r/1280328 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Implement permanent disable_aspmAlex Waterman2017-01-04
| | | | | | | | | | | | | | Implement the permanent disable_aspm() function for XVE on gp106. Bug 200256272 Change-Id: I63338415542381d8a43d746d9d4404a74a5f01cd Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1263273 (cherry picked from commit 7890419f242a50c6d8ec27c3e8eb331823230ed9) Reviewed-on: http://git-master/r/1280309 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Disable ASPM for PCI platformsAlex Waterman2017-01-04
| | | | | | | | | | | | | | Disable ASPM on boot for PCIe platforms. Bug 200256272 Change-Id: I0dc63c1a5a9941a5ecdc6a5d691c0b780fb9a6b5 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1263272 (cherry picked from commit bf576ea8a88326d107b3a91d196fe6d6018185f6) Reviewed-on: http://git-master/r/1274478 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add platform flag to disable ASPMAlex Waterman2017-01-04
| | | | | | | | | | | | | | | Add a platform flag and logic to disable ASPM on boot if a platform does not want ASPM enabled. Bug 200256272 Change-Id: I378997290377ef8ffa21bf8e7f3f59fa134b3d4d Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1263271 (cherry picked from commit 01e4700b74f4b4c6f0b9ffb40747653f2b63ea3c) Reviewed-on: http://git-master/r/1274477 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Handle driver shutdown more gracefullyAlex Waterman2017-01-04
| | | | | | | | | | | | | | | | | | | | | | | | Handle possible asynchronous GPU driver shutdown more gracefully. This occurs when the GPU disappears from the PCI bus, for example, if it overheats or detects an over current event. Also add a preprocessor check to make sure that the gk20a_channel_cancel_pending_sema_waits() is always defined. In some builds CONFIG_SYNC is disabled but the gk20a_remove_support() code does not check for this. Bug 1816516 Bug 1807277 Change-Id: I932e312291c5c6a6ac5e13525ce8ca56a1be3652 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250028 (cherry picked from commit 337810f8c478238a38d8553c1492622d5fa9aafa) Reviewed-on: http://git-master/r/1274476 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Move deferred interrupt wait codeAlex Waterman2017-01-04
| | | | | | | | | | | | | | | | | Move the code that waits for deferred interrupts to nvgpu_common.c and make it global. Also rename that function to use nvgpu_ as the function prefix. Bug 1816516 Bug 1807277 Change-Id: I42c4982ea853af5489051534219bfe8b253c2784 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250027 (cherry picked from commit cb6fb03e20b08e5c3606ae8a5a9c237bfdf9e7da) Reviewed-on: http://git-master/r/1274475 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Misc fixes for crashes on shutdownAlex Waterman2017-01-04
| | | | | | | | | | | | | | | | | | | | Fix miscellaneous issues seen during driver shutdown. o Make sure pointers are valid before accessing them. o Busy the GPU during channel timeout. o Cancel delayed work on channels. o Avoid access to channels that may have been freed. Bug 1816516 Bug 1807277 Change-Id: I62df40373fdfb1c4a011364e8c435176a08a7a96 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250026 (cherry picked from commit 64a95fc96c8ef7c5af9c53c4bb3402626e0d2f60) Reviewed-on: http://git-master/r/1274474 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Handle no GPU cases in helper funcsAlex Waterman2017-01-04
| | | | | | | | | | | | | | | | | | | | | | | | | | In many helper functions like gk20a_readl() the code assumed that the GPU is present and registers and available. However, during GPU shutdown this may not be the case. In theory the driver should not be accessing GPU registers during GPU shutdown (since shutdown is triggered by GPU registers being unavailable) but these changes handle any missed cases where this may happen. This goes for GPU device access as well. Many parts of the code assume that if the struct gk20a is valid, the the GPU dev must be there are well. This isn't always the case, it seems. Bug 1816516 Bug 1807277 Change-Id: Icaf6fd56ab7860724e77bda0f5e8d48f0da15642 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250024 (cherry picked from commit e8c9997b2d7cd424d798ecfce1307e6193c0cf32) Reviewed-on: http://git-master/r/1274473 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: FECS trace support on gp106Thomas Fleury2017-01-04
| | | | | | | | | | | | | Enable FECS ctxsw tracing for gp106. Ensure that FECS records have been written to memory before accessing the ring. Update read index only once all records have been processed. Jira EVLR-424 Change-Id: I1a21f841fcce1588397408906d77e2c3bf4a8c01 Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: http://git-master/r/1258243 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Free arb substructures only if arb allocatedTerje Bergstrom2017-01-04
| | | | | | | | | | | | | nvgpu_clk_arb_init_arbiter() allocates master structure arb, and sub-structures which is assigns as members of arb. At failure, there's a single error label, and it tries to free the members of arb without checking that arb was allocated. Change-Id: Ifac7552b05dad17036835eb3ee624eae351ccb7d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1279226 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Fix memory leak in arb installTerje Bergstrom2017-01-04
| | | | | | | | | | | nvgpu_clk_arb_install_fd() leaks dev if it cannot create an fd, and it leaks both dev and fd if it fails to create a file. Change-Id: I65c03401dba44d88be543d3aec2fa3fcd2fb0dcc Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1279225 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Include correct boardobjgrp headersTerje Bergstrom2017-01-04
| | | | | | | | | | | clk_prog.h and clk_vin.h refer to boardobjgrp_e32 and boardobjgrp_e255.h. Add explicit #includes for their definition. Change-Id: Ib651b071f3c17bbc30ddaea0ef9bc5437ec9f2f4 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1279224 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Use perf table only VBIOS supports itTerje Bergstrom2017-01-04
| | | | | | | | | | | | | | | We retrieve perf table from VBIOS only if respective HAL op is implemented. Later in code we unconditionally dereference the pointer which can lead to NULL pointer access. Fix by early aborting creation of devinit tables if the perf VBIOS getter is missing. Change-Id: If48aa6dac724056dd1feb2ef520e343736d4db85 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1279223 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Check reference clock before useTerje Bergstrom2017-01-04
| | | | | | | | | | | We use GPU reference clock as a divider. Check before division that reference clock is not zero. Change-Id: Ie453a78b422b2e740daeb7c12ce5b06faa52ba76 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275743 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Do not dereference NULL wait_cmdTerje Bergstrom2017-01-04
| | | | | | | | | | | | | | | | | In gk20a_submit_prepare_syncs(), after we have allocated wait_cmd we check the results. If we failed to allocate wait_cmd, we still jump to the error label that tries to free wait_cmd. Create an own error labal for allocation before wait_cmd, and use that if we fail to allocate wait_cmd. Similarly create an error label for incr_cmd, and use that only once incr_cmd has actually been allocated. Change-Id: I1f8bc1d947c524038f5f237358a5e6b0dc2e6ac3 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275742 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Check for NULL in job allocationTerje Bergstrom2017-01-04
| | | | | | | | | | | | | | When allocating job channel_gk20a_job structure we assign the result of allocation to *job_out, but we check the result of allocation in job_out. Change the check to check for result in *job_out. Change-Id: Ia170cfa2dd5730665434b4c223c5a2f9502c744d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275741 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Release VBIOS firmware if alloc failsTerje Bergstrom2017-01-04
| | | | | | | | | | | | | | We first load VBIOS firmware from file, and then attempt to allocate space into which we copy the data. If allocation fails, we do not release the firmware. Add a release_firmware() in the error path. Change-Id: Iaa995e93bf8d5a23e08c5e332f70b203ac2e09db Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275740 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Recursive inclusion of boardobjgrp_*.hTerje Bergstrom2017-01-04
| | | | | | | | | | | | | boardobjgrp.h #includes boardobjgrp_e32.h and boardobjgrp_e255.h. They in turn #include back boardobjgrp.h. Remove recursion. Change-Id: Ic0eb8ddf3ddd3996302fe2b74d9e3ff8e395b1b7 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275739 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Fix NULL check for boardobj allocationTerje Bergstrom2017-01-04
| | | | | | | | | | | | | | When we allocate boardobj object, we assign the allocated address to *ppboardobj. The check for result of allocation checks looks at address in ppboardobj. Fix the check so that it actually checks results of kzalloc(). Change-Id: I90fda36afd1627efcf2fdea46bcd7ad1a7e3bb51 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1275738 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: Cast det_out to u64 for 64-bit calcTerje Bergstrom2017-01-04
| | | | | | | | | | | voltage_get() defines det_out as u32. That variable is used to calculate a 64-bit result, so cast det_out to u64. Change-Id: I054ec299a4c7961cb38dd5ac0cbf0ac173b09efb Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1267692 GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
* gpu: nvgpu: fix out-of-bound access on gr->gpc_tpc_countDeepak Nibade2017-01-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix slab-out-of-bounds issue reported by KASAN [ 29.922710] BUG: KASAN: slab-out-of-bounds in gr_gk20a_init_fs_state+0x1bc/0x898 at addr ffffffc1a0988c04 ... [ 29.961820] INFO: Allocated in gr_gk20a_init_gr_config+0x380/0x1b20 age=374 cpu=5 pid=1 ... Out-of-bound access from [ 30.241943] [<ffffffc0007d2674>] gr_gk20a_init_fs_state+0x1bc/0x898 [ 30.248205] [<ffffffc000839a2c>] gr_gm20b_init_fs_state+0x4c/0x5c8 [ 30.254381] [<ffffffc000871670>] gr_gp10b_init_fs_state+0x160/0x3a8 [ 30.260643] [<ffffffc0007d70ec>] gk20a_init_gr_setup_hw+0x974/0x1530 [ 30.266991] [<ffffffc0007eac6c>] gk20a_init_gr_support+0x14c/0xeb0 [ 30.273164] [<ffffffc00079d9c8>] gk20a_pm_finalize_poweron+0x738/0xd10 [ 30.279684] [<ffffffc00079dfd0>] gk20a_pm_runtime_resume+0x30/0x58 Fix this by using a separate API gr_gk20a_get_tpc_count() which returns tpc count for a gpc and returns 0 if gpc index is greater than available gpcs Bug 200257557 Change-Id: I78856ca93c0381cb4bcef7a56a5210fa269cf3ac Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1277692 GVS: Gerrit_Virtual_Submit Reviewed-by: Sami Kiminki <skiminki@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: compile local t18x codeDeepak Nibade2016-12-28
| | | | | | | | | | | | | | | | | Compile local t18x code from nvgpu repo (in case CONFIG_ARCH_TEGRA_18x_SOC config is set) instead of compiling from $(srctree)/../nvgpu-t18x Remove Makefile.nvgpu-t18x since this Makefile is not needed now Bug 200266498 Change-Id: Ib8ef39be7e948debe0ff895c904a6c370a5711a6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1277119 Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: skip setting preemption modes if already setDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | In gr_gp10b_set_preemption_mode(), skip setting anything if both graphics and compute preemption modes are already set Bug 200263471 Change-Id: I2788464750835da8f6396c6c1ca8356a63758c80 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1275465 GVS: Gerrit_Virtual_Submit Reviewed-by: Lakshmanan M <lm@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: PG statistics updateMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | - PG statistics read support for multiple engines JIRA DNVGPU-71 Change-Id: I2dc3aad243300d21dc3d20a54a5e4736977e071b Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1250507 (cherry picked from commit 985cb3be1d6d990bc6651e417d9e6ba9bfe306e0) Reviewed-on: http://git-master/r/1270991 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: MSCG supportMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | - update gp106 pg engine init/list/features HALs to support MS engine - Added defines & interface for lpwr tables read from vbios. - lpwr module which reads idx/gr/ms table from vbios to map rppg/mscg support with respective p-state - lpwr module public functions to control lpwr features enable/disable mscg/rppg & mclk-change request whenever change in mclk-change parameters - lpwr public functions to know rppg/mscg support for requested pstate, - added mutex t prevent PG transition while arbiter executes pstate transition - nvgpu_clk_arb_get_current_pstate() of clk arbiter to get current pstate JIRA DNVGPU-71 Change-Id: Ifcd640cc19ef630be1e2a9ba07ec84023d8202a0 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247553 (cherry picked from commit 8a441dea2410e1b5196ef24e56a7768b6980e46b) Reviewed-on: http://git-master/r/1270989 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: RPPG supportMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | | | | - Added rppg module to init GR/MS-RPPG. mscg is dependent on gr-rppg & without gr-rppg engage mscg does not engage. - Update pg engines HAL to return supported pg engines & its sub features JIRA DNVGPU-71 Change-Id: Ib0fd2d79b509f6f2f1dabae6e2b5aebcc80b5691 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247486 (cherry picked from commit 86e45fa62e6a6b295f73c0173f0117ae9f78a5e9) Reviewed-on: http://git-master/r/1270762 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: no support for sparse mappingAparna Das2016-12-27
| | | | | | | | | | | | | | | | | | | | | | Currently sparse mapping is not supported for gp10b in virtualized environment. Modify gpu characteristics to reflect non-implementation of this functionality. Also fix return value in vgpu_gp10b_locked_gmmu_map() on error condition. Bug 200243373 Change-Id: Ia367b923b87738a5cad0617cdb074f5a24fb1c81 Signed-off-by: Aparna Das <aparnad@nvidia.com> Reviewed-on: http://git-master/r/1269710 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> Reviewed-by: Sachit Kadle <skadle@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vladislav Buzov <vbuzov@nvidia.com>
* gpu: nvgpu: fix CLFC arbiter vf table updateDavid Nieto2016-12-27
| | | | | | | | | | | | | | | | | | | (1) Adding additional debug in case of VF update failure (2) The length of the tables must be re-initialized prior to requesting the vf table update JIRA: DNVGPU-193 Change-Id: Id5a369359bc5f52ee58da539bfc3ec1ec7887de1 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1252061 (cherry picked from commit dfb6fec02f8e3ff6a22bbea000347923b0306018) Reviewed-on: http://git-master/r/1274547 Reviewed-by: Automatic_Commit_Validation_User Tested-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: arb: fix rounding in effective clocksDavid Nieto2016-12-27
| | | | | | | | | | | | | | | | | | Current code cast casting the frequency to 16 bit before division, giving out incorrect data JIRA DNVGPU-164 Change-Id: I4eb1fa73fb9e8963f550d3d853db39b49b990fa4 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1251663 (cherry picked from commit c0d91a054f8278af9a2383bb3f837465779132a9) Reviewed-on: http://git-master/r/1274546 Reviewed-by: Automatic_Commit_Validation_User Tested-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: cap minimum gpc clocks to HW limitsDavid Nieto2016-12-27
| | | | | | | | | | | | | | | JIRA: DNVGPU-180 Change-Id: I1928e77cea4ac87bf2ba2b6b7b2f2942dfb97de9 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1251493 (cherry picked from commit 7b8a105652a3169d9ec0cb7ce52c3b92e42ca310) Reviewed-on: http://git-master/r/1274545 Reviewed-by: Automatic_Commit_Validation_User Tested-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: use common API to write TPC fusesDeepak Nibade2016-12-27
| | | | | | | | | | | | | Use common fuse write API tegra_fuse_control_write which should work on all kernel versions Bug 200262155 Change-Id: I29e8514e9660549ecf94711287ec4bbf4c897a86 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1270169 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: allow upgrading preemption modesDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | | | | We currently do not allow resetting preemption modes once set Relax this check to allow upgrading preemption modes. Downgrading of preemption modes is still not allowed Bug 200263471 Change-Id: Ie2dae910028929090899a661f4b8b9dd4d6d7ee7 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1269472 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: call set volt always during vf switchVijayakumar2016-12-27
| | | | | | | | | | | | | | | | | bug 1845211 clfc is reset during vf switch. it resets delta values stored in pmu structure. if voltage has not changed, delta calculation happens on top of corrected voltage causing volt to keep on increasing in cases where voltage does not change during a vf switch. Change-Id: I9d1a58b6b7652f22c3a7304162bb8ca6f7d1da6f Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1266632 (cherry picked from commit 74e2e97d4d149d3eac65b5f65b358b977fba463e) Reviewed-on: http://git-master/r/1273911 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: actions before and after vf changeVijayakumar2016-12-27
| | | | | | | | | | | | | | | | | | | JIRA DNVGPU-175 1)Add functions to be called before and after vf change 2)Capture noise unaware vmin value and pass it as param to vf change functions 3)Before VF change disable CLFC and update noise unware vmin 4)After VF change is done enable CLFC Change-Id: I4bb59fbe96ec5a792e8930db3ab4a39ec74c9a71 Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1248211 (cherry picked from commit cf07892204d7ce11a0d27ecbc1f5826fbabbde61) Reviewed-on: http://git-master/r/1270950 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: keep sec2 idleMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | | | | | sec2 falcon reset after secure boot complete to keep sec2 idle issue: ELPG does not engage if PG engine is dependent on sec2 idleness JIRA DNVGPU-71 Change-Id: If264c610dae857ae9b9f9bc77c59f24f239ce1ce Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247290 (cherry-picked from commit de2337de1211e4167993982e50237fe1115053a1) Reviewed-on: http://git-master/r/1267260 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: pstate interface updateMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | lpwr_entry_idx member is required to map pstate with lwpr tables JIRA DNVGPU-71 Change-Id: I4cad54c61dec7ad7e3c1a60178938d0eeaf65e24 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247303 (cherry-picked from commit b1f6e0036922d2104b3d08548219e72a38f2e231) Reviewed-on: http://git-master/r/1267403 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: update pg engine init/list/features HALMahantesh Kumbar2016-12-27
| | | | | | | | | | | | | | | | | - Updated gp10b_pg_gr_init() to post init param based on PG engine parameter - Assigned pg engine list/features HAL to respective functions/NULL JIRA DNVGPU-71 Change-Id: I7d059796746694b22800c6ae0327cbc90331e929 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247407 (cherry-picked from commit aee4e565ca2b475c0680674e4e6345b3b30cc502) Reviewed-on: http://git-master/r/1269321 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-11-06 02:03:25 -0500