summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/nvgpu
Commit message (Collapse)AuthorAge
* gpu: nvgpu: gp10b: Change order of alpha & betaTerje Bergstrom2016-12-27
| | | | | | | | | Change order of alpha & attribute buffers in CB. The new order follows RM. Change-Id: I2b24daa46055b3bd667a1026c282f74d56882623 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/657907
* gpu: nvgpu: gp10b: Program CB sizesTerje Bergstrom2016-12-27
| | | | | | | | | | | Program CB sizes. Bug 1567274 Change-Id: Idc88f69b70e85bf950af852a9ca80a328d95883f Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/654097 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: gp10b: Implement SW methodsTerje Bergstrom2016-12-27
| | | | | | | | Bug 1567274 Change-Id: I6d760eca7ac0931847f9a04a9d4a408519ade511 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/654098
* gpu: nvgpu: gp10b: Calc global context buffer sizeTerje Bergstrom2016-12-27
| | | | | | | | | | In gp10b we need to limit global context buffer size, and it needs to be 128b aligned. Change-Id: I51570e2457a374c09be4d611e683ae30917f9fc0 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/657911 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: gp10b: Add new supported kindTerje Bergstrom2016-12-27
| | | | | | | | | Bug 1567274 Change-Id: I38c3ffd6129893b02f6bef878a579925cf2bfa1e Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/606931 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: gp10b: Define pagepool sizeTerje Bergstrom2016-12-27
| | | | | | | | | Bug 1567274 Change-Id: I4369458d3af0c4da32af8a5881c8fe60b11f7632 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/606932 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: gp10b: Define physical address widthTerje Bergstrom2016-12-27
| | | | | | | | | | | | GP10B physical address width is 37 bits. Use old width for now, and add gp10b specific definition. We can switch to new definition once we've verified them. Bug 1567274 Change-Id: I33cc1b99f14f1a7ee5f6fe3bd3d8b3126c23ecbe Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/601703
* gpu: nvgpu: Write ZBC registers to DSSTerje Bergstrom2016-12-27
| | | | | | | | Bug 1567274 Change-Id: Ife98ae512c62bd26450e59338719c7a10635b5dd Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/601108
* gpu: nvgpu: Define gp10b big page sizeTerje Bergstrom2016-12-27
| | | | | | | | | | Set default big page size of 128kB. Bug 1567274 Change-Id: Ie27c6ffa23b8d75ebd21afca267068604fb57f0b Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/603498
* gpu: nvgpu: Add SM registersTerje Bergstrom2016-12-27
| | | | | | | | | | | | Add SM registers which were taken into use in GPU characteristics. Bug 1551769 Bug 1558186 Change-Id: I705da9ac25556b6b94137199e0acd9af3c8e6422 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/601020
* gpu: nvgpu: Use queried interrupt idsTerje Bergstrom2016-12-27
| | | | | | | Change-Id: I258b54447d09b32adc076de50997d792f0567af5 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/601019 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: gp10b: Implement L2 queryTerje Bergstrom2016-12-27
| | | | | | | | | Bug 1567274 Change-Id: I0b8eaebc0949e70f6d8bfbb101048a3d95bec5e3 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/602858 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: headers for linsim CL 33823014Adeel Raza2016-12-27
| | | | | | | | | Change-Id: I1b9172f0afa0391ce6289aa24dc1a993c723c90e Signed-off-by: Adeel Raza <araza@nvidia.com> Reviewed-on: http://git-master/r/594681 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gp10b: Enable interrupts in linsimTerje Bergstrom2016-12-27
| | | | | | | Change-Id: I7d4211743793b905a20080bb44c62c036f23c854 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/592336 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: gp10b: Fill class numbersTerje Bergstrom2016-12-27
| | | | | | | | | | | Fill class numbers to characteristics structure. Bug 1567274 Change-Id: I129e79fa3f850899ae0c7d93704dc4786ad514d9 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/594404 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: Add own platform data to enable host1xTerje Bergstrom2016-12-27
| | | | | | | | | | | Add gp10b platform data to enable sync point support. Bug 1572701 Change-Id: Iaf03ecb8fb6b8bf4bb824e2a012c80dfe3f4fcae Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/592099 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: gp10b: Add SM debug registersTerje Bergstrom2016-12-27
| | | | | | | | | | Add SM debug registers to gp10b, and regenerate headers. Bug 1567274 Change-Id: Ifcfa65a6fbf16e89023caa5aaf4ae3a7846df749 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/592646
* gpu: nvgpu: gp10b specific CB callbacksTerje Bergstrom2016-12-27
| | | | | | | | | Bug 1570662 Change-Id: Icb7e90b1216acfd19bb3027dc9e9844eb08c99d9 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/592101 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Implement gp10b intr processingTerje Bergstrom2016-12-27
| | | | | | | | | | Bug 1567274 Change-Id: I2a6cef954b56d1f97208d29584e0748ec1c5e29d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/591628 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: t18x, gp10b frameworkKenneth Adams2016-12-27
| | | | | | | | | | | This change adds gp10b to the nvgpu build as well as enabling CMA for buffer allocation. Change-Id: Id3d45ad6ffdab14120395952e68b285dd7364c76 Signed-off-by: Ken Adams <kadams@nvidia.com> Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/553324 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Synchronize gp10b headers with gm20bTerje Bergstrom2016-12-27
| | | | | | | | | | | | Added all registers added to gk20a and gm20b to gp10b. Remove gp10b trim registers, because they will not be accessed by CPU. Bug 1567274 Change-Id: Ib6be34ce3d55901bd7e1f30eea8e43725719a912 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/590312 GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: headers for linsim CL 33759297Adeel Raza2016-12-27
| | | | | Change-Id: Iaafb651875481b7fa31504642df86311ec9933a5 Signed-off-by: Adeel Raza <araza@nvidia.com>
* gpu: nvgpu: headers for linsim CL 33688874Adeel Raza2016-12-27
| | | | | | | | | | Bug 1561645 Change-Id: Iccd909d54fc5b1d1c8fbc903b5908bf6f7f22ec8 Signed-off-by: Adeel Raza <araza@nvidia.com> Reviewed-on: http://git-master/r/553151 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Alexander Van Brunt <avanbrunt@nvidia.com>
* gpu: nvgpu: gp10b headersKen Adams2016-12-27
| | | | | | | | first cut. just to get started... Change-Id: I3682909f9ac0a5395ec834046789356f53d0c47d Signed-off-by: Ken Adams <kadams@nvidia.com> Reviewed-on: http://git-master/r/447753
* gpu: nvgpu: acquire mutex for notifier readDeepak Nibade2016-12-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We use &ch->error_notifier_mutex to protect writes and free of error notifier But we currently do not protect reading of notifier in gk20a_fifo_set_ctx_mmu_error() and vgpu_fifo_set_ctx_mmu_error() Add new API gk20a_set_error_notifier_locked() which is same as gk20a_set_error_notifier() but without the locks. In *_fifo_set_ctx_mmu_error() APIs, acquire the mutex explicitly, and then use this new API gk20a_set_error_notifier() will now just call gk20a_set_error_notifier_locked() within a mutex Bug 1824788 Bug 1844312 Change-Id: I1f3831dc63fe1daa761b2e17e4de3c155f505d6f Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1273471 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Richard Zhao <rizhao@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: set driver unload flag in shutdownDeepak Nibade2016-12-27
| | | | | | | | | | | | | | Call gk20a_driver_start_unload() in the beginning of gk20a_pm_shutdown() so that we prevent new calls to gk20a_busy() Bug 200265373 Change-Id: I240cab4b505be4928341ab3deb13f37241d27aeb Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1275486 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: gk20a: Allow regops lists longer than 128Sami Kiminki2016-12-26
| | | | | | | | | | | | | | | | Process long regops lists in 4-kB fragments, overcoming the overly low limit of 128 reg ops per IOCTL call. Bump the list limit to 1024 and report the limit in GPU characteristics. Bug 200248726 Change-Id: I3ad49139409f32aea8b1226d6562e88edccc8053 Signed-off-by: Sami Kiminki <skiminki@nvidia.com> Reviewed-on: http://git-master/r/1253716 (cherry picked from commit 22314619b28f52610cb8769cd4c3f9eb01904eab) Reviewed-on: http://git-master/r/1266652 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: PG statistics updateMahantesh Kumbar2016-12-26
| | | | | | | | | | | | | | | | | | | | - PG statistics read support for multiple engines - updated stat_dmem_offset member to array to hold dmem offset of PG engines - PMU allocates memory in DMEM for each PG engine requested, updated gk20a_pmu_get_elpg_residency_gating() to get engine statistics for requested PG engine JIRA DNVGPU-71 Change-Id: I2ddade37f85716f757bf33034dbff816184577eb Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1250506 (cherry picked from commit 68ba7a97d6662b87d0e489365d8afb8e2d237a03) Reviewed-on: http://git-master/r/1270972 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: MSCG supportMahantesh Kumbar2016-12-26
| | | | | | | | | | | | | | | | | | | | | | | | | - Added enable_mscg, mscg_enabled & mscg_stat flags, mscg_enabled flag can be used to controll mscg enable/disable at runtime along with mscg_stat flag. - Added defines & interface to support ms/mclk-change/post-init-param - Added defines for lpwr tables read from vbios. - HAL to support post init param which is require to setup clockgating interface in PMU & interfaces used during mscg state machine. - gk20a_pmu_pg_global_enable() can be called when pg support required to enable/disable, this also checks & wait if pstate switch is in progress till it complets - pg_mutex to protect PG-RPPG/MSCG enable/disable JIRA DNVGPU-71 Change-Id: If312cefc888a4de0a5c96898baeaac1a76e53e46 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247554 (cherry picked from commit e6c94948b8058ba642ea56677ad798fc56b8a28a) Reviewed-on: http://git-master/r/1270971 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: rppg supportMahantesh Kumbar2016-12-26
| | | | | | | | | | | | | | | Add defines and interface structures used for sending PMU messages to control RPPG. JIRA DNVGPU-71 Change-Id: Ibec975f3c976619542d8f088b24271796a03f03c Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247487 (cherry picked from commit dd3826abca0a51d473d5d9cb25dc84cada9e7878) Reviewed-on: http://git-master/r/1270793 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: make preemption modes unsignedDeepak Nibade2016-12-21
| | | | | | | | | | | | | | | | | | | | graphics and compute preemption modes are currently defined as int But it is more logical to have them as unsigned int Also, we treat preemption modes as unsigned almost everywhere in the code Fix prints in gk20a_fifo_sched_debugfs_seq_show() to print U32_MAX with %d which is same as printing -1 Bug 200263471 Change-Id: Iabd0ee3923b76d81620898e90a9b1fc5dd75b530 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1272514 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: define common API to write fusesDeepak Nibade2016-12-21
| | | | | | | | | | | | | | | | | | | | | | | We use tegra_fuse_control_write() on k4.4 and tegra_fuse_writel() on previous versions But gr_gm20b_set_gpc_tpc_mask() currently broken since we use tegra_fuse_writel() always to update fuses Hence define tegra_fuse_control_write() on previous kernel versions as well and use it everywhere Bug 200262155 Change-Id: I116ed77d24018dae21884344373c9eaa1750c2bd Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1270168 Reviewed-by: Laxman Dewangan <ldewangan@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove clk writel from TPC FSDeepak Nibade2016-12-21
| | | | | | | | | | | | | | | | | | | | To floorsweep any TPC on gm20b, we first have to set BIT(28) in CLK_RST_CONTROLLER_MISC_CLK_ENB_0 from nvgpu driver But now this bit is set by default from clock driver, hence remove clk_writel() from nvgpu driver Bug 200262155 Change-Id: I65bc60cb017109bdb882d83637f2a06d27586f18 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1265752 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Laxman Dewangan <ldewangan@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix round_rate ops for CCFSrikar Srimath Tirumala2016-12-21
| | | | | | | | | | | | | | | | | Make round_rate return max freq when called with a value greater than the max clock frequency. Bug 200233943 Change-Id: Id128611f2d09b17a0a0edfefd4b526fd8c215bce Signed-off-by: Srikar Srimath Tirumala <srikars@nvidia.com> Reviewed-on: http://git-master/r/1272305 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Jonathan Hunter <jonathanh@nvidia.com> Tested-by: Jonathan Hunter <jonathanh@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Peter De Schrijver <pdeschrijver@nvidia.com> Reviewed-by: Shreshtha Sahu <ssahu@nvidia.com>
* gpu: nvgpu: fix build breakSrikar Srimath Tirumala2016-12-20
| | | | | | | | | | | Fix the build break caused by "commit : I88d94542092f92e68dc63c40444a70991d1f6129" Change-Id: Id457c26b17ba8fc05e26fb5ad3b3a4873362b950 Signed-off-by: Srikar Srimath Tirumala <srikars@nvidia.com> Reviewed-on: http://git-master/r/1274496 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Tejal Kudav <tkudav@nvidia.com>
* gpu: nvgpu: Fix coverity defect in page allocatorAlex Waterman2016-12-20
| | | | | | | | | | | | | | | Fix use-after-free overity defect in page allocator. The alloc struct was getting used after a call for __gk20a_free_pages() which frees the alloc struct passed in. Coverity ID: 468942 Bug 200192125 Change-Id: I4f5d32f245efae967050f93c7806290b4bf3591c Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1272730 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix gpcclk for K4.4Srikar Srimath Tirumala2016-12-20
| | | | | | | | | | | | | | | Move the sw initialization of the gpcclk from gpu rail ungate path to the nvgpu probe path. This allows gpcclk to register itself successfully with CCF and makes it discoverable for other clients early on during boot. Bug 200233943 Bug 200259437 Change-Id: I88d94542092f92e68dc63c40444a70991d1f6129 Signed-off-by: Srikar Srimath Tirumala <srikars@nvidia.com> Reviewed-on: http://git-master/r/1265549 Reviewed-by: Tejal Kudav <tkudav@nvidia.com>
* gpu: nvgpu: gm20b pass correct clk to tegra_dvfsPeter Boonstoppel2016-12-20
| | | | | | | | | | | | | | | | | | | Restoring original behavior. Use gbus instead of gpu_ref clk as the argument to tegra_dvfs_get_fmax_at_vmin_safe_t(). Bug was introduced due to refactoring in 01e61860fafbc0ee045c2db931a79f6c0d5300aa, changing behavior when nvgpu is compiled with CONFIG_TEGRA_CLK_FRAMEWORK. Bug 200233943 Change-Id: Id2deec0107bd0c26a12feb511db22fc69e09a985 Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com> Reviewed-on: http://git-master/r/1269848 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Jonathan Hunter <jonathanh@nvidia.com> Tested-by: Jonathan Hunter <jonathanh@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Shreshtha Sahu <ssahu@nvidia.com>
* gpu: nvgpu: replace tsg list mutex with rwsemKonsta Holtta2016-12-20
| | | | | | | | | | | | | | Lock only for modifications to the tsg channel list, and allow multiple concurrent readers. Bug 1848834 Bug 1814773 Change-Id: Ie3938d4239cfe36a14211f4649ce72b7fc3e2fa4 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1269579 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: PG engines init/allow/disallow updateMahantesh Kumbar2016-12-20
| | | | | | | | | | | | | | | | | | | | | | | - pmu_init_powergating loops & init multiple PG engines based on PG engines supported - generalize pg init param HAL to support multiple PG-engine init based on PG engine parameter - HAL's to return supported PG engines on chip & its sub features of engine. - Send Allow/Disallow for PG engines which are enabled & supported. - Added defines for pg engines JIRA DNVGPU-71 Change-Id: I236601e092e519a269fcb17c7d1c523a4b51405f Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1247409 (cherry-picked from commit 1c138cc475bac7d3c3fbbd5fb18cfcb2e7fdf67a) Reviewed-on: http://git-master/r/1269319 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: copy data into channel context headerseshendra Gadagottu2016-12-20
| | | | | | | | | | | | | | If channel context has separate context header then copy required info into context header instead of main context header. JIRA GV11B-21 Change-Id: I5e0bdde132fb83956fd6ac473148ad4de498e830 Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1229243 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: rename timeout_check to timeout_expiredKonsta Holtta2016-12-19
| | | | | | | | | | | | | | Change "check" to "expired" in nvgpu_timeout_check* and append _expired to nvgpu_timeout_peek to clarify what the boolean-like return value means and thus avoid bugs. Bug 200260715 Change-Id: I47e097ee922e856005a79fa9e27eddb1c8d77f8b Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1269366 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: support noise unaware vmin pmu cmdVijayakumar2016-12-19
| | | | | | | | | | | | | | | | JIRA DNVGPU-184 Add structures and commands to send noise unware vmin value to pmu. This is needed to enable closed loop frequency controller support Change-Id: If2dfd5e76752a25765ba68821460b7fd2df23aed Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1248208 (cherry picked from commit fcd73e0f0bca755ea745f62b52b9e641bc3aa1ae) Reviewed-on: http://git-master/r/1267434 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: add clk freq controller supportVijayakumar2016-12-19
| | | | | | | | | | | | | | JIRA DNVGPU-127 Add pmu interface structure and command definitions Change-Id: I5bb84f47057094f55f3adf2c5755416f430aba89 Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1248207 (cherry picked from commit ad385eb3ce8ffb2d55ae312901c9dcc4e1543b14) Reviewed-on: http://git-master/r/1267433 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: Fix memory leaksAlex Waterman2016-12-19
| | | | | | | | | | | | | | | | Fix a memory leak introduced when making the priv struct for TSGs. Fix another memory leak when introducing a priv struct for channels. Bug 1816516 Change-Id: I7b0e62bb6352f7e65acb5501cab9cef055d1f535 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1266889 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove BUG_ON from _IOC_SIZE checksKonsta Holtta2016-12-19
| | | | | | | | | | | | | | When the user-supplied ioctl argument size is too large, just return -EINVAL from the ioctl instead of crashing on a BUG_ON (for as, ctrl, ctxsw, dbg and tsg nodes - channel and sched nodes are already okay). Bug 1849661 Change-Id: I5b0d1d0c4ee47ce0136c424dda5975353f110c7e Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1266606 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Store pending sema waitsAlex Waterman2016-12-19
| | | | | | | | | | | | | | | | | | | | | | | | | Store pending sema waits so that they can be explicitly handled when the driver dies. If the sema_wait is freed before the pending wait is either handled or canceled problems occur. Internally the sync_fence_wait_async() function uses the kernel timers. That uses a linked list of possible events. That means every so often the kernel iterates through this list. If the list node that is in the sync_fence_waiter struct is freed before it can be removed from the pending timers list then the kernel timers list can be corrupted. When the kernel then iterates through this list crashes and other related problems can happen. Bug 1816516 Bug 1807277 Change-Id: Iddc4be64583c19bfdd2d88b9098aafc6ae5c6475 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250025 (cherry picked from commit 01889e21bd31dbd7ee85313e98079138ed1d63be) Reviewed-on: http://git-master/r/1261920 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Close channels before freeing themAlex Waterman2016-12-19
| | | | | | | | | | | | | | | | Ensure that any open channel is definitely closed before freeing it. Bug 1816516 Bug 1807277 Change-Id: I7f100db5ab6834176ec97d22374646d3336f2856 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250023 (cherry picked from commit 56f1b4b4312c5900f1c27eba55ad970c4b264f24) Reviewed-on: http://git-master/r/1261919 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Allow channel free to be forcedAlex Waterman2016-12-19
| | | | | | | | | | | | | | | | | | Allow forced channel freeing. This is useful when the driver is being cleaned up and the gk20a_wait_until_counter_is_N() could potentially hang. Bug 1816516 Bug 1807277 Change-Id: I711f5f3f6413d0bb30b4857e785ca3b504b494ee Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1250022 (cherry picked from commit e132d0e5ae77d758680ac708622a4883bbd69ba3) Reviewed-on: http://git-master/r/1261918 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Reboot when GPU disappearsAlex Waterman2016-12-19
| | | | | | | | | | | | | | | | | Reboot the GPU when it disappears instead of just printing a warning message. Bug 1805082 Bug 1816516 Bug 1807277 Change-Id: Ifd23c7e6876d5ea86032a82b7181e31d54e877b5 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1260898 (cherry picked from commit 4fdc48c4e6dddf4299a49f387ac90404dd38950f) Reviewed-on: http://git-master/r/1261917 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>