summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/nvgpu/gv100
Commit message (Collapse)AuthorAge
* gpu: nvgpu: vgpu: fix tsg_unbind in recovery casePeter Daifuku2020-02-22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When unbinding a channel from a tsg when virtual, vgpu_tsg_unbind_channel would return an error if unbinding the channel on the guest side failed, and did so before notifying the RM server of the unbind. Later on in the recovery process, the guest OS would remove the channel from the TSG's list, but this would leave the RM server with an out-of-date channel list. Fix this by making the tsg_unbind_channel HAL optional and implemented only for vgpu: the vgpu version now just notifies the RM server so that it can clean up its version of the TSG; if vgpu, always call the tsg_unbind_channel HAL whether or not the local unbind succeeded. Minimal port from dev-main of https://git-master.nvidia.com/r/c/linux-nvgpu/+/2084029 Bug 2766920 Bug 200587845 Change-Id: I75bddf3a28ac20bf4fb7510ff64097a32c7eec3f Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2287774 (cherry picked from commit 471c72c1efcc4fe6d547f556edf7773827fd2674) Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2289928 Reviewed-by: Thomas Steinle <tsteinle@nvidia.com> Reviewed-by: Satish Arora <satisha@nvidia.com> Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: add SET_CTX_MMU_DEBUG_MODE ioctlThomas Fleury2020-01-30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Added NVGPU_DBG_GPU_IOCTL_SET_CTX_MMU_DEBUG_MODE ioctl to set MMU debug mode for a given context. Added gr.set_mmu_debug_mode HAL to change NV_PGPC_PRI_MMU_DEBUG_CTRL for a given channel. HAL implementation for native case is gm20b_gr_set_mmu_debug_mode. It internally uses regops, which directly writes to the register if the context is resident, or writes to gr context otherwise. Added NVGPU_SUPPORT_SET_CTX_MMU_DEBUG_MODE to enable the feature. NV_PGPC_PRI_MMU_DEBUG_CTRL has to be context switched in FECS ucode, so the feature is only enabled on TU104 for now. Bug 2515097 But 2713590 Change-Id: Ib4efaf06fc47a8539b4474f94c68c20ce225263f Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2110720 (cherry-picked from commit af2ccb811d3de06f052b1dee39bd9ffa863ac8ce) Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2208767 Reviewed-by: Kajetan Dutka <kdutka@nvidia.com> Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Winnie Hsu <whsu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit Tested-by: Kajetan Dutka <kdutka@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Enabling/disabling FECS trace supportseshendra2019-09-06
| | | | | | | | | | | | | | | | | | | - To enable FECS trace support, nvgpu should set the MSB of the read pointer (MAILBOX1). - The ucode will check if the feature is enabled/disabled before writing a record into the circular buffer. If the feature is disabled, it will not write the record. - If the feature is enabled and the buffer is not allocated, HW will throw a page fault error. Bug 2459186 Bug 200542611 Change-Id: I6f181643737d1cf1bda02077eaa714a3f4ef3d8c Signed-off-by: seshendra <sgadagottu@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2189250 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: gv100: support usermode submitKonsta Holtta2019-08-15
| | | | | | | | | | | | | | | | | | | | Use usermode_base HAL from gv11b and turn on NVGPU_SUPPORT_USERMODE_SUBMIT for gv100. Bug 200145225 Bug 200541476 Change-Id: I9f60a1fb07ae19ee9e0de9e28d56789fe282907f Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1924509 Signed-off-by: Debarshi Dutta <ddutta@nvidia.com> (cherry picked from commit a39d91b591d79827fc315218393b03365cc6e502 in dev-main) Reviewed-on: https://git-master.nvidia.com/r/2170622 GVS: Gerrit_Virtual_Submit Reviewed-by: Bibek Basu <bbasu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Use TPC_PG_MASK to powergate the TPCDivya Singhatwaria2019-08-02
| | | | | | | | | | | | | | | | | | | | | | | - In GV11B, read fuse_status_opt_tpc_gpc register to read which TPCs are floorswept. - The driver will also read sysfs node: tpc_pg_mask - Based on these two values "can_tpc_powergate" will be set to true or false and mask will be used to write to fuse_ctrl_opt_tpc_gpc register to powergate the TPC. - can_tpc_powergate = true indicates that the mask value sent from userspace is valid and can be used to power gate the desired TPC - can_tpc_powergate = false indicates that the mask value sent from userspace is not valid and cannot be used to power gate the desired TPC. Bug 200532639 Change-Id: Ib0806e4c96305a13b3574e8063ad8e16770aa7cd Signed-off-by: Divya Singhatwaria <dsinghatwari@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2159219 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: fecs ctxsw trace for gm20bDebarshi Dutta2019-05-14
| | | | | | | | | | | | | | | | | | Register gk20a non-arch-specific functions for gm20b gpu_ops.fecs_trace, Register nvgpu_os_linux_ops.fecs_trace.init_debugfs gp10b_fecs_trace_flush is now replaced by gm20b_fecs_trace_flush in fecs_trace_gm20b.* and the fecs_trace_gp10b.* files are removed. Bug 2052906 Change-Id: I245c91ae8e6015b87bafeb3ec023b98fe4c57501 Signed-off-by: Debarshi Dutta <ddutta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2115247 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: add hal to mask/unmask intr during teardownSeema Khowala2019-05-02
| | | | | | | | | | | | | | | | | | | | | | ctxsw timeout error prevents recovery as it can get triggered periodically. Disable ctxsw timeout interrupt to allow recovery. Bug 2092051 Bug 2429295 Bug 2484211 Bug 1890287 Change-Id: I47470e13968d8b26cdaf519b62fd510bc7ea05d9 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2019645 Signed-off-by: Debarshi Dutta <ddutta@nvidia.com> (cherry picked from commit 68c13e2f0447118d7391807c9b9269749d09a4ec in dev-kernel) Reviewed-on: https://git-master.nvidia.com/r/2024899 GVS: Gerrit_Virtual_Submit Reviewed-by: Bibek Basu <bbasu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: using pmu counters for load estimatePeng Liu2019-04-01
| | | | | | | | | | | | | | | | | | | | | | | | | | PMU counters #0 and #4 are used to count total cycles and busy cycles. These counts are used by podgov to estimate GPU load. PMU idle intr status register is used to monitor overflow. Overflow rarely occurs because frequency governor reads and resets the counters at a high cadence. When overflow occurs, 100% work load is reported to frequency governor. Bug 1963732 Change-Id: I046480ebde162e6eda24577932b96cfd91b77c69 Signed-off-by: Peng Liu <pengliu@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1939547 (cherry picked from commit 34df0035194e0203f68f679acdd84e5533a48149) Reviewed-on: https://git-master.nvidia.com/r/1979495 Reviewed-by: Aaron Tian <atian@nvidia.com> Tested-by: Aaron Tian <atian@nvidia.com> Reviewed-by: Rajkumar Kasirajan <rkasirajan@nvidia.com> Tested-by: Rajkumar Kasirajan <rkasirajan@nvidia.com> Reviewed-by: Bibek Basu <bbasu@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: HAL-ify pmm type broadcast valuesmatthewb2018-10-11
| | | | | | | | | | | | | | | | | | | | The PMM type-specific broadcast->unicast expansion calculation was using incorrect values. This caused the invalid register accesses to be generated. This change HAL-ifies the values, so that the expansion will be performed correctly. Bug 200454109 Change-Id: I96c15de27b5e16e4db2e788fd98e6bf7d6e7d564 Signed-off-by: Matthew Braun <matthewb@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1921717 GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove VPR HALs from dGPUsDeepak Nibade2018-09-29
| | | | | | | | | | | | | | | | | | | | gops.fb.dump_vpr_wpr_info() accesses both VPR and WPR registers. Split this into two different HALs gops.fb.dump_vpr_info() and gops.fb.dump_wpr_info() Also unset HALs accessing VPR registers on dGPUs We don't support VPR on dGPUs Remove fb_mmu_vpr_info_r() register and all its accessors from dGPU headers Bug 2173122 Change-Id: I5b2712f8c5389e422a84c375a7e836add48bfd1c Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1850947 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove big page setting on pascal+Deepak Nibade2018-09-29
| | | | | | | | | | | | | | | | | | | | | We don't support big page size beginning Pascal, so set HAL gops.fb.set_mmu_page_size() to NULL on all those platforms Also remove these accessors from corresponding platforms fb_mmu_ctrl_use_pdb_big_page_size_v() fb_mmu_ctrl_use_pdb_big_page_size_true_f() fb_mmu_ctrl_use_pdb_big_page_size_false_f() Bug 2173122 Change-Id: I7353412860a7a6f8a993ca9184a0dc3ca9d749af Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1850946 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add gv11b_gr_clear_sm_error_stateAnup Mahindre2018-09-27
| | | | | | | | | | | | | | | | | All chips were currently using gm20b_gr_clear_sm_error_state It was wrong for chips based on volta and later as the implementation didn't consider non pes-aware vsms mapping Add new HAL implementation for clear_sm_error_state for volta based and later chips to fix this. Bug 200448172 Change-Id: I65988c8cbb35d13089ac628e8333d9a3b58e0eb1 Signed-off-by: Anup Mahindre <amahindre@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1837188 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Move FB reset to MC unitTerje Bergstrom2018-09-27
| | | | | | | | | | | | FB reset is done by accessing MC register. Move the code to MC unit. JIRA NVGPU-954 Change-Id: I1636887af805f016da5490af65e808f9ac015cde Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1823385 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add MC APIs for reset masksTerje Bergstrom2018-09-27
| | | | | | | | | | | | | | Add API for querying reset mask corresponding to a unit. The reset masks need to be read from MC HW header, and we do not want all units to access Mc HW headers themselves. JIRA NVGPU-954 Change-Id: I49ebbd891569de634bfc71afcecc8cd2358805c0 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1823384 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Standardize HAS_SYNCPOINTs checkAlex Waterman2018-09-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Nvgpu uses many ways to check if sync points are enabled. The four ways used to be: platform->has_syncpoints g->has_syncpoints nvgpu_is_enabled(g, NVPGU_HAS_SYNCPOINTS) gk20a_platform_has_syncpoints() This patch standardizes all usage to now be nvgpu_has_syncpoints() which is based on gk20a_platform_has_syncpoints() - just renamed to be general to nvgpu. All usage of the other forms have now been consolidated. However, under the hood nvgpu_has_syncpoints() does check the is_enabled flag. This flag is now set where g->has_syncpoints used to be set based on the platform data. The basic dependency chain is this: nvgpu_has_syncpoints -> NVGPU_HAS_SYNCPOINTS -> platform->has_syncpoints However, note: there are several places where syncpoints can be disabled if some other driver initialization fails (for ex. host1x). Also note that nvgpu_has_syncpoints() also considers a disable variable set by debugfs. Bug 2327574 Change-Id: Ia2375a80f5f2e27285e6175568dd13e6bb25fd33 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1803975 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu:Add sysfs node for GV100 clocksabsalam2018-09-27
| | | | | | | | | | | | | | Creates sysfs nodes to read clk freq on GV100 Following sysfs nodes are created: gpcclk,xbarclk,sysclk Uses default clock source and counters for measurement Bug 200446261 Change-Id: I6903ba77fbe34e3f486f4b663e70eab4e7c5d662 Signed-off-by: absalam <absalam@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1828030 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: commonize errs in *get_litter_value()Philip Elcan2018-09-26
| | | | | | | | | | | | | | | | | | | | | | | No one is checking return values for the *get_litter_value() functions in the 100s of references, and some of the *get_litter_value() functions were already doing a BUG(), we'll just call BUG() in all them. And since we don't return in the error case, and there's no guarantee that an errno won't collide with the litter values, we'll just initialize the local ret value to 0 to avoid problems and confusion. JIRA NVGPU-647 Change-Id: Id974c904a142c4b3abf1ab940121c270208b0b83 Signed-off-by: Philip Elcan <pelcan@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1830582 GVS: Gerrit_Virtual_Submit Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Scott Long <scottl@nvidia.com> Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: fix return type of *get_litter_value()Philip Elcan2018-09-26
| | | | | | | | | | | | | | | | | | | | | | All callers for the *get_litter_value() functions were expecting u32, but the functions were declared to return int's. This is a violation of MISRA 10.3 which prohibits implicit assignment between essential types (signed int and unsigned long int, in this case). The litter values are all u32's anyway. JIRA NVGPU-647 Change-Id: I853d2abee372488e5d12e355050cbeaf1e53a42c Signed-off-by: Philip Elcan <pelcan@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1830581 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Scott Long <scottl@nvidia.com> Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: correct parameters in set_pmm_registerVaibhav Kachore2018-09-26
| | | | | | | | | | | | | | | - This patch corrects parameters in set_pmm_registers - As FBP 6 and 7 are floorswept for GV100, GPU_LIT_NUM_FBPS should not be used - halify get_num_hwpm_perfmon and set_pmm_register Bug 2106999 Change-Id: Ib285b25d0c836c93b529dfe4e26c078159a3e6dd Signed-off-by: Vaibhav Kachore <vkachore@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1785620 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: rename PMU perf unit to pmu_perfDeepak Nibade2018-09-25
| | | | | | | | | | | | | | | | Move all files under perf/* to pmu_perf/* since pmu_perf is logically appropriate name for PMU's perf unit Rename perf.c to pmu_perf.c Also rename the HAL from gops.perf to gops.pmu_perf Jira NVGPU-1102 Change-Id: I79e73b8b102ddf6b49783c2f38d861cd43b0b4c6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1819301 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: ACR load split feature supportMahantesh Kumbar2018-09-25
| | | | | | | | | | | | | | | | | | | | | | | -Added code to copy SEC2-RTOS ucode to non-wpr blob as part of prepare ucode blob. -Added code to setup & bootstrap GSP, as ACR-ASB needs ucode to execute on GSP falcon. -Defined LSF_FALCON_ID_GSPLITE for GSP falcon -Defined HSBIN_ACR_AHESASC_DBG/PROD_UCODE & HSBIN_ACR_ASB_DBG/PROD_UCODE to hold names of ACR AHESASC/ASB ucodes. -Added defines to hold name of SE2C RTOS ucodes JIRA NVGPUT-134 Change-Id: I824afed41f785a4ca0fb393bd023db5396c7a399 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1790179 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move header location of gk20a.hDebarshi Dutta2018-09-25
| | | | | | | | | | | | | | | | change the path of gk20a.h to <nvgpu/gk20a.h> for files in the following directories. gp106/ gv100/ Jira NVGPU-597 Change-Id: I098c12c34cdce764e6fca4ea1d16c5f8dee81026 Signed-off-by: Debarshi Dutta <ddutta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1836707 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: add GSP falcon supportMahantesh Kumbar2018-09-25
| | | | | | | | | | | | | | | | | | | | | | | | | - Defined FALCON_ID_GSPLITE for GSP falcon. - Created variable gsp_flcn of struct nvgpu_falcon for GSP falcon & registered to falcon module to access falcon functions. - Created HAL file gsp_gv100.c/h for GSP. - Modified Makefile & Makefile.sources files to include gsp_gv100 HAL file. - Enabled GSP falcon support for GV100 by registering to common falcon module. - Defined function gv100_gsp_reset() & assigned to falcon reset as GSP engine reset. - Updated falcon HAL init code not to return error if requested falcon is not supported, instead log the info and return non-error. JIRA NVGPU-1160 Change-Id: Ice032cf443ae87254375265628b3c022f41544cd Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1804551 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: read GPC mask from h/wDeepak Nibade2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | In gk20a_ctrl_ioctl_gpu_characteristics() we right now just calculate GPC mask in s/w and return to user space But this could give incorrect result as any GPC could be floorswept in h/w Add gops.fuse.fuse_status_opt_gpc() to read GPC floorsweep status from fuse Add gops.gr.get_gpc_mask() to get actual GPC mask from h/w Set these HALs only for dGPUs right now. Fuse register to read GPC mask is not yet supported in simulation and hence simulation boot fails These HALs will be set for iGPU once simulation issue is resolved Use gops.gr.get_gpc_mask() if it is defined in gk20a_ctrl_ioctl_gpu_characteristics() to send the actual GPC mask to user space Jira NVGPUT-132 Change-Id: I3b552de07883328fcfa41d4334ec0d777e04bdd3 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1822811 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: PMU init sequence changeMahantesh Kumbar2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | -Moved PMU RTOS init & start RTOS from acr_gm20b.c file pmu.c method nvgpu_init_pmu_support() -Modified nvgpu_init_pmu_support() to init required interface for PMU RTOS & does start PMU RTOS in secure & non-secure based on NVGPU_SEC_PRIVSECURITY flag. -Created secured_pmu_start ops under PMU ops to start PMU falcon in low secure mode. -Updated PMU ops update_lspmu_cmdline_args, setup_apertures & secured_pmu_start assignment for gp106 & gv100 to support modified PMU init sequence. -Removed duplicate PMU non-secure bootstrap code from multiple files & defined gm20b_ns_pmu_setup_hw_and_bootstrap()method to handle non secure PMU bootstrap, reused this method for need chips. JIRA NVGPU-1146 Change-Id: I3957da2936b3c4ea0c985e67802c847c38de7c89 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1818099 Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: ACR code refactorMahantesh Kumbar2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | -Created struct nvgpu_acr to hold acr module related member within single struct which are currently spread across multiple structs like nvgpu_pmu, pmu_ops & gk20a. -Created struct hs_flcn_bl struct to hold ACR HS bootloader specific members -Created struct hs_acr to hold ACR ucode specific members like bootloader data using struct hs_flcn_bl, acr type & falcon info on which ACR ucode need to run. -Created acr ops under struct nvgpu_acr to perform ACR specific operation, currently ACR ops were part PMU which caused to have always dependence on PMU even though ACR was not executing on PMU. -Added acr_remove_support ops which will be called as part of gk20a_remove_support() method, earlier acr cleanup was part of pmu remove_support method. -Created define for ACR types, -Ops acr_sw_init() function helps to set ACR properties statically for chip currently in execution & assign ops to point to needed functions as per chip. -Ops acr_sw_init execute at early as nvgpu_init_mm_support calls acr function to alloc blob space. -Created ops to fill bootloader descriptor & to patch WPR info to ACR uocde based on interfaces used to bootstrap ACR ucode. -Created function gm20b_bootstrap_hs_acr() function which is now common HAL for all chips to bootstrap ACR, earlier had 3 different function for gm20b/gp10b, gv11b & for all dgpu based on interface needed. -Removed duplicate code for falcon engine wherever common falcon code can be used. -Removed ACR code dependent on PMU & made changes to use from nvgpu_acr. JIRA NVGPU-1148 Change-Id: I39951d2fc9a0bb7ee6057e0fa06da78045d47590 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1813231 GVS: Gerrit_Virtual_Submit Reviewed-by: svc-misra-checker <svc-misra-checker@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>
* gpu:nvgpu: PMU cleanup for ACRMahantesh Kumbar2018-09-24
| | | | | | | | | | | | | | | | | | | | | - Removed ACR support code from PMU module - Deleted ACR related ops from pmu ops - Deleted assigning of ACR related ops using pmu ops during HAL init -Removed code related to ACR bootstrap & dependent code for all chips. JIRA NVGPU-1147 Change-Id: I47a851a6b67a9aacde863685537c34566f97dc8d Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1817990 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* Revert "gpu: nvgpu: refactor SET_SM_EXCEPTION_MASK ioctl"Konsta Holtta2018-09-21
| | | | | | | | | | | | | This reverts commit c5810a670d367ae1dc405fcc3108e11265df34bb. Bug 2400508 Jira VQRM-4806 Bug 200447406 Bug 2331747 Change-Id: Ie2a2c21f9285ff0349c7033fae24766a7117b462 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1837223
* gpu: nvgpu: refactor SET_SM_EXCEPTION_MASK ioctlaalex2018-09-21
| | | | | | | | | | | | | | | added hal layer for SM exception mask handling for taking care of vitualization case. Jira VQRM-4806 Bug 200447406 Bug 2331747 Change-Id: Ia44778a2e41c1a508c48026b8dee285966f1a544 Signed-off-by: aalex <aalex@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1816284 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu:nvgpu: Update number of LUT entriesVaikundanathan S2018-09-20
| | | | | | | | | | | | | | CTRL_CLK_LUT_NUM_ENTRIES to 128 And fix build issues that appeared with 128 entries. Bug 2331655 Change-Id: If116bff14be9a1923e075f783fdb9a2e992208b8 Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1810493 Reviewed-on: https://git-master.nvidia.com/r/1813861 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu:nvgpu: Add GV10x perf eventVaikundanathan S2018-09-20
| | | | | | | | | | | | | | | In case of VFE update, schedule work to set P0 clocks. Added function nvgpu_clk_set_fll_clk_gv10x to update P0 clocks on perf event. Fixed MISRA issues caused by this excluding external functions and MACROs Bug 2331655 Change-Id: Id96c473092ee7f0b651413aefdd4b6f2f59e0b12 Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1808014 Reviewed-on: https://git-master.nvidia.com/r/1813881 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove NVGPU_DBG_GPU_IOCTL_WRITE_SINGLE_SM_ERROR_STATE APIAnup Mahindre2018-09-19
| | | | | | | | | | | | Remove the API as it has no use cases. Bug 200445906 Change-Id: Ia2803bd05d78853963011a67091b34ba5bdb3732 Signed-off-by: Anup Mahindre <amahindre@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1817629 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* nvgpu: gv100: MISRA Rule 21.2 header guard fixessmadhavan2018-09-14
| | | | | | | | | | | | | | | | | | | | | | | MISRA rule 21.2 doesn't allow the use of macro names which start with an underscore. These leading underscores are to be removed from the macro names. This patch will fix such violations in gv100 by renaming them to follow the convention, 'NVGPU_PARENT-DIR_HEADER-NAME' when there is no keyword repetition between file name and directory or 'NVGPU_HEADER-NAME' when there is repetition. JIRA NVGPU-1028 Change-Id: I0e4fabc8b31d0bfd66ab541435ac8813e5cc4c1d Signed-off-by: smadhavan <smadhavan@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1815554 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Adeel Raza <araza@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Move MC HAL to commonTerje Bergstrom2018-09-13
| | | | | | | | | | | | | | | | | | | | | | | Move implementation of MC HAL to common/mc. Also bump gk20a implementation to gm20b. gk20a_mc_boot_0 was used via a HAL, but we have only one possible implementation. It also has to be anyway called directly to detect which HALs to assign, so make it a true common function. mc_gk20a_handle_intr_nonstall was also used only in os/linux/intr.c so move it there. JIRA NVGPU-954 Change-Id: I79aedc9158f90d578db0edc17b714617b52690ac Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1813519 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Move FB size query to FBTerje Bergstrom2018-09-10
| | | | | | | | | | | | | Vidmem size query was in mm_xxx.c. It involves reading a register from FB, so move the query to FB HAL. JIRA NVGPU-1063 Change-Id: I30dfd2c4fdcdd6c841f85aaab7431d52473759bd Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1801425 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add Top as a unitTejal Kudav2018-09-10
| | | | | | | | | | | | | | | | | | | | | NVHSCLK registers used by NVLINK IP are part of dev_top hardware headers. This patch adds "Top" as a separate unit and exposes HALs to access dev_top registers. The top unit contains top-level configuration information and any extra registers or features that do not fit into another block's feature set. JIRA NVGPU-1053 JIRA NVGPU-966 Change-Id: Id9a43d4a1c5397959897a242ea97a39a1b95f916 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1803632 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove unused regops HALsDeepak Nibade2018-09-05
| | | | | | | | | | | | | | | | | | | | Below regops HALs are not being called from anywhere, so remove them gops.regops.get_runcontrol_whitelist_ranges() gops.regops.get_runcontrol_whitelist_ranges_count() gops.regops.get_qctl_whitelist_ranges() gops.regops.get_qctl_whitelist_ranges_count() HAL gops.regops.apply_smpc_war() is unimplemented for all the chips, and it was originally only needed for gk20a which is not unsupported So remove this HAL and its call too Jira NVGPU-620 Change-Id: Ia2c74883cd647a2e94ee740ffd040a40c442b939 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1813106 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move channel header to commonKonsta Holtta2018-09-05
| | | | | | | | | | | | | channel_gk20a is clear from chip specifics and from most dependencies, so move it under the common directory. Jira NVGPU-967 Change-Id: I41f2160b96d4ec84064288ecc22bb360e82352df Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1810578 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Fix mutex MISRA 17.7 violationsNicolas Benech2018-09-05
| | | | | | | | | | | | | | | | | | MISRA Rule-17.7 requires the return value of all functions to be used. Fix is either to use the return value or change the function to return void. This patch contains fix for calls to nvgpu_mutex_init and improves related error handling. JIRA NVGPU-677 Change-Id: I609fa138520cc7ccfdd5aa0e7fd28c8ca0b3a21c Signed-off-by: Nicolas Benech <nbenech@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1805598 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move therm debugfs to linuxNitin Kumbhar2018-09-05
| | | | | | | | | | | | | | | | | | | Move debugfs related code of therm from common driver to linux specific part of the driver. gp106_therm_debugfs_init() is updated to use nvgpu_os_linux_ops. This also affects gv100 as gp106_therm_debugfs_init is used for gv100 as well. JIRA NVGPU-603 Change-Id: Ia293d14599bc0c91fd1e917b5a430bd8f3d96e56 Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1797906 GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move gp106 clk debugfs to linuxNitin Kumbhar2018-09-05
| | | | | | | | | | | | | | | | | | | | | | | | | Move linux dependencies and CONFIG_DEBUG_FS to linux specific code from common driver for gp106 clk debugfs. There is no code change in functions moved from gp106/clk_gp106.c. It uses nvgpu_os_linux_ops to add gp106 specific clk debugfs ops. The linux specific part of nvgpu driver uses this op to initialize gp106 clk debugfs. As gv100 also uses gp106 clk debugfs ops, set up os ops for gv100. JIRA NVGPU-603 Change-Id: Ib55ef051b13366e5907e1d05376bb18bf42c8653 Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1797904 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> Reviewed-by: Deepak Nibade <dnibade@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* Revert "gpu: nvgpu: gv11b: enable RMW for gpu atomics"Richard Zhao2018-09-04
| | | | | | | | | | | | | | | | The original change caused cuda atomic perf regression. Bug 2310618 This reverts commit 10c3d4447d4206302f5d51695bf1f193255dd889. Change-Id: Iea5391a89fdfadfb9a79cda57e71f1c9e87ca882 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1793880 (cherry picked from commit d0e51ddcb8139de70916335f124a80b8b588308b) Reviewed-on: https://git-master.nvidia.com/r/1804945 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Bump FB gk20a code to gm20bTerje Bergstrom2018-09-04
| | | | | | | | | | Move all code from fb_gk20a.c to fb_gm20b.c. Change-Id: I87fbdfee76599e019564d66bf248aaffcf978498 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1801422 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Split HUB and GPC MMU debug mode setTerje Bergstrom2018-09-04
| | | | | | | | | | | | HUB and GPC MMU debug modes were set in the same function. This introduced a dependency from FB code to GR registers. Split setting of GPC MMU debug mode to GR HAL. Change-Id: I003446f9dfa147f526bd01d3b6130f4037d9b183 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1801420 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Use debug sig for NVDEC if on dbg SKUTerje Bergstrom2018-08-31
| | | | | | | | | | | | | | Debug fused chips do not have production signature. Use debug signature for memory unlock binary. Requires also exporting a HAL for checking debug mode from PMU. Bug 200445202 Change-Id: I7f88ed6db2fe1c614fe9d4074dbf974c3817f453 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1809225 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Use reset_enum to get mc engine maskTejal Kudav2018-08-31
| | | | | | | | | | | | | | | | | | | Currently, we need to include the MC hardware header in nvlink file to generate reset mask. We can use the reset_enum present in DEVICE_INFO table's IOCTRL entry which is meant to index into NV_PMC_ENABLE_DEVICE register bitfields. This allows us to not #include the MC hardware header in nvlink IP file. JIRA NVGPU-966 Change-Id: I037498038b12f795ee444916fb586355ebf04bb3 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1796819 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Correct the device info table parsingTejal Kudav2018-08-31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | We parse the DEVICE_INFO table entries to get IOCTRL(NVLINK) engine related information like the pri_base_addr, reset_enum, and the intr_enum. For grouping the chained entries per IP, the current parsing logic relies on the fact that engine_type entry for an IP will be parsed before other entries in the chained group. As the enum_type entry (which contains the reset_enum) appears ahead of the engine_type entry, the parsing logic fails and we read reset_enum as 0. Modify the parsing logic to group the chained entries correctly. Also we were using a wrong API to extract the reset/intr_enum from the table entry. JIRA NVGPU-966 Change-Id: I68052db5d1c88a15e04f311486f3f639caf9ed9e Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1796808 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: resolve MISRA 10.3 violationsPhilip Elcan2018-08-29
| | | | | | | | | | | | | | | | | | MISRA rule 10.3 prohibits implicit assigning of u64 to u32. The nvgpu was assigning the value returned by ARRAY_SIZE which is a u64 to a u32. This value was then returned in a function defined by gpu_ops. This patch changes the return type for these gpu_ops to u64 and updates the functions that implement the functions and lastly the saved value. This removes the violation in this instance. JIRA NVGPU-647 Change-Id: I2b93929633cf4809d8f65ee41f739f45d4c2cda7 Signed-off-by: Philip Elcan <pelcan@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1805588 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: invoke calls to methods in pmu_gk20a.h via HALDebarshi Dutta2018-08-29
| | | | | | | | | | | | | | | | | | | | In nvgpu repository, we have multiple accesses to methods in pmu_gk20a.h which have register accesses. Instead of directly invoking these methods, these are now called via HALs. Some common methods such as pmu_wait_message_cond which donot have any register accesses are moved to pmu_ipc.c and the method declarations are moved to pmu.h. Also, changed gm20b_pmu_dbg to nvgpu_dbg_pmu all across the code base. This would remove all indirect dependencies via gk20a.h into pmu_gk20a.h. As a result pmu_gk20a.h is now removed from gk20a.h JIRA-597 Change-Id: Id54b2684ca39362fda7626238c3116cd49e92080 Signed-off-by: Debarshi Dutta <ddutta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1804283 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove NVHSCLK coreclk programmingTejal Kudav2018-08-27
| | | | | | | | | | | | | | | | | top_nvhsclk_ctrl_e_clk_core and top_nvhsclk_ctrl_swap_clk_core default to values 1 and 0 respectively on reset. We need not explicitly program them to same values. JIRA NVGPU-966 Change-Id: I71976c73d74cf81184c79ac9a23e01d26c31be42 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1803639 Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-07-04 21:54:06 -0400