summaryrefslogtreecommitdiffstats
path: root/drivers
Commit message (Collapse)AuthorAge
...
* gpu: nvgpu: remove nvlink on driver removalNitin Kumbhar2018-06-14
| | | | | | | | | | | | | | Unregister nvlink and nvlink device when gpu is getting removed. Without this next modprobe of nvgpu results in nvlink registration failure. Bug 1987855 Change-Id: I785e707d1fa90f45a3ff0e9790f3f02fa15510d4 Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1735986 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove ldiv_slowdown_factor sysfs nodeNitin Kumbhar2018-06-14
| | | | | | | | | | | | | | | ldiv_slowdown_factor sysfs node is added with change f9e55fba but it didn't update nvgpu_remove_sysfs() to remove it. This results in EEXIST error for modprobe-rmmod-modprobe sequence of nvgpu driver. Bug 1987855 Change-Id: I4360028ba75435f3e144be23f6d9f42a81dcb94b Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730538 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Add HAL for SW WARTejal Kudav2018-06-14
| | | | | | | | | | | | | | Workaround of setting SAFE_CTR_INIT on NVLINK (WAR for Bug 1888034) is needed only on nvlink 2.0. Add HAL to avoid running the WAR on future chips. Bug 2006692 Change-Id: I85fb90ea5ce7b848946f2c362e7a952787cc1261 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1738401 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Add HAL to get link_maskTejal Kudav2018-06-14
| | | | | | | | | | | | | | | | VBIOS link_disable_mask should be sufficient to find the connected links. As VBIOS is not updated with correct mask, we parse the DT node where we hardcode the link_id. DT method is not scalable as same DT node is used for different dGPUs connected over PCIE. Remove the DT parsing of link id and use HAL to get link_mask based on the GPU. JIRA NVLINK-162 Change-Id: Idb7b639962928ce48711a0d7fc277c4c324bee91 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1738967 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Add HAL for minion INIT* dlcmdTejal Kudav2018-06-14
| | | | | | | | | | | | | | | | | | The sequence of INIT* minion dlcmd varies between nvlink 2.0 and 2.2. The order is strict for 2.2. Also there are new dlcmds added to the nvlink bringup sequence. Add HAL to allow sequence update for nvlink 2.2. Old sequence: INITLANEENABLE-> INITDLPL New Sequence: INITDLPL->INITDLPL_TO_CHIPA->INITTL->INITLANEENABLE JIRA NVLINK-176 Change-Id: I49e0a726f56e7d6122ac4cddf0f0e021d16f1926 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1738329 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Multiple WPR supportMahantesh Kumbar2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | | The WPR will be divided into several sub-WPRs, one for each Falcon and one common for sharing between Falcons which bootstrap falcons - Defined & used flag NVGPU_SUPPORT_MULTIPLE_WPR to know M-WPR support. - Added struct lsfm_sub_wpr to hold subWPR header info - Added struct lsf_shared_sub_wpr_header to hold subWPR info & copied to WPR blob after LSF_WPR_HEADER - Set NVGPU_SUPPORT_MULTIPLE_WPR to false for gp106, gv100 & gv11b. - Added methods to support to multiple WPR support & called by checking flag NVGPU_SUPPORT_MULTIPLE_WPR in ucode blob preparation flow. JIRA NVGPUTU10X / NVGPUT-99 Change-Id: I81d0490158390e79b6841374158805f7a84ee6cb Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1725369 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: gv11b: Handle all SM errorsVinod G2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | Add the missing register bits to identify the SM errors. Except for mmu_nack error, all other errors are handled using a single function. That function sets the error notifier with GR_EXCEPTION, clears interrupt and triggers recovery process. bug 200402677 JIRA NVGPU-573 Change-Id: Icfaff1f20f1f35adb4cd35ce288ce694845aed3c Signed-off-by: Vinod G <vinodg@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730963 Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@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: add fbpa ecc supportRichard Zhao2018-06-14
| | | | | | | | | | | | | | - add fbpa ecc counters - add HALs for init_fbpa and fbpa_isr Jira NVGPUT-69 Jira NVGPUT-68 Change-Id: I3c8fbb664a9b08ece23d860d84881d4860706f77 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1726307 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Read sublink state when neededTejal Kudav2018-06-14
| | | | | | | | | | | | | | | | | | | On nvlink 2.2, we poll for sublink substate to be stable before checking sublink primary state. Currently, we read both TX and RX sublink state during set_sublink_mode() irrespective of which sublink mode is changed. This is not correct when we are polling on substate value while getting sublink state. JIRA NVLINK-164 Change-Id: I474705f059dbf41e5fb7e45bef455c33ee21aa95 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1734539 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>
* gpu: nvgpu: Move SW scratch register read to busTerje Bergstrom2018-06-14
| | | | | | | | | | | | | SW scratch register is in bus register range. Move query of that register to bus HAL from bios. JIRA NVGPU-588 Change-Id: I69f35af3d5f8da3550eb68fe7d060a3ec48ce275 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730898 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Combine variants of init_mm_setup_hwTerje Bergstrom2018-06-14
| | | | | | | | | | | | | | gp10b and gk20a variants of init_mm_setup_hw were essentially the same. Delete the gp10b version and use gk20a variant instead. gv11b variant now also inherits gk20a variant. JIRA NVGPU-588 Change-Id: I842516a1c0be68562ad0ece6e1837a1416d24957 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730897 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Implement bus HAL for bar2 bindTerje Bergstrom2018-06-14
| | | | | | | | | | | | | Implement BAR2 bind as a bus HAL and remove the corresponding MM HAL. BAR2 bind HW API is in bus. JIRA NVGPU-588 Change-Id: I3a8391b00f1ba65f9ed28b633f1d52bf7c984230 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730896 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Use gm20b version of BAR1 bindTerje Bergstrom2018-06-14
| | | | | | | | | | | | | All chips should use the waiting version of BAR1 bind since gm20b. Change gp10b and gp106 to do that. BAR1 is not used in Volta. JIRa NVGPU-588 Change-Id: Ib6957ebea4effa7c64f4d71522447fa6245728ed Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730895 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Do not set MMU page size againTerje Bergstrom2018-06-14
| | | | | | | | | | | | | | | | | MMU page size is set already in MMU initialization. Do not re-set it when binding BAR2. JIRA NVGPU-588 Change-Id: I3b5309baa2adf0917c59a390fe41c29b13398e6c Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730894 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com> 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: Separate timer from busTerje Bergstrom2018-06-14
| | | | | | | | | | | | | Code touching timer registers was combined with bus code. They're two logically separate register spaces, so separate the code accordingly. JIRA NVGPU-588 Change-Id: I40e2925ff156669f41ddc1f2e7714f92a2da367b Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730893 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove setting of PRI timeoutTerje Bergstrom2018-06-14
| | | | | | | | | | | | | PRI timeout should always use the HW initialization value. Do not set it explicitly. JIRA NVGPU-588 Change-Id: Idb63caba07c5fa7e0439e572861443f2783d0adc Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730892 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove direct MC and GR deps from busTerje Bergstrom2018-06-14
| | | | | | | | | | | | | | | | | | bus_gk20a.c had some debug dump references to MC and GR registers. The dumps have not been very useful, so instead of refactoring the code just remove the dumps. JIRA NVGPU-588 Change-Id: Id974731716d058ef4a3fe77240c11b1c53db169c Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730891 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com> 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 setting of BAR0_WINDOW to busTerje Bergstrom2018-06-14
| | | | | | | | | | | | | Move setting of BAR0_WINDOW to bus HAL. Also moves the usage of spinlock to common code so that pramin_gk20a.[ch] can be deleted. JIRA NVGPU-588 Change-Id: I3ceabc56016711b2c93f31fedf07daa778a4873a Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730890 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Move setting priv interrupt to priv_ringTerje Bergstrom2018-06-14
| | | | | | | | | | | | | Registers to set priv interrupts are in priv_ring, but the code was in bus HAL. Move the code and related HALs to priv_ring instead. JIRA NVGPU-588 Change-Id: I708d11f77405dbba86586a0d1da42f65bcc1de9d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730889 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: bus: Remove use of extra includesTerje Bergstrom2018-06-14
| | | | | | | | | | | | | | | | bus_gk20a.c had a few unnecessary includes. Remove them to speed up compilation. JIRA NVGPU-588 Change-Id: I0e94e788104ba6acb259c315734e6b42f69a8074 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730888 Reviewed-by: Automatic_Commit_Validation_User 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: vgpu: clean up nonstall isrsRichard Zhao2018-06-14
| | | | | | | | | | | | | | | | | | It has moved to use TEGRA_VGPU_EVENT_SEMAPHORE_WAKEUP, removing legacy isrs. Jira EVLR-2696 Change-Id: Ie977bba59c0af8589989d872150c3f9b2080854a Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1736399 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Thomas Fleury <tfleury@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: gr: remove only created sysfs nodesNitin Kumbhar2018-06-14
| | | | | | | | | | | | | | | | Sysfs nodes for GR stats are created on GR init. If nvgpu module is removed without any ops, then it tries to remove sysfs nodes which do not exist resulting in kernel panic. Fix this issue by removing sysfs nodes only if ecc counters are initialized. Bug 1987855 Change-Id: I3f967ee92ec02ad19ffbd9bfa8bace5bfd229dd2 Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730536 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: skip destroy if vidmem not initializedNitin Kumbhar2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | The vidmem shall be destroyed only if it has been initialized. If not skipped, it accesses mutexes which are in invalid state. This results in BUG like: BUG: spinlock bad magic on CPU#0, rmmod/1560 Also, destroy vidmem bootstrap allocator which is set up in nvgpu_vidmem_init(). Bug 1987855 Change-Id: I68e91422a54b40feeb9071158b797828e2391303 Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730535 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add Ctrl API to read SM error stateVinod G2018-06-14
| | | | | | | | | | | | | | Expose IOCTL to Ctrl node to read Single SM error under NVGPU_GPU_IOCTL_READ_SINGLE_SM_ERROR_STATE bug 200412642 JIRA NVGPU-700 Change-Id: I3cbcf4d7f23a53dbd2350b38a5e259559d5fd3af Signed-off-by: Vinod G <vinodg@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1728931 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: gpu railgate handling with runtime pmseshendra Gadagottu2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Earlier implementation of railgate disable config is disabling runtime pm during pm_init. This is causing multiple issues: 1. gpu rail will be on as soon as nvgpu driver probe is called. Actual gpu hw init may happen at much later point of time. 2. This is breaking railgate_enable sysfs node functionality. railgate_enable is not working if runtime pm is disabled. To avoid all these issues for railgate disable, enable runtime pm during pm_init and set auto-suspend delay to negative (-1), which will disable runtime pm suspend calls. Also fixed following issues along with this: 1. Updated railgate_enable debugfs implementation to use auto-suspend delay. To disable railgating: Set auto-suspend delay with negative value(-1) which will disable runtime pm suspend. To enable railgating: Set auto-suspend delay with railgate_delay value. Also removed redundant user_railgate_disabled gk20a device data and replaced with can_railgate, where ever it is applicable. 2. Initialized default railgate_delay to 500msec to avoid railgate on/off transitions with railigate enable from disabled state. 3. Created railgate_residency debug fs node irrespective of can_railgate initial state. This is helping with the case, where initial state of railgate state off and then railgate enable is done through sysfs node. Bug 2073029 Change-Id: I531da6d93ba8907e806f65a1de2a447c1ec2665c Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1694944 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: set gv10x boot clockVaikundanathan S2018-06-14
| | | | | | | | | | | | | | | - Set gv10x boot gpcclk to 952 MHz - Created ops to set gv10x boot gpcclk instead of using clk arbiter to set clocks Bug 200399373 Change-Id: Ice5956f79d4a52abf455506a798cf7b914f3d3ed Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1700788 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu : nvgpu: gv100 pmu f/w version updateVaikundanathan S2018-06-14
| | | | | | | | | | | | | | -gv100 f/w version update for ucode https://git-master.nvidia.com/r/#/c/1708170/ Change-Id: I91b900dc3c2e702ec1341ac882b4abc7df875c4c Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1726913 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@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: gv100: Fix therm gopsVaikundanathan S2018-06-14
| | | | | | | | | | | | | Fix test crash with therm sw setup by assigning therm limit and alert HAL functions. Bug 200399373 Change-Id: I972b92d949648a9278d3d351a80cc9a68e23cffc Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1703778 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu:nvgpu: Add gops to load pstate functionsVaikundanathan S2018-06-14
| | | | | | | | | | | | | | | Add gops to choose to/not to enable 1. clk_freq_controller 2. pmgr_domain 3. lpwr_pg Bug 200399373 Change-Id: Ie5131f9ea260f777fded8392f24815acef6cfbea Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1702216 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu:nvgpu: Update vfe_load for GV100Vaikundanathan S2018-06-14
| | | | | | | | | | | | Add gops to choose vfe_load between GP and GV. Bug 200399373 Change-Id: I73e0fbd2f1956e81c241f09639c69f33082e617b Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1702143 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu:nvgpu: Add option for split rail supportVaikundanathan S2018-06-14
| | | | | | | | | | | | Add gops to check whether split rail is suported in the chip Bug 200399373 Change-Id: I5e955127e06d1fbc9b3eca0a895afa0a06f39d91 Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1702130 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Set DMA mask on a per-platform basisAlex Waterman2018-06-14
| | | | | | | | | | | | | | | | | | | | Each GPU platform has different DMA limitations. For older chips the maximum size of a DMA buffer was more limited than newer SoCs (read: Xavier) and discrete GPUs. This patch adds support to set the DMA mask for a GPU on a per platform basis by adding a platform field that is populated with the maximum allowed DMA mask. That mask is programmed by the driver common code. If no mask is specified then the default mask size is 16GB (34 bits). Bug 2043276 Change-Id: I9c3c76c86bac6c485eb1197326e662516fbcaa41 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1700980 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Add HAL for pll setupTejal Kudav2018-06-14
| | | | | | | | | | | | | | | | | | Before nvlink 2.2, driver was responsible for setting the NVLink clocks during NVLink initialization. For the purpose of security, NVLink PLL handling is moved to Minion in nvlink 2.2 and driver should stop writing to these registers. JIRA NVLINK-167 Change-Id: I18392a29c322da55053037bfde62c8f74ee75288 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730597 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: nvlink: Add HAL for RXDETTejal Kudav2018-06-14
| | | | | | | | | | | | | | | | | | | RXDET is supported only on nvlink 2.2 devices and forward. Add HAL to run RXDET selectively based on chip. RXDET needs to be done after the links are out of reset but before any other link level initialization. minion_send_cmd is also made non-static to support RXDET functionality. JIRA NVLINK-160 Change-Id: Ic65b8dbc7281743f62072089ff3c805521ac9b38 Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1729525 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: initialze bundle64 stateDeepak Nibade2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | We receive bundle with address and 64 bit values from ucode on some platforms This patch adds the support to handle 64 bit values Add struct av64_gk20a to store an address and corresponding 64 bit value Add struct av64_list_gk20a to store count and list of av64_gk20a Add API alloc_av64_list_gk20a() to allocate the list that supports 64bit values In gr_gk20a_init_ctx_vars_fw(), if we see NETLIST_REGIONID_SW_BUNDLE64_INIT, load the bundle64 state into above local structures Add new HAL gops.gr.init_sw_bundle64() and call it from gk20a_init_sw_bundle() if defined Also load the bundle for simulation cases in gr_gk20a_init_ctx_vars_sim() Jira NVGPUT-96 Change-Id: I1ab7fb37ff91c5fbd968c93d714725b01fd4f59b Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1736450 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: adding USERMODE enable bit.Prateek Sethi2018-06-14
| | | | | | | | | | | | | | | | | | This change is required to keep enable USERMODE on QNX as part of gpu characteristics unification. Jira VQRM-3996 Change-Id: I9881c8d3a2dfcadf618a56deee847cd9b575ed7b Signed-off-by: Prateek Sethi <prsethi@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1735573 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Richard Zhao <rizhao@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 crash due to accessing incorrect TSG pointerDeepak Nibade2018-06-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In gk20a_gr_isr(), we handle various errors including GPC/TPC errors. And then if BPT errors are pending we call gk20a_gr_post_bpt_events() at the end and pass channel pointer to it gk20a_gr_post_bpt_events() extracts TSG pointer based on ch->tsgid But in some race conditions it is possible that we clear the error and trigger recovery and as a result channel is unbounded from TSG and closed by user space before calling gk20a_gr_post_bpt_events() And in that case the code above results in getting incorrect TSG pointer and hence crashes as below Unable to handle kernel paging request at virtual address ffffff8012000c08 ... [<ffffff8008081f84>] el1_da+0x24/0xb4 [<ffffff80086e72e0>] gk20a_tsg_get_event_data_from_id+0x30/0xb0 [<ffffff80086e7560>] gk20a_tsg_event_id_post_event+0x50/0xc8 [<ffffff800872922c>] gk20a_gr_isr+0x27c/0x12e0 To fix this extract the TSG pointer before handling all the errors and pass this pointer to gk20a_gr_post_bpt_events() will post the events if they are enabled and if TSG is still open Bug 200404720 Change-Id: I4861c72e338a2cec96f31cb9488af665c5f2be39 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1735415 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vinod Gopalakrishnakurup <vinodg@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: vgpu: implement .free_syncpt_bufRichard Zhao2018-06-14
| | | | | | | | | | | | | | | vgpu needs to free the va range besides unmap the syncpt buffer. Jira VFND-4870 Change-Id: Ia9edb687b66db6da8529bf256d348999e24a0bc3 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1693094 Reviewed-by: Automatic_Commit_Validation_User 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: initialize HAL for NEXT_2 gpuDeepak Nibade2018-06-14
| | | | | | | | | | | | | | | | | In gpu_init_hal(), call NVGPU_NEXT_2_INIT_HAL() if we detect chip NVGPU_GPUID_NEXT_2 Jira NVGPUT-95 Change-Id: Ie1121591e53a1587766ea03bb62d0aae01d9ccbf Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1734099 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> 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: add g->fifo_eng_timeout_usThomas Fleury2018-06-14
| | | | | | | | | | | | | | Add g->fifo_eng_timeout_us to define engine timeout in microseconds. It is initialized with GRFIFO_TIMEOUT_CHECK_PERIOD_US. In RM server case, it can be overriden with value defined in device tree. Jira EVLR-2674 Change-Id: I69ac2ce779fe575566c8ba48e8cd2d0e6b2d93cf Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1728391 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove check to disallow gv100 link0/1Tejal Kudav2018-06-14
| | | | | | | | | | | | | | | | | | On GV100, we could not enable reflck repeater at source of PLL which is shared by link 0/1. So we do not allow link 0 and 1 to be used on GV100. This refclk repeater is present only on GV100. Remove the check as we currently use link3 on GV100 and do not plan to use any other link. JIRA NVLINK-162 Change-Id: I9ffcc0b20d084a208271d2c594ec64b5bafaabfb Signed-off-by: Tejal Kudav <tkudav@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1734538 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: support CAU ctxsw listDeepak Nibade2018-05-30
| | | | | | | | | | | | | | | | | | | | | | | CAU (Counter Aggregation Unit) registers might be split out from SMPC registers and moved into their own list on some platforms In gr_gk20a_init_ctx_vars_fw() add support to check if pm_cau list is available If list is available, count will be set to non-zero here In add_ctxsw_buffer_map_entries_gpcs(), parse the pm_cau list if count is non-zero Bug 2139870 Change-Id: Ia630e7d03481a6f927c6739d28ebfe49f221326f Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1733208 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Matthew Braun (SW-GPU) <matthewb@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: gv11b/gv100: add SHADER_CUT_COLLECTOR compute classSeema Khowala2018-05-30
| | | | | | | | | | | | | | | | | | | | Support NVC3C0_SET_SHADER_CUT_COLLECTOR s/w method for compute class. This is needed to enable/disable SHADER_CUT_COLLECTOR_STATE. Bug 2108381 Bug 2099681 Change-Id: I228dcc55b6df605aeeee094f872157023e3c783c Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730634 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Wei Sun <wsun@nvidia.com> Tested-by: Wei Sun <wsun@nvidia.com> Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> 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: posix: undef min, max macros is definedAlex Waterman2018-05-30
| | | | | | | | | | | | | | | | | | | These macros are sometimes defined by the std library headers. So when they are defined #undef them and use our own version. Also explicitly include types.h from gmmu.c since it uses the min and max macros. JIRA NVGPU-525 Change-Id: I905ff23ef7a4a96467be59c4a124cb09b63f1f96 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1721015 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: posix: add impl for nvgpu_is_soc_t194_a01()Alex Waterman2018-05-29
| | | | | | | | | | | | | | | | | This function was added for Linux but not for posix. Thankfully the implementation for posix is trivial: just return false. JIRA NVGPU-525 Change-Id: Ib5af66dedeabb754ce36cbf6f0351e4af3926c52 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730742 Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Seshendra Gadagottu <sgadagottu@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 include path for clockgating headersVinod G2018-05-29
| | | | | | | | | | | | Removed the reference for $NVGPU/drivers/gpu/nvgpu/common from Makefile and fixed the include path for the clockgating headers in HAL files. Change-Id: I34c179866d28c932501b38184ec18d20dce81480 Signed-off-by: Vinod G <vinodg@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1730759 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: gv11b: move to use gops.fifo.check_tsg_ctxsw_timeoutRichard Zhao2018-05-25
| | | | | | | | | | | | | Fixing RM server crash when handles ctxsw timeout. RM server needs to call its own HAL of .check_tsg_ctxsw_timeout. Jira EVLR-2691 Change-Id: Ibbc09cbcda39d44dc2a721c9b270d065e13fa9e2 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1729900 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: abstract submit profilingKonsta Holtta2018-05-25
| | | | | | | | | | | | | | | | Add gk20a_fifo_profile_snapshot() to store the submit time in a profiling entry that was acquired from gk20a_fifo_profile_acquire(). Also get rid of ifdef CONFIG_DEBUG_FS by stubbing the acquire and free functions when debugfs is not enabled. This reduces some cyclomatic complexity in the submit path. Jira NVGPU-708 Change-Id: I39829a6475cfe3aa582620219e420bde62228e52 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1729545 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove empty gk20a_mm_debugfs_initKonsta Holtta2018-05-25
| | | | | | | | | | | | gk20a_mm_debugfs_init() used to initialize one mm-specific debugfs knob, but now that there aren't any, delete the function and the related files. Change-Id: Ic3177945bbab501c506b5199b44c87450df75452 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1729530 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove unused function declarationsAlex Waterman2018-05-25
| | | | | | | | | | | | Change-Id: I36f2d13ed3797719137c670afef9b644d48ea16e Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1727485 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Konsta Holtta <kholtta@nvidia.com> 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>
generated by cgit v1.2.2 (git 2.25.0) at 2024-07-17 02:17:23 -0400