summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/nvgpu
Commit message (Collapse)AuthorAge
* gpu: nvgpu: add ioctls for TSG enable/disableDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | | Add ioctls to enable/disable/preempt a TSG 1. NVGPU_IOCTL_TSG_ENABLE enable all the channels in a TSG 2. NVGPU_IOCTL_TSG_DISABLE disable all the channels in a TSG 3. NVGPU_IOCTL_TSG_PREEMPT preempt a TSG with given id Bug 1514064 Change-Id: I2db6404b8536e872243cbe57b99e7c6d14243fa5 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/494671 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add API to preempt TSGDeepak Nibade2015-03-18
| | | | | | | | | | | | | | Add API gk20a_fifo_preempt_tsg() which takes ID of tsg and preempts it Bug 1514064 Bug 1470692 Change-Id: I1d52c1dd7a9aecc1314b0f223fe4eedecc033629 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/495583 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove gk20a_handleDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | | | | | Remove static variable gk20a_handle used to store pointer to struct gk20a Use below device tree APIs to get pointer to platform_device and then struct gk20a device_node = of_find_matching_node() platform_device = of_find_device_by_node(device_node) Also, use two versions of do_idle()/do_unidle() APIs - one will receive void (to be used from outside GPU driver) and another will receive platform_device (to be used within GPU driver where it is available) Change-Id: I9f2c7610646c5fbcd3d99a1b03dc0364201272a8 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/496508 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Ken Adams <kadams@nvidia.com> GVS: Gerrit_Virtual_Submit
* gpu: nvgpu: gk20a: check ctx valid bitMayank Kaushik2015-03-18
| | | | | | | | | | | | | | | When determining the chid for the current context, first check the ctx valid bit. Bug 1485555 Change-Id: I6c3096d800a6cef38b656d525437a2c4f8b45774 Signed-off-by: Mayank Kaushik <mkaushik@nvidia.com> Reviewed-on: http://git-master/r/496140 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Geoffrey Gerfin <ggerfin@nvidia.com> Tested-by: Geoffrey Gerfin <ggerfin@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Initialize ELPG ref-count early.Neil Gabriel2015-03-18
| | | | | | | | | | | | | | | | | | | gk20a_pmu_disable_elpg can be called before the PMU driver has received and processed the INIT message from the PMU. If change ensures that the ELPG ref-count has been initialized to zero before that can happen. Bug 200016313 Change-Id: Ic80ec1ee69b1eb0499effb1abf556f78cb041f5e Signed-off-by: Neil Gabriel <ngabriel@nvidia.com> Reviewed-on: http://git-master/r/429161 Reviewed-on: http://git-master/r/433299 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Robert Shih <rshih@nvidia.com> Tested-by: Robert Shih <rshih@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Use pgsz_idx instead of page_sizeTerje Bergstrom2015-03-18
| | | | | | | | | | | | | Alloc space writes the page size to a field that requires pgsz_idx. That can cause corruption in internal kernel structures. Clear_sparse treated a parameter as page size instead of index. Bug 1549451 Change-Id: I73ce17b99aae6865056facce72d2ab9ca8b3f81d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/495692
* gpu: nvgpu: Bypass for GM20B post-divider changeAlex Frid2015-03-18
| | | | | | | | | | | Switch GM20b GPCPLL under bypass when changing post-divider setting (for now, don't assume that post-divider is glitch-less). Change-Id: I62b1285c035de0913207a86c41f37b7765da3893 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/495300 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Bo Yan <byan@nvidia.com>
* gpu: nvgpu: get VM reference for TSGDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | | | We store a reference to common address space of channels in struct tsg_gk20a without increasing the refcount This could result in freeing the address space even when some channel in TSG needs it or when we need to free common gr_ctx Fix this by getting ref using gk20a_vm_get() when we store the VM reference. We drop this reference with gk20a_vm_put() when closing the TSG Bug 1470692 Change-Id: Ifc1f29d32cd721810bfbb5a4db96095770318c17 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/495668 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add refcounting for TSGDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | | | Add refcounting for TSGs and manage the refcounts as below : - initialize ref when TSG is opened - get ref when channel is bound to TSG - drop the ref when channel is unbound (i.e. during channel close) - drop the ref when TSG is closed - when refcount drops to zero, we free the TSG This refcounting makes it possible to close channels or TSG in any order Bug 1470692 Change-Id: Ia4b39164a4582c8169da62a91b9131094c67f5f8 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/495667 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Fixes in dupe freeSupriya2015-03-18
| | | | | | | | | | | | | gr_gk20a.c : railgating path the crash was seen with multiple frees happening acr_gm20b.c : failure path, kernel panic was seen, with multiple frees Change-Id: Ifc5e78c0ee74799c7f78e6030c02d1a27d545a1e Signed-off-by: Supriya <ssharatkumar@nvidia.com> Reviewed-on: http://git-master/r/494161 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gm20b: Support for falctraceSupriya2015-03-18
| | | | | | | | | | | | Adding support for falc_trace for ACR Change-Id: Iad638b0de72ff122f43f2250dce6a37adab4cecb Signed-off-by: Supriya <ssharatkumar@nvidia.com> Reviewed-on: http://git-master/r/494162 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gm20b: Regenerate clock gating listsTerje Bergstrom2015-03-18
| | | | | | | | | | Regenerate clock gating lists. Add new blocks, and takes them into use. Also moves some clock gating settings to be applied at the earliest possible moment right after reset. Change-Id: I21888186c200f7a477c63bd3332e8ed578f63741 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/457698
* gpu: nvgpu: remove config GK20A_PHYS_PAGE_TABLESDeepak Nibade2015-03-18
| | | | | | | | | | | | | | remove config GK20A_PHYS_PAGE_TABLES since all code dependent on this config is now moved to runtime selection Change-Id: I27d2722a9ad91cf4e0537a30943675c9132d6924 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/494499 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Increase GM20b debug monitor cyclesAlex Frid2015-03-18
| | | | | | | | Change-Id: I913b6879e0d1ac89b740c1d088d639cc9b13b9b4 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/494200 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Sivaram Nair <sivaramn@nvidia.com>
* gpu: nvgpu: Add GM20b pll registers error dumpAlex Frid2015-03-18
| | | | | | | | Change-Id: I67fe2c4cbab1d43670131d95bbea732e932c0910 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/494164 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Clear PTE ref after freeingTerje Bergstrom2015-03-18
| | | | | | | | | | | | | | When clearing sparse buffers, pte->ref must be cleared once the PTE is freed. Bug 1549451 Change-Id: Ie7d3e438ef2c43cbcf893709ae50a67823bf0c9c Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/494670 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
* gpu: nvgpu: Fix max comptag calculationTerje Bergstrom2015-03-18
| | | | | | | | | | | | | Fix order of calculation for max comptag line calculation. Bug 1549451 Change-Id: I13bf657f0f0b8aafa4d64dacacb74d7224fed379 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/494657 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Shridhar Rasal <srasal@nvidia.com>
* gpu: nvgpu: Fix and enable L2 error processingTerje Bergstrom2015-03-18
| | | | | | | | | | | | | Fix L2 error processing to look into interrupts in each L2 and slice. Enable L2 error interrupts. Bug 1549451 Change-Id: If6dd77f1333426a10b6a148c9432c12df8d879c7 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/494656 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
* gpu: nvgpu: gm20b: Enable rail-gating with max delaySeshendra Gadagottu2015-03-18
| | | | | | | | | | | Enable gpu rail gating with INT_MAX delay. This will allow teams to experiment with different rail-gate entry delay. Change-Id: I8c696140aba2374c797365282999b6589432047c Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/491615 GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
* gpmu:nvgpu: Falcon debug prints.Vaikundanathan S2015-03-18
| | | | | | | | | | | | | | | Display the Falcon Trace prints in the right format. Embedd the parameters in the string instead of printing it separately. Bug NA Change-Id: Ia61fc43384cf6e44a867c7aa9cbb828127146099 Signed-off-by: Vaikundanathan S <vaikuns@nvidia.com> Reviewed-on: http://git-master/r/488757 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: gm20b: update regops whitelistKevin Huang2015-03-18
| | | | | | | | | | | Bug 1500195 Change-Id: Ie2253f2650844cbc707a3083cc2f6b5150c4a17b Signed-off-by: Kevin Huang <kevinh@nvidia.com> Reviewed-on: http://git-master/r/488508 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add HAL for regopsKevin Huang2015-03-18
| | | | | | | | | | | Bug 1500195 Change-Id: I5545d1a95a58e7daa5a74cc20f3fc6828774fc42 Signed-off-by: Kevin Huang <kevinh@nvidia.com> Reviewed-on: http://git-master/r/488507 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Update GM20b GPCPLL operationsAlex Frid2015-03-18
| | | | | | | | | | | | | | | | | | | | | | Moved detection of idempotent GPCPLL operations from set_pll_freq() function to its callers, e.g., explicitly check when enable operation is called on already enabled PLL, instead of passing same frequency to set_pll_freq() in such case. Similarly explicitly check when disable operation is called on already disabled PLL. Also moved check for GPU powered on from set_pll_freq() to callers, and skip call to set interface if not. Added last GPCPLL configuration structure updated after successful completion of set_pll_freq() function. Bug 1450787 Change-Id: I8c14b8cab2a8548e98c9b2d223c465c68fb87b61 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/488027 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Enable gm20b fecs/gpccs bootloaderTerje Bergstrom2015-03-18
| | | | | | | | | | Change-Id: Ia9ab5ef8fbe3244b44c911d8808123e0aaf860cf Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/488611 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
* gpu: nvgpu: cde: Map backing store as read-onlyLauri Peltonen2015-03-18
| | | | | | | | | The cde shader will only read data from the global compbit backing store. Map it as read-only to enforce this. Change-Id: If5be44b8daedd5e7fdee650a6e76befa7bdecfd6 Signed-off-by: Lauri Peltonen <lpeltonen@nvidia.com> Reviewed-on: http://git-master/r/486679
* gpu: nvgpu: gm20b: dynamically detect priv security for secure boot of falconVijayakumar2015-03-18
| | | | | | | | | | | based on the config setting and fuse secure no non secure boot is done Change-Id: I5937ba945c5a3a86f72e0f2a9078fcde01977137 Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/487684 Tested-by: Terje Bergstrom <tbergstrom@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Re-factor GM20b clk_slide_gpc_pll()Alex Frid2015-03-18
| | | | | | | | | | | | Passed pll structure to GM20b clk_slide_gpc_pll() function instead of just feedback divider N value. Change-Id: Ic99d23895ae27e48ccd5a12de99a58bab320df16 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/488025 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Re-factor GM20b clk_lock_gpc_pll_under_bypass()Alex Frid2015-03-18
| | | | | | | | | | | | Passed pll structure to GM20b clk_lock_gpc_pll_under_bypass() function instead of individual M/N/PL dividers values. Change-Id: I4881f6fad0e4be63a0eefb7277894d6900e9bb13 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/488024 Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Re-factor GM20b clk_program_gpc_pll()Alex Frid2015-03-18
| | | | | | | | | | | | | Passed pll structure to GM20b clk_program_gpc_pll() function instead of enclosing clock structure. Change-Id: I81a3a3c03365f4b6997c17894c5210ebdadcbca6 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/488023 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Add debugfs access to GM20b GPCPLLAlex Frid2015-03-18
| | | | | | | | | | | Added direct read and write debugfs access to GM20b GPCPLL registers. Change-Id: I203621906ee094991eecd5c18fd5b6c70b20a4c1 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/487314 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Bo Yan <byan@nvidia.com>
* gpu: nvgpu: Disable GM20b idle slow down by defaultAlex Frid2015-03-18
| | | | | | | | Change-Id: I955fe300702f268e5403aab6f47859dd113f92a3 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/487301 GVS: Gerrit_Virtual_Submit Reviewed-by: Bo Yan <byan@nvidia.com>
* gpu: nvgpu: remove hard coded GPU nameDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | In gk20a_do_idle(), to get pointer to platform_device of gk20a, we use bus_find_device_by_name() and pass "gk20a.0" to it But this hard coding fails on gm20b since GPU device name there is "gpu" Hence to fix this add a static pointer handle "gk20a_handle" to struct gk20a in gk20a.c Now we can access this global pointer inside do_idle() to get gk20a pointer and from that we can get pointer to platform_device Change-Id: I1a65588e34ad36efed0fa587bb365f0ee81e253d Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/486887 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: cde: Re-use contextArto Merilainen2015-03-18
| | | | | | | | | | | | | | | | Currently cde reinitialises the context each time before submitting work to the channel. This was done to ensure that we are able to get clean context for the shader during development phase. However, as the shader has been tested to work w/o reinitialising the context, we can remove the reinitialisation to gain better performance. Change-Id: If0b0e03133058528da943faaeb72ca500d3ddb14 Signed-off-by: Arto Merilainen <amerilainen@nvidia.com> Reviewed-on: http://git-master/r/486673 Reviewed-by: Jussi Rasanen <jrasanen@nvidia.com> Tested-by: Jussi Rasanen <jrasanen@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Lauri Peltonen <lpeltonen@nvidia.com>
* gpu: nvgpu: Disable GM20b clock slowdown for monitorAlex Frid2015-03-18
| | | | | | | | | | | Disabled GM20b idle clock slowdown during rate measurements. Change-Id: I20127c1f2816b7a8fe2f208eb21d2decc986d727 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/486324 Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: Add clock idle slowdown registerAlex Frid2015-03-18
| | | | | | | | | | | | | Added clock idle slowdown register. Fixed duplicated/overlapping therm_peakpower_config8_r and therm_peakpower_config1_r definitions. Change-Id: I37dad714ce5a6730a2f0b7c1b31b509bb1823975 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/486323 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* TEMP: gpu: nvgpu: gm20b: Mask LTC interruptsArto Merilainen2015-03-18
| | | | | | | | | | | LTC interrputs were set to random values at boot. For now, disable all interrupts. Change-Id: Ibb032cac91d3ea9a951fd8c2eb62a783af5bd1a1 Signed-off-by: Arto Merilainen <amerilainen@nvidia.com> Reviewed-on: http://git-master/r/482639 Reviewed-by: Lauri Peltonen <lpeltonen@nvidia.com> Tested-by: Lauri Peltonen <lpeltonen@nvidia.com>
* gpu: nvgpu: Don't increase GPCPLL rate before bypassAlex Frid2015-03-18
| | | | | | | | | | | | | | | | Do not force GM20b GPCPLL post divider to 1:2 settings before switching to bypass clock if PLL output frequency is increased as a result. Move this step under bypass. However, this step is still needed in case when PLL can be configured without switch to bypass. Bug 1450787 Change-Id: Iab81b0e5a71f44f738a64e15b05df41fdbd61ebe Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/456505 Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
* gpu: nvgpu: gm20b: Fix pm refs in VPR info fetchArto Merilainen2015-03-18
| | | | | | | | | | | | | | | | | The code took reference to gk20a by using gk20a_busy_noresume(). This function takes pm runtime reference only to the GPU, however, the code dropped the reference by calling gk20a_idle() which also drops the reference to the platform dependencies (host1x). This patch modifies gm20b_mm_mmu_vpr_info_fetch_wait() to drop only the GPU reference. Change-Id: Ied59381fa302452356768ed59e8ad9af18284e3d Signed-off-by: Arto Merilainen <amerilainen@nvidia.com> Reviewed-on: http://git-master/r/482721 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: support gk20a virtualizationAingara Paramakuru2015-03-18
| | | | | | | | | | | | | The nvgpu driver now supports using the Tegra graphics virtualization interfaces to support gk20a in a virtualized environment. Bug 1509608 Change-Id: I6ede15ee7bf0b0ad8a13e8eb5f557c3516ead676 Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com> Reviewed-on: http://git-master/r/440122 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: manage phys pages at runtimeDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | Current implementation is based on config GK20A_PHYS_PAGE_TABLES to have APIs to create/free/map/unmap phys pages Remove this config based implementaion and move the APIs so that they are called at runtime based on tegra_platform_is_linsim() In generic APIs, we first check if platform is linsim and if it is then we forward the call to phys page specific APIs Change-Id: I23eb6fa6a46b804441f18fc37e2390d938d62515 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/488843 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Set PB timeout only in gk20aTerje Bergstrom2015-03-18
| | | | | | | | | | | | | PB timeout has been removed in gm20b, so write it only in gk20a. Change-Id: I2aab92fe7d1d5de151dad768f8b3f6901ec0bbb0 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/486358 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Tested-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Kevin Huang (Eng-SW) <kevinh@nvidia.com>
* gpu: nvgpu: Do not rail gate in simulationTerje Bergstrom2015-03-18
| | | | | | | | | | | Simulation does not model rails, so do not try to control them. Change-Id: I52ec12e7865e18764274dd9ce7a2fbd196b6b9d1 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/482181 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Thomas Cherry <tcherry@nvidia.com> Tested-by: Thomas Cherry <tcherry@nvidia.com>
* gpu: nvgpu: gm20b: add pm callbacksSeshendra Gadagottu2015-03-18
| | | | | | | | | | | Add powergate/powerungate callbacks for gm20b configuration. Change-Id: Ieb681b74de7ea19d172922ef68260be81b675a56 Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/457352 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Bo Yan <byan@nvidia.com>
* gpu: nvgpu: Disable GM20b GPCPLL SYNC modeAlex Frid2015-03-18
| | | | | | | | | | | | | | Disabled GPCPLL SYNC mode after GM20b is switched to bypass clock when powering down GPU. Bug 1450787 Change-Id: Ifaec2c562e51c0ae1328b7505faafd19607a77f2 Signed-off-by: Alex Frid <afrid@nvidia.com> Reviewed-on: http://git-master/r/456504 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Bo Yan <byan@nvidia.com>
* gpu: nvgpu: 3d.emc bandwidth ratio policySamuel Russell2015-03-18
| | | | | | | | | | | | | Modify the 3d.emc policy to use a formula based on bandwidth and utilization instead of the current sku-dependent policy. Bug 1364894 Change-Id: Id97f765a48f0aa9f5ebeb0c82bccb22db474a1ae Signed-off-by: Samuel Russell <samuelr@nvidia.com> Reviewed-on: http://git-master/r/453586 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add support for multiple GPC/TPCsMayank Kaushik2015-03-18
| | | | | | | | | | | Add support for multiple GPCs/TPCs to the GPC/TPC exception handling code. Change-Id: Ifb4b53a016e90cb54c4d985a9e17760f87c6046f Signed-off-by: Mayank Kaushik <mkaushik@nvidia.com> Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/411660 Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: gm20b: use gpc_mmu to check debug modeKevin Huang2015-03-18
| | | | | | | | | | Bug 1534793 Change-Id: I8a4c35914b58dd13a7c10c668de9d4662d947d8c Signed-off-by: Kevin Huang <kevinh@nvidia.com> Reviewed-on: http://git-master/r/441377 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Increase PBDMA timeoutTerje Bergstrom2015-03-18
| | | | | | | | | | | | | | PBDMA timeout can cause stale data in FIFO. Default value equals 1ms. Increase it to max. Bug 1537636 Change-Id: I1c6c6b10abaece3a64b77b9b3ef77ff726ff67cf Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/457047 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Allen Chang <allchang@nvidia.com> Tested-by: Allen Chang <allchang@nvidia.com>
* gpu: nvgpu: clear sparse in space freeKevin Huang2015-03-18
| | | | | | | | | | | | | | Gk20a unmaps the addresses binding to dummy page to clear sparse. On Gm20b, we need to free the allocated page table entry for sparse memory. Bug 1538384 Change-Id: Ie2409ab016c29f42c5f7d97dd7287b093b47f9df Signed-off-by: Kevin Huang <kevinh@nvidia.com> Reviewed-on: http://git-master/r/448645 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add ioctl to force reset channelDeepak Nibade2015-03-18
| | | | | | | | | | | | | | | | | | | Add below ioctl to force channel reset/recovery. NVHOST_IOCTL_CHANNEL_FORCE_RESET This recovery/reset is initiated by triggering mmu fault on channel so as to force the channel out (as oppose to waiting until channel is preempted) Bug 200027958 Change-Id: Idd3c10ef5fa691d746e34a8b890bd79aca815a20 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/456084 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-11-09 15:47:12 -0500