summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAge
* gpu: nvgpu: use hww_esr_reset field to reset hwww_esrSeema Khowala2017-06-13
| | | | | | | | | | | Use hww_esr_reset field to clear hww errors Change-Id: I4b5da20c8a4bcfe2dea357d3d2ebd53678673b48 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1500965 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add sked exception detection and handlingSeema Khowala2017-06-13
| | | | | | | | | | | | | Needed to detect and clear sked exception Bug 200315442 Change-Id: Ia85e8827e563addf7b9d0f95ef192379bb808638 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1500860 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: reorganize PMU F/W supportMahantesh Kumbar2017-06-13
| | | | | | | | | | | | | | | | | | | | - Moved pmu f/w related support from pmu_gk20a.c to "drivers/gpu/nvgpu/common/pmu/pmu_fw.c" file - Prepended with nvgpu_ for global functions & replaced wherever used - Moved below list related to PMU f/w init/remove, PMU version specific ops, non-secure ucode blob prepare, JIRA NVGPU-56 Change-Id: Ifdad8c560bd233e98728717d5868119e9d8e8d90 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1480636 GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
* gpu: nvgpu: reorganize PMU FB alloc/freeMahantesh Kumbar2017-06-13
| | | | | | | | | | | | | | | | | | Moved PMU FB access related code from pmu_gk20a.c to "drivers/gpu/nvgpu/common/pmu/pmu.c" file - Prepended with nvgpu_ for global functions & replaced wherever used. JIRA NVGPU-56 JIRA NVGPU-94 Change-Id: I42bfd9d216e6b35672a9738f01302d954b32b69e Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1480551 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
* gpu: nvgpu: reorganize PMU initMahantesh Kumbar2017-06-12
| | | | | | | | | | | | | | | | | | | | | | | | - Moved PMU init code from pmu_gk20a.c to "drivers/gpu/nvgpu/common/pmu/pmu.c" file - Moved below related methods SW/HW init, init msg handler, deinit/destroy, PMU state machine -Created HAL methods to read message queue tail & supported mutex count. -prepend with nvgpu_ for pmu init global mehtods JIRA NVGPU-56 JIRA NVGPU-92 Change-Id: Iea9efc194fefa74fb5641d2b2f4633577d2c3a47 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1480002 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: move TEGRA_VGPU_ATTRIB_PREEMPT_CTX_SIZE to constantsRichard Zhao2017-06-09
| | | | | | | | | | | | | | Also removed deprecated TEGRA_VGPU_ATTRIB_*, but leave a place holder in case someone wants to use this command in future. Jira VFND-3796 Change-Id: Ic36a59db238d276b0e3dd68a9d8ec5834a04333d Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1457497 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: reorganize PMU IPCMahantesh Kumbar2017-06-09
| | | | | | | | | | | | | | | | | | | | - Moved PMU IPC related code to drivers/gpu/nvgpu/common/pmu/pmu_ipc.c file, -Below is the list which are moved seq mutex queue cmd/msg post & process event handling NVGPU-56 Change-Id: Ic380faa27de4e5574d5b22500125e86027fd4b5d Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1478167 GVS: Gerrit_Virtual_Submit Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Move error notifier free to Linux moduleTerje Bergstrom2017-06-08
| | | | | | | | | | | | | | | Freeing error notifier involves calling dma_buf API, which is Linux specific. Move the free to happen in Linux specific channel close path. JIRA NVGPU-65 Change-Id: Ifd8b31bb8c8af13975c34add00f51dd869cfd76a Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1498583 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com>
* gpu: nvgpu: Update PMU firmware version.Deepak Goyal2017-06-08
| | | | | | | | | | | | | | | This patch also updates PMU cmdline args as required by updated firmware. GPUT19x-30 Change-Id: I44214007046081a44acc7284eb2854d0548a8da8 Signed-off-by: Deepak Goyal <dgoyal@nvidia.com> Reviewed-on: http://git-master/r/1498188 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
* gpu: nvgpu: use nvgpu specific nvhost APIsDeepak Nibade2017-06-08
| | | | | | | | | | | | | | | | | | | | | | | | | | Remove use of linux specifix header files <linux/nvhost.h> and <linux/nvhost_ioctl.h> and use nvgpu specific header file <nvgpu/nvhost.h> instead This is needed to remove all Linux dependencies from nvgpu driver Replace all nvhost_*() calls by nvgpu_nvhost_*() calls from new nvgpu library Remove platform device pointer host1x_dev from struct gk20a and add struct nvgpu_nvhost_dev instead Jira NVGPU-29 Change-Id: Ia7af70602cfc16f9ccc380752538c05a9cbb8a67 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1489726 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: add nvhost abstraction filesDeepak Nibade2017-06-08
| | | | | | | | | | | | | | | | | | | | | Add new abstraction file common/linux/nvhost.c for all nvhost APIs and operations and export them from header <nvgpu/nvhost.h> This file will be compiled only if config CONFIG_TEGRA_GK20A_NVHOST is set Define struct nvgpu_nvhost_dev in a separate private header nvhost_priv.h Jira NVGPU-29 Change-Id: I17e1f7836d4854feadff0c339bc093e78ba7f3eb Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1489725 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Split non-stall interrupt handlingTerje Bergstrom2017-06-07
| | | | | | | | | | | | | | | | | | | | | | Split handling of stalling interrupt to Linux specific chip agnostic and OS independent chip specific parts. Linux specific chip independent part contains handler for ISR and passing the control to a bottom half worker. It uses the new MC HALs intr_nonstall (query interrupt status), intr_nonstall_pause (pause interrupts), intr_nonstall_resume (resume interrupts), and is_intr1_pending (query per-engine interrupt bit). MC HAL isr_nonstall is removed, because its work is now handled in chip independent code. JIRA NVGPU-26 Change-Id: I3e4c9905ef6eef7f1cc9f71b0278518ae663f87e Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1497048 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add MC HAL is_intr1_pendingTerje Bergstrom2017-06-07
| | | | | | | | | | | | | | | Add MC HAL is_intr1_pending. At the same time introduce nvgpu_unit that is passed as parameter to is_intr1_pending. The API is passed contents of intr1 register and an engine number, and returns true if there's an interrupt pending for the engine. JIRA NVGPU-26 Change-Id: I8e6363dd78572f8e41dbab2b258036ed168b6f75 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1497870 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: implement chip specific fb cbc_initseshendra Gadagottu2017-06-07
| | | | | | | | | | | | | Add function pointer in fb to add chip specific cbc init. GPUT19X-70 Change-Id: I12f73945d99498de965a671fd8e258b5c95bbabe Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1484524 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Separate GMMU mapping impl from mm_gk20a.cAlex Waterman2017-06-06
| | | | | | | | | | | | | | | Separate the non-chip specific GMMU mapping implementation code out of mm_gk20a.c. This puts all of the chip-agnostic code into common/mm/gmmu.c in preparation for rewriting it. JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: I6f7fdac3422703f5e80bb22ad304dc27bba4814d Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1480228 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Remove extraneous VM init/deinit APIsAlex Waterman2017-06-06
| | | | | | | | | | | | | | | | | | | | Support only VM pointers and ref-counting for maintaining VMs. This dramatically reduces the complexity of the APIs, avoids the API abuse that has existed, and ensures that future VM usage is consistent with current usage. Also remove the combined VM free/instance block deletion. Any place where this was done is now replaced with an explict free of the instance block and a nvgpu_vm_put(). JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: Ib73e8d574ecc9abf6dad0b40a2c5795d6396cc8c Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1480227 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Unify vm_init for vGPU and regular GPUAlex Waterman2017-06-06
| | | | | | | | | | | | | | | | | Unify the initialization routines for the vGPU and regular GPU paths. This helps avoid any further code divergence. This also assumes that the code running on the regular GPU essentially works for the vGPU. The only addition is that the regular GPU path calls an API in the vGPU code that sends the necessary RM server message. JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: I37af1993fd8b50f666ae27524d382cce49cf28f7 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1480226 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Fix big_pages logic in nvgpu_vm_initAlex Waterman2017-06-06
| | | | | | | | | | | | | | | | | | | | | | | Fix the way big_pages is handled in nvgpu_vm_init(). Prior to this patch big_pages could wind up being true even if disable_bigpages is set in the mm struct. Clearly this is wrong. The logic is now simplified a little bit and makes it so that if the disable_bigpages field is set then the resulting VM created by nvgpu_vm_init() has only one user area (no need for a second LP user area) and the big_pages field for the VM is set to false. JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: If5dc7fcf3fa4e070f87295406f0afe414269b702 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1493318 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: split vidmem_is_vidmemKonsta Holtta2017-06-06
| | | | | | | | | | | | | | | | | | | | | As the vidmem_is_vidmem flag has got two separate meanings in one bit, split it in two bits into the enabled() API: Add NVGPU_MM_HONORS_APERTURE bit, which is the same as vidmem_is_vidmem with its original meaning, and use it to test which aperture bits to write to hardware. Add NVGPU_MM_UNIFIED_MEMORY bit, which has the opposite meaning: that the GPU shares the SoC memory. When this flag is false, the GPU has its own local video memory. Jira NVGPU-86 Change-Id: I2d0bed3b1ede5a712be99323d3035b154bb23c3a Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1496080 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move clk_gm20b debugfs to Linux moduleDeepak Nibade2017-06-06
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Move debugfs code from clk_gm20b.c to file in Linux module common/linux/debug_clk.c This file will be compiled only if CONFIG_DEBUG_FS is set Define below new HAL APIs for various clock operations which can be accessed from debug file init_debugfs() get_voltage() get_gpcclk_clock_counter() pll_reg_write() get_pll_debug_data() Export nvgpu_pl_to_div() and nvgpu_div_to_pl() so that these can be accessed from debug_clk.c Add new structure nvgpu_clk_pll_debug_data so that all required register values for debugging can be made available in debug_clk.c Add new API gm20b_get_gpc_pll_parms() so that statically defined variable can be accessed in debug_clk.c too Remove global variable dvfs_safe_max_freq and add it to struct clk_gk20a so that it can accessed from both clk_gm20b.c and debug_clk.c Jira NVGPU-62 Change-Id: I3ae70b40235e78141a686686930e1f178ad59453 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1488903 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix use of untrusted scalar valueDeepak Nibade2017-06-06
| | | | | | | | | | | | | | | | | | | | | | | | Kind value can be passed to API nvgpu_vm_map() from User space (through IOCTL NVGPU_AS_IOCTL_MAP_BUFFER_EX) But kind value is not checked for sane values before storing it in bfr.kind_v And then we use this kind value as array index in gk20a_kind_is_supported() which is incorrect Fix this by ensuring in nvgpu_vm_map() that the kind value is well within range Bug 200291879 Coverity id : 2567923 Coverity id : 2567924 Change-Id: Ic57395018727cbd2260c929581db256e427316c6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1496597 GVS: Gerrit_Virtual_Submit Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove logically dead codeDeepak Nibade2017-06-06
| | | | | | | | | | | | | | | | | In nvgpu_vm_map(), variable "inserted" can never be true in error path Hence remove the logically dead code Bug 200291879 Coverity id : 2567920 Change-Id: I5428f7d52f1d4f815c04d90ea651668dd72ba985 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1495906 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
* gpu: nvgpu: fix resource leakDeepak Nibade2017-06-06
| | | | | | | | | | | | | | | | | | | | | | | | | | We pass (struct device_attribute *) to gp10b_ecc_stat_create() and gr_gp10b_ecc_stat_create() and then assign a memory allocation to this pointer But since this pointer is local copy to function, static pointer variables are never set in gr_gp10b_create_sysfs() This also results in a resource leak since we never free the storage assigned to local variable Fix this by adding correct parameter (struct device_attribute **) so that the address of the allocation is returned to the caller correctly Bug 200291879 Coverity id : 2567934 Change-Id: I7ac79810d9e22a568ae3cd1a69eb3f59a8d356ac Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1495905 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
* gpu: nvgpu: fix recursive include from clk.hDeepak Nibade2017-06-06
| | | | | | | | | | | | | | | | | | | | Fix recursion in header include sequence : gk20a.h -> clk.h -> gk20a.h by removing gk20a.h include from clk/clk.h Fix the compile time error by forward declaring struct gk20a Coverity id : 2567917 Bug 200291879 Change-Id: I8fc3a8787dae91ae1a070c63bae6550596734603 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1495904 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
* gpu: nvgpu: remove duplicate \n from log messagesStephen Warren2017-06-06
| | | | | | | | | | | | | | | | | | nvgpu_log/info/warn/err() internally add a \n to the end of the message. Hence, callers should not include a \n at the end of the message. Doing so results in duplicate \n being printed, which ends up creating empty log messages. Remove the duplicate \n from all err/warn messages. (This message was updated in parallel with the previous change to fix this particular issue) Bug 1928311 Change-Id: I789f8c4b4084539ac901ed0f6b815518900cee90 Signed-off-by: Stephen Warren <swarren@nvidia.com> Reviewed-on: http://git-master/r/1495020 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Use nvgpu_cond in notifier wqTerje Bergstrom2017-06-05
| | | | | | | | | | | | | Change notifier wait queue to use nvgpu_cond instead of Linux wait queue. JIRA NVGPU-14 Change-Id: I197a0ef6c0a2331ca0dbb3480bdb89d45ba73020 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1469853 Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User
* gpu: nvgpu: moved & renamed "struct pmu_gk20a"Mahantesh Kumbar2017-06-05
| | | | | | | | | | | | | | | | | | | - Renamed "struct pmu_gk20a" to "struct nvgpu_pmu" then moved to file "pmu.h" under folder "drivers/gpu/nvgpu/include/nvgpu/" - Included header file "pmu.h" to dependent file & removed "pmu_gk20a.h" include if its usage is not present. - Replaced "struct pmu_gk20a" with "struct nvgpu_pmu" in dependent source & header files. JIRA NVGPU-56 Change-Id: Ia3c606616831027093d5c216959c6a40d7c2632e Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1479209 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add support for engine specific countersDavid Nieto2017-06-04
| | | | | | | | | | | | | Add support for chip engine specific error counters JIRA: GPUT19X-82 Change-Id: I1b2686bd58c2d4e060a0a79c6b9e505811490a90 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1490824 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu : GPC MMU ECC supportDavid Nieto2017-06-04
| | | | | | | | | | | | | | Adding support for handling of GPC MMU errors JIRA: GPUT19X-112 Change-Id: Iadeef017587e5dce3698026eef4ad94676c3c02b Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1490771 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: chip specific L2 ECC error supportDavid Nieto2017-06-04
| | | | | | | | | | | | | Adding support for handling of chip specific ECC memory errors JIRA: GPUT19X-112 Change-Id: I1c04ac1d5233c332b300540eade1b73527c46ff7 Signed-off-by: David Nieto <dmartineznie@nvidia.com> Reviewed-on: http://git-master/r/1489020 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: nvgpu_thread to handle PMU state changesMahantesh Kumbar2017-06-02
| | | | | | | | | | | | | | | | | | | | | | | | | - Replaced schedule_worker() with nvgpu_thread along with nvgpu_cond_wait() to handle PMU state machine changes during boot. - Added new state "PMU_STATE_EXIT" to exit PMU state machine loop & wait for the thread stop signal. - In gk20a_init_pmu_setup_sw() thread creates & starts thread execution to handle PMU state changes. - In pmu_destroy() thread post PMU_STATE_EXIT & waits for pending operation to complete before thread destroy. JIRA NVGPU-56 Change-Id: I951208bf88e82c281e3e678ddc603d58aec5ab10 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1487882 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: move debugfs code to linux moduleDeepak Nibade2017-06-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since all debugfs code is Linux specific, remove it from common code and move it to Linux module Debugfs code is now divided into below module specific files : common/linux/debug.c common/linux/debug_cde.c common/linux/debug_ce.c common/linux/debug_fifo.c common/linux/debug_gr.c common/linux/debug_mm.c common/linux/debug_allocator.c common/linux/debug_kmem.c common/linux/debug_pmu.c common/linux/debug_sched.c Add corresponding header files for above modules too And compile all of above files only if CONFIG_DEBUG_FS is set Some more details of the changes made - Move and rename gk20a/debug_gk20a.c to common/linux/debug.c - Move and rename gk20a/debug_gk20a.h to include/nvgpu/debug.h - Remove gm20b/debug_gm20b.c and gm20b/debug_gm20b.h and call gk20a_init_debug_ops() directly from gm20b_init_hal() - Update all debug APIs to receive struct gk20a as parameter instead of receiving struct device pointer - Update API gk20a_dmabuf_get_state() to receive struct gk20a pointer instead of struct device - Include <nvgpu/debug.h> explicitly in all files where debug operations are used - Remove "gk20a/platform_gk20a.h" include from HAL files which no longer need this include - Add new API gk20a_debug_deinit() to deinitialize debugfs and call it from gk20a_remove() - Move API gk20a_debug_dump_all_channel_status_ramfc() to gk20a/fifo_gk20a.c Jira NVGPU-62 Change-Id: I076975d3d7f669bdbe9212fa33d98529377feeb6 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1488902 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: use nvgpu specific lock APIs in kmemDeepak Nibade2017-06-02
| | | | | | | | | | | | | | | | | Use lock/mutex APIs from nvgpu/lock.h instead of using Linux specific APIs in kmem.c This patch is needed in order to remove Linux dependency from nvgpu driver Jira NVGPU-62 Change-Id: Ic3484857bc2fa1917724681f68c1626c1235baea Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1492107 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: *gr_bind_fecs_elpg called only if can_elpg setSeema Khowala2017-06-01
| | | | | | | | | | | | | | | gk20a_init_gr_bind_fecs_elpg(g) should not be called if system does not support gpmu Bug 200306035 Change-Id: Ifdc3bb326993cd42bfa9aece06881c8426b83a8b Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1486043 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: pass right data to aelpg control callsVijayakumar2017-06-01
| | | | | | | | | | | | | | | | | | Fill aelpg controller id explicitly and use right structure within command union bug 1932265 Change-Id: Ie06bf8b1b124e67871dd1443e14a1080473a7ab1 Signed-off-by: Vijayakumar <vsubbu@nvidia.com> Reviewed-on: http://git-master/r/1493125 Reviewed-by: Alex Waterman <alexw@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Adeel Raza <araza@nvidia.com> Tested-by: Adeel Raza <araza@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
* gpu: nvgpu: Avoid NULL dereference of flcnMahantesh Kumbar2017-05-31
| | | | | | | | | | | | | | | | | | | | | | | | -issue: flcn pointer in nvgpu_flcn_sw_init() will be NULL in default case of switch, and that results in NULL pointer dereference on flcn->flcn_id. -Fix: Used flcn_id parameter to print falcon id in default case. Coverity ID: 2514311 Coverity ID: 2514313 Bug 200291879 Change-Id: I7008817c22cdf8d9d9027cc1b724e2424b4a3d8e Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1491694 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Move unify_address_spaces to flagsAlex Waterman2017-05-30
| | | | | | | | | | | | | | | | | Use the enabled flags API to handle the unify_address_sapce spaces flag. JIRA NVGPU-84 JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: Id1b59aed4b349d6067615991597d534936cc5ce9 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1488307 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Begin removing variables in struct gk20aAlex Waterman2017-05-30
| | | | | | | | | | | | | | | | | | | | | | Begin removing all of the myriad flag variables in struct gk20a and replace that with one API that checks for flags being enabled or disabled. The API is as follows: bool nvgpu_is_enabled(struct gk20a *g, int flag); bool __nvgpu_set_enabled(struct gk20a *g, int flag, bool state); These APIs allow many of the gk20a flags to be replaced by defines. This makes flag usage consistent and saves a small amount of memory in struct gk20a. Also it makes struct gk20a easier to read since there's less clutter scattered through out. JIRA NVGPU-84 Change-Id: I6525cecbe97c4e8379e5f53e29ef0b4dbd1a7fc2 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1488049 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: add fifo ops get_mmu_fault_infoSeema Khowala2017-05-30
| | | | | | | | | | | | | | | | | | | | This is needed to take care of gp10b h/w header changes. gp10b changes as compared to legacy gpu chips -fault_info_fault_type field width is changed -fault_info_write field is removed -fault_info_access_type field is added -fault_info_engine_subid is removed -fault_info_client_type is added -fault_info_client field width has changed JIRA GPUT19X-7 JIRA GPUT19X-12 Change-Id: Iebf28cc6c851830524049b67a71cd72fb4a28948 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1487319 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: use mmu_fault_info struct for legacy gpu chipsSeema Khowala2017-05-30
| | | | | | | | | | | | | | | Removed fifo_mmu_fault_info_gk20a struct to use new mmu_fault_info struct JIRA GPUT19X-7 JIRA GPUT19X-12 Change-Id: I1987ff1b07e7dbdbee58d7e5f585faacf4846e54 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1487240 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove "gk20a_channel_worker_process" printsSeema Khowala2017-05-30
| | | | | | | | | | | | | dbg_mask option that enables gpu_dbg_fn bit litters uart with "gk20a_channel_worker_process" prints. Change-Id: I0489db630cc94e909a871233744ec264627b4cea Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1490979 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add enable_exceptions gr opsSeema Khowala2017-05-30
| | | | | | | | | | | | This is needed to enable chip specific gr exceptions JIRA GPUT19X-75 Change-Id: I5ca8d0e51d00947c3ab1675bb6331207def433a4 Signed-off-by: Seema Khowala <seemaj@nvidia.com> Reviewed-on: http://git-master/r/1474851 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: drop tegra idle registration callsKonsta Holtta2017-05-29
| | | | | | | | | | | The deprecated functions tegra_{register,unregister}_idle_unidle() have not existed in ages, so remove this dead code. Change-Id: I45005844d59282ff9638cce1c61002bddab74ce2 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1488813 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Fix build failure by missing headersskadamati2017-05-29
| | | | | | | | | | | | | | | | | | | | Forward declare struct file & inode ../../../nvgpu/drivers/gpu/nvgpu/gk20a/fecs_trace_gk20a.c:26:0: ../../../nvgpu/drivers/gpu/nvgpu/gk20a/ctxsw_trace_gk20a.h:29:57: error: 'struct file' declared inside parameter list [-Werror] int gk20a_ctxsw_dev_release(struct inode *inode, struct file *filp); Bug 200310575 Change-Id: I872b3a2483fb4dda9569aca1b4729bcd8acd5968 Signed-off-by: skadamati <skadamati@nvidia.com> Reviewed-on: http://git-master/r/1490166 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-by: Alex Waterman <alexw@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sumeet Gupta <sumeetg@nvidia.com>
* gpu: nvgpu: add chip specific sync point supportseshendra Gadagottu2017-05-26
| | | | | | | | | | | | | | Added support for chip specific sync point implementation. Relevant fifo hal functions are added and updated for legacy chips. JIRA GPUT19X-2 Change-Id: I9a9c36d71e15c384b5e5af460cd52012f94e0b04 Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1258232 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Fix build failure by missing headersskadamati2017-05-26
| | | | | | | | | | | | | | | | | | Move the platform_gk20a.h include out of the ifdef CONFIG_DEBUG_FS in the CDE code since dev_from_gk20a() is used regardless of whether debugfs is enabled. Also modify some of the CE ops to take a struct gk20a instead of a struct device. This avoids any requirement for including linux/device.h or platform_gk20a.h. Bug 200310575 Change-Id: Ifef963cd0f66d05094a698200386cc6140920eac Signed-off-by: skadamati <skadamati@nvidia.com> Reviewed-on: http://git-master/r/1487830 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: remove duplicate \n from log messagesStephen Warren2017-05-26
| | | | | | | | | | | | | | | nvgpu_log/info/warn/err() internally add a \n to the end of the message. Hence, callers should not include a \n at the end of the message. Doing so results in duplicate \n being printed, which ends up creating empty log messages. Remove the duplicate \n from all err/warn messages. Bug 1928311 Change-Id: I99362c5327f36146f28ba63d4e68181589735c39 Signed-off-by: Stephen Warren <swarren@nvidia.com> Reviewed-on: http://git-master/r/1487232 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Split stalling interrupt handlingTerje Bergstrom2017-05-26
| | | | | | | | | | | | | | | | | | | | | | Split handling of stalling interrupt to Linux specific chip agnostic and OS independent chip specific parts. Linux specific chip independent part contains handler for ISR and passing the control to a bottom half. It uses the new MC HALs intr_stall (query interrupt status), intr_pause (pause interrupts) and intr_resume (resume interrupts). MC HAL isr_stall now returns void and gets called in thread context and thus remove isr_thread_stall and replace the implementation with isr_stall. JIRA NVGPU-26 Change-Id: I206f330f6fc4a1f4def47c5f986585ac4080216d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1480243 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* gpu: nvgpu: Add and use VM init/deinit APIsAlex Waterman2017-05-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Remove the VM init/de-init from the HAL and instead use a single set of routines that init/de-init VMs. This prevents code divergence between vGPUs and regular GPUs. This patch also clears up the naming of the routines a little bit. Since some VMs are used inplace and others are dynamically allocated the APIs for freeing them were confusing. Also some free calls also clean up an instance block (this is API abuse - but this is how it currently exists). The new API looks like this: void __nvgpu_vm_remove(struct vm_gk20a *vm); void nvgpu_vm_remove(struct vm_gk20a *vm); void nvgpu_vm_remove_inst(struct vm_gk20a *vm, struct nvgpu_mem *inst_block); void nvgpu_vm_remove_vgpu(struct vm_gk20a *vm); int nvgpu_init_vm(struct mm_gk20a *mm, struct vm_gk20a *vm, u32 big_page_size, u64 low_hole, u64 kernel_reserved, u64 aperture_size, bool big_pages, bool userspace_managed, char *name); void nvgpu_deinit_vm(struct vm_gk20a *vm); JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: Ia4016384c54746bfbcaa4bdd0d29d03d5d7f7f1b Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1477747 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Refactor VM init/cleanupAlex Waterman2017-05-26
| | | | | | | | | | | | | | | | | Refactor the API for initializing and cleaning up VMs. This also involved moving a bunch of GMMU code out into the gmmu code since part of initializing a VM involves initializing the page tables for the VM. JIRA NVGPU-12 JIRA NVGPU-30 Change-Id: I4710f08c26a6e39806f0762a35f6db5c94b64c50 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1477746 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>