summaryrefslogtreecommitdiffstats
path: root/include/trace/events
Commit message (Collapse)AuthorAge
* drivers: string handlingdmitry pervushin2020-05-13
| | | | | | | | | | | | | | | | gcc9 is more strict about using strncpy... and in many cases it is right Replacing strncpy with strdup (when possible) or strlcpy Bug 2973859 Change-Id: I1283db0385d7b35f747d129d3963e8f293e83dc3 Signed-off-by: dmitry pervushin <dpervushin@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2342280 Reviewed-by: automaticguardword <automaticguardword@nvidia.com> Reviewed-by: Phoenix Jung <pjung@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* devfreq: podgov: use cycles/sec to estimate loadPeng Liu2019-05-07
| | | | | | | | | | | | | | | | | | | | | | | | GPU clock may change within the period of time defined by smooth. Thus the result of averaging load percentages within smooth window has less meanning. New method keeps track of active GPU cycle count per time unit, and average load is average active cycle count divided by current GPU clock (total cycle count per time unit). Bug 1963732 Change-Id: I88cfb998f9bcfa0d6d0397f653f8e3096d4b3eed Signed-off-by: Peng Liu <pengliu@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/2033266 (cherry picked from commit 4080e458dd4e1651ef61f4d9cf3f2b5ea6eb6a1f) Reviewed-on: https://git-master.nvidia.com/r/2104701 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Aaron Tian <atian@nvidia.com> Tested-by: Aaron Tian <atian@nvidia.com> Reviewed-by: Rajkumar Kasirajan <rkasirajan@nvidia.com> Reviewed-by: Bibek Basu <bbasu@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* tegra: camera: rtcpu: add nvcsi trace supportVincent Chung2019-02-01
| | | | | | | | | | | | | | | | | | | | | Add support for NVCSI global and correctable/uncorrectable interrupt status traces, originating from RCE. Bug 2315922 Change-Id: I2008f09300bf2d653ca7a6fd42925dd2f9069021 Signed-off-by: Vincent Chung <vincentc@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1829199 (cherry picked from commit 5e0ff02048ac4bc937d67fb9fdb4ff9c084931f5) Reviewed-on: https://git-master.nvidia.com/r/2003156 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Ian Kaszubski <ikaszubski@nvidia.com> Reviewed-by: Ruicheng Dai <rdai@nvidia.com> Reviewed-by: Pekka Pessi <ppessi@nvidia.com> Reviewed-by: Frank Chen <frankc@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* tegra: dc: insure CRCs taken from same frameAron Wong2018-07-30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Insure CRC collection does not cross a frame boundary by checking the frame_num at the start and finish of CRC collection, and retrying CRC collection if a frame boundary was crossed. This addresses an error condition seen during testing of C6/CC6 changes which randomly introduced milliseconds of delay in between the start and end of reading CRCs. Add related display_crc tracing functions to aid future debugging. These trace functions are: display_crc_read display_crc_late display_crc_rgnl display_crc_rgnl_stat display_crc_boundary_crossed Jira TDS-3717 Jira TDS-3687 Jira TDS-3428 Bug 2070900 Change-Id: I8468634f41bd5c90f4d8d8a014c13e2b050c2407 Signed-off-by: Aron Wong <awong@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1667689 Reviewed-by: Shu Zhong <shuz@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Ujwal Patel <ujwalp@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* video: tegra: host: podgov: add trace eventsKonsta Holtta2018-07-06
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add the trace events header for the POD devfrqe governor used when CONFIG_DEVFREQ_GOV_POD_SCALING=y. This file is copied from linux 4.4; the original consists of these three commits: 5e6afca7aef06a7e9df9c0cc91ee3a19f279349f drivers: video: tegra: 3d scaling uses devfreq 122a4c533b13711363e94b27ca13d7af5c04675a video: tegra: host: add 3dfs user space control 9ee601182294d82e2273710640798c7fbc145c79 video: tegra: host: podgov: Add dev to trace events Bug 1853519 Change-Id: Idcf5a67443c698cc0740452ccb130550f12d1b3f Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1454590 (cherry picked from linux-4.9 commit e981a42830212e5924296505e133dedf630b65ec) Reviewed-on: https://git-master.nvidia.com/r/1772234 GVS: Gerrit_Virtual_Submit Reviewed-by: Bitan Biswas <bbiswas@nvidia.com> Reviewed-by: Timo Alho <talho@nvidia.com> Tested-by: Timo Alho <talho@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: trace: events: fix rtcpu_stringPekka Pessi2018-06-13
| | | | | | | | | | | | | | | | The rtcpu_string trace events are not NUL-terminated. Jira CAMC-627 Change-Id: I94a64ae21e5add672a4196dcc8fca5f700d4eb9b Signed-off-by: Pekka Pessi <ppessi@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1743919 Tested-by: Mika Liljeberg <mliljeberg@nvidia.com> Reviewed-by: Kalle Jokiniemi <kjokiniemi@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Mika Liljeberg <mliljeberg@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: Move input-cfboost header files to nvidia repoNicolin Chen2018-06-08
| | | | | | | | | | | | | | | | The input-cfboost driver was moved to nvidia repo while its header files were not. So this patch move its header files to nvidia repo as well. Bug 200419967 Change-Id: Id9e18f7c395dabf8fe19df360050a681d8eefab0 Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1743008 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* nvhost:pva: Add VPU performance trackingSaleh Dindar2018-06-05
| | | | | | | | | | | | | VPU performance tracking is added by using post-actions and delivering results to the trace JIRA PVA-1087 Change-Id: Ia0030348665c8c0857cf107f4f76d9cc6052f1f2 Signed-off-by: Saleh Dindar <sdindar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1719719 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: add iso trace headerAjay Nandakumar2018-05-10
| | | | | | | | | | | | | | Added trace/events/isomgr.h as these headers required for iso manager. Bug 200410446 Change-Id: I3cc2264fdbc37b73c4f3fd116057892a41456a54 Signed-off-by: Ajay Nandakumar <anandakumarm@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1710273 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* video: tegra: host: pva: Add statistics to trace logVinod G2018-03-29
| | | | | | | | | | | | | Add the task statistics to trace log JIRA PVA-930 Change-Id: I8a20ecf5a6bac7428540bc6e7cf91c94924efc34 Signed-off-by: Vinod G <vinodg@nvidia.com> Signed-off-by: Saleh Dindar <sdindar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1672236 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* video: tegra: host: pva: Include device name in trace logVinod G2018-03-09
| | | | | | | | | | | | | | | | | Add support in the trace log to include the device name. This helps tod distinguish the trace is captured for which pva node. JIRA PVA-953 Change-Id: I4751bef65a8d21a092b97ddb680b2a387d59ceef Signed-off-by: Vinod G <vinodg@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1670716 Reviewed-by: Saleh Dindar <sdindar@nvidia.com> Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* trace: move bpmp thermal trace header to linux-nvidiaTimo Alho2018-03-09
| | | | | | | | | | | | | | | | BPMP thermal driver is located in linux-nvidia repository so remove the header from kernel repository and add it to nvidia repository. Change-Id: I9b88ae4d81a3695521159de7243b5ff2b2f6c2e2 Signed-off-by: Timo Alho <talho@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1670416 Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-by: Srikar Srimath Tirumala <srikars@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Bitan Biswas <bbiswas@nvidia.com> Tested-by: Bitan Biswas <bbiswas@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* t194: bwmgr:update dram eff wrto dram refresh rateSanjay Chandrashekara2018-03-05
| | | | | | | | | | | | | | | | | | | | On T194 total dram efficiency numbers are different as per dram refresh rates. This patch adds support in bwmgr, to register to the thermal framework and get events when trip points(85 C) are crossed. At a later stage, functionality will be added to poll/get dram refresh rate from bpmp once temperature crosses above 85'C and set the efficiency correctly. Bug 1702427 Bug 1923111 JIRA: TPM-1209 Change-Id: I68861a71a69af3672a3e537943338b2d1d08823f Signed-off-by: Sanjay Chandrashekara <sanjayc@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1654577 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* tegra: bwmgr: Add ftrace to tegra_bwmgr_set_emcRyan O'Leary2018-03-01
| | | | | | | | | | | | | | | | | | | | | | Add ftrace trace point to tegra_bwmgr_set_emc function including arguments. JIRA TPM-1205 Change-Id: I097ae6bc8e3be39a52b5f1b6eff39c974a70c2eb Signed-off-by: Ryan O'Leary <roleary@nvidia.com> (cherry picked from commit 444adfc783ab3eeec9f44fc93b8c75cf4ca88f0c) Signed-off-by: Ian Kaszubski <ikaszubski@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1662122 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sanjay Chandrashekara <sanjayc@nvidia.com> Reviewed-by: Ajith Kumar <ajithk@nvidia.com> Reviewed-by: Jon Mayo <jmayo@nvidia.com> Reviewed-by: Krishna Sitaraman <ksitaraman@nvidia.com> Reviewed-by: Bhanu Murthy V <bmurthyv@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: trace: events: Remove trace of pagepool_fill_lotsAshish Mhetre2018-03-01
| | | | | | | | | | | | | | | | | Remove code for tracing nvmap_pp_fill_lots as it is no longer used. Bug 200386771 Change-Id: I072f7bfe61b723eb6d3677c5c838c4e7a8ebf346 Signed-off-by: Ashish Mhetre <amhetre@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1666572 Reviewed-by: Pritesh Raithatha <praithatha@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Tested-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* iio: meter: ina3221: Add channel poll and eventSomdutta Roy2018-02-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Added support for generating ftrace events in specified intervals. This is particularly helpful in automated power measurement environments. Enable per channel event generation - echo <time in ms> > /sys/bus/i2c/devices/<ina_device>/ iio_device/polling_delay_<channel_number> Disable per channel event generation - echo 0 > /sys/bus/i2c/devices/<ina_device>/ iio_device/polling_delay_<channel_number> Enable ina3221 power event - echo 1 > /sys/kernel/debug/tracing/event/ina3221/event Disable ina3221 power event - echo 0 > /sys/kernel/debug/tracing/event/ina3221/event Event format in ftrace - ina3221_power: channel_name=<name> channel_power=<val> eg. ina3221_power: channel_name=VDD_SYS_GPU channel_power=1527 APP-34 Change-Id: Ide63bf0ab968e6b80297278b3b25232d27bbfde6 Signed-off-by: Somdutta Roy <somduttar@nvidia.com> Reviewed-on: http://git-master/r/1484236 (cherry picked from commit 44087c0f4a4c9c25e028f64d33f3ec59b191eed1) Reviewed-on: http://git-master/r/1497392 GVS: Gerrit_Virtual_Submit Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Laxman Dewangan <ldewangan@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1663163 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: trace: events: rectify TRACE_INCLUDE_PATHSachin Nikam2017-11-20
| | | | | | | | | | | | | | | After some repos collapsed into nvidia repo TRACE_INCLUDE_PATH needs to be rectified. Bug 2024620 Change-Id: I96e51128d7723d78ee307ef8b00a0b80071043a3 Signed-off-by: Sachin Nikam <snikam@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1601476 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> Tested-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-by: Mikko Perttunen <mperttunen@nvidia.com>
* tracing: Add atrace counter type eventsSomdutta Roy2017-11-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | Add support events for atrace counter types. This enables generating atrace events which resemble systrace counter type atraces. enable: echo 1 > /sys/kernel/debug/tracing/ events/atrace/atrace_counter/enable disable: echo 0 > /sys/kernel/debug/tracing/ events/atrace/atrace_counter/enable AV-446 Change-Id: Ib465256cf145858eb06a0f496b67f0485e100a87 Signed-off-by: Somdutta Roy <somduttar@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1537813 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Steve Rogers <srogers@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1577403 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1597368 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* Merge remote-tracking branch 'remotes/origin/dev/linux-t19x' into linux-nvidiaDeepak Nibade2017-11-16
|\ | | | | | | | | | | | | Bug 200363166 Change-Id: Id0fcee1cc01fe1648afe7e3f2d44f820563898ca Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
| * t19x: Change all references from nvhost to nvidiaIshan Mittal2017-06-28
| | | | | | | | | | | | | | - Change references from nvhost to nvidia - Change references from nvhost-t19x to t19x Change-Id: I6c9b275bdb20dfa975145124395b61493a1ff5a9
| * video: tegra: host: pva: cleanup and format pva tracesPuneet Saxena2017-04-07
| | | | | | | | | | | | | | | | | | | | | | | | | | It cleans up the code and format trace points. JIRA PVA-111 JIRA PVA-148 Change-Id: Ied9a315e077e9c317464ca3f1156d92257f15ade Signed-off-by: Puneet Saxena <puneets@nvidia.com> Reviewed-on: http://git-master/r/1455886 Reviewed-by: Arto Merilainen <amerilainen@nvidia.com> Tested-by: Arto Merilainen <amerilainen@nvidia.com>
| * pva: copy ucode trace buffer to kernel ftracePuneet Saxena2017-04-03
| | | | | | | | | | | | | | | | | | It copies ucode trace buffer to kernel ftrace buffer. When ucode trace block is full, it copies it to kernel-ucode shared trace buffer. From this trace_buffer traces are copied to kernel ftrace buffer. JIRA PVA-111 JIRA PVA-148 Change-Id: I05c83d818d289115361f146b11e6ae62a41a1ceb Signed-off-by: Puneet Saxena <puneets@nvidia.com> Reviewed-on: http://git-master/r/1317874 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* platform: tegra: rtcpu: new VI notify tracesMika Liljeberg2017-11-02
| | | | | | | | | | | | | | | | | | Add new VI notify event and error traces with 64-bit VI timestamps. The timestamps can be directly compared with any TSC based timestamp. Bug 1989513 Change-Id: Ie4ea867b650c8bcee3776cda8c60db6776c6fd96 Signed-off-by: Mika Liljeberg <mliljeberg@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1577834 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Jihoon Bang <jbang@nvidia.com> Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: Frank Chen <frankc@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* include: trace: Add vivid trace eventsBhanu Murthy V2017-11-01
| | | | | | | | | | | | Bug 1898472 Change-Id: I53074fa582cf3c6ec180acf4042adaf649cc59b4 Signed-off-by: Bhanu Murthy V <bmurthyv@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1587268 GVS: Gerrit_Virtual_Submit Reviewed-by: Jihoon Bang <jbang@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* i2c: camrtc: Fix ivc rpc callbackAshish Singh2017-10-26
| | | | | | | | | | | | | | | | | Following additions and fixes done in this patch 1. Add support for callback for i2c writes, that is non-blocking calls. This currently disabled though. 2. Fix a bug for starting timer for callbacks in rpc. 3. Add tracing support in rpc for debugging. Bug 1853141 Change-Id: I91511828e3be21fc9dd878af4bcb07d4d14d50a1 Signed-off-by: Ashish Singh <assingh@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1559498 GVS: Gerrit_Virtual_Submit Reviewed-by: Bhanu Murthy V <bmurthyv@nvidia.com> Reviewed-by: Jihoon Bang <jbang@nvidia.com>
* trace: sensors: Add ATRACE macros for sensor eventsRobert Collins2017-10-19
| | | | | | | | | | | | | | Adding ATRACE macros will enable tracking motion sensor events for end-to-end latency. AV-388 Change-Id: I774dff325d92b954aaecb660f81899f277566cf2 Signed-off-by: Robert Collins <rcollins@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1536969 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Akhilesh Khumbum <akhumbum@nvidia.com>
* tegra: dc: Add latency measurement supportArun Swain2017-10-13
| | | | | | | | | | | | | | | | | | | Add support for end-to-end latency measurement in dc. This helps to track and figure out the time spent in processing a frame from its source until scanout. JIRA : TDS-2447 JIRA : TDS-2484 JIRA : TDS-2557 Change-Id: I4e155a89fcc0b9ad3684fd6b315a18a3a91e3503 Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1530827 (cherry picked from commit aa349584a2d23d02d2de1a98641165d820bd0a69) Reviewed-on: https://git-master.nvidia.com/r/1541614 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
* tegra: dc: trace: add trace event for dropped flipPeng Liu2017-09-26
| | | | | | | | | | | | | | | | | | Add trace event to track dropping a flip. Some trace analysis tool can use this to detect the (rare) case that a flip is enqueued and then dropped. Bug 1996268 Change-Id: Iec7e1e896de741c02f2c26fae39c2ea8254b6efa Signed-off-by: Peng Liu <pengliu@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1568075 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Adam Cheney <acheney@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Ujwal Patel <ujwalp@nvidia.com>
* tracing: Add event tracing mechanismSuril2017-09-15
| | | | | | | | | | | | | | | | | | | | | | Add traces for latency measurement to monitor performance. Add events for async_atrace. enable: echo 1 > /sys/kernel/debug/tracing/events/atrace/enable disable: echo 0 > /sys/kernel/debug/tracing/events/atrace/enable AV-388 Change-Id: Id88ab72d1aeab20afc7c0d48dc0fdb905404f5f6 Signed-off-by: Suril Dhruv <sdhruv@nvidia.com> Reviewed-on: http://git-master/r/1497930 Reviewed-on: http://git-master/r/1505062 Reviewed-on: https://git-master.nvidia.com/r/1511675 Reviewed-on: https://git-master.nvidia.com/r/1560227 Reviewed-by: Maneet Maneet Singh <mmaneetsingh@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com>
* video: tegra: host: Add TSP trace eventArto Merilainen2017-08-21
| | | | | | | | | | | | | | | This change adds a trace event for tracking the time the jobs take on engines. This is needed for profiling the engine execution time. Bug 1963657 Bug 1972994 Change-Id: Ic7bf483d10203719fe81fe99caa51f30ca82b002 Signed-off-by: Arto Merilainen <amerilainen@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1538755 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Mikko Perttunen <mperttunen@nvidia.com>
* dc: define IMP trace eventsShu Zhong2017-07-19
| | | | | | | | | | | | | | | | | | | | Add tracepoints for the following IMP events that occur when: 1) An IMP PROPOSE request is received from userspace and queued 2) An IMP flip request is queued, starts execution, and completes 3) The display bandwidth driver reserves and programs the core bandwidth settings 4) The display driver programs any IHUB register settings 5) The display driver specifically adjusts the mempool settings across the other heads TDS-2082 Bug 1600993 Change-Id: I5e2dd05610432d48fac4ddaf28bbb4757f374a88 Signed-off-by: Shu Zhong <shuz@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/1516564 GVS: Gerrit_Virtual_Submit Reviewed-by: Ujwal Patel <ujwalp@nvidia.com>
* Merge 'nvhost/dev-kernel' into nvidiaIshan Mittal2017-06-30
|\ | | | | | | Change-Id: I92c1e2454c19832cf1642bef532be97ee1cb2748
| * include: trace: move nvhost trace files kernel-nvhostShridhar Rasal2016-04-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - this moves nvhost trace events include file to kernel-nvhost [25a8902] <Deepak Nibade> video: tegra: host: deprecate priority support [520d8c2] <Arto Merilainen> video: tegra: host: Improve debugging traces [1c96a92] <Sam Payne> video: tegra: host: remove multiple powergate ids [cd95145] <Shridhar Rasal> video: tegra: host: add traces for actmon load [68e0b2d] <Kevin Huang> video: tegra: host: add trace event for acm [f949d24] <Amit Sharma> video: tegra: host: add trace events for map/unmap [512fb28] <Antti P Miettinen> video: tegra: host: Fix a compile warning [6d64315] <Arto Merilainen> video: tegra: host: gk20a: Add own trace events [f16467e] <Terje Bergstrom> video: tegra: host: Fix compile warnings [38d5198] <Terje Bergstrom> video: tegra: host: Reimplement nvmap_pin in nvhost [e540114] <Ken Adams> video: tegra: host: add ftrace events for nvhost_as [6b717a6] <Terje Bergstrom> video: tegra: host: Add gpfifo tracing [742e520] <Ken Adams> video: tegra: add gpfifo submit trace event [66dba06] <Terje Bergstrom> video: tegra: host: Allow setting save/restore buf [9e283d5] <Terje Bergstrom> video: tegra: host: New submit interface [a1bb1a1] <Mayuresh Kulkarni> video: tegra: host: add per device module [9ad087c] <Terje Bergstrom> video: tegra: host: Add trace events for ACM [7757c5c] <Terje Bergstrom> video: tegra: host: Throttle lower priority jobs [4f82d55] <Terje Bergstrom> video: tegra: host: Replace nvmap structs with own [f36f1d0] <Mayuresh Kulkarni> video: tegra: host: rewrite nvhost_job_pin/unpin APIs [398641b] <Terje Bergstrom> video: tegra: host: Add syncpt trace events [e7ff745] <Terje Bergstrom> video: tegra: host: Add context switch to trace dump [c400f95] <Terje Bergstrom> video: tegra: host: Split submit into subfunctions [f599525] <Terje Bergstrom> video: tegra: host: Add syncpt value to traces [57dac66] <Terje Bergstrom> video: tegra: host: Support for right shift on reloc patches [c0ae81d] <Terje Bergstrom> video: tegra: host: Add syncpt and cmdbuf to trace [1bb6a7f] <Terje Bergstrom> nvhost: Move include files to kernel/include Change-Id: Ia6d222666a3581978bd6b8d4294d5cbaaa037c1b Signed-off-by: Shridhar Rasal <srasal@nvidia.com> Reviewed-on: http://git-master/r/1127346 Reviewed-by: Arto Merilainen <amerilainen@nvidia.com> GVS: Gerrit_Virtual_Submit
* Merge branch 'display/dev-kernel' into nvidiaIshan Mittal2017-06-23
|\ | | | | | | | | | | | | | | | | | | Pulling in all patches from display into nvidia Bug 200295104 Change-Id: I7100ad77b5152d6b9d4ee39c6fb291e5e58557e8 Signed-off-by: Ishan Mittal <imittal@nvidia.com>
| * tegra: dc: Add support for frame/flip lock.Arun Swain2017-04-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Adds support for frame and flip lock. For usecases where there is a need to drive multiple displays on different heads in a synchronized fashion, we need to lock the rasters on the heads and at the same time all the concerned heads need to be flip-locked also so that the changes in images happen in the same frame for all the heads. Since such strict timings (promoting multiple heads atomically) can't be guaranteed via sequential MMIO register writes in dc driver, host1x push-buffer programming is being used where a job for a channel belonging to NvDisplay class is being submitted to host1x. Host1x h/w executes the job of promoting multiple heads at a stretch (within few cycles). This patch does the following : - Implements Frame Locking - Implements Flip Locking. - Adds debugfs nodes. - Adds ioctl support via control interface. Note : Frame lock isn't supported for dsi interface currently Jira TDS-1463 Jira TDS-1466 Jira TDS-2025 Change-Id: Iad713e9cd159eb0823175277b31bcc845f713dcb Reviewed-on: http://git-master/r/1455072 (cherry picked from commit 2dd2247fd1bb9a9082ce79aaa4927663e4ec8234) Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: http://git-master/r/1305691 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * video: tegra: Enhance tracing for display flipsArun Kannan2017-04-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Enhace trace events with additional information that can be used to identify which windows are being flipped and their corresponding buffer handles. These tracepoints were updated: flip_rcvd_syncpt_upd, sync_wt_ovr_syncpt_upd scanout_syncpt_upd Bug 1893996 Change-Id: I31de03d8c9e5923dd474423a3d12bba0f9cc37b2 Signed-off-by: Arun Kannan <akannan@nvidia.com> Reviewed-on: http://git-master/r/1456381 Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com> Reviewed-by: Arun Swain <arswain@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * video: tegra: Add scanline tracepointArun Kannan2017-04-01
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add vblank and vpulse3 scanline tracepoint. Accurate timestamps of these events are embedded in the ftrace prints and they are extrapolations based on current scanline and timestamp (timebase is cycle counter TSC). It can be enabled/disabled by writing to this debugfs node: tracing/events/nvdisp/nvdisp_scanline The ftrace print includes display controller #, frame # and scanline # in addition to timestamp in nsec. The scanline # for VBLANK is specially indicated using value U16_MAX. Bug 1858948 Change-Id: Ib727bcbeb935f39df0e4b4443c97a9b537cf053c Signed-off-by: Arun Kannan <akannan@nvidia.com> Reviewed-on: http://git-master/r/1300684 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
| * video: tegra: dc: add ftrace for vblankThomas Fleury2016-05-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a tracepoint on VBLANK interrupt to indicate the frame counter for current display. 16-bit frame counter is read from DC_COM_RG_DPCA_0 EVLR-315 Change-Id: I92652e746eb766d56460d41a49b50d0a759af58c Reviewed-on: http://git-master/r/1141635 (cherry picked from commit f495f925f5fa24dcb47ba71a3212775fdc5490a7) Reviewed-on: http://git-master/r/1128447 Tested-by: Thomas Fleury <tfleury@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Sungwook Kim <sungwookk@nvidia.com> Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * tegra: dc: trace: Add trace event for hdrArun Swain2016-05-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add trace event for debugging hdr.When enabled this prints out the hdr struct received from hwcomposer in flip. Change-Id: I2b5da80cd829c5881edb06e70cbcf8aad458d65d (cherry picked from commit d11087ec2f9b0e3cedb84f2cd73c29927c715b7b) Reviewed-on: http://git-master/r/926598 Reviewed-on: http://git-master/r/1000368 (cherry picked from commit d81de9b996cb8f1a75d3bba10220eaefcb3a9185) Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: http://git-master/r/1135173 GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * tegra: dc: New trace event for dc balance statsArun Swain2015-05-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Adds a new trace event to get a ball park value for the amount of dc imbalance accumulated after a particular flip. Bug 1638544 Reviewed-on: http://git-master/r/735360 (cherry picked from commit 29088179936e562362814537c809fee36993de39) Change-Id: If788a418c38dfefd00d866bb8c130cba431c82fa Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: http://git-master/r/738662 GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * tegra: dc: New trace event for latency measurementArun Swain2015-05-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Adds a new trace event to get the timestamp when the dc gets unblocked on pre_syncpt_fence for a particular flip. This (sync_wt_ovr_syncpt_upd) alongwith the existing trace events (flip_rcvd_syncpt_upd and scanout_syncpt_upd) help us in measuring latency from the point we receive a flip, the point at which the frame is ready for scan-out and the instant dc actually scans out the same frame. Reviewed-on: http://git-master/r/729291 (cherry picked from commit f16e6c6344e48081e079348610d05ac80df0e1ad) Change-Id: Icc007a58f161570b7dab090bcc843cc8065a1bc6 Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: http://git-master/r/738658 GVS: Gerrit_Virtual_Submit Reviewed-by: Mitch Luban <mluban@nvidia.com>
| * tegra: dc: Add trace events to measure latencyArun Swain2015-04-04
| | | | | | | | | | | | | | | | | | | | | | | | | | Add new trace events for latency measurements. This is the time elapsed between the moment when dc receives a flip and the point in time when dc scans out the same flip. Change-Id: Ib7480cccc71c053e40c85360e5489e78289f0910 Signed-off-by: Arun Swain <arswain@nvidia.com> Reviewed-on: http://git-master/r/680773 GVS: Gerrit_Virtual_Submit Reviewed-by: Jon Mayo <jmayo@nvidia.com>
| * video: tegra: dc: request bandwidth from isomgrJon Mayo2015-03-18
| | | | | | | | | | | | | | | | | | | | | | | | Report event TEGRA_DC_EXT_EVENT_BANDWIDTH through tegra_dc_ctrl device when there is not enough bandwidth. Bug 1169265 Change-Id: Ia95b1ecc7eb16db6f3a709e7c9efc59ab2490ead Signed-off-by: Jon Mayo <jmayo@nvidia.com> Reviewed-on: http://git-master/r/207766 Reviewed-by: Automatic_Commit_Validation_User
| * video: tegra: dc: report correct device id in tracesJon Mayo2015-03-18
| | | | | | | | | | | | | | | | | | | | Display traces were reporting everything as dc0. This fixes that issue. Change-Id: If1378a8777dbd83484b62f44c6138068ff06bd66 Signed-off-by: Jon Mayo <jmayo@nvidia.com> Reviewed-on: http://git-master/r/188357 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Kevin Huang (Eng-SW) <kevinh@nvidia.com>
| * video: tegra: dc: use trace eventsJon Mayo2015-03-18
| | | | | | | | | | | | | | | Use trace events instead of trace_printk. Removed some unnecessary traces. Bug 990469 Change-Id: I060369b12c852b5584634641b8971e23f60fc399 Signed-off-by: Jon Mayo <jmayo@nvidia.com> Reviewed-on: http://git-master/r/138797 Reviewed-by: Simone Willett <swillett@nvidia.com> Tested-by: Simone Willett <swillett@nvidia.com> Rebase-Id: Rf2a4526603f03aea2a7535dfcb48dc4ab2647bd0
* Merge 'nvmap/dev-kernel' into nvidiaIshan Mittal2017-06-15
|\ | | | | | | Change-Id: I9acade6996490fedab64e81ea58871e129897b4d
| * video: tegra: nvmap: update copyrightsSri Krishna chowdary2017-04-26
| | | | | | | | | | | | | | | | | | | | | | | | Update the text used in copyright as per GPLv2. bug 200302395 Change-Id: I5ae6186cbb55f485f81804397db656845c94fcbf Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1469578 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Sachin Nikam <snikam@nvidia.com>
| * video: tegra: nvmap: Add traces in page pool codeSri Krishna chowdary2016-10-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some sample traces collected on t186 are shown below [002] ...1 708.998920: pp_clean_cache: dirty_pages=0, cache_maint_th=512, cache_maint_by_set_ways=1 [002] ...1 709.000100: get_page_list_page: pages left in list=7902 [002] ...1 708.998925: nvmap_pp_alloc_lots: requested:1 alloced:1 [002] ...1 709.632639: nvmap_pp_fill_zero_lots: inserted 1 pages to zero list, freed 0 pages, did not process 0 pages bug 1821934 Change-Id: I17c3bdc9efbea513c5e7d43c568a7a41424fcc76 Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com> Reviewed-on: http://git-master/r/1231316 Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
| * video: tegra: nvmap: expand parameter list for tracepointsThomas Fleury2016-05-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | LTTng does not have access to nvmap private structures. Need to expand parameter list, so that it can hook into tracepoints. Added tag label in traces (nvmap_handle_summary class) EVLR-317 Change-Id: Ic5d70d8c2e9c090f9e955375def8cc15e5d7dcdb Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: http://git-master/r/1127592 GVS: Gerrit_Virtual_Submit Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
| * video: tegra: nvmap: traces points for handle trackingThomas Fleury2016-04-14
| | | | | | | | | | | | | | | | | | | | Jira EVLR-242 Change-Id: I8ecfaa3349a13ae9c82c059fd2c543cb2ecb1de7 Signed-off-by: Thomas Fleury <tfleury@nvidia.com> Reviewed-on: http://git-master/r/1119975 GVS: Gerrit_Virtual_Submit Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2025-04-11 04:06:52 -0400