summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/nvgpu
Commit message (Collapse)AuthorAge
* gpu: nvgpu: Sparse fixes in gpfifo_mem user gpfifoKonsta Holtta2016-06-21
| | | | | | | | | | | | | | 1) Keep the __user tag in the type of the user gpfifo when copying, 2) use NULL instead of 0 for initializing user_gpfifo pointer. Bug 200067946 Change-Id: I631b4bca44ded0900204134338fa1d62d0017df0 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1168441 GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: use gpfifo_mem via gk20a_mem_{rd,wr}Konsta Holtta2016-06-20
| | | | | | | | | | | | | | | | | | Use gk20a_mem_*() accessors for gpfifo memory in work submission instead of direct cpu accesses in order to support other apertures than sysmem. The gpfifo memory is still allocated from sysmem for dgpus too. Split the copying of priv_cmds and the main gpfifo to be submitted in gk20a_submit_channel_gpfifo() into separate functions. JIRA DNVGPU-21 Change-Id: If271ca8e7e34235f00d31855dbccf77c0008e10b Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1145923 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* Revert "gpu: nvgpu: Disable channel watchdog"Deepak Nibade2016-06-20
| | | | | | | | | | | | | | | | This reverts commit edd080b05ab118307c7c7b01426ea1e7c1cc9be7. Re-enable the watchdog since power management races are now resolved Bug 200198908 Change-Id: I74b97e564583aaedd858bc968adcfcaa275ea739 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1165746 GVS: Gerrit_Virtual_Submit Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: disable batch map buffer in gpu characteristicsRichard Zhao2016-06-17
| | | | | | | | | | | | | | | vgpu has not implemented batch map buffer yet, so report it in gpu characteristics. Bug 200201431 Change-Id: Ia9bfd71735889706242f0c06a1c44c5ed318ab6d Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1157467 (cherry picked from commit c6999995f9a48f645d6ffb6b7361d29cf641e5e3) Reviewed-on: http://git-master/r/1156636 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: ngpu: gm206: use vidmem allocator for ucode blobKonsta Holtta2016-06-17
| | | | | | | | | | | | | Use the general video memory allocator for reserving wpr space for acr ucode blob instead of crafting a mem_desc manually. Jira DNVGPU-16 Change-Id: Ie1b1e4b76b9678a33f4ef10ddcbf85259bfab5fd Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1165643 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: add read ptimer supportRichard Zhao2016-06-16
| | | | | | | | | | | | | Bug 1395833 Change-Id: Id0d427b6a1ddaecfeec33c61a6161679cf596c92 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1159588 (cherry picked from commit d33aa89420990626fb377c56ed5517a00f717c2a) Reviewed-on: http://git-master/r/1158897 Reviewed-by: Thomas Fleury <tfleury@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add read_ptimer to gopsRichard Zhao2016-06-16
| | | | | | | | | | | | | | | Move all places that read ptimer to use the callback. It's for add vgpu implementation of read ptimer. Bug 1395833 Change-Id: Ia339f2f08d75ca4969a443fffc9a61cff1d3d2b7 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1159587 (cherry picked from commit a01f804684f875c9cffc31eb2c1038f2f29ec66f) Reviewed-on: http://git-master/r/1158449 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Allow nvgpu sync_pts to be introspectedAlex Waterman2016-06-16
| | | | | | | | | | | | | | | Allow nvgpu to identify sync_pts that were made by nvgpu so that the underlying data structures can be accessed. This is important for the semaphore fast-path that allows nvgpu to skip doing a long CPU wait on a sync_fence. Bug 1732449 JIRA DNVGPU-12 Change-Id: Iea43de21d2d7a4e75db6b6dbf24efb78ce64d619 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1162688 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix nbsp in KconfigKonsta Holtta2016-06-16
| | | | | | | | | | | Replace an accidental non-breaking space character with a normal space, fixing the "ignoring unsupported character" build warning. Change-Id: Ib3faca8489f083bb0027a8cfea82b256221b4e43 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1165134 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: PMU version updateMahantesh Kumbar2016-06-15
| | | | | | | | | JIRA DNVGPU-34 Change-Id: Ib9618bdd928a02917b40e6f9619265bf27aa6879 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1162632 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add vidmem allocation APIKonsta Holtta2016-06-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | Add in-nvgpu APIs for allocating and freeing mem_descs in video memory. Changes for gmmu tables etc. will be added in upcoming changes. Video memory is allocated via nvmap by initially registering the aperture size to it and binding it to a struct device, and then going via the usual dma alloc. This API allows also fixed-address allocations, meant for reserving special memory areas at boot. The aperture registration is skipped completely if vidmem isn't found for the particular device. gk20a_gmmu_alloc_attr() still uses sysmem, and the unmap/free paths select internally the correct path by the mem_desc's aperture. Video memory allocation is off by default, and can be turned on with CONFIG_GK20A_VIDMEM. JIRA DNVGPU-16 Change-Id: I77eae5ea90cbed6f4b5db0da86c5f70ddf2a34f9 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1157216 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: sysfs: use snprintf instead of sprintfSeshendra Gadagottu2016-06-14
| | | | | | | | | | | | | Use snprintf instead of sprintf to avoid any buffer overflows. Bug 200192125 Change-Id: I6df43c6d6ee62677f5fd4d4e99f16be77c9e101e Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1164312 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Export and rename alloc_fenceAlex Waterman2016-06-14
| | | | | | | | | | | | | | | Rename alloc_fence() to gk20a_alloc_fence() and allow this function to be called by the channel_sync_gk20a.c code. Bug 1732449 JIRA DNVGPU-12 Change-Id: Ic17131db2c8545832a2e8caacbd092cf970af4d1 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1162687 Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: export gk20a_free_priv_cmdbufAlex Waterman2016-06-14
| | | | | | | | | | | | | | | Export gk20a_free_priv_cmdbuf() so that the channel_sync_gk20a.c code can call this function. This is necessary for error paths in the semaphore wait/incr functions. Bug 1732449 JIRA DNVGPU-12 Change-Id: Id2ea13e5553d50475ee1bbf94781e18590321fdf Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1162686 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Fix gk20a_busy() in debug dumpTerje Bergstrom2016-06-14
| | | | | | | | | | | | | | | | | When debug dump is called from an interrupt thread, we do not want to call gk20a_busy() because it causes race in case rail gating is being engaged at the same time. It has to be called from all debugfs paths. Bug 200198908 Bug 1770522 Change-Id: I7eda7d029b0a59cce0320ecc1b750dc2f4d7ccf0 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1163440 GVS: Gerrit_Virtual_Submit Tested-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Disable channel watchdogTerje Bergstrom2016-06-14
| | | | | | | | | | Bug 200198908 Change-Id: I4dfb3517f5467f8b5449e65290453ba1c828243d Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1163439 Tested-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Do not register debug dump to nvhostTerje Bergstrom2016-06-14
| | | | | | | | | | | | | | | | | Do not register device for debug dump to nvhost. This can cause races if nvhost calls debug dump spew at the same time when GPU is being powered off. Bug 200198908 Bug 1770522 Change-Id: Ia7e57437d647041e82dd4c61ffd08fb1cbe1f32f Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1163441 GVS: Gerrit_Virtual_Submit Tested-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
* gpu: nvgpu: Do not complain about default runlistTerje Bergstrom2016-06-14
| | | | | | | | | | | | Do not spew an error when choosing the default runlist for engine. That is normal behavior. Change-Id: Ide786712f3f74bf59aee48de98c2186db1d97378 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1163511 GVS: Gerrit_Virtual_Submit Reviewed-by: Lakshmanan M <lm@nvidia.com> Tested-by: Lakshmanan M <lm@nvidia.com>
* gpu: nvgpu: Balance curly bracesAlex Waterman2016-06-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | In some of the conditionally compiled code in the nvgpu driver there are places where the code looks like: #ifdef LINUX_VERSION_CODE < KERNEL_VERSION(3,18,0) some-loop { #else a-diff-loop { #endif /* Some code... */ } This leaves unbalanced curley braces: two open braces for one close brace. This messes up some editors syntax highlighting and auto- indentation features. This patch puts in the extra brace. It's not necessary for compiling code but it makes some editors much happier. Change-Id: Ida28bc001cc840fe52a43982db934d49c07cc7d3 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1153668 Reviewed-by: Konsta Holtta <kholtta@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add uapi support for non-graphics enginesLakshmanan M2016-06-13
| | | | | | | | | | | | | | | | | | | Extend the existing NVGPU_GPU_IOCTL_OPEN_CHANNEL interface to allow opening channels for other than the primary (i.e., the graphics) runlists. This is required to push work to dGPU engines that have their own runlists, such as the asynchronous copy engines and the multimedia engines. Minor change - Added active_engines_list allocation and assignment for fifo_vgpu back end. JIRA DNVGPU-25 Change-Id: I3ed377e2c9a2b4dd72e8256463510a62c64e7a8f Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1161541 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: optimize mem_desc accessor loopsKonsta Holtta2016-06-13
| | | | | | | | | | | | | | Instead of going via gk20a_mem_{wr,rd}32() on each iteration, do direct memcpy/memset with sysmem, and minimize the enter/exit overhead with vidmem. JIRA DNVGPU-23 Change-Id: I5437e35f8393a746777a40636c1e9b5d93ced1f6 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1159524 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Support third GPU version on T18xTerje Bergstrom2016-06-13
| | | | | | | | Change-Id: I3f1645ed7a465c93b0a0a6f885ef77bea0066ed0 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1160372 GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
* gpu: nvgpu: Check result of gk20a_pmu_initTerje Bergstrom2016-06-13
| | | | | | | | | | | | | If PMU version is not supported, gk20a_pmu_init returns an error code. Check the error code and fail poweron if gk20a_pmu_init fails. Change-Id: Ia1d6a6fcbcc5a144d2e5bc88734df778e887fa53 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1160371 Reviewed-by: Alex Waterman <alexw@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
* gpu: nvgpu: Rework the channel timeout handler messagesAlex Waterman2016-06-13
| | | | | | | | | | | | | | Rework how the messages in the channel timeout handler to be a little bit more verbose and more clear about what is happening. Bug 1732449 JIRA DNVGPU-12 Change-Id: Ifc018d99c647b3036caa8ad453e5e3dfc4151396 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1153669 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Remove dead priv_cmdbuf codeAlex Waterman2016-06-13
| | | | | | | | | | | | | | Remove the gp_get and gp_put pointers from the priv_cmdbuf code. These pointers appear to track the position of th the priv_cmdbuf in the gp_fifo. However, these pointers are not used for anything nor are they needed for anything in the future. This code appears to be a relic left over from the past. Change-Id: Ibed1a6d51fa0cac12c5e0429760e8e2f611fc899 Signed-off-by: Alex Waterman <alexw@nvidia.com> Reviewed-on: http://git-master/r/1161859 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add uapi support for NVGPU_GPU_IOCTL_GET_ENGINE_INFOLakshmanan M2016-06-10
| | | | | | | | | | | | | | | | Implement NVGPU_GPU_IOCTL_GET_ENGINE_INFO for retrieving the list of supported engines and their corresponding run list id:s. JIRA DNVGPU-25 Change-Id: I8703388660190f7dcb509c0676f283ca4b820b6f Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1160939 Reviewed-by: Sami Kiminki <skiminki@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix sparse warningsLakshmanan M2016-06-10
| | | | | | | | | | | | | | | | | | | | Fixed the following sparse warnings: - warning: symbol 'gm206_ce_isr' was not declared. Should it be static? - warning: symbol ''gm206_ce_nonstall_isr' was not declared. Should it be static? Bug 200088648 Change-Id: I30f66ba4225d5544d6110bc4a70235234ad4001d Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1161604 Reviewed-by: Amit Sharma (SW-TEGRA) <amisharma@nvidia.com> Reviewed-by: Sachin Nikam <snikam@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Alex Waterman <alexw@nvidia.com> Reviewed-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: fix event id pollingDeepak Nibade2016-06-10
| | | | | | | | | | | | | | | | | | | In gk20a_event_id_poll(), we always set the mask value and return it. This causes poll() from UMD to be always successful irrespective of event is really generated or not Fix this by adding a flag event_posted for each event Set this flag while posting the event In gk20a_event_id_poll(), set the mask value only if this flag is set. If flag is set, set mask and clear the flag Bug 200089620 Change-Id: If14236547c611fe4bfa1410ff5b69c9fa02d43bb Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1160253 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: ACR interface updateMahantesh Kumbar2016-06-09
| | | | | | | | | | | | | | | - ACR interface update to support next GPU chip ACR boot - Udpate falcon ID JIRA DNVGPU-34 Change-Id: Ic9e5e1f9bd965dbb65b4feaadcf63e457b49263b Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161695 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: update PMU version, interface & codeMahantesh Kumbar2016-06-09
| | | | | | | | | | | | | | | | | - update PMU interface/code to support latest version of secure boot FW - Add PMU FW version for next GPU support - can_elpg check in pmu_setup_hw helps to fix queue error JIRA DNVGPU-34 Change-Id: Iecf47fbc5b71cbf0f4bcdfeafad5c635cb6bff82 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1161107 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: add general event supportRichard Zhao2016-06-09
| | | | | | | | | | | | | | | | Events like bpt int/pause will help cuda work properly. Bug 200173403 VFND-1568 Change-Id: I29e534969028bf08aedd81c99f5a536779f431d1 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1159621 (cherry picked from commit a266e53c514639e15ed166e2c8ce5a55efc48eda) Reviewed-on: http://git-master/r/1152154 Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: add channel enable supportRichard Zhao2016-06-09
| | | | | | | | | | | | | | Bug 200173403 VFND-1568 Change-Id: I3636a77bbbbd719e961dce5ca7ca7bdd5aa33881 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Reviewed-on: http://git-master/r/1159620 (cherry picked from commit b22fb6518da15a09c3e298213af5e60b8e6907a2) Reviewed-on: http://git-master/r/1155403 Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: vgpu: add channel force resetSachit Kadle2016-06-09
| | | | | | | | | | | | | | | | Add forced channel reset support for vgpu Bug 200187507 JIRA EVLR-337 Change-Id: I48e3e2b430f3a4ae94244225232902a8c037cb07 Signed-off-by: Sachit Kadle <skadle@nvidia.com> Reviewed-on: http://git-master/r/1154781 (cherry picked from commit abd6688801fe76c822d6f67f554c18705d9f23d6) Reviewed-on: http://git-master/r/1161259 GVS: Gerrit_Virtual_Submit Tested-by: Richard Zhao <rizhao@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* Revert "gpu: nvgpu: take power refcount in ISR"Terje Bergstrom2016-06-09
| | | | | | | | | This reverts commit 2219f38727ffa17291e15c1898bd3e65f43d09fd. It leaves GPU in on state for some tests that require powering down GPU. Change-Id: I79d44fed729e98692021c57bbeff6a0ef2e8c983 Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1161846
* gpu: nvgpu: include matching header in mm_gm106.cKonsta Holtta2016-06-09
| | | | | | | | | | | | | Include mm_gm106.h in mm_gm106.c to bring function declarations visible and to fix a Sparse warning. Bug 200088648 Change-Id: Ifbedafdd75ce0ee019b39d507b8b113cccdc8918 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1161608 GVS: Gerrit_Virtual_Submit Reviewed-by: Sachin Nikam <snikam@nvidia.com>
* gpu: nvgpu: detect vidmem configuration from HWKonsta Holtta2016-06-08
| | | | | | | | | | | | | Read video memory size from hardware during initialization for devices that support it. JIRA DNVGPU-14 Change-Id: If190f2d89f7148520ee274ca674f972987c8056d Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1157215 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: take power refcount in ISRDeepak Nibade2016-06-08
| | | | | | | | | | | | | | | | | | | | | | | | We sometimes see race conditions where power refcount is zero during ISR or bottom half. If bottom half calls gk20a_busy(), it will lead to boot up of GPU, but it is also possible that we are already trying to poweroff GPU since power refcount is zero Fix this by taking a power refcount with gk20a_busy_noresume() in ISR and then dropping this refcount at the end of bottom half Add new API gk20a_idle_nosuspend() to drop a refcount without initiating suspend Bug 200198908 Bug 1770522 Change-Id: Iec3d4dc8d468f49b71919d2bbc327da48b97bcab Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1160035 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Add multiple engine and runlist supportLakshmanan M2016-06-07
| | | | | | | | | | | | | | | | | | | | | | | This CL covers the following modification, 1) Added multiple engine_info support 2) Added multiple runlist_info support 3) Initial changes for ASYNC CE support 4) Added ASYNC CE interrupt handling support for gm206 GPU family 5) Added generic mechanism to identify the CE engine pri_base address for gm206 (CE0, CE1 and CE2) 6) Removed hard coded engine_id logic and made generic way 7) Code cleanup for readability JIRA DNVGPU-26 Change-Id: I2c3846c40bcc8d10c2dfb225caa4105fc9123b65 Signed-off-by: Lakshmanan M <lm@nvidia.com> Reviewed-on: http://git-master/r/1155963 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* drivers: gpu: nvgpu: Update PMU version for gk20aSupriya2016-06-07
| | | | | | | | | | | | | | | | | -T124 P4 Cl for the change 20824361 -P4 CL Removes accesses to ZBC L2 save/restore -during ELPG Bug 1746047 Bug 200204625 Change-Id: I5a52de7de51e723eae02f82c6c6fc9a213f9cd0e Signed-off-by: Supriya <ssharatkumar@nvidia.com> Reviewed-on: http://git-master/r/1159464 Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com> Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: add call back for get_cur_freqsreenivasulu velpula2016-06-07
| | | | | | | | | | | | | | | | | | | | | | | | When thermal throttling triggers gpcclk clock changes, devfreq driver need to have call back for get_cur_freq to get current gpu frequency. With out this change, "17000000.gp10b/cur_freq" interface won't show the current gpcclk frequency, when thermal throttling triggers gpcclk frequency changes. Bug 1740309 Change-Id: I2484728094883abc285b2a3808bb2cef26a4ea96 Signed-off-by: sreenivasulu velpula <svelpula@nvidia.com> Reviewed-on: http://git-master/r/1145912 (cherry picked from commit 0a6ef7b121d1b8aeba42cefa6e8b090b1ccd15e7) Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1147652 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: remove clockgate_delay paramSeshendra Gadagottu2016-06-07
| | | | | | | | | | | | Removed platform data parameter clockgate_delay, since it is not really used for gpu clock gating any more. Also use railgate_delay as autosuspend delay instead of clockgate_delay. Change-Id: I5b594b5a0e84295ed9971ecdf4865dc1a7dd936d Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1159593 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: cache whole bar0_window for mem accessesKonsta Holtta2016-06-07
| | | | | | | | | | | | | | Save the whole bar0 window register that encodes also the target aperture (vid/sys mem) instead of only the base address that could overlap between the two. JIRA DNVGPU-23 Change-Id: I2ccbea0e1f7c7310c1ca6b158afafe8fd974a615 Signed-off-by: Konsta Holtta <kholtta@nvidia.com> Reviewed-on: http://git-master/r/1159523 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu:nvgpu: add sysfs nodes for ptimer freqSeshendra Gadagottu2016-06-06
| | | | | | | | | | | | | | | | | | | | | | With current ptimer_scale_factor sysfs node, some precision is lost while converting scaling factor to floating point and similarly more precision will be lost while converting back to fixed point. To avoid this, kernel will export following two sysfs nodes: ptimer_ref_freq : ptimer reference frequency( in hz) ptimer_src_freq : ptimer source frequency (in hz) in current chip architecture. Client will apply proper scaling factor by doing ptimer_ref_freq / ptimer_src_freq. Change-Id: I84516e235cc3fffe4cb9a73903416478f4050a9a Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com> Reviewed-on: http://git-master/r/1139985 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
* gpu: nvgpu: vgpu: add support for max_freqPeter Daifuku2016-06-06
| | | | | | | | | | | | | | | | | | Add vgpu support for max_freq characteristic Bug 200182714 JIRASW VFND-1570 Change-Id: Ibeddfbba1bf0529d6f576cefcb82978dbae315d1 Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com> Reviewed-on: http://git-master/r/1149216 (cherry picked from commit 8e8b5979e87268401d5b0fc658a73589710a2e09) Reviewed-on: http://git-master/r/1155416 Reviewed-by: Automatic_Commit_Validation_User Reviewed-by: Richard Zhao <rizhao@nvidia.com> Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com> GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: return if no fecs intrDeepak Nibade2016-06-06
| | | | | | | | | | | | | | | In gk20a_gr_handle_fecs_error(), if we do not see any error interrupt from gr_fecs_host_int_status_r(), just return immediately Bug 1646259 Change-Id: Iea037e0dab57111d2a0fb41c5c19529b7d6c83c0 Signed-off-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-on: http://git-master/r/1158591 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu; pmu version updateMahantesh Kumbar2016-06-06
| | | | | | | | | | | | | | | | | - P4 CL 20527959 - pmu version update for idle slowdown ucode CL http://git-master/r/#/c/1029404/ - configure LDIV slowdown factor to BY16 using linear slowdown NV_THERM_FPDIV_BY16-0x1e value Bug 200144583 Change-Id: Id15441a88ca980ab3f4f8a70e86cae5e59976829 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1159232 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: Fix calculation of timeoutTerje Bergstrom2016-06-05
| | | | | | | | | | | Fix calculation of timeout in multiple places. The #defines GR_IDLE_CHECK_DEFAULT and GR_IDLE_CHECK_MAX are meant to be used only for defining the frequency of checking for timeout. Using them for actual timeouts makes the timeout really short. Change-Id: I3d0f8cbc91d619be8e5a9168ee1ab1d6298f129b Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com> Reviewed-on: http://git-master/r/1158269
* gpu: nvgpu: enable gm204/gm206 GPMU secure bootMahantesh Kumbar2016-06-05
| | | | | | | | | | | | enable gm204/gm206 GPMU secure boot & build. JIRA DNVGPU-11 Change-Id: I3502d227d0baad9e3a27f46d1d6b0d2a83503b6c Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1156331 Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: PMU support for gm204/gm206Mahantesh Kumbar2016-06-05
| | | | | | | | | | | | | | Adding PMU modules to boot & comunicate with PMU F/W JIRA DNVGPU-11 Change-Id: I5afc9209f70fc13376268f9c94daef6b75527c71 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1156028 GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
* gpu: nvgpu: PMU interface's for gm204/gm206Mahantesh Kumbar2016-06-05
| | | | | | | | | | | | | | Adding PMU interface's to support gm206/gm204 JIRA DNVGPU-11 Change-Id: I55671239cdb44804e7dd740d5e22a54e668005f4 Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com> Reviewed-on: http://git-master/r/1155940 Reviewed-by: Automatic_Commit_Validation_User GVS: Gerrit_Virtual_Submit Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com> Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-10-28 19:45:00 -0400