The following changes implements the initial (as per bringup) nvlink driver.
(1) SW initialization of nvlink core driver structures
(2) Nvlink interrupt handling
(3) Device initialization (IOCTRL, pll and clocks, device level intr)
(4) Falcon support for minion
(5) Minion load and bootstrapping
(6) Link initialization and DL PROD settings
(7) Device Interface init (and switching HSHUB to nvlink)
(8) HS set/get mode for both link and sublink
(9) Topology discovery and VBIOS settings.
(10) Ensures we get physical contiguous memory when Nvlink is enabled
This driver includes a hack for the current single dev/single link limitation.
JIRA: EVLR-2331
JIRA: EVLR-2330
JIRA: EVLR-2329
JIRA: EVLR-2328
Change-Id: Idca9a819179376cc655784482b24b575a52fa9e5
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1656790
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
GV100 currently has has_syncpoint flag set to false and thus basic syncpoint
SHIM requirements are not initialized for GV100
Hence disable syncpoint address support flag for GV100 until has_syncpoint is
enabled
Bug 200327559
Jira NVGPU-511
Change-Id: Iaf73efe0a2939cba802823d64fe7cb93e25bdbd8
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1658065
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add User space API NVGPU_AS_IOCTL_GET_SYNC_RO_MAP to get read-only syncpoint
address map in user space
We already map whole syncpoint shim to each address space with base address
being vm->syncpt_ro_map_gpu_va
This new API exposes this base GPU_VA address of syncpoint map, and unit size
of each syncpoint to user space.
User space can then calculate address of each syncpoint as
syncpoint_address = base_gpu_va + (syncpoint_id * syncpoint_unit_size)
Note that this syncpoint address is read_only, and should be only used for
inserting semaphore acquires.
Adding semaphore release with this address would result in MMU_FAULT
Define new HAL g->ops.fifo.get_sync_ro_map and set this for all GPUs supported
on Xavier SoC
Bug 200327559
Change-Id: Ica0db48fc28fdd0ff2a5eb09574dac843dc5e4fd
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1649365
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add characteristic flag NVGPU_GPU_FLAGS_SUPPORT_SYNCPOINT_ADDRESS to indicate if
platform supports semaphore GPU_VA address for a syncpoint
Define NVGPU_SUPPORT_SYNCPOINT_ADDRESS for core driver book keeping
Set this flag for both GV100 and GV11B since Xavier SoC supports a semaphore
GPU_VA address for a syncpoint through syncpoint SHIM
Bug 200327559
Change-Id: I1f31673c9fd59f493d0b35a80d23151fc063ae06
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1649364
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-pd, scc, ds, ssync, mme and sked exceptions are
enabled. This will be useful for debugging
-Handle enabled interrupts
-Add gr ops to handle ssync hww. For legacy
chips, ssync hww_esr register is gpcs_ppcs_ssync_hww_esr.
Since ssync hww is not enabled on legacy chips, added
ssync hww exception handling for volta only.
Change-Id: I63ba2eb51fa82e74832df26ee4cf3546458e5669
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1644751
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The message to tell RM server to unbind channel has to be sent after
client unbinds the channel and before client calls tsg release. The
channel has to belong to a tsg on RM server before client submit a
runlist to remove the channel. Or there's a bare channel problem.
By moving .tsg_unbind_channl one layer lower, gk20a_tsg_unbind_channel()
will be common functions for all chip, and it'll call tsg release after
call .tsg_unbind_channel. So vgpu won't need to worry about tsg was
released before sending msg to RM server.
Bug 200382695
Bug 200382785
Change-Id: I32acc122f3f9d5d0628049ccf673225f9e90c87a
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1645383
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Created nv_pmu_rpc_struct_acr_bootstrap_gr_falcons struct
- gv100_load_falcon_ucode() function to bootstrap GR
flacons using RPC, wait for INIT_WPR_REGION before
creating & executing BOOTSTRAP_GR_FALCONS RPC.
- Added code to handle BOOTSTRAP_GR_FALCONS ack in
RPC handler
Change-Id: If70dc75bb2789970382853fb001d970a346b2915
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1613316
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Created nv_pmu_rpc_struct_acr_init_wpr_region struct
- Function gv100_pmu_init_acr() to create & execute
INIT_WPR_REGION using RPC.
- Updated gv100 HAL .init_wpr_region to point
to gv100_pmu_init_acr()
- Added code to handle INIT_WPR_REGION ack in
RPC handler.
Change-Id: I699fa945790689e5f24ad5d3de022efb458662e0
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1613290
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Pascal has support for more comptags than Maxwell, but we were using
gm20b definitions for cbc_ctrl on all chips. Specifically field
clear_upper_bound is one bit wider in Pascal.
Implement gp10b version of cbc_ctrl and take that into use in Pascal
and Volta.
Bug 200381317
Change-Id: I7d3cb9e92498e08f8704f156e2afb34404ce587e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1642574
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Lots of code paths were split to T19x specific code paths and structs
due to split repository. Now that repositories are merged, fold all of
them back to main code paths and structs and remove the T19x specific
Kconfig flag.
Change-Id: Id0d17a5f0610fc0b49f51ab6664e716dc8b222b6
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1640606
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Added sw method support for SET_BES_CROP_DEBUG4.
In this sw method:
CLAMP_FP_BLEND_TO_MAXVAL forces overflow and
CLAMP_FP_BLEND_TO_INF blend results to clamp to FP maxval.
Added support for this sw method in gp10b/gp106/gv11b
and gv100.
Bug 2046636
Change-Id: I3a9e97587aca76718f7f504ea3b853f87409092a
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1641529
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
During bringup and before nvlink is up GV100 on the DDPX platform operates
with a very, very slow sysmem link. In order to get sysmem test to pass
it is neccesary to significantly increase most timeouts by an order the
magnitude.
Bug 2040544
Change-Id: I26858afde4ae80c70f86b47cfff674b6b00b5bf8
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1627417
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add an alignment check for compressible-kind fixed-address
mappings. If we're using page size smaller than the comptag line
coverage window, the GPU VA and the physical buffer offset must be
aligned in respect to that window.
Bug 1995897
Bug 2011640
Bug 2011668
Change-Id: If68043ee2828d54b9398d77553d10d35cc319236
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1606439
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove gv11b_init_uncompressed_kind_map(), gv11b_init_kind_attr(), and
the related kind setup code. They are not needed anymore.
While we're doing these changes, remove a redundant assignment of
g->bootstrap_owner in hal_gv100.c.
Bug 1902982
Change-Id: Ib40d8f55cfbfa34143a3765c2b4913926ca021fd
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1560931
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move fuse override DT handling to Linux code. All the chip specific
fuse override functions did the same thing, so delete the HAL and
call the same function to read the DT overrides on all chips.
Also remove the fuse override functionality from dGPU. There are no
DT entries for PCIe devices, so it would've failed anyway.
JIRA NVGPU-259
Change-Id: Ic672e25090cdfc207d9771ab61b6cf53185113a4
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1593693
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Make GPU characteristics flags specific to Linux code only. The
rest of driver is moved to using nvgpu_is_enabled() API.
JIRA NVGPU-259
Change-Id: I46a5a90bb34f170e9e755e7683be142ed6b18cce
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1583992
GVS: Gerrit_Virtual_Submit
- in the native case, replace calls for init_cyclestats with
the gm20b version, as each chip had identical versions of the code.
- in the virtual case, use the vgpu version of the function in order
to get the new max_css_buffer_size characteristic set to the mempool
size.
JIRA ESRM-54
Bug 200296210
Change-Id: I475876cb392978fb1350ede58e37d0962ae095c3
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1578934
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Added method to load mem unlock binary into
nvdec falcon & execute to perform mem unlock
if VPR enabled.
- Updated .mem_unlock gv100 HAL to point
method gv100_fb_memory_unlock().
- Updated .mem_unlock gv11b HAL to NULL.
- Added vpr info hw registers
- Added nvdec enable hw register
Change-Id: Ia4bf820ae103baede679d300d1d390fd748c919a
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
(cherry picked from commit 2e176ad9d47316bf4d001692a2ae07e6c1fb1ccb)
Reviewed-on: https://git-master.nvidia.com/r/1573101
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Updated following hal functions for css gv11b and reused
them for gv100:
enable_snapshot
disable_snapshot
check_data_available
These changes are needed because of following reasons:
1. Register offsets for perf_pmasys_* are changed
for gv11b/gv100 from gk20a.
2. Updated memory type for perf_pmasys_mem_block_target
based on memory aperture used for hwpm inst_block.
Bug 200327596
Change-Id: I500d17670e2f389d8d0e77884374bcc3504a41f8
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1507546
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
SMID tables were generated according with the local tpc and the pagepool and cb
buffers from a different chip and did not take performance in consideration,
which made compute kernels hang with CTAs on the fly.
This change ensures we are using the right sizes and adds proper enumeration
of smids.
JIRA: NVGPUGV100-36
bug 2004378
Change-Id: Ic8f50c325d6d6720cca41d9740ae4f5f51e1100a
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1581664
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Change required for equivalent change on nvgpu. This is required
since a few HALs were added that must be populated for all chips.
This patch adds those HAL definitions for gv11b, gv100, and the
vgpu.
JIRA NVGPU-30
JIRA NVGPU-138
Change-Id: I65374764350a5cacce8624b15d98947fada35a4a
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1579865
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Updated following hal functions for gv11b and reused
them for gv100:
perfbuffer_enable
perfbuffer_disable
These changes are needed because of following reasons:
1. Register offsets for perf_pmasys_* are changed
for gv11b/gv100 from gk20a.
2. Updated memory type for perf_pmasys_mem_block_target
to sys_ncoh_f().
Bug 200327596
Change-Id: Ia672ac561917c8ed36caea9cc7e74b7fc7ce8188
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1571074
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
These changes allow GV100 to init the basic HALs to pass
nvgpu_submit_twod
(1) Allocate fault buffer from vidmem instead of sysmem to prevent coherency
issues
(2) Properly enable FB
(3) Fan control requires the execution of the pre-os FW, without it the SKU201
is extremely noisy
JIRA: NVGPUGV100-9
Change-Id: I9b2072737e45432f957e7faae6d33bc0ab43b817
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1539926
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
We right now call gk20a_fifo_tsg_unbind_channel_verify_status() to verify
channel status while unbinding a channel from TSG while closing
Add support to do this verification per-platform and keep this disabled
for vgpu platforms
Bug 200327095
Change-Id: I6e2a6a09c784d24ac49477d5450b7d4b671878e3
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1572369
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
