On gv11b we can have multiple SMs per TPC. Add sm_per_tpc in
vgpu constants to properly dimension the virtual SM to TPC/GPC
mapping in virtualization case.
Use TEGRA_VGPU_CMD_GET_SMS_MAPPING to query current mapping.
Bug 2039676
Change-Id: I817be18f9a28cfb9bd8af207d7d6341a2ec3994b
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1631203
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Check the availability of ecc units by checking
relevant ecc fuse and fuse overrides.
During gpu boot, initialize ecc units by scrubbing
individual ecc units available. ECC initialization
should be done before gr initialization.
Following ecc units are scrubbed:
SM LRF
SM L1 DATA
SM L1 TAG
SM CBU
SM ICACHE
Bug 200339497
Change-Id: I54bf8cc1fce639a9993bf80984dafc28dca0dba3
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1612734
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In __gr_gk20a_exec_ctx_ops(), we directly access linux specific pages to check
if memory is allocated or not
Since we need to remove this linux specific dependency from common code,
use common API nvgpu_mem_is_valid() to check if memory is allocated or not
Jira NVGPU-448
Change-Id: Iad62482ad1c0dfad3b96c6c125c2641bbe6ea596
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1612445
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Alex Waterman <alexw@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>
In gr_gk20a_init_access_map(), we declare num_entries as "unsigned int"
But this variable is implicitly type casted into "int" while calling subsequent
functions
Hence explicitly declare it as type "int"
Also declare variable "w" as "int" too since we use it to compare against
num_entries
Jira NVGPU-446
Change-Id: I289da6951db0a9ed6b8d6bcb3ee4f6071a4ddaf0
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1612444
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Alex Waterman <alexw@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>
Remove linux specific #include "common/linux/os_linux.h" from common source
files gr_gk20a.c/gr_gm20b.c/gr_gp10b.c
Remove use of ZERO_OR_NULL_PTR() and simply check if pointer is NULL or not
Jira NVGPU-405
Change-Id: I663fe298cc720f0b0e22beaa05697b18b375a204
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1607233
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
For gv11b, configured gfx preemption wfi timeout in usec.
Set timeout unit as usec in gr_gv11b_init_preemption_state.
Used default timeout as 1msec and this timeout value can
be modified through sysfs node:
/sys/devices/gpu.0/gfxp_wfi_timeout_count
For gp10b:
gfxp_wfi_timeout_count is in syclk cycles
For gv11b:
gfxp_wfi_timeout_count is in usec
Bug 2003668
Change-Id: I68d52ce996a83df90b8b3a8164debb07e5cb370f
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1599658
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
With recent rework in nvgpu most of the <uapi/linux/nvgpu.h> includes
are not needed so remove them
Remove use of NVGPU_DBG_GPU_REG_OP_* in gk20a/gr_gk20a.c and use common
definition instead
Remove use of NVGPU_ALLOC_GPFIFO_FLAGS_REPLAYABLE_FAULTS_ENABLE in
gp10b/fifo_gp10b.c by defining new common flag
NVGPU_GPFIFO_FLAGS_REPLAYABLE_FAULTS_ENABLE and then parsing it in API
nvgpu_gpfifo_user_flags_to_common_flags()
Jira NVGPU-363
Change-Id: I8e653275ea3f443f24be7284d54f2115636aba3f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1606108
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
All the linux specific error_notifier codes are defined in linux specific
header file <uapi/linux/nvgpu.h> and used in all the common driver
But since they are defined in linux specific file, we need to move all the
uses of those error_notifiers in linux specific code only
Hence define new error_notifiers in include/nvgpu/error_notifier.h and
use them in the common code
Add new API nvgpu_error_notifier_to_channel_notifier() to convert common
error_notifier of the form NVGPU_ERR_NOTIFIER_* to linux specific error
notifier of the form NVGPU_CHANNEL_*
Any future additions to error notifiers requires update to both the form
of error notifiers
Move all error notifier related metadata from channel_gk20a (common code)
to linux specific structure nvgpu_channel_linux
Update all accesses to this data from new structure instead of channel_gk20a
Move and rename below APIs to linux specific file and declare them
in error_notifier.h
nvgpu_set_error_notifier_locked()
nvgpu_set_error_notifier()
nvgpu_is_error_notifier_set()
Add below new API and use it in fifo_vgpu.c
nvgpu_set_error_notifier_if_empty()
Include <nvgpu/error_notifier.h> wherever new error_notifier codes are used
NVGPU-426
Change-Id: Iaa5bfc150e6e9ec17d797d445c2d6407afe9f4bd
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1593361
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This patch removes the dependency on the header file "uapi/linux/nvgpu.h"
for regops_gk20a.c. The original structure and definitions in the
uapi/linux/nvgpu.h is maintained for userspace libnvrm_gpu.h. The
following changes are made in this patch.
1) Defined common versions of the NVGPU_DBG_GPU_REG_OP* definitions inside
regops_gk20a.h.
2) Defined common version of struct nvgpu_dbg_gpu_reg_op inside
regops_gk20a.h naming it struct nvgpu_dbg_reg_op.
3) Constructed APIs to convert the NVGPU_DBG_GPU_REG_OP* definitions from
linux versions to common and vice versa.
4) Constructed APIs to convert from struct nvgpu_dbg_gpu_reg_op to
struct nvgpu_dbg_reg_op and vice versa.
5) The ioctl handler nvgpu_ioctl_channel_reg_ops first copies from
userspace into a local storage based on struct nvgpu_dbg_gpu_reg_op which
is copied into the struct nvgpu_dbg_reg_op using the APIs above and
after executing the regops handler passes the data back into userspace
by copying back data from struct nvgpu_dbg_reg_op to struct
nvgpu_dbg_gpu_reg_opi.
JIRA NVGPU-417
Change-Id: I23bad48d2967a629a6308c7484f3741a89db6537
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1596972
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a translation layer to convert from the NVGPU_AS_* flags to
to new set of NVGPU_VM_MAP_* and NVGPU_VM_AREA_ALLOC_* flags.
This allows the common MM code to not depend on the UAPI header
defined for Linux.
In addition to this change a couple of other small changes were
made:
1. Deprecate, print a warning, and ignore usage of the
NVGPU_AS_MAP_BUFFER_FLAGS_MAPPABLE_COMPBITS flag.
2. Move the t19x IO coherence flag from the t19x UAPI header
to the regular UAPI header.
JIRA NVGPU-293
Change-Id: I146402b0e8617294374e63e78f8826c57cd3b291
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1599802
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Add update_patch_count parameter to ctx_patch_write_begin/end functions
If True, the main_image_patch_count register will be updated. Previously,
the patch count would be updated if the cpu_va for the graphics context
was non-NULL, but this only works for sysmem (cpu_va is always 0 for vidmem)
- Remove unused patch parameter for the commit_global_timeslice functions
JIRA ESRM-74
Bug 2012077
Change-Id: I35d0a9eb48669a227833bba1d2e63e9fe8fd8aa9
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1594790
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gr_gp10b_alloc_gr_ctx(), we use linux specific flags NVGPU_ALLOC_OBJ_FLAGS_*
Since common code should be independent of linux specific code, define new flags
NVGPU_OBJ_CTX_FLAGS_SUPPORT_* in common code and use them wherever needed
Linux code will parse the user flags and send appropriate flags to
g->ops.gr.alloc_obj_ctx()
Also remove use of NVGPU_ALLOC_OBJ_FLAGS_LOCKBOOST_ZERO since this seems to be
deadcode anyways
Jira NVGPU-382
Change-Id: Id82efe0d46ddc3e2c063610025ea57f283bc3510
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1594452
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Since NVGPU_AS_MAP_BUFFER_FLAGS_DIRECT_KIND_CTRL was made mandatory,
kernel does not need to know the details about the PTE kinds
anymore. Thus, we can remove the kind_gk20a.h header and the code
related to kind table setup, as well as simplify buffer mapping code
a bit.
Bug 1902982
Change-Id: Iaf798023c219a64fb0a84da09431c5ce4bc046eb
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1560933
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: Iba64a5d53bf4eb94198c0408a462620efc2ddde4
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1593687
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Make NVGPU_AS_MAP_BUFFER_FLAGS_DIRECT_KIND_CTRL mandatory for all map
IOCTLs. We'll clean up the legacy kernel code in subsequent patches.
Remove support for NVGPU_AS_IOCTL_MAP_BUFFER. It has been superseded
by NVGPU_AS_IOCTL_MAP_BUFFER_EX.
Remove legacy definitions to nvgpu_map_buffer_args and the related
flags, and update the in-kernel map calls accordingly by switching to
the newer definitions.
Bug 1902982
Change-Id: Ie9a7f02b8d5d0ec7c3722c4481afab6d39b4fbd0
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1560932
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-Power features should be enabled only if s/w flags xxcg_enabled
are set for corresponding features. These flags control whether
feature should be kept disabled in the hardware or not. For disable
case, register programming will happen for CG registers
and they will be set to disabled. For ELPG, init command will be
sent to PMU, but “ELPG_ALLOW” will not be sent to PMU.
Also these flags can be modified using sysfs. These flags
are noop if corresponding can_xxxg flags are set to flase.
S/w flags can_xxxg tell the ability of platform to support
a power feature and cannot be modified by syfs. Setting these
flags to false will avoid any HW register write or init sequence
for the power feature from executing. For ELPG, no commands will
be sent to PMU.
-g->elcg_enabled flag should not be modified here.
It should be modified only by sysfs. This will be cleaned up in
follow up implementation where debug session will have some kind
of lock where it will keep power features disabled as long as it
wants to. Debugger cannot rely on this flag to keep power
management disabled as these flags can be changed from sysfs.
Due to this issue someone can easily break debugging session
by accidentally changing something in sysfs.
Proper fix for this is being tracked in NVGPU-320
Bug 1982434
Change-Id: I660ef02491f4df9910bf4dea3561ac8a0838e1b1
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1587205
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
All the event ids NVGPU_IOCTL_CHANNEL_EVENT_ID_* are defined in linux
specific user header uapi/linux/nvgpu.h and can't be used in common
code
Hence add new definitions of type NVGPU_EVENT_ID_* for all the events
in common code and use them wherever required in common code
For future additions to event ids, we need to update both
NVGPU_IOCTL_CHANNEL_EVENT_ID_* and NVGPU_EVENT_ID_* fields
Also add new API nvgpu_event_id_to_ioctl_channel_event_id() to convert
common event_id of the form NVGPU_EVENT_ID_* to Linux specific event_id
of the form NVGPU_IOCTL_CHANNEL_EVENT_ID_*
Use this API in gk20a_channel/tsg_event_id_post_event() to get correct
event_id
Jira NVGPU-259
Change-Id: I15a7f41181fdbb8f1876f88bbcd044447d88325f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1591434
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>
gr_gk20a_ctx_patch_write_begin() updates the patch buffer data_count
when the associated graphics context memory buffer has been
CPU-mapped; it was doing so by looking for a non-null cpu_va.
However, if the graphics context has been allocated from vidmem,
cpu_va is always 0, so we can't tell if nvgpu_mem_begin() was called
for the context buffer or not.
Instead:
- add a cpu_accessible flag to the nvgpu_mem struct and set
it in nvgpu_mem_begin()
- return the value of that flag in nvgpu_mem_cpu_accessible()
- gr_gk20a_ctx_patch_write_begin() now calls this new function
instead of checking cpu_va.
Bug 2012077
JIRA ESRM-74
Change-Id: I8401699f30b4ae7154111721c25c7ec3ff95d329
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1587293
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_gr_reset(), we acquire g->gr.fecs_mutex and call a bunch of APIs
But in case any of these APIs fail, we don't release the mutex and just
return the error leaking the mutex
So the next attempt to acquire g->gr.fecs_mutex results in a deadlock
Fix this by releasing the mutex before returning error
Bug 2015370
Change-Id: I9a0214ff53515f819c6566c7d44d1898027416e1
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589062
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
API gr_gp10b_create_sysfs() and GR HAL create_gr_sysfs() right now receive
linux specific struct device
But since this function is called from/declared in common code, we need to
remove linux dependency from it
Hence update the API and GR HAL to receive struct gk20a pointer instead
of device pointer
Jira NVGPU-259
Change-Id: I7effa16407d47a2ab5f9562ec4a4dec975a32d6c
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588464
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Split the ctxsw trace "core" API code into <nvgpu/ctxsw_trace.h>. This
is not perect though since there's some Linuxisms present in the HAL
and as such that code has to be hidden by the ctxsw tracing CONFIG. But
this patch should work for QNX such that it will allow the code to
build as long as CONFIG_GK20A_CTXSW_TRACE is not set.
Also fix the copywrite notice in the ctxsw code present under
common/linux to be GPL.
JIRA NVGPU-287
Change-Id: I94715864caf335b7220185492e4629d713b025e0
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589429
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Use nvgpu_alloc_obj_ctx_args structure specific to Linux code only.
Pass the fields of the structure as separate arguments to all common
functions.
gr_ops_gp10b.h referred to the struct, but it's not used anywhere,
so delete the file.
JIRA NVGPU-259
Change-Id: Idba78d48de1c30f205a42da2fe47a9f8c03735f1
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586563
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Migrate ctxsw_trace_gk20a.c to common/linux/ctxsw_trace.c. This
has been done becasue the ctxsw tracing code is currently too
tightly tied to the Linux OS due to usage of a couple system calls:
- poll()
- mmap()
And general Linux driver framework code. As a result pulling the
logic out of the FECS tracing code is simply too large a scope for
time time being.
Instead the code was just copied as much as possible. The HAL ops
for the FECS code was hidden behind the FECS tracing config so
that the vm_area_struct is not used when QNX does not define said
config. All other non-HAL functions called by the FECS ctxsw
tracing code ha now also been hidden by this config. This is not
pretty but for the time being it seems like the way to go.
JIRA NVGPU-287
Change-Id: Ib880ab237f4abd330dc66998692c86c4507149c2
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586547
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Delte the Linux headers and make some modifications to get rid of the
minor compilation issues that resulted.
- Add <linux/iommu.h> to os_linux.h
- Delete #if 0 code that "flushed" a buffer in gr_gk20a.c
- Delete FLUSH_CPU_DCACHE() macro
- Move the cache flush definitions to <nvgpu/linux/vm.h>
and include this header in sim_gk20a.c. This file will
not be used by QNX so this should be fine.
- Add <linux/pci_ids.h> to gp106/bios_gp106.c and
gp106/mclk_gp106.c.
- Move function to common/linux/dmabuf.h since it is a
dmabuf related function and uses a struct device pointer
as an argument.
JIRA NVGPU-30
Change-Id: I11f56b98524c7fac3efa91b4686592130e5f8a46
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1585510
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a sysfs node to allow root user to set PRI_FE_GFXP_WFI_TIMEOUT, for gp10b
only, in units of sysclk cycles. Store the set value in a variable, and write
the set value to register after GPU is un-railgated.
NV_PGRAPH_PRI_FE_GFXP_WFI_TIMEOUT is engine_reset after Bug 1623341.
Change default value to be specified in cycles, rather than time. This value
is almost the current value in cycles calculated each boot.
Bug 1932782
Change-Id: I0a4207e637cd1413a1be95abe2bcce3adccf76fa
Reviewed-on: https://git-master.nvidia.com/r/1540939
Signed-off-by: Jonathan McCaffrey <jmccaffrey@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1580999
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
We right now initialize czf_bypass value in gr_gp10b_init_preemption_state()
which is run at every rail ungate
And that results in any user specified value through sysfs getting lost after
railgate
To fix this, move initialization of czf_bypass to gk20a_init_gr_setup_sw() so
that it gets initialized only once
Add new HAL g->ops.gr.init_czf_bypass to initialize same and define it for
gp10b/gp106/vgpu-gp10b
Bug 2008262
Change-Id: I80a38ef527c86e32c6d64d0626b867239db9ea51
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1585224
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move much of the remaining generic MM code to a new common location:
common/mm/mm.c. Also add a corresponding <nvgpu/mm.h> header. This
mostly consists of init and cleanup code to handle the common MM
data structures like the VIDMEM code, address spaces for various
engines, etc.
A few more indepth changes were made as well.
1. alloc_inst_block() has been added to the MM HAL. This used to be
defined directly in the gk20a code but it used a register. As a
result, if this register hypothetically changes in the future,
it would need to become a HAL anyway. This path preempts that
and for now just defines all HALs to use the gk20a version.
2. Rename as much as possible: global functions are, for the most
part, prepended with nvgpu (there are a few exceptions which I
have yet to decide what to do with). Functions that are static
are renamed to be as consistent with their functionality as
possible since in some cases function effect and function name
have diverged.
JIRA NVGPU-30
Change-Id: Ic948f1ecc2f7976eba4bb7169a44b7226bb7c0b5
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1574499
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Updated gk20a_gr_handle_class_error with
sub channel info, mme related info.
Also printing the correct method info from
isr_data->offset by left shifting it by 2.
Generated following hw definitions for gk20a/gm20b/gp10b/gp106
to dump relevant data in gk20a_gr_handle_class_error:
gr_trapped_addr_mme_generated_v
gr_trapped_addr_datahigh_v
gr_trapped_addr_priv_v
gr_trapped_data_lo_r
gr_trapped_data_mme_r
gr_trapped_data_mme_pc_v
Bug 2003671
Change-Id: I02e15ef16d7498b6a7dc2af547a14e84d570e8a7
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1574061
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Patch buffer can hold 128 u32 entries. Each patch write
takes total of 2 u32 entries, 1 u32 for addr and 1 u32
for data. Ideally 64 entries could be written before buffer
overflows. Driver patch some things when creating the channel,
and later when context switch type is changed after channel is loaded.
Reset patch_ctx.data_count before beginning patch
write otherwise system might not be in a state to accept all
patch writes even if patch buffer has valid entries.
If the patch buffer has non-zero entries, then the patch buffer
would be read and all pri writes would be sent out. Once done,
ucode updates the main header patch buffer count to 0.
Without this fix, below priv errors seen on t186 platforms
SYS Write error for ADR 0, INFO 0d000200 and CODE badf1100
Error info decodes as:
NV_PPRIV_SYS_PRIV_ERROR_INFO R[0x00122128]
SUBID [29:24] 13 (?)
LOCAL_ORDERING [22:22] 0 (I)
PRIV_LEVEL [21:20] 0 (I)
SENDING_RS [17:12] 0 (I)
PENDING [ 9: 9] 1 (?)
ORPHAN [ 8: 8] 0 (I)
PRIV_MASTER [ 5: 0] 0 (I)
Ctxsw ucode(subid 13 i.e. 0xd) makes only few pri transactions
at priv level 0. Patch buffer pri writes are one of those.
Bug 200350539
Change-Id: If9e71b5fef4d85600d72a8a633a082d9261c3e1b
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1581591
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Handle the possibility of failing gr init due to smid table initialization
failures
bug 2004378
Change-Id: I904b918a0ea31c32292edb3ab8ac3b1459c38a28
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1581661
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Move most of the dma_buf usage present in the mm_gk20a.c code
out to Linux specific code and some commom/mm code. There's
two primary groups of code:
1. dma_buf priv field code (for holding comptag data)
2. Comptag usage that relies on dma_buf pointers
For (1) the dma_buf code was simply moved to common/linux/dmabuf.c
since most of this code is clearly Linux specific.
The comptag code was a bit more complicated since there is two
parts to the comptag code. Firstly there's the code that manages
the comptag memory. This is essentially a simple allocator. This
was moved to common/mm/comptags.c since it can be shared across
all chips. The second set of code is moved to
common/linux/comptags.c since it is the interface between dma_bufs
and the comptag memory.
Two other fixes were done as well:
- Add struct gk20a to the comptag allocator init so that
the proper nvgpu_vzalloc() function could be used.
- Add necessary includes to common/linux/vm_priv.h.
JIRA NVGPU-30
JIRA NVGPU-138
Change-Id: I96c57f2763e5ebe18a2f2ee4b33e0e1a2597848c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1566628
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add abstraction of IO aperture accessors. Add new functions
gk20a_io_exists() and gk20a_io_valid_reg() to remove dependencies to
aperture fields from common code.
Implement Linux version of the abstraction by moving gk20a_readl()
and gk20a_writel() to new Linux specific io.c. Move the fields
defining IO aperture to nvgpu_os_linux.
Add t19x specific IO aperture initialization functions and add t19x
specific section to nvgpu_os_linux.
JIRA NVGPU-259
Change-Id: I09e79cda60d11a20d1099a9aaa6d2375236e94ce
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1569698
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
For Simualtion/Emulation platforms,clock gating
should be skipped as it is not supported.
Added new flags "can_"X"lcg" to check platform
capability before doing SLCG,BLCG and ELCG.
Bug 200314250
Change-Id: I4124d444a77a4c06df8c1d82c6038bfd457f3db0
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1566049
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Added new defines for following litter values:
GPU_LIT_SMPC_PRI_BASE
GPU_LIT_SMPC_PRI_SHARED_BASE
GPU_LIT_SMPC_PRI_UNIQUE_BASE9
GPU_LIT_SMPC_PRI_STRIDE
Calculate offsets for ctx operations considering
sm per tpc. Following functions are modified for this:
gr_gk20a_get_ctx_buffer_offsets
gr_gk20a_get_pm_ctx_buffer_offsets
__gr_gk20a_exec_ctx_ops
Bug 200337994
Change-Id: I3a4ca470a4107d3078b708f38601762626ce1bf1
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1539069
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
