While posting CILP preemption complete event to
user space, raise the event to all channels of TSG
(if channel is part of TSG)
This is a WAR until we have proper sync mechanism
with user space to raise CILP events
Bug 200156699
Change-Id: Ieedc866498a8c5464cf65962257a803b37da6826
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1001696
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add CILP support for gp10b by defining below function
pointers (with detailed explanation)
pre_process_sm_exception()
- for CILP enabled channels, get the mask of errors
- if we need to broadcast the stop_trigger, suspend all SMs
- otherwise suspend only current SM
- clear hww_global_esr values in h/w
- gr_gp10b_set_cilp_preempt_pending()
- get ctx_id
- using sideband method, program FECS to generate
interrupt on next ctxsw
- disable and preempt the channel/TSG
- set cilp_preempt_pending = true
- clear single step mode
- resume current SM
handle_fecs_error()
- we get ctxsw_intr1 upon next ctxsw
- clear this interrupt
- get handle of channel on which we first
triggered SM exception
- gr_gp10b_clear_cilp_preempt_pending()
- set cilp_preempt_pending = false
- send events to channel and debug session fd
Bug 200156699
Change-Id: Ia765db47e68fb968fada6409609af505c079df53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/925897
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Restore comptags to be bitmap-allocated, like they were before we had
the buddy allocator.
Bug 200145635
Change-Id: I681493871096f437014b7eca1182fefbaf7f6a74
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/839240
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
It'll detect dead semaphore acquire. The worst case is when
ACQUIRE_SWITCH is disabled, semaphore acquire will poll and
consume full gpu timeslicees.
The timeout value is set to half of channel WDT.
Bug 1636800
Change-Id: Idbd4bfa52981e8a849b62a168e3a6828330112f5
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: http://git-master/r/928830
Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The server only releases ownership of the ctxsw buffer mappings
after the GR ctx has been released. Update the sequence to
account for this.
JIRA VFND-1117
Bug 1708163
Change-Id: I3aed015805b4ca51433e7d37ad32de2f8353999f
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/922817
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vladislav Buzov <vbuzov@nvidia.com>
gr_*__set_alpha_circular_buffer_size() left max_batches field of
gr_pd_ab_dist_cfg1_r as 0 which results in too many alpha beta
transitions and poor performance when tessellation or geometry
shaders are used
Change-Id: Ic3673f45b60674b3527641a6fdda0cedc6861db5
Signed-off-by: David Li <davli@nvidia.com>
Reviewed-on: http://git-master/r/840079
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Some of the allocated buffers are used during normal graphics
processing. Mark them as GPU cacheable to improve performance.
Bug 1695718
Change-Id: I71d5d1538516e966526abe5e38a557776321597f
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/827087
(cherry picked from commit 60b40ac144c94e24a2c449c8be937edf8865e1ed)
Reviewed-on: http://git-master/r/828493
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
VM server only know big page and small page, so convert
gmmu_page_size_kernel to according page size index.
JIRA VFND-890
Change-Id: Id1f932752b8ca33d14635ac9d71019364aa89dc4
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: http://git-master/r/816359
(cherry picked from commit 5bfc4a2a55889f5457bd34aa06861c042ee67421)
Reviewed-on: http://git-master/r/827131
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vladislav Buzov <vbuzov@nvidia.com>
gp10b introduces support for preemption (GfxP and CILP).
Add a new interface to allow allocating buffers needed
to support this functionality.
Bug 1677153
Change-Id: I8578a7b0a4327f3496d852eeb8be5fc778e2c225
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/806963
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/817039
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Fix support for kinds C32_MS4_4CBRA and C64_MS4_4CBRA. They're both
compressible and ZBC kinds, so mark them as such, too.
Change-Id: Ide09ea79a885361ecfc3c188606799c6b2fbdd2e
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: http://git-master/r/816015
(cherry picked from commit 302b06b76aed5278286487225d6e7280b747d4b3)
Reviewed-on: http://git-master/r/816014
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add gp10b PROD value for FE_GO_IDLE_TIMEOUT. Use the PROD value
written in gk20a_init_gr_setup_hw() instead of hard coding here.
Change-Id: If3bd981c1c0d9cc8ad19c21c220b7de81fdb529e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/813959
We used to allocate 1.5x buffer size. This leads to memory waste, as
we do not set the CB size via SW methods anymore.
Bug 1686189
Change-Id: I45cbdeadc154f59b65138f99f50a72d97511cb78
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/801865
(cherry picked from commit 791f2fe03d16521206649ab90498443e91e284e2)
Reviewed-on: http://git-master/r/815683
Spill buffer size is in chunks of 256B. Multiply the size by
granularity to get the size in bytes.
Bug 1686189
Change-Id: I0462293668322645bd1eab190c12faaeb6c316c1
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/801344
(cherry picked from commit 4bf6de7d9c9014a9eaeff56b19437d1841d7cfb0)
Reviewed-on: http://git-master/r/815680
If pagepool size equals max we should use zero. Add the comparison
to do that.
Bug 1686189
Change-Id: I15bd43663550b1089a726c0256b89f849c193e21
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/801526
(cherry picked from commit 9d89ea5ba345b19d2cff86130ba9d3c4c5f07e6e)
Reviewed-on: http://git-master/r/815681
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
The powergating APIs only work if the BPMP is running. Skip
these calls if it's not available, instead of relying on
is_linsim, which doesn't work under all environments.
Change-Id: I34325847b2ebf33c5db2f31111c57d22ed28ef53
Signed-off-by: Matt Craighead <mcraighead@nvidia.com>
Reviewed-on: http://git-master/r/812415
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
