Move preallocation of priv cmdbuf metadata structs to the priv cmdbuf
level and do it always, not only on deterministic channels. This makes
job tracking simpler and loosens dependencies from jobs to cmdbuf
internals. The underlying dma memory for the cmdbuf data has always been
preallocated.
Rename the priv cmdbuf functions to have a consistent prefix.
Refactor the channel sync wait and incr ops to free any priv cmdbufs
they allocate. They have been depending on the caller to free their
resources even on error conditions, requiring the caller to know how
they work.
The error paths that could occur after a priv cmdbuf has been allocated
have likely been wrong for a long time. Usually the cmdbuf queue allows
allocating only from one end and freeing from only the other end, as
that's natural with the hardware job queue. However, in error conditions
the just recently allocated entries need to be put back. Improve the
interface for this.
[not part of the cherry-pick:] Delete the error prints about not enough
priv cmd buffer space. That is not an error. When obeying the
user-provided job sizes more strictly, momentarily running out of job
tracking resources is possible when the job cleanup thread does not
catch up quickly enough. In such a case the number of inflight jobs on
the hardware could be less than the maximum, but the inflight job count
that nvgpu sees via the consumed resources could reach the maximum.
Also remove the wrong translation to -EINVAL from err from one call to
nvgpu_priv_cmdbuf_alloc() - the -EAGAIN from the failed allocation is
important.
[not part of the cherry-pick: a bunch of MISRA mitigations.]
Jira NVGPU-4548
Change-Id: I09d02bd44d50a5451500d09605f906d74009a8a4
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2329657
(cherry picked from commit 25412412f31436688c6b45684886f7552075da83)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2332506
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Avoid repetitive branching on the c->deterministic flag and on build
time flags by breaking the submit function on the runtime flag into two
functions of which one gets called.
In deterministic mode the job tracking conditions are simpler, there are
a few extra prechecks to guarantee deterministic latency and the
railgate corner case, and deferred cleanup is never done.
In nondeterministic mode job tracking has more conditions, a power
reference is taken for the job lifetime, and deferred cleanup is
assumed.
These two paths still share some common code. Split it to two more
functions to act as easy building blocks so that the main logic is
apparent.
Jira NVGPU-4548
Change-Id: I64f91dcf09acb16f409dc04a12ad1e144d0cce56
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2333728
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
As a part of refactoring move nvgpu_clk_domain struct from public
to private.
This will help to have arch consistency across all units.
Use public functions to fetch the data across other units.
The following functions are added to access data in clk_domain unit.
*nvgpu_pmu_clk_domain_get_f_points()--> To get freq points
*nvgpu_pmu_clk_domain_update_clk_info() --> To update change seq script
with clock domain data
NVGPU-4689
Change-Id: Idc85e3cf5bbe1b80766ce6c9f07b3305ef04cbdc
Signed-off-by: Abdul Salam <absalam@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2332185
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Ramesh Mylavarapu <rmylavarapu@nvidia.com>
Reviewed-by: Vaibhav Kachore <vkachore@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Aggressive sync destroy is used on some platforms where the amount of
syncpoints is limited. It can cause sync objects to get allocated and
freed in the submit path and when jobs are cleaned up, so require
deferred cleanup. Allocations do not belong to job tracking in a
deterministic submit path.
Although this has been technically allowed before, deterministic
channels have likely not been a priority on those old platforms with
aggressive sync destroy set.
Update virtualized gp10b platform data to match on a gp10b-vgpu compat
string instead of gk20a-vgpu. gk20a (Tegra T124) hasn't been supported
for a long time. Delete the aggressive sync destroy field from this
platform. It's got enough syncpoints to not dynamically allocate them;
having this property set for gp10b-vgpu has likely been a mistake.
This is not a completely pure cherry-pick: also extend the gpu
characteristics to not advertise full deterministic submit support when
aggressive sync destroy is off. This platform flag cannot be adjusted by
the user unlike many other flags.
Jira NVGPU-4548
Change-Id: I283f546d48b79ac94b943d88e5dce55710858330
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2322042
(cherry picked from commit b1ba2b997b2174e365bcb0782ef3e67260ff9e57)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328411
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add an accessor function in the priv cmdbuf object for gva and size to
be written in a gpfifo entry once the cmdbuf build is finished. This
helps in eventually hiding the struct priv_cmd_entry as an
implementation detail.
Add a sanity check to verify that the buffer has been filled exactly to
the requested size. The cmdbufs are used to hold wait and increment
commands for syncpoints or gpu semaphores. A prefence buffer can hold a
number of wait commands of equal size, and the postfence buffer holds
exactly one increment.
Jira NVGPU-4548
Change-Id: I83132bf6de52794ecc419e033e9f4599e488fd68
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2325102
(cherry picked from commit d1831463a487666017c4c80fab0292a0b85c7d83)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2331339
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Currently, for platforms with canRailgate device characteristics disabled,
suspend can block as deterministic channels hold busy references. This
patch makes the change to first hold off any new jobs for deterministic
channels and then reverts back the busy references taken by those
channels. Following this, suspend also waits for the device to get idle
by waiting (with timeout) for the nvgpu's internal usage counter to be
come zero. This ensures there are no further jobs in progress and
allows the system to go into a suspend state.
Bug 200598228
Bug 2930266
Change-Id: Id02b4d41a9c2dd64303b2e2449dbed48c12aea4c
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328489
(cherry picked from commit 9d1e07ca18)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2330159
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add an API to append data to a priv cmdbuf entry. Hold the write pointer
offset internally in the entry instead of having the user keep track of
where those words are written to.
This helps in eventually hiding struct priv_cmd_entry from users and
provides a more consistent interface in general. The wait and incr
commands are now slightly easier to read as well when they're just
arrays of data.
A syncfd-backed prefence may be composed of several individual fences.
Some of those (or even a fence backed by just one) may be already
expired, and currently the syncfd export design releases and nulls
semaphores when expired (see gk20a_sync_pt_has_signaled()) so for those
the wait cmdbuf is appended with zeros; the specific function is for
this purpose.
Jira NVGPU-4548
Change-Id: I1057f98c1b5b407460aa6e1dcba917da9c9aa9c9
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2325099
(cherry picked from commit 6a00a65a86d8249cfeb06a05682abb4771949f19)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2331336
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Error logging bits within the nvlink blocks like TLC and MIF are
persistent through reset, to enable them to be polled following
a reset event. That means that they are in an unknown state at
cold reset, and may contain error state after a warm reset event.
Software is expected to reset them, either by writing ones to the
status bits or by writing to the DEBUG_RESET register at the IOCTRL
top level, to clear the state out before enabling error reporting.
JIRA NVGPU-4352
Change-Id: Iab4e96388fd827c0d694eada61b20f24bbddd1ff
Signed-off-by: tkudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2317683
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Enable logging and error reporting for MIF, DLPL, and TLC blocks.
Configure the NVLIPT and IOCTRL interrupt registers to rollup
the MIF and TLC errors on the link-specific fatal line and the
DLPL interrupts on link-specific intr_a(fatal) line. Both
link_err_fatal and link_intr_a are rolled up to stall interrupt line.
In the handling ISR, clear the interrupt status registers and print
an error.
Move the interrupt handling HAL code to /common/hal.
JIRA NVGPU-4350
JIRA NVGPU-4351
JIRA NVGPU-5231
JIRA NVGPU-4354
JIRA NVGPU-4355
JIRA NVGPU-4356
Change-Id: I14812499caf506592f3ae84d6681d857730d31ff
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2313221
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reduce the priv cmdbuf allocation size to match the actual space needed
in the worst case when num_in_flight is not specified. Although
synchronization may indeed take up to 2/3 of the gpfifo entries, the
number of jobs is what matters and it will be the remaining 1/3.
Each job uses up at most one wait and incr command from the pre and post
fences, so half of the 2/3 will be only wait commands and the other half
will be only incr commands.
Jira NVGPU-4548
Change-Id: Ib3566a76b97d8f65538d961efb97408ef23ec281
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2325233
(cherry picked from commit 515deae4f58fedc7d004988f0f85470a7a894ddf)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328413
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The semaphore wait and incr sizes are not 8 and 10 for gv11b onwards.
Use the specific HAL API to retrieve their sizes and compute the priv
cmdbuf queue based on them instead of the up-to-gp10b values.
We haven't run out of space likely for several reasons:
1) userspace may not need both pre and post fences for absolutely each
submitted job
2) submitted jobs may consist of more than one gpfifo entry, reducing
the relative required sync capacity
3) the queue size is rounded up to the next power of two which leaves
some margin for error in this calculation
4) the gpfifo size based num-in-flight guess has been twice as big as it
needs to be (fixed in a next patch)
Jira NVGPU-4548
Change-Id: I172b5c0d8bb7d2231cc45cbed5e1e8b60ce7c707
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2323148
(cherry picked from commit 03fb194d105242c3eb20a9857a22743f5f64b9b9)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328412
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Instead of one HAL op with a boolean flag to decide whether to do one
thing or another entirely different thing, use two separate HAL ops for
filling priv cmd bufs with semaphore wait and semaphore increment
commands. It's already two ops for syncpoints, and explicit commands are
more readable than boolean flags.
Change offset into cmdbuf in sem wait HAL to be relative to the cmdbuf,
so the HAL adds the cmdbuf internal offset to it.
While at it, modify the syncpoint cmdbuf HAL ops' prototypes to be
consistent.
Jira NVGPU-4548
Change-Id: Ibac1fc5fe2ef113e4e16b56358ecfa8904464c82
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2323319
(cherry picked from commit 08c1fa38c0fe4effe6ff7a992af55f46e03e77d0)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328409
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
dma_buf_kmap was introduced a decade ago to map a dma_buf partially
by the input number of pages, when 32-bit was fairly common. It was
added to not exhaust vmalloc space. Starting from kernel 5.6, it is
deprecated as vmap calls should succeed with larger available
vmalloc space.
Use dma_buf_vmap/vunmap instead of dma_buf_kmap/kunmap for handling
mapping of notifier memory in gk20a_channel_wait_semaphore.
Also update the debug prints and add speculation barrier to the
start of gk20a_channel_wait.
Bug 2925664
Change-Id: I49078fa81f050a57a5b66a793e62006dd66e3ba3
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2326513
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Vaibhav Kachore <vkachore@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Following commit updated the debug message in the function
nvgpu_vm_find_mapping w.r.t reuse of mapping.
commit 2f00d9adfc4fc91a6b84b14cc513f9b855d39cad
Author: Sagar Kamble <skamble@nvidia.com>
gpu: nvgpu: fix null pointer access in nvgpu_vm_find_mapping
That reuse log is about the mapping and not SGT. Fix the log
and add details about different handling of SGT for dmabuf
drvdata cases in the comment.
Bug 2834141
Change-Id: I3630de1c45a2bf55ff18bdb426f0597efe83f72c
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328427
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Move struct priv_cmd_queue to priv_cmdbuf.c so that its definition does
not need to be visible to all users of channel.h. This also forces it to
be separately allocated (during channel init time).
While at it, rename the functions to allocate and free priv cmdbuf
queues now that they're not in channel.c anymore. A private command
buffer queue is a piece of dma memory from which entries for incr and
wait command lists are suballocated. As the name implies, it's a queue;
allocations and frees of the bufs must happen in certain order.
Jira NVGPU-4548
Change-Id: I1b47029f3a478e1942f24292918b7b59a5d91528
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2323147
(cherry picked from commit 1fcf9b04275f44638059c0147dc16c1dc6956510)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2328407
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
A corner case has existed since ancient times for syncpoint-backed
prefences to not cause a gpu wait if the fence is found to be completed
in the submit path. This adds some unnecessary complexity, so don't
check for completion in software. Let the gpu "wait" for these
known-to-be-trivial waits too. Necessary priv cmdbuf space has been
allocated anyway.
Originally nvhost had 16-bit fences which would wrap around relatively
quickly, so waiting for an old fence could have looked like waiting for
a fence that will expire long in the future. With 32-bit thresholds,
this hasn't been the case for several Tegra generations anymore, and
nvhost doesn't ignore waits like this either.
The wait priv cmdbuf in submit path can still be missing even with a
prefence supplied because the Android sync framework supports sync fds
that contain zero fences inside; this can happen at least when merging
fences that have all been expired. In such conditions the wait cmdbuf
wouldn't even get allocated.
[this is squashed with commit 8b3b0cb12d118 (gpu: nvgpu: allow no wait
cmd with valid input fence) from
https://git-master.nvidia.com/r/c/linux-nvgpu/+/2325677]
Jira NVGPU-4548
Change-Id: Ie81fd8735c2614d0fedb7242dc9869d0961610eb
Signed-off-by: Konsta Hölttä <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2321762
(cherry picked from commit 8f3dac44934eb727b1bf4fb853f019cf4c15a5cd)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2324254
Reviewed-by: automaticguardword <automaticguardword@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
