There are instances (such as non-recoverable GPU page faults) where
NVKM decides that a channel's context is no longer viable, and will
be removed from the runlist.
This commit notifies the owner of the channel when this happens, so
it has the opportunity to take some kind of recovery action instead
of hanging.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We never have any need for a double-linked list here, and as there's
generally a large number of these objects, replace it with a single-
linked list in order to save some memory.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We want a supervisor client of NVKM (such as the DRM) to be able to
allow sharing of resources (such as memory objects) between clients.
To allow this, the supervisor creates all its clients as children of
itself, and will use an upcoming ioctl to permit sharing.
Currently it's not possible for indirect clients to use subclients.
Supporting this will require an additional field in the main ioctl.
This isn't important currently, but will need to be fixed for virt.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
It turns out we have a nice and convenient way of looking up a specific
object type already, by using the func pointer as a key.
This will be used to remove the separate object trees for each type we
need to be able to search for.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Split the reset function into more meaningful and reusable ones.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Split the act of building the ACR blob from firmware files from the rest
of the (chip-dependent) secure boot logic. ACR logic is moved into
acr_rxxx.c files, where rxxx corresponds to the compatible release of
the NVIDIA driver. At the moment r352 and r361 are supported since
firmwares have been released for these versions. Some abstractions are
added on top of r352 so r361 can easily be implemented on top of it by
just overriding a few hooks.
This split makes it possible and easy to reuse the same ACR version on
different chips. It also hopefully makes the code much more readable as
the different secure boot logics are separated. As more chips and
firmware versions will be supported, this is a necessity to not get lost
in code that is already quite complex.
This is a big commit, but it essentially moves things around (and split
the nvkm_secboot structure into two, nvkm_secboot and nvkm_acr). Code
semantics should not be affected.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Since GR has moved to using the falcon library to start the falcons,
this function is not needed anymore.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Use the falcon library functions in secure boot. This removes a lot of
code and makes the secure boot flow easier to understand as no register
is directly accessed.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These functions should use the nvkm_secboot_falcon enum. Fix this.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add a dummy PMU device so the PMU falcon is instanciated and can be used
by secure boot.
We could reuse gk20a's implementation here, but it would fight with
secboot over PMU falcon's ownership and secboot will reset the PMU,
preventing it from operating afterwards. Proper handout between secboot
and pmu is coming along with the actual gm20b PMU implementation, so
use this as a temporary solution.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Have an instance of nvkm_falcon in the PMU structure, ready to be used
by other subdevs (i.e. secboot).
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Falcon processors are used in various places of GPU chips. Although there
exist different versions of the falcon, and some variants exist, the
base set of actions performed on them is the same, which results in lots
of duplicated code.
This patch consolidates the current nvkm_falcon structure and extends it
with the following features:
* Ability for an engine to obtain and later release a given falcon,
* Abstractions for basic operations (IMEM/DMEM access, start, etc)
* Abstractions for secure operations if a falcon is secure
Abstractions make it easy to e.g. start a falcon, without having to care
about its details. For instance, falcons in secure mode need to be
started by writing to a different register.
Right now the abstractions variants only cover secure vs. non-secure
falcon, but more will come as e.g. SEC2 support is added.
This is still a WIP as other functions previously done by
engine/falcon.c need to be reimplemented. However this first step allows
to keep things simple and to discuss basic design.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add a function that allows us to query whether a given subdev is
currently enabled or not.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Constify the local variables declared in these macros so we can pass
const pointers to them.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
gm20b's FB has the same capabilities as gm200, minus the ability to
allocate RAM. Create a device that reflects this instead of re-using the
gk20a device which may be incorrect.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-By: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Karol's work which greatly improves volt/clock changes on a
heap of boards, nothing too exciting beyond a random collection of fixes.
* 'linux-4.9' of git://github.com/skeggsb/linux: (33 commits)
drm/nouveau/fb/nv50: defer DMA mapping of scratch page to oneinit() hook
drm/nouveau/fb/gf100: defer DMA mapping of scratch page to oneinit() hook
drm/nouveau/pci: set streaming DMA mask early
drm/nouveau/kms: add Maxwell to backlight initialization
drm/nouveau/bar/nv50: fix bar2 vm size
drm/nouveau/disp: remove unused function in sorg94.c
drm/nouveau/volt: use kernel's 64-bit signed division function
drm/nouveau/core: add missing header dependencies
drm/nouveau/gr/nv3x: add 0x0597 kelvin 3d class support
drm/nouveau/drm/nouveau: add a LED driver for the NVIDIA logo
drm/nouveau/fb/ram: Use Kepler implementation on Maxwell
drm/nouveau/volt: Make use of cvb coefficients
drm/nouveau/volt/gf100-: Add speedo
drm/nouveau/volt: Add implementation for gf100
drm/nouveau/bios/vmap: unk0 field is the mode
drm/nouveau/volt: Don't require perfect fit
drm/nouveau/clk: Allow boosting only when NvBoost is set
drm/nouveau/bios: Add parsing of VPSTATE table
drm/nouveau/clk: Respect voltage limits in nvkm_cstate_prog
drm/nouveau/clk: Fixup cstate selection
...
We received a donation of a Titan which has this useless feature
allowing users to control the brightness of the LED behind the
logo of NVIDIA. In the true spirit of open source, let's expose
that to the users of very expensive cards!
This patch hooks up this LED/PWM to the LED subsystem which allows
blinking it in sync with cpu/disk/network/whatever activity (heartbeat
is quite nice!). Users may also implement some breathing effect or
morse code support in the userspace if they feel like it.
v2:
- surround the use of the LED framework with ifdef CONFIG_LEDS_CLASS
v3:
- avoid using ifdefs everywhere, follow the recommendations of
/doc/Documentation/CodingStyle. Suggested by Emil Velikov.
v4 (Ben):
- squashed series of fixes from ml
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
v5: Squashed speedo related commits.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Since gf100 we need a speedo value for calculating the voltage. The readout
will be added in a later patch.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Depending on the value a different formular is used to calculated the
voltage for this entry.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
0: base clock from the vbios is max clock (default)
1: boost only to boost clock from the vbios
2: boost to max clock available
v2: Moved into nvkm_cstate_valid.
v4: Check the existence of the clocks before limiting.
v5: Default to boost level 0.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This table contains three important clocks:
base clock: This is the non boosted max clock.
tdp clock: The clock at wich the vbios guarentees the TDP won't ever be
exceeded at max load (seems to be always the same as the base
clock, but behaves differently).
boost clock: The avg clock the gpu will stay boosted to. It doesn't seem to
affect the behaviour of the nvidia driver at all though.
v2: Make clear that base/boost/tdp fields are ids.
v5: Rename Base clock to vpstate.
Make vbios pointers 32bit.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We should never allow to select a cstate which current voltage (depending
on the temperature) is higher than
1. the max volt entries in the voltage map table.
2. what tha gpu actually can volt to.
v3: Use find_best for all cstates before actually trying.
Add nvkm_cstate_get function to get cstate by index.
v5: Cstates with voltages lower then min_uv are valid.
Move nvkm_cstate_get into the previous commit.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Now the cstatei parameter can be used of the nvkm_cstate_prog function to
select a specific cstate.
v5: Make a constant for the magic value.
Use list_last_entry.
Add nvkm_cstate_get here instead of in the next commit.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The voltage entries actually may map to a different voltage depending on
the current temperature.
v2: Only read the temperature when actually needed.
v5: Be smarter about using max().
Don't read the temperature anymore.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This way other subdevs can notify the clk subdev about temperature changes
without the need of clk to poll that value.
Also make this function safe to be called from an interrupt handler.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
It is better to read out the id out of the cstate struct directly instead
of iterating over the list of cstates over and over again. Especially when
we start saving pointers to a nvkm_cstate struct, it makes things easier.
v5: Rename field to id.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Each pstate has its own voltage map entry like each cstate has.
The voltages of those entries act as a floor value for the currently
selected pstate and nvidia never sets a voltage below them.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
There are at least three "max" entries, which specify the max voltage.
Because they are actually normal voltage map entries, they can also be
affected by the temperature.
Nvidia respects those entries and if they get changed, nvidia uses the
lower voltage from all three.
We shouldn't exceed those voltages at any given time.
v2: State what those entries do in the source.
v3: Add the third max entry.
v5: Better describe the entries.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
nvkm_volt_map_min is a copy of nvkm_volt_map, which always returns the
lowest possible voltage for a cstate.
nvkm_volt_map will get a temperature parameter there later and also fix
the voltage calculation, so that this functions will be completly
different later.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Tested-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
There is a field in the voltage table which tells us if the VIDs are taken
from the entries or calculated through the header.
v2: Don't break older versions.
v5: Reverse flag name.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Tested-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Previously we parsed that table a bit wrong:
1. The entry layout depends on the sensor type used.
2. We have all resitors in one entry for the INA3221.
3. The config is already included in the vbios.
This commit addresses that issue and with that we should be able to read
out the right power consumption for every GPU with a INA209, INA219 and
INA3221.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This reverts commit aff51175cd.
The commit caused fence timeouts within nvc0_screen_destroy and most likely
other places as well.
The most obvious effect is, that userspace processes take minutes to
actually quit.
Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This flag's only remaining function is to ignore the uncached flag for
BOs on coherent architectures.
However the reason for allocating an object uncache on a non-coherent
architecture (namely because the cost of doing explicit flushes/
invalidations is higher than the benefit of caching the data because
accesses are few and far between) should also apply on architectures for
which coherency is maintained implicitly. Thus allocate coherent objects
as uncached on all architectures.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Due to the GPU preventing us from touching NV_PLTCG_LTCS_LTSS_CBC_BASE,
we cannot provide CBC/ZBC support without signed PMU firmware to handle
the task for us...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
GFxxx/GM1xx support the selection of 64/128KiB big pages globally.
GM2xx supports the same, as well as another mode where the page size
can be selected per-instance.
We default to 128KiB pages (With per-instance for GM200, but the current
code selects 128KiB there already) as the MMU code isn't currently able
to handle otherwise.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Makes common the code that was previously used by the PMU table parsing,
as it appears other tables need this too.
Not much of an idea what this is all about...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
We shouldn't set voltages below the min or above the max voltage the gpu is
able to set, so save the range for future lookups.
Signed-off-by: Karol Herbst <karolherbst@gmail.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Tested-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The GPU speedo ID is required to select the right clk/volt parameters on
GM20B.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
There are cases where subdevs need to perform additonal actions around
the master reset, so we want to expost the operations separately.
This commit also adds a flag to the NV_PMC_ENABLE bitfield definitions
which allow skipping the automatic reset() called from core/subdev.c.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
v2: add list_del call, reword error message
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
v2: add list_del calls
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
In case of successful suspend, devinit will have to be run and this is
the behavior currently hardcoded. However, as FD bug 94725 suggests,
there might be cases where runtime suspend leaves the GPU powered, and
in such cases devinit should not be run on resume.
On GF100+ we have a reliable way to know whether we need to run devinit.
Use it instead of blindly trusting the flag set by nvkm_devinit_fini().
The code around the NvForcePost also needs to be slightly reworked in
order to keep working.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Suggested-by: Dave Airlie <airlied@redhat.com>
Suggested-by: Karol Herbst <nouveau@karolherbst.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
GM20B requires an extra clock compared to GK20A. Add that information
into the platform data and acquire and enable this clock if necessary.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add a basic clock driver that reuses the GK20A logic.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add basic GM20B volt driver that reuses the GK20A logic.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This class supports a WFI method (0x0078) that's not present on the
KeplerChannelGpfifoA class.
The binary driver exposes both classes on these GPUs for some reason,
though there doesn't appear to be any difference in the setup that's
done for each (ie. even if you allocate GpfifoA, the WFI method will
still work).
We shall just expose GpfifoB, as I don't see a good reason to report
the presence of both.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
based on Martins initial work
v3: fix ina2x9 calculations
v4: don't kmalloc(0), fix the lsb/pga stuff
v5: add a field to tell if the power reading may be invalid
add nkvm_iccsense_read_all function
check for the device on the i2c bus
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Karol Herbst:
v4: don't kmalloc(0)
v5: stricter validation
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Add secure boot support for the GM20B chip found in Tegra X1. Secure
boot on Tegra works slightly differently from desktop, notably in the
way the WPR region is set up.
In addition, the firmware bootloaders use a slightly different header
format.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add secure-boot for the dGPU set of GM20X chips, using the PMU as the
high-secure falcon.
This work is based on Deepak Goyal's initial port of Secure Boot to
Nouveau.
v2. use proper memory target function
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
On GM200 and later GPUs, firmware for some essential falcons (notably
GR ones) must be authenticated by a NVIDIA-produced signature and
loaded by a high-secure falcon in order to be able to access privileged
registers, in a process known as Secure Boot.
Secure Boot requires building a binary blob containing the firmwares
and signatures of the falcons to be loaded. This blob is then given to
a high-secure falcon running a signed loader firmware that copies the
blob into a write-protected region, checks that the signatures are
valid, and finally loads the verified firmware into the managed falcons
and switches them to privileged mode.
This patch adds infrastructure code to support this process on chips
that require it.
v2:
- The IRQ mask of the PMU falcon was left - replace it with the proper
irq_mask variable.
- The falcon reset procedure expecting a falcon in an initialized state,
which was accidentally provided by the PMU subdev. Make sure that
secboot can manage the falcon on its own.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add memcpy functions to copy a buffer to a gpuobj and vice-versa. This
will be used by the secure boot code.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Most of the per-chipset differences will go away when we fully switch
to using the register lists provided by the firmware files, which will
leave all the remaining code "belonging" to GM200.
This is a preemptive rename from GM204 to GM200.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add two functions nvkm_firmware_get() and nvkm_firmware_put() to load a
firmware file and free its resources, respectively. Since firmware files
are becoming a necessity for new GPUs, and their location has been
standardized to nvidia/chip/, this will prevent duplicate and
error-prone name-generation code.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
v2: rename and group functions
v4: change copyright information
move printing of pcie speeds into oneinit,
rename all pcie functions to nvkm_pcie_*
don't try to raise the pcie version when no higher one is supported
v5: revert Copyright changes and rename nvkm_pcie_raise_version to nvkm_pcie_set_version
v6: remove some useless pci_is_pcie checks and rework messages
Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
NVIDIA have indicated that the workaround is required on all GK10[467]
boards that have the PGOB fuse set.
I've left the commandline option in place for now, as paranoia.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
No locking is required for the traversal of this list, as it only
happens during suspend/resume where nothing else can be executing.
Fixes some of the issues noticed during parallel piglit runs.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Avoids waiting for VBLANKS that never arrive on headless or otherwise
unconventional set-ups. Strategy taken from MEMX.
Signed-off-by: Roy Spliet <rspliet@eclipso.eu>
Tested-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
If the hardware supports extended tag field (8-bit ones), then enable it.
This is usually done by the VBIOS, but not on some MBPs (see fdo#86537).
In case extended tag field is not supported, 5-bit tag field is used which
limits the possible number of requests to 32. Apparently bits 7:0 of
0x08841c stores some number of outstanding requests, so cap it to 32 if
extended tag is unsupported.
Fixes: fdo#86537
v2: Restrict changes to chipsets >= 0x84
v3:
* Add nvkm_pci_mask to pci.h
* Mask bit 8 before setting it
v4:
* Rename `add` argument of nvkm_pci_mask to `value`
* Move code from nvkm_pci_init to g84_pci_init and remove PCIe and chipset
checks
v5:
* Rebase code on latest PCI structure
* Restore PCIe check
* Fix namings in nvkm_pci_mask
* Rephrase part of the commit message
Signed-off-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
coverity.com reported that memset was using a buffer of size 0, on
checking the code it turned out that the function was not being used. So
remove it.
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Was not able to obtain a trace of NVRM due to kernel version annoyances,
however, experimentally confirmed that the WAR we use on NV50/G8x boards
works here too.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Increase clock timeout of some unknown engines in order to avoid failure
at high gpcclk rate.
This fixes IBUS read faults on my GF119 when reclocking is manually
enabled. Note that memory reclocking is completely broken and NvMemExec
has to be disabled to allow core clock reclocking only.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Most Keplers actually use the GPIO-based voltage management instead of the new
PWM-based one. Use the GPIO mode as a fallback as it already gracefully handles
the case where no GPIOs exist.
All the Maxwells seem to use the PWM method though.
v2:
- Do not forget to commit the PWM configuration change!
Signed-off-by: Martin Peres <martin.peres@free.fr>
Current Tegra code taking advantage of the IOMMU assumes a hardcoded
value for the IOMMU bit. Make it a platform property instead for
flexibility.
v2 (Ben Skeggs): remove nvkm dependence on drm structures
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Allow clients to manually flush and invalidate L2. This will be useful
for Tegra systems for which we want to write instmem using the CPU.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These are useful for systems without a coherent CPU/GPU bus. For such
systems we may need to maintain the L2 ourselves.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Reintroduce macros allowing us to test a register against a certain
mask, since this is the most common usage pattern for the more generic
nvkm_xsec macros and makes the code more concise and readable.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
The copyright header in nvkm/engine/device/platform.c has been replaced
with the NVIDIA one from drm/nouveau_platform.c, as most of the actual
code is now theirs.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This ensures we have a valid mask of disabled engines before we start
trying to execute fini()/init() on the subdevs, potentially touching
devices that don't exist.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
An upcoming commit requires being able to modify the PRAMIN BAR page
tables while already holding the MMU subdev mutex.
To solve this issue, each VM has been given its own mutex. As a nice
side-effect, this also allows separate VMs to be updated concurrently.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
A variety of tweaks to the NVIF library interfaces, mostly ripping out
things that turned out to be not so useful.
- Removed refcounting from nvif_object, callers are expected to not be
stupid instead.
- nvif_client is directly reachable from anything derived from nvif_object,
removing the need for heuristics to locate it
- _new() versions of interfaces, that allocate memory for the object
they construct, have been removed. The vast majority of callers used
the embedded _init() interfaces.
- No longer storing constructor arguments (and the data returned from
nvkm) inside nvif_object, it's more or less unused and just wastes
memory.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Replaces the piece-by-piece (in response to NV_DEVICE ctor args) device
contruction with a once-off all-or-nothing approach, eliminating some
tricky refcounting issues. The partial device init capability was only
required by some tools, and has been moved to probe time instead.
Temporarily removes a workaround for some boards where we need to fiddle
with AGP registers before executing the DEVINIT scripts. A later commit
in this series reinstates it.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These require an explicit struct nvkm_gpuobj pointer, unlike the previous
macros which take a void *, and work with any nvkm_object.
New semantics require acquiring/releasing a gpuobj before accessing them,
which will be made use of in later patches to greatly reduce the overhead
of accesses, particularly when a direct mmio mapping of the object is not
available (suspend/resume, out of ioremap() space, and on GK20A).
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These require an explicit pointers to nvkm_object/nvkm_subdev/nvkm_device,
depending on which macros are used. This is unlike the previous macros
which take a void *, and work for anything derived from nvkm_object (by
way of some awful heuristics).
The output will be a bit confused until everything has been transitioned,
as the logging format used is a more standard style that previously.
In addition, usage of pr_cont(), which doesn't work correctly with the
dev_*() printk functions (and was potentially racy to begin with), will
be replaced.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These require an explicit struct nvkm_device pointer, unlike the previous
macros which take a void *, and work for (almost) anything derived from
nvkm_object by using some heuristics.
These macros are more general than the previous ones, and can be used to
handle PTIMER-based busy-waits (will be used in later devinit fixes) as
well as more complicated wait conditions.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These require an explit struct nvkm_device pointer, unlike the previous
macros which take a void *, and assume it's any old nvkm_subdev.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Pretty much every subdev/engine is going to need access to nvkm_device
shortly to touch registers and/or output messages.
The odd placement of the includes is necessary to work around some
inter-dependencies that currently exist. This will be fixed later.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
A future commit will hide the platform/pci specifics from nvkm_device,
but it's still very useful in a lot of places to have access to the
Linux device struct.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will be used in upcoming commits to remove the need for lookup/runtime
type-checking functions when accessing foreign subdevs.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will be utilised in upcoming commits to remove the need for heuristics
to lookup the device a subdev belongs to.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Add support for GM20B's graphics engine, based on GK20A. Note that this
code alone will not allow the engine to initialize on released devices
which require PMU-assisted secure boot.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is going to be very useful for GF100+ because each GPC can
have its own domain of counters.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These signals and sources have been reverse engineered from CUPTI
(Linux). Graphics signals exposed by PerfKit (Windows only) will be
added later. I need to reverse engineer them and it's a bit painful.
This commit also adds a new class for GF108 and GF117.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These signals and sources have been reverse engineered from NVIDIA
PerfKit (Windows) and CUPTI (Linux), they will be used to build complex
hardware events from the userspace.
This commit also adds a new class for GT200.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Configuring counters from the userspace require the kernel to handle some
logic related to performance counters. Basically, it has to find a free
slot to assign a counter, to handle extra counting modes like B4/B6 and it
must return and error when it can't configure a counter.
In my opinion, the kernel should not handle all of that logic but it
should only write the configuration sent by the userspace without
checking anything. In other words, it should overwrite the configuration
even if it's already counting and do not return any errors.
This patch allows the userspace to configure a domain instead of
separate counters. This has the advantage to move all of the logic to
the userspace.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This adds a new method NVIF_PERFCTR_V0_INIT which starts a batch of
hardware counters for sampling. This will allow the userspace to start
a monitoring session using the INIT method and to stop it with SAMPLE,
for example before and after a frame is rendered.
This commit temporarily breaks nv_perfmon but this is going to be fixed
with the upcoming patch.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This allows to query the ID, the mask and the user-readable name of
sources for each signal.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
A source (or multiplexer) is a tuple addr+mask+shift which allows to
control a block of signals. The maximum number of sources that a signal
can define is arbitrary limited to 8 and this should be large enough.
This patch allows to define multi-level of sources for a signal.
Each different sources are stored to a global list and will be exposed
to the userspace through the nvif interface in order to avoid conflicts.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
16 bits is large enough to store the maximum number of signals available
for one domain (i.e. 256).
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This will allow to configure performance counters with hardware signal
indexes instead of user-readable names in an upcoming patch.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This allows to query the number of available domains, including the
number of hardware counter and the number of signals per domain.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This commit introduces the NVIF_IOCTL_NEW_V0_PERFMON class which will be
used in order to query domains, signals and sources. This separates the
querying and the counting interface.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
PDAEMON signals don't have to be exposed by the perfmon engine.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Some of the bits in there are similar to the bits in the gt215 rammap.
Signed-off-by: Roy Spliet <rspliet@eclipso.eu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Might need some generalisation to < GT200. For those: use at your own risk!
Signed-off-by: Roy Spliet <rspliet@eclipso.eu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
In preparation of NV50 reclocking, where there is no version
Signed-off-by: Roy Spliet <rspliet@eclipso.eu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Uncertain whether the GPC pack change is due to a newer driver version,
or a legitimate difference from GM204. My GM204 has broken vram, so
can't currently try a newer binary driver on it to confirm.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>