Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Unlike subdevs, these aren't initialised in a defined order.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

It's supposed to always be 0, but at least nv_iowr() temporarily violates
this. Since the ih touches $r0, it should be stored.
Signed-off-by: NRoy Spliet <rs855@cam.ac.uk>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NKarol Herbst <nouveau@karolherbst.de>
Reviewed-by: NMartin Peres <martin.peres@free.fr>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

the macro deals with target specific differences and so we should always use
this
Signed-off-by: NKarol Herbst <nouveau@karolherbst.de>
Reviewed-by: NMartin Peres <martin.peres@free.fr>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

on gk208+ we can simply mov 32bits, so we should have a single mov there

v2: use or operator instead of add
Signed-off-by: NKarol Herbst <nouveau@karolherbst.de>
Reviewed-by: NMartin Peres <martin.peres@free.fr>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NKarol Herbst <nouveau@karolherbst.de>
Reviewed-by: NMartin Peres <martin.peres@free.fr>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Most calls to nvkm_ramht_new use 0x8000 as the size. This results in a
fairly sizeable chunk of memory to be allocated, which may not be
available with kzalloc. Since this is done fairly rarely (once per
channel), use vzalloc instead.
Signed-off-by: NIlia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

A channel may still be processed by the PBDMA even after removal, unless
it is properly kicked. Some chips are more sensible to this than others,
with GM20B triggering the issue very easily (the PBDMA will try to fetch
methods from the previously-removed channel after a new one is added).

Make sure this cannot happen by kicking the channel right after it is
disabled, and before the new runlist is submitted.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

When using the DMA-API for instmem, we may obtain a write-combined
mapping. For such cases, add a write barrier in
gk20a_instobj_release_dma() to make sure that all writes have reached
memory at this time.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Without this buffer inconsistencies may appear between the CPU
and GPU when using a PCI GPU on an ARM64 board.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Registration of the hwmon device will fail on non-PCI systems since
dev->pdev is NULL in that case. Use the more generic drm_device::dev
member that points to the same and is always set no matter the platform.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

On non-PCI devices, nobody should really care if the device does not
provide HDMI...
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

The DMA API has different semantics on different architectures.
Currently on arm64, it can only provide memory from a small pool which
dries up quickly if we attempt to allocate big buffers from it.

Do not consider that option when running on non-x86, since regular TTM
buffers are the (current) best-fit for ARM platforms.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

LTC operations timeout was set to 2ms, which may be too low for devices
that run at very low clocks (e.g. GM20B) and trigger timeout messages.

Set the timeout to the default 2s. Also remove the redundant error
messages since nvkm_wait_msec() will already display a warning.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Bits 28:29 of RUNLIST_BASE specify the memory target of the runlist. Set
it to 0x3 (SYS_MEM_NONCOHERENT) if the runlist object resides in system
memory.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Bits 28:29 of RUNLIST_BASE specify the memory target of the runlist. Set
it to 0x3 (SYS_MEM_NONCOHERENT) if the runlist object resides in system
memory.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Fix the channel id bit mask in FIFO schedule timeout error handling.

FIFO_ENGINE_STATUS_NEXT_ID is bit 27:16 thus 0x0fff0000.
FIFO_ENGINE_STATUS_ID      is bit 11:0  thus 0x00000fff.
Signed-off-by: NXia Yang <xiay@nvidia.com>
Reviewed-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

DMA mask is typically set in nouveau_ttm_init(), but this function is
called late during initialization and GK20A's instmem will have called
DMA functions before this happens.

Having a wrongly set DMA mask can result in the use of unneeded bounce
buffers. Set it early to avoid this.
Signed-off-by: NAlexandre Courbot <acourbot@nvidia.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>