it requires to initialize HDP_NONSURFACE_BASE, so as to avoid
using the value left by a previous VM under sriov scenario.

v2: it should not hurt baremetal, generalize it for both sriov
and baremetal
Signed-off-by: NEmily Deng <Emily.Deng@amd.com>
Signed-off-by: NTiecheng Zhou <Tiecheng.Zhou@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

During S3/S4 bootloader will re-init ras state behind us.
Resume might fail or raise a gpu reset.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NJames Zhu <James.Zhu@amd.com>
Tested-by: NJames Zhu <James.Zhu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For Vega10 SR-IOV VF, skip setting some regs due to:
1, host will program them
2, avoid VF register programming violations
Signed-off-by: NTrigger Huang <Trigger.Huang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

request a gpu reset if ras return EAGAIN.
we will run late init again so it is ok to do nothing this time.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

For SR-IOV, vram_width can't be read from ATOM as
RAVEN, and DF related registers is not readable, so hardcord
is the only way to set the correct vram_width.
Reviewed-by: NYintian Tao <yttao@amd.com>
Signed-off-by: NTrigger Huang <Trigger.Huang@amd.com>
Signed-off-by: NYintian Tao <yttao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

otherwise screen corrupts during modprobe.
Signed-off-by: NFlora Cui <flora.cui@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

IP initialize ras in late_init, because of the BUGs of PSP or any
other components, driver receives unexpected irqs. It is ok to add such
check anyway.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

handle ras enable on boot.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Further testing showed that the idea with the chash doesn't work as expected.
Especially we can't predict when we can remove the entries from the hash again.

So replace the chash with a ring buffer/hash mix where entries in the container
age automatically based on their timestamp.

v2: use ring buffer / hash mix
v3: check the timeout to make sure all entries age
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> (v2)
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

query sram ecc capability via amdgpu_atomfirmware_ecc_default_enabled
query ecc availability via amdgpu_atomfirmware_sram_ecc_supported
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Suspend will put irq, so resume need get irq back.
And in the same time, skip other ras initialization.
Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

RAS ECC event will combine with GPU reset event, due to
ECC interrupts are caused by uncorrectable error that triggers
GPU reset.

v2: Fix misleading-indentation warning
v3: fix build with CONFIG_HSA_AMD disabled
Signed-off-by: NEric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: Nxinhui pan <xinhui.pan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Use function parameter mc as the second parameter of amdgpu_gmc_vram_location,
so codes look more consistent.
Signed-off-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NChristian Konig <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

All the gmc_*_set_pde_pte functions are the same across different ASICs,
so we can eliminate the set_pde_pte function pointer and instead use a
generic function.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We only need to clear the bit in a 32bit integer.

This fixes a crah on ARM64 and PPC64LE caused by
"drm/amdgpu: update the vm invalidation engine layout V2"
Signed-off-by: NChristian König <christian.koenig@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This commit fixes DRM failures on Xen PV systems that were introduced in
v4.17 by the following commits:

82626363 drm: add func to get max iomem address v2
fd5fd480 drm/amdgpu: only enable swiotlb alloc when need v2
1bc3d3cc drm/radeon: only enable swiotlb path when need v2

The introduction of ->need_swiotlb to the ttm_dma_populate() conditionals
in the radeon and amdgpu device drivers causes Gnome to immediately crash
on Xen PV systems, returning the user to the login screen.  The following
kernel errors get logged:

[   28.554259] radeon_dp_aux_transfer_native: 200 callbacks suppressed
[   31.219821] radeon 0000:01:00.0: swiotlb buffer is full (sz: 2097152 bytes)
[   31.220030] [drm:radeon_gem_object_create [radeon]] *ERROR* Failed to allocate GEM object (16384000, 2, 4096, -14)
[   31.226109] radeon 0000:01:00.0: swiotlb buffer is full (sz: 2097152 bytes)
[   31.226300] [drm:radeon_gem_object_create [radeon]] *ERROR* Failed to allocate GEM object (16384000, 2, 4096, -14)
[   31.300734] gnome-shell[1935]: segfault at 88 ip 00007f39151cd904 sp 00007ffc97611ad8 error 4 in libmutter-cogl.so[7f3915178000+aa000]
[   31.300745] Code: 5f c3 0f 1f 40 00 48 8b 47 78 48 8b 40 40 ff e0 66 0f 1f 44 00 00 48 8b 47 78 48 8b 40 48 ff e0 66 0f 1f 44 00 00 48 8b 47 78 <48> 8b 80 88 00 00 00 ff e0 0f 1f 00 48 8b 47 78 48 8b 40 68 ff e0
[   38.193302] radeon_dp_aux_transfer_native: 116 callbacks suppressed
[   40.009317] radeon 0000:01:00.0: swiotlb buffer is full (sz: 2097152 bytes)
[   40.009488] [drm:radeon_gem_object_create [radeon]] *ERROR* Failed to allocate GEM object (16384000, 2, 4096, -14)
[   40.015114] radeon 0000:01:00.0: swiotlb buffer is full (sz: 2097152 bytes)
[   40.015297] [drm:radeon_gem_object_create [radeon]] *ERROR* Failed to allocate GEM object (16384000, 2, 4096, -14)
[   40.028302] gnome-shell[2431]: segfault at 2dadf40 ip 0000000002dadf40 sp 00007ffcd24ea5f8 error 15
[   40.028306] Code: 20 6e 31 00 00 00 00 00 00 00 00 37 e3 3d 2d 7f 00 00 80 f4 e6 3d 2d 7f 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 <00> 00 00 00 00 00 00 00 c1 00 00 00 00 00 00 00 80 e1 d2 03 00 00

This commit renames drm_get_max_iomem() to drm_need_swiotlb(), adds a
xen_pv_domain() check to it, and moves the bit shifting comparison that
always follows its usage into the function (simplifying the drm driver
code).
Signed-off-by: NMichael D Labriola <michael.d.labriola@gmail.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NChristian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/286987/

sriov need to restrict max_pfn below AMDGPU_GMC_HOLE.
access the hole results in a range fault interrupt IIRC.
Signed-off-by: NWentao Lou <Wentao.Lou@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Note if this is a retry fault or not and cleanup the message a bit.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Initializing structures with { } is known to be problematic since
it doesn't necessararily initialize all bytes, in case of padding,
causing random failures when structures are memcmp().

This patch fixes the structure initialisation related compiler
error by memset().

V2: rectified missing piece in coding
Signed-off-by: NShirish S <shirish.s@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We need new invalidation engine layout due to new SDMA page
queues added.

V2: fix coding style and add correct return value
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The GMC/VM subsystem is causing the faults, so move the handling here as
well.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We ignored the return code here.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Use this to track whether an asic supports xgmi rather than
checking the asic type everywhere.
Reviewed-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

With GFXOFF enabled, this patch will cause PCO amdgpu_test failed,
but GFXOFF is necessary for PCO, so revert the patch.

This reverts commit b83761bb.

v2: add a comment for future reference (Alex)
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NJack Gui <Jack.Gui@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The MMHUB is not affected by this.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NEmily Deng <Emily.Deng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This code is not performance critical.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NEmily Deng <Emily.Deng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Move the kiq handling into amdgpu_virt.c and drop the fallback.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NEmily Deng <Emily.Deng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Consistently use the ring name instead.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Start using drm_gpu_scheduler.ready isntead.

v3:
Add helper function to run ring test and set
sched.ready flag status accordingly, clean explicit
sched.ready sets from the IP specific files.

v4: Add kerneldoc and rebase.
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add a flush_type parameter to that series of functions.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We always want those to be setup correctly.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Treat them all as Raven rather than adding a new picasso
asic type.  This simplifies a lot of code and also handles the
case of rv2 chips with the 0x15d8 pci id.  It also fixes dmcu
fw handling for picasso.
Acked-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Remove some functions due to the design change.
All the mmhub power gating sequence is moved to
smu fw.Driver sends the message to enable mmhub
powergating.We can also skip the fw version check
since the old fw version is in a very early stage
and we don't use that fw for release.
Signed-off-by: NKenneth Feng <kenneth.feng@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Same as raven.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

On hives with xgmi enabled, the fb_location aperture is a size
which defines the total framebuffer size of all nodes in the
hive.  Each GPU in the hive has the same view via the fb_location
aperture.  GPU0 starts at offset (0 * segment size),
GPU1 starts at offset (1 * segment size), etc.

For access to local vram on each GPU, we need to take this offset into
account. This including on setting up GPUVM page table and GART table

v2: squash in "drm/amdgpu: Init correct fb region for none XGMI configuration"
Acked-by: NHuang Rui <ray.huang@amd.com>
Acked-by: NSlava Abramov <slava.abramov@amd.com>
Signed-off-by: NShaoyun Liu <Shaoyun.Liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Acked-by: NHuang Rui <ray.huang@amd.com>

Used to populate the xgmi info on vega20.

v2: PF_MAX_REGION is val - 1 (Ray)
Acked-by: NHuang Rui <ray.huang@amd.com>
Acked-by: NSlava Abramov <slava.abramov@amd.com>
Reviewed-by :Shaoyun liu <Shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by :Shaoyun liu <Shaoyun.liu@amd.com>

Enable the old AGP aperture to avoid GART mappings.

v2: don't enable it for SRIOV
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NJunwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Vega20 does not appear to be affected by the same issue
as vega10.  Enable the full stolen memory handling on
vega20.  Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

vega12 does not appear to be affected by the same issue
as vega10.  Enable the full stolen memory handling on
vega12.  Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>