The SOC15_REG_OFFSET() macro wasn't used, making the soft recovery fail.

v2: use WREG32_SOC15 instead of WREG32 + SOC15_REG_OFFSET
Signed-off-by: NPierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@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>
Cc: stable@vger.kernel.org

This reverts commit 9ed2c993.

SET_CONFIG_REG writes to memory if register shadowing is enabled,
causing a VM fault.

NGG streamout is unstable anyway, so all UMDs should use legacy
streamout. I think Mesa is the only driver using NGG streamout.
Signed-off-by: NMarek Olšák <marek.olsak@amd.com>
Reviewed-by: NLe Ma <Le.Ma@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Without this pin, the csb buffer will be filled with inconsistent
data after S3 resume. And that will causes gfx hang on gfxoff
exit since this csb will be executed then.
Signed-off-by: NLikun Gao <Likun.Gao@amd.com>
Tested-by: NPaul Gover <pmw.gover@yahoo.co.uk>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

VCN 2.0 firmware now requires a packet start command to be sent before
any other decode ring buffer command.
Signed-off-by: NThong Thai <thong.thai@amd.com>
Reviewed-by: NLeo Liu <leo.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Sets the CMD_SOURCE bit for VCN 2.0 Decoder Ring Buffer commands. This
bit was previously set by the RBC HW on older firmware. Newer firmware
uses a SW RBC and this bit has to be set by the driver.
Signed-off-by: NThong Thai <thong.thai@amd.com>
Reviewed-by: NLeo Liu <leo.liu@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

VCN should be used for Vega20 later ASICs while UVD and VCE
are for previous ASICs.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NKenneth Feng <kenneth.feng@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Coccinelle reports a path that the array "data" is never initialized.
The path skips the checks in the conditional branches when either
of callback functions, read_wave_vgprs and read_wave_sgprs, is not
registered. Later, the uninitialized "data" array is read
in the while-loop below and passed to put_user().

Fix the path by allocating the array with kcalloc().

The patch is simplier than adding a fall-back branch that explicitly
calls memset(data, 0, ...). Also it does not need the multiplication
1024*sizeof(*data) as the size parameter for memset() though there is
no risk of integer overflow.
Signed-off-by: NWang Xiayang <xywang.sjtu@sjtu.edu.cn>
Reviewed-by: NChunming Zhou <david1.zhou@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We always need to drop the ctx reference and should check
for errors first and then dereference the fence pointer.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NChunming Zhou <david1.zhou@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

DPM state relates are not supported on the new SW SMU ASICs. But still
it's not OK to trigger null pointer dereference on accessing them.
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This was missed during the addition of VegaM support
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NKent Russell <kent.russell@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add missing break statement in order to prevent the code from falling
through to case AMDGPU_IRQ_STATE_ENABLE.

This bug was found thanks to the ongoing efforts to enable
-Wimplicit-fallthrough.

Fixes: a644d85a ("drm/amdgpu: add gfx v10 implementation (v10)")
Cc: stable@vger.kernel.org
Reviewed-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NGustavo A. R. Silva <gustavo@embeddedor.com>

On vega20, there is an SMU message to query it.  On navi, it's fetched
from the metrics table.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Since we are using the signed FW now, and also using PSP firmware loading,
but it's still potential to break driver when loading FW directly
instead of PSP, so we should add offset.
Signed-off-by: NLeo Liu <leo.liu@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

this function is not needed any more. error injection is
the only way to validate ras but it can't be executed in
amdgpu_ras_init, where gpu is even not initialized
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

error injection to other IP blocks (except UMC) will be enabled
until RAS feature stablize on those IP blocks
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

GFX RAS has not been stablized yet. disable GFX ras until
it is fully funcitonal.
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

driver shouldn't init any ras debugfs/sysfs node for ASICs that don't have ras
hardware ability
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The GDS and GWS blocks default to allowing all VMIDs to
access all entries. Graphics VMIDs can handle setting
these limits when the driver launches work. However,
compute workloads under HWS control don't go through the
kernel driver. Instead, HWS firmware should set these
limits when a process is put into a VMID slot.

Disable access to these devices by default by turning off
all mask bits (for OA) and setting BASE=SIZE=0 (for GDS
and GWS) for all compute VMIDs. If a process wants to use
these resources, they can request this from the HWS
firmware (when such capabilities are enabled). HWS will
then handle setting the base and limit for the process when
it is assigned to a VMID.

This will also prevent user kernels from getting 'stuck' in
GWS by accident if they write GWS-using code but HWS
firmware is not set up to handle GWS reset. Until HWS is
enabled to handle GWS properly, all GWS accesses will
MEM_VIOL fault the kernel.

v2: Move initialization outside of SRBM mutex
Signed-off-by: NJoseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The dpm sensor function already does this for us.  This fixes
the freq*_input files with the new SMU implementation.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The register debugfs interface was using the wrong bitmask for vmid
selection for GFX_CNTL.
Signed-off-by: NTom St Denis <tom.stdenis@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

As the lock was already held on the entrance to smu_handle_task.

- V2: lock in small granularity
Signed-off-by: NEvan Quan <evan.quan@amd.com>
Reviewed-by: NKevin Wang <kevin1.wang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Under memory pressure, buffer moves between RAM to VRAM  can
fail when there is no GTT space available. In those cases
amdgpu_bo_move falls back to ttm_bo_move_memcpy, which seems to
succeed, although it doesn't really support non-contiguous or
invisible VRAM. This manifests as VM faults with corrupted page
table entries in KFD eviction stress tests.

Print some helpful messages when lack of GTT space is causing buffer
moves to fail. Check that source and destination memory regions are
supported by ttm_bo_move_memcpy before taking that fallback.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Not used anymore.
Reviewed-by: NEvan Quan <evan.quan@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Noticed-by: NDave Airlie <airlied@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Prefetch mode 0 is not supported and can lead to hangs with certain very
specific code patterns. Set a sound prefetch mode for all VMIDs rather
than forcing all shaders to set the prefetch mode at the beginning.

Reduce code duplication a bit while we're at it. Note that the 64-bit
address mode enum and the retry all enum are both 0, so the only
functional change is in the INITIAL_INST_PREFETCH field.
Signed-off-by: NNicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: NMarek Olšák <marek.olsak@amd.com>
Acked-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The legacy navi10 sos binary will not carry on kdb image. the kdb_start_addr
is actually the start address of sys_drv image and shouldn't be sent to psp
bootloader.
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

When starting a new mm_node, the page_offset becomes 0.
Signed-off-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>

The simple_strtol() function is deprecated. kstrto[l,u32]() is
the correct replacement as it can properly handle overflows.

This patch replaces the deprecated simple_strtol() use introduced recently.
As clk is of type uint32_t, we are safe to use kstrtou32().

It is also safe to return zero on string parsing error,
similar to the case of returning zero if buf is empty in parse_clk().

Fixes: bb5a2bdf ("drm/amdgpu: support dpm level modification under virtualization v3")
Signed-off-by: NWang Xiayang <xywang.sjtu@sjtu.edu.cn>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It is annoying to have #warnings that trigger in randconfig
builds like

drivers/gpu/drm/amd/amdgpu/soc15.c:653:3: error: "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
drivers/gpu/drm/amd/amdgpu/nv.c:400:3: error: "Enable CONFIG_DRM_AMD_DC for display support on navi."

Remove these and rely on the users to turn these on.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The perf counter for Vega20 is 108, instead of 104 which it was on all
previous GPUs, so add a check to use the appropriate value.
Signed-off-by: NKent Russell <kent.russell@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The ability to select GFX GRBM me/pipe/queue/vmid was missing from
the gfx10 driver.  This patch adds it.  Used by the debugfs register
interface to select GFX resources when read/writing registers.
Signed-off-by: NTom St Denis <tom.stdenis@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add 5 bits to the offset for SRBM selection to handle VMIDs.  Also
update the select_me_pipe_q() callback to also select VMID.
Signed-off-by: NTom St Denis <tom.stdenis@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Apply the same setting to SH_MEM_CONFIG and VM_CONTEXT1_CNTL. This
makes the noretry param no longer KFD-specific. On GFX10 I'm not
changing SH_MEM_CONFIG in this commit because GFX10 has different
retry behaviour in the SQ and I don't have a way to test it at the
moment.
Suggested-by: NChristian König <Christian.Koenig@amd.com>
CC: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by : Shaoyun.liu < Shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Starting from navi10, driver should send Key Database Load command
to bootloader before loading sys_drv and sos
Signed-off-by: NJohn Clements <John.Clements@amd.com>
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The command will be sent to psp bootloader from driver
to ask psp bootloader to exerise tOS, sys_drv and kdb loading
Signed-off-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Use the IP discovery table rather than hardcoding the
settings in the driver.
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

ID of DCE_HWIP from vbios is DMU_HWID,
mismatch cause null pointer crash in navi10 modprobe.
Reviewed-by: NFeifei Xu <Feifei.Xu@amd.com>
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Ntiancyin <tianci.yin@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

With mm_nodes larger than 4GB, byte_count in amdgpu_fill_buffer would
overflow.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We need to serialize access to the psp ring if there are multiple
callers at runtime.
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It's only available on navi and newer.
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

New parameters added for navi lack documentation.
Reviewed-by: NXiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>