There are other reset sources that pass NULL as the job pointer, such as
amdgpu_amdkfd_reset_work. Therefore, using the job pointer to check if
the FLR comes from the host does not work.
Add a flag in reset_context to explicitly mark host triggered reset, and
set this flag when we receive host reset notification.
Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Zhigang Luo <zhigang.luo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Some times a hang GPU causes multiple reset sources to schedule resets.
The second source will be able to trigger an unnecessary reset if they
schedule after we call amdgpu_device_stop_pending_resets.
Move amdgpu_device_stop_pending_resets to after the reset is done. Since
at this point the GPU is supposedly in a good state, any reset scheduled
after this point would be a legitimate reset.
Remove unnecessary and incorrect checks for amdgpu_in_reset that was
kinda serving this purpose.
Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
VF can't access FB when host is doing mode1 reset. Using sizeof to get
vf2pf info size, instead of reading it from vf2pf header stored in FB.
Signed-off-by: Zhigang Luo <Zhigang.Luo@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
on same heap. The basic problem here is that after the move the old
location is simply not available any more.
Some fixes were suggested, but essentially we should call the move
notification before actually moving things because only this way we have
the correct order for DMA-buf and VM move notifications as well.
Also rework the statistic handling so that we don't update the eviction
counter before the move.
v2: add missing NULL check
Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: 94aeb41173 ("drm/amdgpu: fix ftrace event amdgpu_bo_move always move on same heap")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3171
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
CC: stable@vger.kernel.org
Subtract the VRAM pinned memory when checking for available memory
in amdgpu_amdkfd_reserve_mem_limit function since that memory is not
available for use.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The "instance" variable needs to be signed for the error handling to work.
Fixes: 8b2faf1a4f ("drm/amdgpu: add error handle to avoid out-of-bounds")
Reviewed-by: Bob Zhou <bob.zhou@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add initial support for GMC v12.
v1: Add gmc v12_0 ip block support.
v2: Switch to gfx.kiq array.
v3: Switch to vmhubs_mask.
v4: Switch to AMDGPU_MMHUB0(0) and AMDGPU_GFXHUB(0)
v5: Rebase (Alex)
v6: Squash in fixes for AGP handling, gfxhub init order,
vmhub index (Alex)
v7: Rebase (Alex)
v8: squash in ecc fix (Alex)
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If the BO pages pinned for RDMA is not contiguous on VRAM, evict it to
system memory first to free the VRAM space, then allocate contiguous
VRAM space, and then move it from system memory back to VRAM.
v6: user context should use interruptible call (Felix)
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Clear resource leak warning that when the prepare fails,
the allocated amdgpu job object will never be released.
Signed-off-by: Tim Huang <Tim.Huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
because the ue valid mca count will only be cleared after gpu reset,
so only dump mca log on the first time to get mca bank after receive RAS interrupt.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v1:
because SMU CE valid mca bank will be cleared after reading,
this patch adds mca cache at the driver level to ensure that the mca bank is not lost.
v2:
refine amdgpu_mca_init/fini/reset() function name.
v3:
add mca_cache.lock support
only add CE bank to mca bank cache.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add initial support for MMHUB 4.1.0.
v1: Add mmhub v4_1_0 ip block support.
v2: Switch to AMDGPU_MMHUB0(0).
v3: squash in fix for ip version check (Alex)
v4: squash in vm_contexts_disable fix (Alex)
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When TTM failed to alloc VRAM, TTM try evict BOs from VRAM to system
memory then retry the allocation, this skips the KFD BOs from the same
process because KFD require all BOs are resident for user queues.
If TTM with TTM_PL_FLAG_CONTIGUOUS flag to alloc contiguous VRAM, allow
TTM evict KFD BOs from the same process, this will evict the user queues
first, and restore the queues later after contiguous VRAM allocation.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Define macro AMDGPU_MAX_SG_SEGMENT_SIZE 2GB, because struct scatterlist
length is unsigned int, and some users of it cast to a signed int, so
every segment of sg table is limited to size 2GB maximum.
For contiguous VRAM allocation, don't limit the max buddy block size in
order to get contiguous VRAM memory. To workaround the sg table segment
size limit, allocate multiple segments if contiguous size is bigger than
AMDGPU_MAX_SG_SEGMENT_SIZE.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
on same heap. The basic problem here is that after the move the old
location is simply not available any more.
Some fixes were suggested, but essentially we should call the move
notification before actually moving things because only this way we have
the correct order for DMA-buf and VM move notifications as well.
Also rework the statistic handling so that we don't update the eviction
counter before the move.
v2: add missing NULL check
Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: 94aeb41173 ("drm/amdgpu: fix ftrace event amdgpu_bo_move always move on same heap")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3171
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
CC: stable@vger.kernel.org
RDMA device with limited scatter-gather ability requires contiguous VRAM
buffer allocation for RDMA peer direct support.
Add a new KFD alloc memory flag and store as bo alloc flag
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS. When pin this bo to export for RDMA
peerdirect access, this will set TTM_PL_FLAG_CONTIFUOUS flag, and ask
VRAM buddy allocator to get contiguous VRAM.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Assign value to clock to fix the warning below:
"Using uninitialized value res. Field res.clock is uninitialized"
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
