| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Prepare to handle pasid poison consumption.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Retire bad pages for umc v12_0.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add condition check for amdgpu_umc_fill_error_record.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add delay work to retire bad pages.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
1. umc v12_0 logs ecc errors.
2. Reserve newly detected ecc error pages.
3. Add tag for bad pages, so that they can
be retired later.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Umc v12_0 converts error address.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add interface to update umc v12_0 ecc status.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add poison creation handler.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Prepare for logging ecc errors.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add message fifo to handle RAS poison events.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Initialize the size before calling amdgpu_vce_cs_reloc, such as case 0x03000001.
V2: To really improve the handling we would actually
need to have a separate value of 0xffffffff.(Christian)
Signed-off-by: Jesse Zhang <[email protected]>
Suggested-by: Christian König <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
We can't use a shared fence location because each transaction
should be considered independently.
Reviewed-by: Shaoyun.liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
As we use wb slots more dynamically, we need to lock
access to avoid racing on allocation or free.
Reviewed-by: Shaoyun.liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
kmd_fw_shared changed in VCN5
Signed-off-by: Sonny Jiang <[email protected]>
Reviewed-by: Ruijing Dong <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
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 <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
jpeg ip version v2.1 and higher supports 16kx16k resolution decode
Signed-off-by: Sathishkumar S <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add ip dump for each ip of the asic in the
devcoredump for all the ips where a callback
is registered for register dump.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Invoke the dump_ip_state function for each ip before
the asic resets and save the register values for
debugging via devcoredump.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add support to print ip information to be
used to print registers in devcoredump
buffer.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add the protoype for print ip state to be used
to print the registers in devcoredump during
a gpu reset.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Adding gfx10 gc registers to be used for register
dump via devcoredump during a gpu reset.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add the prototype to dump ip registers
for all ips of different asics and set
them to NULL for now. Based on the
requirement add a function pointer for
each of them.
Signed-off-by: Sunil Khatri <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Add interface to reserve bad page.
Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Christian König <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
return 0 to avoid returning an uninitialized variable r
Signed-off-by: Ma Jun <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Delete fence fallback timer to fix the ramdom
use-after-free issue.
v2: move to amdgpu_mes.c
Signed-off-by: Jack Xiao <[email protected]>
Acked-by: Lijo Lazar <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
This avoids a potential conflict with firmwares with the newer
HDP flush mechanism.
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Tune coarse grain clock gating idle threshold and rlc idle timeout to
achieve better kernel launch latency.
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Rajneesh Bhardwaj <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Replace tmz flag into buffer flag to make it easier to understand
and extend
Signed-off-by: Likun Gao <[email protected]>
Signed-off-by: Frank Min <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
To adapt to different gc versions in gfx_v9_4_3.c file.
Signed-off-by: Le Ma <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Reviewed-by: Lijo Lazar <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Here are the corrections needed for the queue ring buffer size
calculation for the following cases:
- Remove the KIQ VM flush ring usage.
- Add the invalidate TLBs packet for gfx10 and gfx11 queue.
- There's no VM flush and PFP sync, so remove the gfx9 real
ring and compute ring buffer usage.
Signed-off-by: Prike Liang <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
umsch test needs full GPU functionality(e.g., VM update, TLB flush,
possibly buffer moving under memory pressure) which may be not ready
under these states. Just skip it to avoid potential issues.
Signed-off-by: Lang Yu <[email protected]>
Reviewed-by: Christian König <[email protected]>
Reviewed-by: Veerabadhran Gopalakrishnan <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Use the macro PCI_IRQ_INTX instead of the deprecated PCI_IRQ_LEGACY macro.
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Damien Le Moal <[email protected]>
Signed-off-by: Bjorn Helgaas <[email protected]>
Acked-by: Alex Deucher <[email protected]>
|
|
Delete fence fallback timer to fix the ramdom
use-after-free issue.
v2: move to amdgpu_mes.c
Signed-off-by: Jack Xiao <[email protected]>
Acked-by: Lijo Lazar <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
This avoids a potential conflict with firmwares with the newer
HDP flush mechanism.
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
|
|
Here are the corrections needed for the queue ring buffer size
calculation for the following cases:
- Remove the KIQ VM flush ring usage.
- Add the invalidate TLBs packet for gfx10 and gfx11 queue.
- There's no VM flush and PFP sync, so remove the gfx9 real
ring and compute ring buffer usage.
Signed-off-by: Prike Liang <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
umsch test needs full GPU functionality(e.g., VM update, TLB flush,
possibly buffer moving under memory pressure) which may be not ready
under these states. Just skip it to avoid potential issues.
Signed-off-by: Lang Yu <[email protected]>
Reviewed-by: Christian König <[email protected]>
Reviewed-by: Veerabadhran Gopalakrishnan <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
|
|
Make SVM BOs more likely to get evicted than other BOs. These BOs
opportunistically use available VRAM, but can fall back relatively
seamlessly to system memory. It also avoids SVM migrations evicting
other, more important BOs as they will evict other SVM allocations
first.
Signed-off-by: Felix Kuehling <[email protected]>
Acked-by: Mukul Joshi <[email protected]>
Tested-by: Mukul Joshi <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
The vpe dpm settings should be done before firmware is loaded.
Otherwise, the frequency cannot be successfully raised.
Signed-off-by: Peyton Lee <[email protected]>
Reviewed-by: Lang Yu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
HDP Flush request bit can be kept unique per AID, and doesn't need to be
unique SOC-wide. Assign only bits 10-13 for SDMA v4.4.2.
Signed-off-by: Lijo Lazar <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
|
|
When page table BOs were evicted but not validated before
updating page tables, VM is still in evicting state,
amdgpu_vm_update_range returns -EBUSY and
restore_process_worker runs into a dead loop.
v2: Split the BO validation and page table update into two
separate loops in amdgpu_amdkfd_restore_process_bos. (Felix)
1.Validate BOs
2.Validate VM (and DMABuf attachments)
3.Update page tables for the BOs validated above
Fixes: 50661eb1a2c8 ("drm/amdgpu: Auto-validate DMABuf imports in compute VMs")
Signed-off-by: Lang Yu <[email protected]>
Acked-by: Christian König <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
|
|
Free the sync object if the memory allocation fails for any
reason.
Signed-off-by: Mukul Joshi <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
Cc: [email protected]
|
|
Make SVM BOs more likely to get evicted than other BOs. These BOs
opportunistically use available VRAM, but can fall back relatively
seamlessly to system memory. It also avoids SVM migrations evicting
other, more important BOs as they will evict other SVM allocations
first.
Signed-off-by: Felix Kuehling <[email protected]>
Acked-by: Mukul Joshi <[email protected]>
Tested-by: Mukul Joshi <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Avoid returning an uninitialized value if we never enter the loop.
This case should never be hit in practice, but returning 0 doesn't
hurt.
The same fix is applied to the 4 places using the same pattern.
v2: - fixed typos in commit message (Alex)
- use "return 0;" before the done label instead of initializing
r to 0
Signed-off-by: Pierre-Eric Pelloux-Prayer <[email protected]>
Reviewed-by: Alex Deucher <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Makes it easier to review the logs when there are MES
errors.
v2: use dbg for emitted, add helpers for fetching strings
v3: fix missing commas (Harish)
v4: drop command prefixes (Felix)
v5: squash in bounds fix (Jun)
Acked-by: Felix Kuehling <[email protected]>
Reviewed by Shaoyun.liu <[email protected]> (v2)
Signed-off-by: Alex Deucher <[email protected]>
|
|
The vpe dpm settings should be done before firmware is loaded.
Otherwise, the frequency cannot be successfully raised.
Signed-off-by: Peyton Lee <[email protected]>
Reviewed-by: Lang Yu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
HDP Flush request bit can be kept unique per AID, and doesn't need to be
unique SOC-wide. Assign only bits 10-13 for SDMA v4.4.2.
Signed-off-by: Lijo Lazar <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
In order to support more test cases, support user
change reset_method at runtime.
Signed-off-by: Stanley.Yang <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Maíra needs a backmerge to apply v3d patches, and Danilo for some
nouveau patches.
Signed-off-by: Maxime Ripard <[email protected]>
|
|
Add clear page support in vram memory region.
v1(Christian):
- Dont handle clear page as TTM flag since when moving the BO back
in from GTT again we don't need that.
- Make a specialized version of amdgpu_fill_buffer() which only
clears the VRAM areas which are not already cleared
- Drop the TTM_PL_FLAG_WIPE_ON_RELEASE check in
amdgpu_object.c
v2:
- Modify the function name amdgpu_ttm_* (Alex)
- Drop the delayed parameter (Christian)
- handle amdgpu_res_cleared(&cursor) just above the size
calculation (Christian)
- Use AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE for clearing the buffers
in the free path to properly wait for fences etc.. (Christian)
v3(Christian):
- Remove buffer clear code in VRAM manager instead change the
AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE handling to set
the DRM_BUDDY_CLEARED flag.
- Remove ! from amdgpu_res_cleared(&cursor) check.
v4(Christian):
- vres flag setting move to vram manager file
- use dma_fence_get_stub in amdgpu_ttm_clear_buffer function
- make fence a mandatory parameter and drop the if and the get/put dance
Signed-off-by: Arunpravin Paneer Selvam <[email protected]>
Suggested-by: Christian König <[email protected]>
Acked-by: Felix Kuehling <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Christian König <[email protected]>
|
|
- Add tracking clear page feature.
- Driver should enable the DRM_BUDDY_CLEARED flag if it
successfully clears the blocks in the free path. On the otherhand,
DRM buddy marks each block as cleared.
- Track the available cleared pages size
- If driver requests cleared memory we prefer cleared memory
but fallback to uncleared if we can't find the cleared blocks.
when driver requests uncleared memory we try to use uncleared but
fallback to cleared memory if necessary.
- When a block gets freed we clear it and mark the freed block as cleared,
when there are buddies which are cleared as well we can merge them.
Otherwise, we prefer to keep the blocks as separated.
- Add a function to support defragmentation.
v1:
- Depends on the flag check DRM_BUDDY_CLEARED, enable the block as
cleared. Else, reset the clear flag for each block in the list(Christian)
- For merging the 2 cleared blocks compare as below,
drm_buddy_is_clear(block) != drm_buddy_is_clear(buddy)(Christian)
- Defragment the memory beginning from min_order
till the required memory space is available.
v2: (Matthew)
- Add a wrapper drm_buddy_free_list_internal for the freeing of blocks
operation within drm buddy.
- Write a macro block_incompatible() to allocate the required blocks.
- Update the xe driver for the drm_buddy_free_list change in arguments.
- add a warning if the two blocks are incompatible on
defragmentation
- call full defragmentation in the fini() function
- place a condition to test if min_order is equal to 0
- replace the list with safe_reverse() variant as we might
remove the block from the list.
v3:
- fix Gitlab user reported lockup issue.
- Keep DRM_BUDDY_HEADER_CLEAR define sorted(Matthew)
- modify to pass the root order instead max_order in fini()
function(Matthew)
- change bool 1 to true(Matthew)
- add check if min_block_size is power of 2(Matthew)
- modify the min_block_size datatype to u64(Matthew)
v4:
- rename the function drm_buddy_defrag with __force_merge.
- Include __force_merge directly in drm buddy file and remove
the defrag use in amdgpu driver.
- Remove list_empty() check(Matthew)
- Remove unnecessary space, headers and placement of new variables(Matthew)
- Add a unit test case(Matthew)
v5:
- remove force merge support to actual range allocation and not to bail
out when contains && split(Matthew)
- add range support to force merge function.
v6:
- modify the alloc_range() function clear page non merged blocks
allocation(Matthew)
- correct the list_insert function name(Matthew).
Signed-off-by: Arunpravin Paneer Selvam <[email protected]>
Signed-off-by: Matthew Auld <[email protected]>
Suggested-by: Christian König <[email protected]>
Suggested-by: Matthew Auld <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Christian König <[email protected]>
|