* On Thu, 2026-10-22 at 22:17 +1100, Alistair Popple wrote:
On 2026-10-22 at 18:25 +1100, Thomas Hellström thomas.hellstrom@linux.intel.com wrote...
On Thu, 2026-10-22 at 17:52 +1100, Alistair Popple wrote:
On 2026-10-21 at 23:37 +1100, Jason Gunthorpe jgg@nvidia.com wrote...
On Wed, Oct 21, 2026 at 08:24:40AM +0200, Thomas Hellström wrote:
struct dma_buf_mapping_exp_ops Base type for the per-mapping type exporter provided functions. This would be the map/unmap callbacks. Each mapping type can provide its own functions for map/unmap type operations with optimal type signatures.
Does it make sense to try to land this patch first, plus a conversion of pcie_p2p so we could agree on what the contract should look like?
I think it would be good to focus on this patch as the main 'crux' of the series. The API contract is the main agreement. I'm relucant to merge code that has no users, so it woudl be ebtter to go up to at least through SGT.
s/mapping/interconnect/? My gut feeling is that "interconnect" best describes what's typically going on, but "mapping" perhaps better describes all cases.
My intention was to cover more than just the phyiscal transport. We do really want to get away from scatterlist, so having PCIe map with scatterlist and PCIe map with <something else> still ends up with two mapping types in the system.
This is why I choose the name over interconnect.
Location of common protocols which typically carry cross- subsystem dependencies? drivers/dma-buf/mapping_types? drivers/dma-buf/interconnects?
I'd encourage people to design more like PCI where the actual *interconnect* has its own home and there is just some minor call outs from dmabuf to help the matching logic.
As discussed previously: Agree on theoretically possible matches at attach time, Match at mapping time and guarantee the match is valid until invalidate_mappings().
I was thinking about this some more, and I'm less sure now.
If I think about mlx5, in a multi-path PCIe configuration, it can move the translation around within a single PCIe path, but it cannot move it to another path without creating disruption for the application. This is a HW limitation in how the internal routing works..
I strongly suspect this will be the norm for any hardware that doesn't rely on decorated page tables to select the IO path..
So, while I agree we should support hardware that can fully change the path on each and every map, we also need to suport hardware that must pin the path during attach.
Probably this points to needing a 'pin' operation for the mapping selection after attach.
If I'm understanding things correctly we're expecting a change in path between attach and map time to be rare in practice. Therefore the need to handle this case is mostly as a fallback to not break things. So instead of pinning could new attachments just invalidate all existing incompatible attachments on the list by setting eg. attach->valid = 0?
I agree, (although I think the "invalidate_attachment" needs to be discussed). In the end the importer should be given a choice, either pin and accept that subsequent attachers might see errors or accept app disruption.
Attachment could also scan existing attachments to preferentially pick matching mapping_types that are compatible with existing attachments, thus avoiding invalidation where possible.
Current design appears to be that attach only determines the set of theoretically possible mapping types, disregarding other attachments. Taking other attachments into account is also problematic because the dma-resv lock is not held.
Oh I see. Do you foresee any problems just taking the dma-resv lock to walk the current attachments? If so we could probably resolve it with RCU, but I'd rather keep it simple if we can.
It looks like dma_buf_dynamic_attach() actually takes the dma_resv lock to update the attachment list, so that should work. Provided we want to take existing attachments into account already at this stage.
Need to take care, though, not to have the resv lock held over the ops-
attach callback into the driver.
Looking at current GPU drivers, what you describe above is typically done at pin() time, but if some importers want an early very likely decision on what mapping_type to use, one could introduce a separate function that match the mapping_types, but that would be very similar to the map() function but without returning a sgt/mapping, or a pin() without actually pinning. One could reuse the invalidate_mappings() callback to indicate the mapping type is no longer valid?
I did wonder about that, but a callback for attachment invalidation seems like it might be a pain for importers to syncrhonize with. What I'm thinking, which I think is similar to what you describe, is something like the following:
- Importer gets the likley attachment by passing a list of mapping
types in prefered order to dma_buf_mapping_attach() which returns the dma_buf_attachment that would work based on current attachments and what the exporter provides:
Something like this sounds OK, although given Jason's use-case, I added some comments:
attach = dma_buf_mapping_attach(...)
Just filter out impossible mappings.
- Takes dmabuf->resv lock.
dma_buf_match_mapping_type(); Determines a mapping that is valid until the next invalidate_mappings(). NOP if a valid mapping already exists. Allows masking mapping_types. This allows Jason's use-case while keeping the attachment as a callback anchor.
- Pins the attachment (if required):
dma_buf_match_mapping_type(); Determines a mapping that is valid until the next invalidate_mappings(). NOP if a valid mapping already exists. Allows masking mapping_types. This allows Jason's use-case while keeping the attachment as a callback anchor.
rc = dma_buf_pin(attach)
This would implicitly pin also the mapping_type, but question is what happens if a link is severed? Then we'd want an invalidate_mappings() to re-negotiate the mapping type, but a pinned dma-buf that receives an invalidate_mappings() is revoked by definition.
DMA-BUF core revalidates the attachment is still valid (ie. by checking the match again or via some other mechanism to detect the attachment path/location has changed such as a sequence/generation number).
Since the resv is locked, nothing could have changed since dma_buf_match_mapping_type();
/Thomas
On error the importer can either fail or try to create a new attachment.
- Map
rc = dma_buf_[sgt|pcie_p2p]_map(attach, ...)
Follows the same revalidation process as dma_buf_pin().
Thoughts?
- Alistair
/Thomas
Map time functions (eg. dma_buf_sgt_map_attachment) would check attach->valid and return a failure if a subsequent attachment/event had invalidated the mapping type.
Importers with invalidated attachments would then have to retry creating the attachment, probably getting a different mapping_type. Would this be acceptable? Or do some importers absolutely require the mapping_type to never change once the intial match/attachment has happened?
- Alistair
+/*
- Match items are generated by the importer using the
DMA_BUF_IMAPPING_*() and
- the exporter using the DMA_BUF_EMAPPING_*() functions.
Each mapping type
- defines its own signature with its own data to make the
match and attachment.
- */
+struct dma_buf_mapping_match {
- const struct dma_buf_mapping_type *type;
- const struct dma_buf_mapping_exp_ops *exp_ops;
- union {
- /* Each mapping_type has unique match
parameters here */
- };
Do we really need to add all global mapping types here? Then we'd need something for driver-private mapping types as well.
IIRC it is fixed size up front like this because of how the structure's memory is managed in this design..
If you want a driver private thing then I'd add a 'u64 driver_private[2]' to the union and the driver can cast over it.
But this is the kernel, if you want to add an xe_mapping_type, then just add it. I don't know we need to do driver private things.
Jason
linaro-mm-sig@lists.linaro.org
-
Thomas Hellström