[PATCH RFC v4 0/4] iommu/arm-smmu-v3: Support shared Stream IDs

[Peng Fan (OSS)]

Some SoCs have a limited number of IOMMU Stream IDs and hardware
that inherently shares them.  The NXP i.MX95, for example, has
only 64 SIDs -- the internal bus carries just 6 bits of requester
ID -- serving 64+ DMA initiators spread across separate IP blocks:
MMC, SD, NET, PCI, DMA, NPU, DSP, DISPLAY and more.  Because the
SID space is exhausted, genuinely distinct platform devices (with
their own DT nodes and drivers) share a SID by hardware design.

The current ARM SMMUv3 driver rejects this situation with:
  "Aliasing StreamID unsupported, expect DMA to be broken"

This series adds support for multiple single-SID masters to share
a Stream ID, allowing such constrained SoCs to function with
IOMMU translation enabled.

Patch 1 fixes a pre-existing bug where rb_erase() is called on
duplicate SID entries that were never inserted into the RB tree,
which can corrupt the tree.  Bridged PCI devices may produce
duplicated Stream IDs; the insertion path already skips them but
the removal and error rollback paths did not.

Patch 2 adds shared-SID tracking so that when a second single-SID
master registers an already-owned SID, it joins the existing
stream rather than being rejected.  The stream structure is shared
directly between masters via a linked list. On removal, ownership
transfers to the next sharer.

Patch 3 places devices that share a SID into the same IOMMU
group, ensuring they share a single IOMMU domain (required
because one STE can only point to one cd_table).

Patch 4 wires up STE write ordering (first master writes, last
master tears down) and gates features that require unambiguous
SID-to-device mapping: SVA, IOPF/stall, and vSMMU nesting are
disabled for shared-SID masters.

Changes since RFC v3:
- Added a standalone bugfix for duplicate-SID rb_erase (new patch 1).
- Stream structures are now shared directly between masters
  instead of duplicating them (Nicolin).  No ref_count field;
  sharing is detected via list_empty(&stream->shared_masters).
- On owner removal, use rb_replace_node() + list_splice_init()
  to transfer the RB tree entry and shared_masters list to the
  next sharer, avoiding use-after-free.
- INIT_LIST_HEAD(&stream->shared_masters) moved after sort() to
  avoid list pointer corruption from bitwise memory swaps.
- Both sides of the sharing pair are checked for num_streams == 1.

Changes since RFC v2:
- Dropped the RB tree to XArray conversion patch (Nicolin).
  The RB tree is retained as-is; a new arm_smmu_find_stream()
  helper provides stream-level lookup.
- No per-master shared_sid bool; replaced by
  list_empty(&master->shared_masters_elm) (Nicolin).
- Only SID-sharing for single SID device
- Follow Nicolin's suggestion https://lore.kernel.org/linux-iommu/arG6hmng3NddGEHm@xxxxxxxxxx/
- Link to v2: https://lore.kernel.org/linux-iommu/20260921-smmu-shared-sid-v2-0-4b656ce68178@xxxxxxx/

Changes since RFC v1:
- Revised cover letter to drop eDMA channel example (Jason).

Signed-off-by: Peng Fan <peng.fan@xxxxxxx>
---
Peng Fan (4):
      iommu/arm-smmu-v3: Skip duplicate SIDs when erasing streams from RB tree
      iommu/arm-smmu-v3: Support shared SIDs in insert/remove_master
      iommu/arm-smmu-v3: Group aliasing devices into the same IOMMU group
      iommu/arm-smmu-v3: Wire up shared-SID STE ordering and feature gating

 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c    |   2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c    |   3 +
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c        | 174 +++++++++++++++++----
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h        |   3 +
 4 files changed, 150 insertions(+), 32 deletions(-)
---
base-commit: 6474fa070f2b8013b4b87350b775b8c3be6e8aac
change-id: 20260930-smmu-shared-sid-ver3-96807c4f4d93

Best regards,
--  
Peng Fan <peng.fan@xxxxxxx>