DMA zones code assumes that DMA lower limit is zero. When there is no RAM 
below 4GB, arm64 platform code sets DMA/DMA32 zone limits to cover the entire 
RAM[0].

The platform I have has RAM starting at 32GB. Devices with 30-bit DMA mask are 
mapped to 1GB at the bottom of RAM, between 32GB - 33GB. A DMA zone over the 
entire RAM breaks DMA allocation for these devices.

In response to a previous RFC hack[1] Catalin Marinas suggested to add a
separate offset value as base address for the DMA zone. This RFC series 
attempts to implement that suggestion.

With this series applied, the DMA zone covers the right RAM range for my 
platform.

[0] See commit 791ab8b2e3db ("arm64: Ignore any DMA offsets in the 
    max_zone_phys() calculation")

[1] https://lore.kernel.org/all/9af8a19c3398e7dc09cfc1fbafed98d795d9f83e.1699464622.git.baruch@tkos.co.il/

Baruch Siach (4):
  of: get dma area lower limit
  of: unittest: add test for of_dma_get_cpu_limits() 'min' param
  dma-direct: add offset to zone_dma_bits
  arm64: mm: take DMA zone offset into account

 arch/arm64/mm/init.c       | 18 +++++++++++++-----
 drivers/of/address.c       | 38 +++++++++++++++++++++++++++-----------
 drivers/of/unittest.c      | 17 ++++++++++-------
 include/linux/dma-direct.h |  1 +
 include/linux/of.h         | 11 ++++++++---
 kernel/dma/direct.c        | 10 ++++++----
 kernel/dma/pool.c          |  2 +-
 kernel/dma/swiotlb.c       |  5 +++--
 8 files changed, 69 insertions(+), 33 deletions(-)

-- 
2.43.0