[PATCH v7] mtd: rawnand: sunxi: Add MDMA support

[Miquel Raynal]

Hi Manuel,

Manuel Dipolt <mdipolt at robart.cc> wrote on Mon, 12 Oct 2020 17:41:22
+0200 (CEST):

> This patch enables NAND MDMA (MBUS DMA) mode for 
> the Allwinner SoCs A23/A33/H3. 
> 
> The DMA transfer method gets sets now to MBUS DMA as default for
> the sun8i-a23-nand-controller (till now DMA transfer was executed
> via the shared DMA engine).
> 
> The main advantage is more bandwidth for the users of the shared DMA
> engine and also that the MBUS DMA setup requires less configuration
> effort. For example you don't need to define a dedicated DMA channel
> in the device-tree any more.
> 
> 
> Reviewed-by: Boris Brezillon <boris.brezillon at collabora.com>
> Signed-off-by: Manuel Dipolt <manuel.dipolt at robart.cc>

I tested your patch, it breaks my CHIP pro (sun5i R8):

[    1.775606] nand: device found, Manufacturer ID: 0x98, Chip ID: 0xd7
[    1.782168] nand: Toshiba TC58TEG5DCLTA00
[    1.786292] nand: 4096 MiB, MLC, erase size: 4096 KiB, page size: 16384, OOB size: 1280
[    1.798037] Scanning device for bad blocks
[    2.808728] sunxi_nand 1c03000.nand-controller: wait interrupt timedout
[    2.983031] random: fast init done
[    3.848719] sunxi_nand 1c03000.nand-controller: wait interrupt timedout
[    4.017501] random: crng init done
[    4.859050] sunxi_nand 1c03000.nand-controller: wait for empty cmd FIFO timedout
[    5.870270] sunxi_nand 1c03000.nand-controller: wait for empty cmd FIFO timedout
[    6.881406] sunxi_nand 1c03000.nand-controller: wait for empty cmd FIFO timedout
[    6.892444] nand_bbt: can't scan flash and build the RAM-based BBT
[    6.902268] sunxi_nand 1c03000.nand-controller: failed to init nand chips
[    6.912925] sunxi_nand: probe of 1c03000.nand-controller failed with error -110

I don't have the time to debug it right now, I'm sorry.

Thanks,
Miquèl