On 11/23/2021 2:06 AM, Kalle Valo wrote:
Mark Herbert <mark.herbert42@xxxxxxxxx> writes:
Tried this on Dell XPS 13 9310
Maybe this patch is good for 6855, but 6390 in Dell seems to be killed
completely with it. Reverting it makes things work again.
[ 5.537034] ath11k_pci 0000:72:00.0: chip_id 0x0 chip_family 0xb
board_id 0xff soc_id 0xffffffff
[ 5.537038] ath11k_pci 0000:72:00.0: fw_version 0x101c06cc
fw_build_timestamp 2020-06-24 19:50 fw_build_id
[ 5.537236] ath11k_pci 0000:72:00.0: failed to fetch board data for
bus=pci,qmi-chip-id=0,qmi-board-id=255,variant=DE_1901 from
ath11k/QCA6390/hw2.0/board-2.bin
[ 5.537255] ath11k_pci 0000:72:00.0: failed to fetch board-2.bin or
board.bin from QCA6390/hw2.0
[ 5.537257] ath11k_pci 0000:72:00.0: qmi failed to fetch board file: -2
[ 5.537258] ath11k_pci 0000:72:00.0: failed to load board data file: -2
Doh, I didn't realise that. I only tested this on my NUC testbox, I
should have tested this on my XPS 13 9310 as well. Thanks for the
report!
I think I need to revert this and rethink how to handle the backwards
compatibility.
ath10k has patches to handle backwards compatibility for this issue, I
think ath11k can also follow it.
https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/drivers/net/wireless/ath?id=c8489668065a283d3027e86e877b103a87f99d22
ath10k: search all IEs for variant before falling back
https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/drivers/net/wireless/ath?id=2bc2b87bb35a4d7b022016819fc28ce9e2b13adc
ath10k: add option for chip-id based BDF selection
