summaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
authorTomeu Vizoso <tomeu@tomeuvizoso.net>2026-08-24 17:26:11 +0200
committerRob Herring (Arm) <robh@kernel.org>2026-08-24 17:20:58 -0500
commitdb9deec5a345abc538d081fb221dc0b00a9695bd (patch)
tree852fcb3ea47b65f178b193cddd6705fb1c482a2b /drivers/gpu
parent7ab64476a610fe65858fdc37c7a30caa13e334ac (diff)
downloadlinux-next-db9deec5a345abc538d081fb221dc0b00a9695bd.tar.gz
linux-next-db9deec5a345abc538d081fb221dc0b00a9695bd.zip
accel: ethosu: Don't read the U65 rounding mode as a storage mode
Bits 15:14 of NPU_SET_{IFM,OFM}_PRECISION select the activation storage mode on U85 only. On U65 the same field holds the rounding mode, and the command stream parser has read it as a storage mode since the driver was added. That went unnoticed while unknown values fell through the switch, but now that they are rejected, every U65 command stream that asks for natural rounding (2) fails CMDSTREAM_BO_CREATE with -EINVAL. Mesa emits it for average pooling, concatenation, split, unpack, strided slice, LUT and argmax, which is 72 failures of the Teflon test suite on an i.MX93. Truncating rounding (1) is misread as well: it picks the two-tile address path and computes a bogus feature map size from tile bases the command stream never set. Read the field as a storage mode only on the hardware where it is one. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Fixes: 6b7e0066294d ("accel: ethosu: Handle U85 internal chaining buffer") Assisted-by: Claude:claude-opus-5 Signed-off-by: Tomeu Vizoso <tomeu@tomeuvizoso.net> Link: https://patch.msgid.link/20260824152612.751007-1-tomeu@tomeuvizoso.net Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Diffstat (limited to 'drivers/gpu')
0 files changed, 0 insertions, 0 deletions