Package: linux-image-7.1.0+debian+tj
Followup-For: Bug #1141183
X-Debbugs-Cc: [email protected]
Control: forwarded -1 https://bugzilla.kernel.org/show_bug.cgi?id=221713
Bisection has taken some time and false started but we've now confirmed:
v7.2-rc2 @ dd3210c47e8d3ac6 is broken:
[ 83.224361] ata4.00: exception Emask 0x0 SAct 0x2000 SErr 0x0 action 0x0
[ 83.224432] ata4.00: failed command: READ FPDMA QUEUED
[ 83.224457] ata4.00: cmd 60/00:68:00:99:5d/04:00:02:00:00/40 tag 13 ncq dma
524288 in
res 40/00:01:06:4f:c2/00:00:00:00:00/00 Emask 0x40
(internal error)
[ 83.224525] ata4.00: status: { DRDY }
[ 83.333448] ata4.00: configured for UDMA/133
[ 83.333481] ata4: EH complete
Bisection shows the regression is in the IOMMU Merge tag 'iommu-updates-v6.19'
ce5cfb0fa20dc.
So far attempting to bisect inside that merge has resulted in unrelated
failures that prevent the ability to initiate the tests that provoke the
exception.
Since the mainline merge is itself a merge on the iommu tree of several
branches at 0d081b16946ef449fc:
Merge branches 'arm/smmu/updates', 'arm/smmu/bindings', 'mediatek',
'nvidia/tegra', 'intel/vt-d', 'amd/amd-vi' and 'core' into next
I tried to isolate the likely candidate branches intel/vt-d and core but as
those branches have moved on I've not been able to accurately identify the
collection of patches that come from each branch at that time.
However, I suspect d373449d8e97891434 "iommu/vt-d: Use the generic iommu page
table" that removes the original intel_iommu PT code is the most likely culprit.
Continuing to try to find usable bisect points in that merge series.
