The selftests: kvm: irqfd_test consistently fails across all test platforms since its introduction in Linux next-20250625. The failure occurs due to a KVM_IRQFD ioctl returning errno 11 (Resource temporarily unavailable). This has been observed from day one and is reproducible on all test runs.
Reproducibility: 100% failure on all test platforms since next-20250625..next-20250929
Test fails on the below list * graviton4 * rk3399-rock-pi-4b
## Initial Observations: The test is attempting to register an IRQFD but fails with EAGAIN (errno 11). This likely indicates resource exhaustion or unsupported behavior on affected ARM-based platforms.
Could you please advise on the way forward for this test? Should we treat this as an unsupported case on ARM platforms, or is there a missing implementation/configuration that needs to be addressed?
## Test log selftests: kvm: irqfd_test Random seed: 0x6b8b4567 ==== Test Assertion Failure ==== include/kvm_util.h:527: !ret pid=721 tid=721 errno=11 - Resource temporarily unavailable 1 0x000000000040250f: kvm_irqfd at kvm_util.h:527 2 0x000000000040222f: main at irqfd_test.c:100 3 0x0000ffffbd43229b: ?? ??:0 4 0x0000ffffbd43237b: ?? ??:0 addr2line: 5 0x000000000040206f: DWARF error: mangled line number section (bad file number) addr2line: DWARF error: mangled line number section (bad file number) _start at ??:? KVM_IRQFD failed, rc: -1 errno: 11 (Resource temporarily unavailable) not ok 4 selftests: kvm: irqfd_test exit=254
## Links * https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250929/tes... * https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250929/tes...
On Tue, Sep 30, 2025, Naresh Kamboju wrote:
The selftests: kvm: irqfd_test consistently fails across all test platforms since its introduction in Linux next-20250625. The failure occurs due to a KVM_IRQFD ioctl returning errno 11 (Resource temporarily unavailable). This has been observed from day one and is reproducible on all test runs.
It's a known issue[*], that I think we kinda forgot about. The underlying issue is that KVM ARM needs the test to create a vGIC, but the fix stalled out a bit because there isn't one single, "obviously correct" way to do that.
I'll Cc you and ping Oliver on the other thread.
[*] https://lore.kernel.org/all/20250825155203.71989-1-sebott@redhat.com