kernel/tools/testing/selftests/powerpc/security/spectre_v2.c, branch linux-6.2.y

selftests/powerpc/pmu: fix spelling mistake "mis-match" -> "mismatch"

2022-05-22T05:59:54Z

There are a few spelling mistakes in error messages. Fix them. Signed-off-by: Colin Ian King Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220319232025.22067-1-colin.i.king@gmail.com

selftests/powerpc: Better reporting in spectre_v2

2022-05-22T05:58:28Z

In commit f3054ffd71b5 ("selftests/powerpc: Return skip code for spectre_v2"), the spectre_v2 selftest is updated to be aware of cases where the vulnerability status reported in sysfs is incorrect, skipping the test instead. This happens because qemu can misrepresent the mitigation status of the host to the guest. If the count cache is disabled in the host, and this is correctly reported to the guest, then the guest won't apply mitigations. If the guest is then migrated to a new host where mitigations are necessary, it is now vulnerable because it has not applied mitigations. Update the selftest to report when we see excessive misses, indicative of the count cache being disabled. If software flushing is enabled, also warn that these flushes are just wasting performance. Signed-off-by: Russell Currey [mpe: Rebase and update change log appropriately] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210608064809.199116-1-ruscur@russell.cc

selftests/powerpc: Fix typo in spectre_v2

2022-05-04T09:37:46Z

Signed-off-by: Russell Currey Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210608054851.164659-1-ruscur@russell.cc

selftests/powerpc/pmu: Add macros to parse event codes

2022-03-01T12:38:12Z

Each platform has raw event encoding format which specifies the bit positions for different fields. The fields from event code gets translated into performance monitoring mode control register (MMCRx) settings. Patch add macros to extract individual fields from the event code. Add functions for sanity checks, since testcases currently are only supported in power9 and power10. Signed-off-by: Madhavan Srinivasan [mpe: Read PVR directly rather than using /proc/cpuinfo] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220127072012.662451-4-kjain@linux.ibm.com

selftests/powerpc/spectre_v2: Return skip code when miss_percent is high

2021-12-09T11:41:21Z

A mis-match between reported and actual mitigation is not restricted to the Vulnerable case. The guest might also report the mitigation as "Software count cache flush" and the host will still mitigate with branch cache disabled. So, instead of skipping depending on the detected mitigation, simply skip whenever the detected miss_percent is the expected one for a fully mitigated system, that is, above 95%. Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211207130557.40566-1-cascardo@canonical.com

selftests/powerpc: Skip security tests on older CPUs

2020-09-08T12:24:05Z

Both these tests use PMU events that only work on newer CPUs, so skip them on older CPUs. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-6-mpe@ellerman.id.au

selftests/powerpc: Return skip code for spectre_v2

2020-07-29T13:47:52Z

When running under older versions of qemu of under newer versions with old machine types, some security features will not be reported to the guest. This will lead the guest OS to consider itself Vulnerable to spectre_v2. So, spectre_v2 test fails in such cases when the host is mitigated and miss predictions cannot be detected as expected by the test. Make it return the skip code instead, for this particular case. We don't want to miss the case when the test fails and the system reports as mitigated or not affected. But it is not a problem to miss failures when the system reports as Vulnerable. Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200728155039.401445-1-cascardo@canonical.com

selftests/powerpc: Add a test of spectre_v2 mitigations

2019-10-30T04:43:57Z

This test uses the PMU to count branch prediction hits/misses for a known loop, and compare the result to the reported spectre v2 mitigation. This gives us a way of sanity checking that the reported mitigation is actually in effect. Sample output for some cases, eg: Power9: sysfs reports: 'Vulnerable' PM_BR_PRED_CCACHE: result 368 running/enabled 5792777124 PM_BR_MPRED_CCACHE: result 319 running/enabled 5792775546 PM_BR_PRED_PCACHE: result 2147483281 running/enabled 5792773128 PM_BR_MPRED_PCACHE: result 213604201 running/enabled 5792771640 Miss percent 9 % OK - Measured branch prediction rates match reported spectre v2 mitigation. sysfs reports: 'Mitigation: Indirect branch serialisation (kernel only)' PM_BR_PRED_CCACHE: result 895 running/enabled 5780320920 PM_BR_MPRED_CCACHE: result 822 running/enabled 5780312414 PM_BR_PRED_PCACHE: result 2147482754 running/enabled 5780308836 PM_BR_MPRED_PCACHE: result 213639731 running/enabled 5780307912 Miss percent 9 % OK - Measured branch prediction rates match reported spectre v2 mitigation. sysfs reports: 'Mitigation: Indirect branch cache disabled' PM_BR_PRED_CCACHE: result 2147483649 running/enabled 20540186160 PM_BR_MPRED_CCACHE: result 2147483649 running/enabled 20540180056 PM_BR_PRED_PCACHE: result 0 running/enabled 20540176090 PM_BR_MPRED_PCACHE: result 0 running/enabled 20540174182 Miss percent 100 % OK - Measured branch prediction rates match reported spectre v2 mitigation. Power8: sysfs reports: 'Vulnerable' PM_BR_PRED_CCACHE: result 2147483649 running/enabled 3505888142 PM_BR_MPRED_CCACHE: result 9 running/enabled 3505882788 Miss percent 0 % OK - Measured branch prediction rates match reported spectre v2 mitigation. sysfs reports: 'Mitigation: Indirect branch cache disabled' PM_BR_PRED_CCACHE: result 2147483649 running/enabled 16931421988 PM_BR_MPRED_CCACHE: result 2147483649 running/enabled 16931416478 Miss percent 100 % OK - Measured branch prediction rates match reported spectre v2 mitigation. success: spectre_v2 Signed-off-by: Michael Ellerman Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190520105520.22274-1-mpe@ellerman.id.au