libvirt/tests/cputestdata/x86_64-cpuid-baseline-Cascadelake+Skylake-IBRS.xml

<cpu mode='custom' match='exact'>
  <model fallback='allow'>Skylake-Server-IBRS</model>
  <vendor>Intel</vendor>
  <feature policy='require' name='hypervisor'/>
  <feature policy='require' name='ss'/>
  <feature policy='require' name='tsc_adjust'/>
  <feature policy='require' name='mpx'/>
  <feature policy='require' name='clflushopt'/>
  <feature policy='require' name='umip'/>
  <feature policy='require' name='pku'/>
  <feature policy='require' name='ssbd'/>
  <feature policy='require' name='xsaves'/>
  <feature policy='require' name='skip-l1dfl-vmentry'/>
</cpu>
cputest: Add some real world baseline tests Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-21 16:25:15 +00:00			`<cpu mode='custom' match='exact'>`
cpu_x86: Penalize disabled features when computing CPU model For finding the best matching CPU model for a given set of features while we don't know the CPU signature (i.e., when computing a baseline CPU model) we've been using a "shortest list of features" heuristics. This works well if new CPU models are supersets of older models, but that's not always the case. As a result it may actually select a new CPU model as a baseline while removing some features from it to make it compatible with older models. This is in general worse than using an old CPU model with a bunch of added features as a guest OS or apps may crash when using features that were disabled. On the other hand we don't want to end up with a very old model which would guarantee no disabled features as it could stop a guest OS or apps from using some features provided by the CPU because they would not expect them on such an old CPU. This patch changes the heuristics to something in between. Enabled and disabled features are counted separately so that a CPU model requiring some features to be disabled looks worse than a model with fewer disabled features even if its complete list of features is longer. The penalty given for each additional disabled feature gets bigger to make longer list of disabled features look even worse. https://bugzilla.redhat.com/show_bug.cgi?id=1851227 Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-26 13:06:30 +00:00			`<model fallback='allow'>Skylake-Server-IBRS</model>`
cputest: Add some real world baseline tests Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-21 16:25:15 +00:00			`<vendor>Intel</vendor>`
			`<feature policy='require' name='hypervisor'/>`
cpu_map: Sort cpu features Some feature words were not sorted correctly. Signed-off-by: Tim Wiederhake <twiederh@redhat.com> Reviewed-by: Jiri Denemark <jdenemar@redhat.com> 2024-02-01 21:03:49 +00:00			`<feature policy='require' name='ss'/>`
cputest: Add some real world baseline tests Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-21 16:25:15 +00:00			`<feature policy='require' name='tsc_adjust'/>`
cpu_map: Drop 'mpx' from x86 cpu models The mpx feature was removed from the corresponding qemu cpu models. With mpx in the libvirt cpu models, libvirt believes the feature to be implicitly enabled when creating qemu VMs, while in fact it is disabled. This became an issue when commit 94eacd5a5f introduced new vmx-* features, of which some are dependent on mpx (see "feature_dependencies" table in qemu target/i386/cpu.c), e.g. vmx-exit-clear-bndcfgs and vmx-entry-load-bndcfgs. These features cannot be enabled by qemu without also mpx being enabled, leading to the error message error: Failed to create domain from testdomain.xml error: operation failed: guest CPU doesn't match specification: missing features: mpx,vmx-exit-clear-bndcfgs, vmx-entry-load-bndcfgs when trying to create a VM with a "host-model" cpu on a host that does support mpx and the mentioned vmx-* features: <domain> ... <cpu mode='host-model' check='full' /> ... </domain> Resolve the issue by removing mpx from libvirt's cpu models as well. Signed-off-by: Tim Wiederhake <twiederh@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> 2024-02-09 10:52:56 +00:00			`<feature policy='require' name='mpx'/>`
cpu_x86: Penalize disabled features when computing CPU model For finding the best matching CPU model for a given set of features while we don't know the CPU signature (i.e., when computing a baseline CPU model) we've been using a "shortest list of features" heuristics. This works well if new CPU models are supersets of older models, but that's not always the case. As a result it may actually select a new CPU model as a baseline while removing some features from it to make it compatible with older models. This is in general worse than using an old CPU model with a bunch of added features as a guest OS or apps may crash when using features that were disabled. On the other hand we don't want to end up with a very old model which would guarantee no disabled features as it could stop a guest OS or apps from using some features provided by the CPU because they would not expect them on such an old CPU. This patch changes the heuristics to something in between. Enabled and disabled features are counted separately so that a CPU model requiring some features to be disabled looks worse than a model with fewer disabled features even if its complete list of features is longer. The penalty given for each additional disabled feature gets bigger to make longer list of disabled features look even worse. https://bugzilla.redhat.com/show_bug.cgi?id=1851227 Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-26 13:06:30 +00:00			`<feature policy='require' name='clflushopt'/>`
cputest: Add some real world baseline tests Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-21 16:25:15 +00:00			`<feature policy='require' name='umip'/>`
			`<feature policy='require' name='pku'/>`
cpu_x86: Penalize disabled features when computing CPU model For finding the best matching CPU model for a given set of features while we don't know the CPU signature (i.e., when computing a baseline CPU model) we've been using a "shortest list of features" heuristics. This works well if new CPU models are supersets of older models, but that's not always the case. As a result it may actually select a new CPU model as a baseline while removing some features from it to make it compatible with older models. This is in general worse than using an old CPU model with a bunch of added features as a guest OS or apps may crash when using features that were disabled. On the other hand we don't want to end up with a very old model which would guarantee no disabled features as it could stop a guest OS or apps from using some features provided by the CPU because they would not expect them on such an old CPU. This patch changes the heuristics to something in between. Enabled and disabled features are counted separately so that a CPU model requiring some features to be disabled looks worse than a model with fewer disabled features even if its complete list of features is longer. The penalty given for each additional disabled feature gets bigger to make longer list of disabled features look even worse. https://bugzilla.redhat.com/show_bug.cgi?id=1851227 Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-26 13:06:30 +00:00			`<feature policy='require' name='ssbd'/>`
cputest: Add some real world baseline tests Signed-off-by: Jiri Denemark <jdenemar@redhat.com> Reviewed-by: Michal Privoznik <mprivozn@redhat.com> 2022-04-21 16:25:15 +00:00			`<feature policy='require' name='xsaves'/>`
			`<feature policy='require' name='skip-l1dfl-vmentry'/>`
			`</cpu>`