summaryrefslogtreecommitdiff
path: root/kvm
Commit message (Collapse)AuthorAgeFilesLines
* Synchronize kvm headersMarcelo Tosatti2010-01-312-2/+11
| | | | Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* Release script: document external dependencies in tarballAvi Kivity2009-12-201-0/+7
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* kvm headers: fix __user exportMichael S. Tsirkin2009-12-021-1/+1
| | | | | | | | __user macro does not appear in exported headers and should not be in headers qemu-kvm includes. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
* Synchronize kvm headersAvi Kivity2009-11-152-114/+175
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* Import internal error data header updates from kvm.gitAvi Kivity2009-11-151-0/+4
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* tests: The order of the fields are in reverse one isr stack.Gleb Natapov2009-11-031-4/+4
| | | | | Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* tests: Move typedefs to one place.Gleb Natapov2009-11-034-14/+6
| | | | | Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* vmxcap: improve bool formattingAvi Kivity2009-11-011-1/+2
| | | | | | yes/no replaces True/False. Signed-off-by: Avi Kivity <avi@redhat.com>
* vmxcap: report MISC and EPT/VPID capabilitiesAvi Kivity2009-10-291-0/+36
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* vmxcap: support msrs with numerical subfieldsAvi Kivity2009-10-291-0/+23
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* Remove kvmctl from kvm/user/config-x86-common.makMarcelo Tosatti2009-10-201-2/+1
| | | | Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* Drop kvm/bios/ treeAvi Kivity2009-10-1517-16914/+0
| | | | | | | Equivalent code is now in the roms/pcbios/ submodule. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* Update kvm headersAvi Kivity2009-10-087-43/+67
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* Consolidate kvm header CONFIG_ handling into a central fileAvi Kivity2009-10-089-320/+43
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* Remove kernel-internal kvm headersAvi Kivity2009-10-0813-4011/+0
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* test: vmexit: inl from pmtimerMarcelo Tosatti2009-10-061-0/+13
| | | | | | | Add inl(ACPI_PMTIMER_PORT) test. Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
* test: vmexit: run parallel tests on each cpuMarcelo Tosatti2009-10-061-9/+34
| | | | | | | So one can measure SMP overhead. Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
* test: add on_cpu_asyncMarcelo Tosatti2009-10-062-4/+19
| | | | | | | Non-wait version of on_cpu. Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
* vmxcap: add PAUSE-loop exiting reportingAvi Kivity2009-09-231-0/+1
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* vmxcap: fix 'Unrestricted Guest' reportingAvi Kivity2009-09-231-1/+1
| | | | | | It's a secondary execution control, not a pin-based control. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: Auto-tune vmexit testAvi Kivity2009-09-221-6/+10
| | | | | | Scale up iterations until we measure at least 1G cycles. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: Add ipi_halt benchmarkAvi Kivity2009-09-221-0/+11
| | | | | | | Wait for 2000 cycles after the IPI to allow the host to schedule out. Measures wake-from-idle overhead. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: add ipi latency testAvi Kivity2009-09-221-0/+18
| | | | Signed-off-by: Avi Kivity <avi@redhat.com>
* test: add conditional execution for vmexit testsAvi Kivity2009-09-221-0/+6
| | | | | | ipi tests can only run on smp for example. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: optimize smp_id()Avi Kivity2009-09-221-2/+15
| | | | | | | Rather than reading it from the APIC, read it from the per-cpu area. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: set up per-cpu areaAvi Kivity2009-09-221-0/+11
| | | | | | Currently sharing space with the stack. Signed-off-by: Avi Kivity <avi@redhat.com>
* test: issue EOI after IPIAvi Kivity2009-09-221-0/+1
| | | | | | Otherwise, we can't take more than one IPI. Signed-off-by: Avi Kivity <avi@redhat.com>
* update qemu-ifup for modern ip route outputDustin Kirkland2009-09-181-1/+1
| | | | | | | | | | | | | | | update qemu-ifup for modern ip route output The output from the /sbin/ip utility has changed, adding two more columns, which breaks the qemu-ifup script, as it was depending on the last column being the interface name. Change this from $NF to $5. https://bugs.edge.launchpad.net/ubuntu/+source/qemu-kvm/+bug/430652 Signed-off-by: Dustin Kirkland <kirkland@canonical.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: avoid deleting intermediate .o filesAvi Kivity2009-09-161-1/+8
| | | | | | | | | | | | If make doesn't see an intermediate file mentioned explicitly, it deletes it after making the target. This silly behaviour causes needless rebuilds. Add all intermediates as explicit dependncies to prevent this behaviour. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Fix compilation rule for assembly files wrt autodependenciesAvi Kivity2009-09-161-1/+1
| | | | | | | | Only compile the first dependency (the source file), not the rest (headers). Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: fix autodependenciesAvi Kivity2009-09-161-0/+2
| | | | | | | The autodependencies files were generated, but not included. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: drop irq.flatAvi Kivity2009-09-163-121/+1
| | | | | | | Obsolete. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: port smp runtime to real apicAvi Kivity2009-09-163-68/+12
| | | | | | | instead of the old fake apic. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: wait for all processors to complete initializationAvi Kivity2009-09-161-0/+7
| | | | | | | so we can start blasting them with IPIs. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: initialize apic/x2apic on all processorsAvi Kivity2009-09-161-0/+5
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: initialize idt on all processorsAvi Kivity2009-09-161-0/+6
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Use xapic_write() to enable xapic()Avi Kivity2009-09-161-1/+1
| | | | | | | | | apic_write() depends on apic_ops, which is shared among cpus and can be modified if another cpu enabled x2apic. Use xapic_write() which is race-proof. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: add apic_id() accessorAvi Kivity2009-09-162-0/+19
| | | | | | | | apic and x2apic have different formats for the ID register, so we need an accessor for it. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: switch 64-bit smp startup to real APICAvi Kivity2009-09-161-31/+43
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Move apic functions to libcflatAvi Kivity2009-09-166-128/+169
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: apic: use 1:1 mapping for apicAvi Kivity2009-09-161-2/+2
| | | | | | | | This allows the apic code to be run early, before virtual memory is set up. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: vm: map mmio 1:1Avi Kivity2009-09-161-0/+3
| | | | | | | | With this assumption, the apic code will be able to run either before or after the vm is set up. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Add fwcfg interface for getting the cpu countAvi Kivity2009-09-162-0/+7
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: add support for the firmware configuration interfaceAvi Kivity2009-09-163-0/+79
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: add x2apic testAvi Kivity2009-09-161-0/+46
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: use new apic_icr_write() to issue IPIAvi Kivity2009-09-161-2/+2
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Use function table for APIC accessAvi Kivity2009-09-161-2/+39
| | | | | | | Prepare for x2apic. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Mask PIC interrupts before APIC testAvi Kivity2009-09-161-0/+13
| | | | | | | We aren't ready to handle PIC interrupts, so mask them. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: add cr8 latency testsAvi Kivity2009-09-161-0/+16
| | | | | | | In light of the recent cr8/ept problem. Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* test: Add vmcall latency testAvi Kivity2009-09-161-0/+8
| | | | | Signed-off-by: Avi Kivity <avi@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>