kernel.git/arch/arm64/kvm, branch linux-3.13.y

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

2013-11-15T04:51:36Z

Pull KVM changes from Paolo Bonzini: "Here are the 3.13 KVM changes. There was a lot of work on the PPC side: the HV and emulation flavors can now coexist in a single kernel is probably the most interesting change from a user point of view. On the x86 side there are nested virtualization improvements and a few bugfixes. ARM got transparent huge page support, improved overcommit, and support for big endian guests. Finally, there is a new interface to connect KVM with VFIO. This helps with devices that use NoSnoop PCI transactions, letting the driver in the guest execute WBINVD instructions. This includes some nVidia cards on Windows, that fail to start without these patches and the corresponding userspace changes" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits) kvm, vmx: Fix lazy FPU on nested guest arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu arm/arm64: KVM: MMIO support for BE guest kvm, cpuid: Fix sparse warning kvm: Delete prototype for non-existent function kvm_check_iopl kvm: Delete prototype for non-existent function complete_pio hung_task: add method to reset detector pvclock: detect watchdog reset at pvclock read kvm: optimize out smp_mb after srcu_read_unlock srcu: API for barrier after srcu read unlock KVM: remove vm mmap method KVM: IOMMU: hva align mapping page size KVM: x86: trace cpuid emulation when called from emulator KVM: emulator: cleanup decode_register_operand() a bit KVM: emulator: check rex prefix inside decode_register() KVM: x86: fix emulation of "movzbl %bpl, %eax" kvm_host: typo fix KVM: x86: emulate SAHF instruction MAINTAINERS: add tree for kvm.git Documentation/kvm: add a 00-INDEX file ...

Merge tag 'kvm-arm64/for-3.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into kvm-next

2013-11-11T11:05:20Z

A handful of fixes for KVM/arm64: - A couple a basic fixes for running BE guests on a LE host - A performance improvement for overcommitted VMs (same as the equivalent patch for ARM) Signed-off-by: Paolo Bonzini Conflicts: arch/arm/include/asm/kvm_emulate.h arch/arm64/include/asm/kvm_emulate.h

arm64: KVM: vgic: byteswap GICv2 access on world switch if BE

2013-11-06T10:10:12Z

Ensure that accesses to the GICH_* registers are byteswapped when the kernel is compiled as big-endian. Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas

arm64: KVM: initialize HYP mode following the kernel endianness

2013-11-06T10:10:01Z

Force SCTLR_EL2.EE to 1 if the kernel is compiled as BE. Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas

arm64: KVM: Yield CPU when vcpu executes a WFE

2013-10-29T18:25:25Z

On an (even slightly) oversubscribed system, spinlocks are quickly becoming a bottleneck, as some vcpus are spinning, waiting for a lock to be released, while the vcpu holding the lock may not be running at all. The solution is to trap blocking WFEs and tell KVM that we're now spinning. This ensures that other vpus will get a scheduling boost, allowing the lock to be released more quickly. Also, using CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance when the VM is severely overcommited. Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier

ARM64: KVM: Implement kvm_vcpu_preferred_target() function

2013-10-02T18:29:40Z

This patch implements kvm_vcpu_preferred_target() function for KVM ARM64 which will help us implement KVM_ARM_PREFERRED_TARGET ioctl for user space. Signed-off-by: Anup Patel Signed-off-by: Pranavkumar Sawargaonkar Signed-off-by: Christoffer Dall

arm64: KVM: add missing dsb before invalidating Stage-2 TLBs

2013-08-09T12:19:28Z

When performing a Stage-2 TLB invalidation, it is necessary to make sure the write to the page tables is observable by all CPUs. For this purpose, add dsb instructions to __kvm_tlb_flush_vmid_ipa and __kvm_flush_vm_context before doing the TLB invalidation itself. Signed-off-by: Marc Zyngier

arm64: KVM: perform save/restore of PAR_EL1

2013-08-09T12:19:28Z

Not saving PAR_EL1 is an unfortunate oversight. If the guest performs an AT* operation and gets scheduled out before reading the result of the translation from PAREL1, it could become corrupted by another guest or the host. Saving this register is made slightly more complicated as KVM also uses it on the permission fault handling path, leading to an ugly "stash and restore" sequence. Fortunately, this is already a slow path so we don't really care. Also, Linux doesn't do any AT* operation, so Linux guests are not impacted by this bug. Signed-off-by: Marc Zyngier

arm64: KVM: Kconfig integration

2013-07-04T12:40:26Z

Finally plug KVM/arm64 into the config system, making it possible to enable KVM support on AArch64 CPUs. Signed-off-by: Marc Zyngier Signed-off-by: Paolo Bonzini

arm64: KVM: enable initialization of a 32bit vcpu

2013-06-12T15:42:18Z

Wire the init of a 32bit vcpu by allowing 32bit modes in pstate, and providing sensible defaults out of reset state. This feature is of course conditioned by the presence of 32bit capability on the physical CPU, and is checked by the KVM_CAP_ARM_EL1_32BIT capability. Reviewed-by: Catalin Marinas Signed-off-by: Marc Zyngier