1. 15 Feb, 2017 15 commits
  2. 09 Feb, 2017 3 commits
  3. 08 Feb, 2017 15 commits
  4. 07 Feb, 2017 7 commits
    • Paolo Bonzini's avatar
      Merge tag 'kvm-s390-next-4.11-2' of... · 8f00067a
      Paolo Bonzini authored
      Merge tag 'kvm-s390-next-4.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD
      
      KVM: s390: Fixes and features for 4.11 (via kvm/next)
      
      - enable some simd extensions for guests
      - enable nx for guests
      - debug log for cpu model
      - PER fixes
      - remove bitwise annotation from ar_t
      - detect guests in operation exception program check loops
      - fix potential null-pointer dereference for ucontrol guests
      
      - also contains merge for fix that went into 4.10 to avoid conflicts
      8f00067a
    • Paolo Bonzini's avatar
      Merge tag 'kvm_mips_4.11_1' of... · d9c0e59f
      Paolo Bonzini authored
      Merge tag 'kvm_mips_4.11_1' of git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/kvm-mips into HEAD
      
      KVM: MIPS: GVA/GPA page tables, dirty logging, SYNC_MMU etc
      
      Numerous MIPS KVM fixes, improvements, and features for 4.11, many of
      which continue to pave the way for VZ support, the most interesting of
      which are:
      
       - Add GVA->HPA page tables for T&E, to cache GVA mappings.
       - Generate fast-path TLB refill exception handler which loads host TLB
         entries from GVA page table, avoiding repeated guest memory
         translation and guest TLB lookups.
       - Use uaccess macros when T&E needs to access guest memory, which with
         GVA page tables and the Linux TLB refill handler improves robustness
         against TLB faults and fixes EVA hosts.
       - Use BadInstr/BadInstrP registers when available to obtain instruction
         encodings after a synchronous trap.
       - Add GPA->HPA page tables to replace the inflexible linear array,
         allowing for multiple sparsely arranged memory regions.
       - Properly implement dirty page logging.
       - Add KVM_CAP_SYNC_MMU support so that changes in GPA mappings become
         effective in guests even if they are already running, allowing for
         copy-on-write, KSM, idle page tracking, swapping, and guest memory
         ballooning.
       - Add KVM_CAP_READONLY_MEM support, so writes to specified memory
         regions are treated as MMIO.
       - Implement proper CP0_EBase support in T&E.
       - Expose a few more missing CP0 registers to userland.
       - Add KVM_CAP_NR_VCPUS and KVM_CAP_MAX_VCPUS support, and allow up to 8
         VCPUs to be created in a VM.
       - Various cleanups and dropping of dead and duplicated code.
      d9c0e59f
    • Paolo Bonzini's avatar
      Merge branch 'kvm-ppc-next' of... · d5b798c1
      Paolo Bonzini authored
      Merge branch 'kvm-ppc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD
      
      The big feature this time is support for POWER9 using the radix-tree
      MMU for host and guest.  This required some changes to arch/powerpc
      code, so I talked with Michael Ellerman and he created a topic branch
      with this patchset, which I merged into kvm-ppc-next and which Michael
      will pull into his tree.  Michael also put in some patches from Nick
      Piggin which fix bugs in the interrupt vector code in relocatable
      kernels when coming from a KVM guest.
      
      Other notable changes include:
      
      * Add the ability to change the size of the hashed page table,
        from David Gibson.
      
      * XICS (interrupt controller) emulation fixes and improvements,
        from Li Zhong.
      
      * Bug fixes from myself and Thomas Huth.
      
      These patches define some new KVM capabilities and ioctls, but there
      should be no conflicts with anything else currently upstream, as far
      as I am aware.
      d5b798c1
    • Marcelo Tosatti's avatar
      KVM: x86: add KVM_HC_CLOCK_PAIRING hypercall · 55dd00a7
      Marcelo Tosatti authored
      Add a hypercall to retrieve the host realtime clock and the TSC value
      used to calculate that clock read.
      
      Used to implement clock synchronization between host and guest.
      Signed-off-by: default avatarMarcelo Tosatti <mtosatti@redhat.com>
      Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      55dd00a7
    • David Hildenbrand's avatar
      KVM: nVMX: vmx_complete_nested_posted_interrupt() can't fail · 6342c50a
      David Hildenbrand authored
      vmx_complete_nested_posted_interrupt() can't fail, let's turn it into
      a void function.
      Signed-off-by: default avatarDavid Hildenbrand <david@redhat.com>
      Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      6342c50a
    • David Hildenbrand's avatar
      KVM: nVMX: kmap() can't fail · 42cf014d
      David Hildenbrand authored
      kmap() can't fail, therefore it will always return a valid pointer. Let's
      just get rid of the unnecessary checks.
      Signed-off-by: default avatarDavid Hildenbrand <david@redhat.com>
      Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      42cf014d
    • Benjamin Herrenschmidt's avatar
      powerpc/powernv: Remove separate entry for OPAL real mode calls · ab9bad0e
      Benjamin Herrenschmidt authored
      All entry points already read the MSR so they can easily do
      the right thing.
      Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
      Signed-off-by: default avatarPaul Mackerras <paulus@ozlabs.org>
      Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      ab9bad0e