1. 24 3月, 2009 1 次提交
  2. 12 11月, 2008 1 次提交
  3. 29 7月, 2008 1 次提交
    • A
      mmu-notifiers: core · cddb8a5c
      Andrea Arcangeli 提交于
      With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages.
       There are secondary MMUs (with secondary sptes and secondary tlbs) too.
      sptes in the kvm case are shadow pagetables, but when I say spte in
      mmu-notifier context, I mean "secondary pte".  In GRU case there's no
      actual secondary pte and there's only a secondary tlb because the GRU
      secondary MMU has no knowledge about sptes and every secondary tlb miss
      event in the MMU always generates a page fault that has to be resolved by
      the CPU (this is not the case of KVM where the a secondary tlb miss will
      walk sptes in hardware and it will refill the secondary tlb transparently
      to software if the corresponding spte is present).  The same way
      zap_page_range has to invalidate the pte before freeing the page, the spte
      (and secondary tlb) must also be invalidated before any page is freed and
      reused.
      
      Currently we take a page_count pin on every page mapped by sptes, but that
      means the pages can't be swapped whenever they're mapped by any spte
      because they're part of the guest working set.  Furthermore a spte unmap
      event can immediately lead to a page to be freed when the pin is released
      (so requiring the same complex and relatively slow tlb_gather smp safe
      logic we have in zap_page_range and that can be avoided completely if the
      spte unmap event doesn't require an unpin of the page previously mapped in
      the secondary MMU).
      
      The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know
      when the VM is swapping or freeing or doing anything on the primary MMU so
      that the secondary MMU code can drop sptes before the pages are freed,
      avoiding all page pinning and allowing 100% reliable swapping of guest
      physical address space.  Furthermore it avoids the code that teardown the
      mappings of the secondary MMU, to implement a logic like tlb_gather in
      zap_page_range that would require many IPI to flush other cpu tlbs, for
      each fixed number of spte unmapped.
      
      To make an example: if what happens on the primary MMU is a protection
      downgrade (from writeable to wrprotect) the secondary MMU mappings will be
      invalidated, and the next secondary-mmu-page-fault will call
      get_user_pages and trigger a do_wp_page through get_user_pages if it
      called get_user_pages with write=1, and it'll re-establishing an updated
      spte or secondary-tlb-mapping on the copied page.  Or it will setup a
      readonly spte or readonly tlb mapping if it's a guest-read, if it calls
      get_user_pages with write=0.  This is just an example.
      
      This allows to map any page pointed by any pte (and in turn visible in the
      primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an
      full MMU with both sptes and secondary-tlb like the shadow-pagetable layer
      with kvm), or a remote DMA in software like XPMEM (hence needing of
      schedule in XPMEM code to send the invalidate to the remote node, while no
      need to schedule in kvm/gru as it's an immediate event like invalidating
      primary-mmu pte).
      
      At least for KVM without this patch it's impossible to swap guests
      reliably.  And having this feature and removing the page pin allows
      several other optimizations that simplify life considerably.
      
      Dependencies:
      
      1) mm_take_all_locks() to register the mmu notifier when the whole VM
         isn't doing anything with "mm".  This allows mmu notifier users to keep
         track if the VM is in the middle of the invalidate_range_begin/end
         critical section with an atomic counter incraese in range_begin and
         decreased in range_end.  No secondary MMU page fault is allowed to map
         any spte or secondary tlb reference, while the VM is in the middle of
         range_begin/end as any page returned by get_user_pages in that critical
         section could later immediately be freed without any further
         ->invalidate_page notification (invalidate_range_begin/end works on
         ranges and ->invalidate_page isn't called immediately before freeing
         the page).  To stop all page freeing and pagetable overwrites the
         mmap_sem must be taken in write mode and all other anon_vma/i_mmap
         locks must be taken too.
      
      2) It'd be a waste to add branches in the VM if nobody could possibly
         run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if
         CONFIG_KVM=m/y.  In the current kernel kvm won't yet take advantage of
         mmu notifiers, but this already allows to compile a KVM external module
         against a kernel with mmu notifiers enabled and from the next pull from
         kvm.git we'll start using them.  And GRU/XPMEM will also be able to
         continue the development by enabling KVM=m in their config, until they
         submit all GRU/XPMEM GPLv2 code to the mainline kernel.  Then they can
         also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n).
         This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM
         are all =n.
      
      The mmu_notifier_register call can fail because mm_take_all_locks may be
      interrupted by a signal and return -EINTR.  Because mmu_notifier_reigster
      is used when a driver startup, a failure can be gracefully handled.  Here
      an example of the change applied to kvm to register the mmu notifiers.
      Usually when a driver startups other allocations are required anyway and
      -ENOMEM failure paths exists already.
      
       struct  kvm *kvm_arch_create_vm(void)
       {
              struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
      +       int err;
      
              if (!kvm)
                      return ERR_PTR(-ENOMEM);
      
              INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
      
      +       kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops;
      +       err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm);
      +       if (err) {
      +               kfree(kvm);
      +               return ERR_PTR(err);
      +       }
      +
              return kvm;
       }
      
      mmu_notifier_unregister returns void and it's reliable.
      
      The patch also adds a few needed but missing includes that would prevent
      kernel to compile after these changes on non-x86 archs (x86 didn't need
      them by luck).
      
      [akpm@linux-foundation.org: coding-style fixes]
      [akpm@linux-foundation.org: fix mm/filemap_xip.c build]
      [akpm@linux-foundation.org: fix mm/mmu_notifier.c build]
      Signed-off-by: NAndrea Arcangeli <andrea@qumranet.com>
      Signed-off-by: NNick Piggin <npiggin@suse.de>
      Signed-off-by: NChristoph Lameter <cl@linux-foundation.org>
      Cc: Jack Steiner <steiner@sgi.com>
      Cc: Robin Holt <holt@sgi.com>
      Cc: Nick Piggin <npiggin@suse.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Kanoj Sarcar <kanojsarcar@yahoo.com>
      Cc: Roland Dreier <rdreier@cisco.com>
      Cc: Steve Wise <swise@opengridcomputing.com>
      Cc: Avi Kivity <avi@qumranet.com>
      Cc: Hugh Dickins <hugh@veritas.com>
      Cc: Rusty Russell <rusty@rustcorp.com.au>
      Cc: Anthony Liguori <aliguori@us.ibm.com>
      Cc: Chris Wright <chrisw@redhat.com>
      Cc: Marcelo Tosatti <marcelo@kvack.org>
      Cc: Eric Dumazet <dada1@cosmosbay.com>
      Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
      Cc: Izik Eidus <izike@qumranet.com>
      Cc: Anthony Liguori <aliguori@us.ibm.com>
      Cc: Rik van Riel <riel@redhat.com>
      Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      cddb8a5c
  4. 27 4月, 2008 2 次提交
  5. 04 2月, 2008 1 次提交
  6. 31 1月, 2008 1 次提交
  7. 30 1月, 2008 1 次提交
  8. 23 10月, 2007 1 次提交
  9. 13 10月, 2007 1 次提交
    • A
      KVM: Use the scheduler preemption notifiers to make kvm preemptible · 15ad7146
      Avi Kivity 提交于
      Current kvm disables preemption while the new virtualization registers are
      in use.  This of course is not very good for latency sensitive workloads (one
      use of virtualization is to offload user interface and other latency
      insensitive stuff to a container, so that it is easier to analyze the
      remaining workload).  This patch re-enables preemption for kvm; preemption
      is now only disabled when switching the registers in and out, and during
      the switch to guest mode and back.
      
      Contains fixes from Shaohua Li <shaohua.li@intel.com>.
      Signed-off-by: NAvi Kivity <avi@qumranet.com>
      15ad7146
  10. 23 9月, 2007 1 次提交
  11. 19 8月, 2007 1 次提交
  12. 23 7月, 2007 1 次提交
  13. 20 7月, 2007 1 次提交
    • A
      i386: Allow KVM on i386 nonpae · 2d9ce177
      Avi Kivity 提交于
      Currently, CONFIG_X86_CMPXCHG64 both enables boot-time checking of
      the cmpxchg64b feature and enables compilation of the set_64bit() family.
      Since the option is dependent on PAE, and since KVM depends on set_64bit(),
      this effectively disables KVM on i386 nopae.
      
      Simplify by removing the config option altogether: the boot check is made
      dependent on CONFIG_X86_PAE directly, and the set_64bit() family is exposed
      without constraints.  It is up to users to check for the feature flag (KVM
      does not as virtualiation extensions imply its existence).
      Signed-off-by: NAvi Kivity <avi@qumranet.com>
      Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      2d9ce177
  14. 16 7月, 2007 2 次提交
  15. 10 5月, 2007 1 次提交
  16. 14 12月, 2006 1 次提交
  17. 11 12月, 2006 1 次提交
    • A
      [PATCH] kvm: userspace interface · 6aa8b732
      Avi Kivity 提交于
      web site: http://kvm.sourceforge.net
      
      mailing list: kvm-devel@lists.sourceforge.net
        (http://lists.sourceforge.net/lists/listinfo/kvm-devel)
      
      The following patchset adds a driver for Intel's hardware virtualization
      extensions to the x86 architecture.  The driver adds a character device
      (/dev/kvm) that exposes the virtualization capabilities to userspace.  Using
      this driver, a process can run a virtual machine (a "guest") in a fully
      virtualized PC containing its own virtual hard disks, network adapters, and
      display.
      
      Using this driver, one can start multiple virtual machines on a host.
      
      Each virtual machine is a process on the host; a virtual cpu is a thread in
      that process.  kill(1), nice(1), top(1) work as expected.  In effect, the
      driver adds a third execution mode to the existing two: we now have kernel
      mode, user mode, and guest mode.  Guest mode has its own address space mapping
      guest physical memory (which is accessible to user mode by mmap()ing
      /dev/kvm).  Guest mode has no access to any I/O devices; any such access is
      intercepted and directed to user mode for emulation.
      
      The driver supports i386 and x86_64 hosts and guests.  All combinations are
      allowed except x86_64 guest on i386 host.  For i386 guests and hosts, both pae
      and non-pae paging modes are supported.
      
      SMP hosts and UP guests are supported.  At the moment only Intel
      hardware is supported, but AMD virtualization support is being worked on.
      
      Performance currently is non-stellar due to the naive implementation of the
      mmu virtualization, which throws away most of the shadow page table entries
      every context switch.  We plan to address this in two ways:
      
      - cache shadow page tables across tlb flushes
      - wait until AMD and Intel release processors with nested page tables
      
      Currently a virtual desktop is responsive but consumes a lot of CPU.  Under
      Windows I tried playing pinball and watching a few flash movies; with a recent
      CPU one can hardly feel the virtualization.  Linux/X is slower, probably due
      to X being in a separate process.
      
      In addition to the driver, you need a slightly modified qemu to provide I/O
      device emulation and the BIOS.
      
      Caveats (akpm: might no longer be true):
      
      - The Windows install currently bluescreens due to a problem with the
        virtual APIC.  We are working on a fix.  A temporary workaround is to
        use an existing image or install through qemu
      - Windows 64-bit does not work.  That's also true for qemu, so it's
        probably a problem with the device model.
      
      [bero@arklinux.org: build fix]
      [simon.kagstrom@bth.se: build fix, other fixes]
      [uril@qumranet.com: KVM: Expose interrupt bitmap]
      [akpm@osdl.org: i386 build fix]
      [mingo@elte.hu: i386 fixes]
      [rdreier@cisco.com: add log levels to all printks]
      [randy.dunlap@oracle.com: Fix sparse NULL and C99 struct init warnings]
      [anthony@codemonkey.ws: KVM: AMD SVM: 32-bit host support]
      Signed-off-by: NYaniv Kamay <yaniv@qumranet.com>
      Signed-off-by: NAvi Kivity <avi@qumranet.com>
      Cc: Simon Kagstrom <simon.kagstrom@bth.se>
      Cc: Bernhard Rosenkraenzer <bero@arklinux.org>
      Signed-off-by: NUri Lublin <uril@qumranet.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: Roland Dreier <rolandd@cisco.com>
      Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
      Signed-off-by: NAnthony Liguori <anthony@codemonkey.ws>
      Signed-off-by: NAndrew Morton <akpm@osdl.org>
      Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      6aa8b732