Commit Graph

95 Commits

Author SHA1 Message Date
Marcelo Tosatti
b1a368218a KVM: MMU: collapse remote TLB flushes on root sync
Collapse remote TLB flushes on root sync.

kernbench is 2.7% faster on 4-way guest. Improvements have been seen
with other loads such as AIM7.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:55:43 +02:00
Marcelo Tosatti
60c8aec6e2 KVM: MMU: use page array in unsync walk
Instead of invoking the handler directly collect pages into
an array so the caller can work with it.

Simplifies TLB flush collapsing.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:55:43 +02:00
Marcelo Tosatti
ecc5589f19 KVM: MMU: optimize set_spte for page sync
The write protect verification in set_spte is unnecessary for page sync.

Its guaranteed that, if the unsync spte was writable, the target page
does not have a write protected shadow (if it had, the spte would have
been write protected under mmu_lock by rmap_write_protect before).

Same reasoning applies to mark_page_dirty: the gfn has been marked as
dirty via the pagefault path.

The cost of hash table and memslot lookups are quite significant if the
workload is pagetable write intensive resulting in increased mmu_lock
contention.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:55:02 +02:00
Eduardo Habkost
13673a90f1 KVM: VMX: move vmx.h to include/asm
vmx.h will be used by core code that is independent of KVM, so I am
moving it outside the arch/x86/kvm directory.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:52:27 +02:00
Izik Eidus
2843099fee KVM: MMU: Fix aliased gfns treated as unaliased
Some areas of kvm x86 mmu are using gfn offset inside a slot without
unaliasing the gfn first.  This patch makes sure that the gfn will be
unaliased and add gfn_to_memslot_unaliased() to save the calculating
of the gfn unaliasing in case we have it unaliased already.

Signed-off-by: Izik Eidus <ieidus@redhat.com>
Acked-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:51:50 +02:00
Sheng Yang
291f26bc0f KVM: MMU: Extend kvm_mmu_page->slot_bitmap size
Otherwise set_bit() for private memory slot(above KVM_MEMORY_SLOTS) would
corrupted memory in 32bit host.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:51:45 +02:00
Sheng Yang
64d4d52175 KVM: Enable MTRR for EPT
The effective memory type of EPT is the mixture of MSR_IA32_CR_PAT and memory
type field of EPT entry.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:51:45 +02:00
Sheng Yang
74be52e3e6 KVM: Add local get_mtrr_type() to support MTRR
For EPT memory type support.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-12-31 16:51:45 +02:00
Marcelo Tosatti
0c0f40bdbe KVM: MMU: fix sync of ptes addressed at owner pagetable
During page sync, if a pagetable contains a self referencing pte (that
points to the pagetable), the corresponding spte may be marked as
writable even though all mappings are supposed to be write protected.

Fix by clearing page unsync before syncing individual sptes.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-11-23 15:24:19 +02:00
Marcelo Tosatti
c41ef344de KVM: MMU: increase per-vcpu rmap cache alloc size
The page fault path can use two rmap_desc structures, if:

- walk_addr's dirty pte update allocates one rmap_desc.
- mmu_lock is dropped, sptes are zapped resulting in rmap_desc being
freed.
- fetch->mmu_set_spte allocates another rmap_desc.

Increase to 4 for safety.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-11-11 20:53:34 +02:00
Marcelo Tosatti
6ad9f15c94 KVM: MMU: sync root on paravirt TLB flush
The pvmmu TLB flush handler should request a root sync, similarly to
a native read-write CR3.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-28 14:09:27 +02:00
Marcelo Tosatti
582801a95d KVM: MMU: add "oos_shadow" parameter to disable oos
Subject says it all.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:27 +02:00
Marcelo Tosatti
0074ff63eb KVM: MMU: speed up mmu_unsync_walk
Cache the unsynced children information in a per-page bitmap.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:26 +02:00
Marcelo Tosatti
4731d4c7a0 KVM: MMU: out of sync shadow core
Allow guest pagetables to go out of sync.  Instead of emulating write
accesses to guest pagetables, or unshadowing them, we un-write-protect
the page table and allow the guest to modify it at will.  We rely on
invlpg executions to synchronize individual ptes, and will synchronize
the entire pagetable on tlb flushes.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:25 +02:00
Marcelo Tosatti
6844dec694 KVM: MMU: mmu_convert_notrap helper
Need to convert shadow_notrap_nonpresent -> shadow_trap_nonpresent when
unsyncing pages.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:24 +02:00
Marcelo Tosatti
0738541396 KVM: MMU: awareness of new kvm_mmu_zap_page behaviour
kvm_mmu_zap_page will soon zap the unsynced children of a page. Restart
list walk in such case.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:23 +02:00
Marcelo Tosatti
ad8cfbe3ff KVM: MMU: mmu_parent_walk
Introduce a function to walk all parents of a given page, invoking a handler.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:22 +02:00
Marcelo Tosatti
a7052897b3 KVM: x86: trap invlpg
With pages out of sync invlpg needs to be trapped. For now simply nuke
the entry.

Untested on AMD.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:21 +02:00
Marcelo Tosatti
0ba73cdadb KVM: MMU: sync roots on mmu reload
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:20 +02:00
Marcelo Tosatti
e8bc217aef KVM: MMU: mode specific sync_page
Examine guest pagetable and bring the shadow back in sync. Caller is responsible
for local TLB flush before re-entering guest mode.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:19 +02:00
Marcelo Tosatti
38187c830c KVM: MMU: do not write-protect large mappings
There is not much point in write protecting large mappings. This
can only happen when a page is shadowed during the window between
is_largepage_backed and mmu_lock acquision. Zap the entry instead, so
the next pagefault will find a shadowed page via is_largepage_backed and
fallback to 4k translations.

Simplifies out of sync shadow.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:18 +02:00
Marcelo Tosatti
a378b4e64c KVM: MMU: move local TLB flush to mmu_set_spte
Since the sync page path can collapse flushes.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:17 +02:00
Marcelo Tosatti
1e73f9dd88 KVM: MMU: split mmu_set_spte
Split the spte entry creation code into a new set_spte function.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:16 +02:00
Marcelo Tosatti
4c2155ce81 KVM: switch to get_user_pages_fast
Convert gfn_to_pfn to use get_user_pages_fast, which can do lockless
pagetable lookups on x86. Kernel compilation on 4-way guest is 3.7%
faster on VMX.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2008-10-15 14:25:06 +02:00
Sheng Yang
d40a1ee485 KVM: MMU: Modify kvm_shadow_walk.entry to accept u64 addr
EPT is 4 level by default in 32pae(48 bits), but the addr parameter
of kvm_shadow_walk->entry() only accept unsigned long as virtual
address, which is 32bit in 32pae. This result in SHADOW_PT_INDEX()
overflow when try to fetch level 4 index.

Fix it by extend kvm_shadow_walk->entry() to accept 64bit addr in
parameter.

Signed-off-by: Sheng Yang <sheng.yang@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:25 +02:00
Avi Kivity
3201b5d9f0 KVM: MMU: Fix setting the accessed bit on non-speculative sptes
The accessed bit was accidentally turned on in a random flag word, rather
than, the spte itself, which was lucky, since it used the non-EPT compatible
PT_ACCESSED_MASK.

Fix by turning the bit on in the spte and changing it to use the portable
accessed mask.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:24 +02:00
Avi Kivity
171d595d3b KVM: MMU: Flush tlbs after clearing write permission when accessing dirty log
Otherwise, the cpu may allow writes to the tracked pages, and we lose
some display bits or fail to migrate correctly.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:24 +02:00
Avi Kivity
2245a28fe2 KVM: MMU: Add locking around kvm_mmu_slot_remove_write_access()
It was generally safe due to slots_lock being held for write, but it wasn't
very nice.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:24 +02:00
Avi Kivity
bc2d429979 KVM: MMU: Account for npt/ept/realmode page faults
Now that two-dimensional paging is becoming common, account for tdp page
faults.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:23 +02:00
Avi Kivity
140754bc80 KVM: MMU: Convert direct maps to use the generic shadow walker
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:23 +02:00
Avi Kivity
3d000db568 KVM: MMU: Add generic shadow walker
We currently walk the shadow page tables in two places: direct map (for
real mode and two dimensional paging) and paging mode shadow.  Since we
anticipate requiring a third walk (for invlpg), it makes sense to have
a generic facility for shadow walk.

This patch adds such a shadow walker, walks the page tables and calls a
method for every spte encountered.  The method can examine the spte,
modify it, or even instantiate it.  The walk can be aborted by returning
nonzero from the method.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:23 +02:00
Avi Kivity
6c41f428b7 KVM: MMU: Infer shadow root level in direct_map()
In all cases the shadow root level is available in mmu.shadow_root_level,
so there is no need to pass it as a parameter.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:22 +02:00
Avi Kivity
6e37d3dc3e KVM: MMU: Unify direct map 4K and large page paths
The two paths are equivalent except for one argument, which is already
available.  Merge the two codepaths.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:22 +02:00
Avi Kivity
135f8c2b07 KVM: MMU: Move SHADOW_PT_INDEX to mmu.c
It is not specific to the paging mode, so can be made global (and reusable).

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:22 +02:00
Dave Hansen
6ad18fba05 KVM: Reduce stack usage in kvm_pv_mmu_op()
We're in a hot path.  We can't use kmalloc() because
it might impact performance.  So, we just stick the buffer that
we need into the kvm_vcpu_arch structure.  This is used very
often, so it is not really a waste.

We also have to move the buffer structure's definition to the
arch-specific x86 kvm header.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:18 +02:00
Avi Kivity
5b5c6a5a60 KVM: MMU: Simplify kvm_mmu_zap_page()
The twisty maze of conditionals can be reduced.

[joerg: fix tlb flushing]

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:12 +02:00
Avi Kivity
31aa2b44af KVM: MMU: Separate the code for unlinking a shadow page from its parents
Place into own function, in preparation for further cleanups.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-10-15 10:15:12 +02:00
Sheng Yang
534e38b447 KVM: VMX: Always return old for clear_flush_young() when using EPT
As well as discard fake accessed bit and dirty bit of EPT.

Signed-off-by: Sheng Yang <sheng.yang@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-09-11 11:48:19 +03:00
Andrea Arcangeli
e930bffe95 KVM: Synchronize guest physical memory map to host virtual memory map
Synchronize changes to host virtual addresses which are part of
a KVM memory slot to the KVM shadow mmu.  This allows pte operations
like swapping, page migration, and madvise() to transparently work
with KVM.

Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-29 12:33:53 +03:00
Avi Kivity
577bdc4966 KVM: Avoid instruction emulation when event delivery is pending
When an event (such as an interrupt) is injected, and the stack is
shadowed (and therefore write protected), the guest will exit.  The
current code will see that the stack is shadowed and emulate a few
instructions, each time postponing the injection.  Eventually the
injection may succeed, but at that time the guest may be unwilling
to accept the interrupt (for example, the TPR may have changed).

This occurs every once in a while during a Windows 2008 boot.

Fix by unshadowing the fault address if the fault was due to an event
injection.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-27 11:34:10 +03:00
Joerg Roedel
5f4cb662a0 KVM: SVM: allow enabling/disabling NPT by reloading only the architecture module
If NPT is enabled after loading both KVM modules on AMD and it should be
disabled, both KVM modules must be reloaded. If only the architecture module is
reloaded the behavior is undefined. With this patch it is possible to disable
NPT only by reloading the kvm_amd module.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-27 11:34:09 +03:00
Avi Kivity
722c05f219 KVM: MMU: Fix potential race setting upper shadow ptes on nonpae hosts
The direct mapped shadow code (used for real mode and two dimensional paging)
sets upper-level ptes using direct assignment rather than calling
set_shadow_pte().  A nonpae host will split this into two writes, which opens
up a race if another vcpu accesses the same memory area.

Fix by calling set_shadow_pte() instead of assigning directly.

Noticed by Izik Eidus.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:40 +03:00
Marcelo Tosatti
376c53c2b3 KVM: MMU: improve invalid shadow root page handling
Harden kvm_mmu_zap_page() against invalid root pages that
had been shadowed from memslots that are gone.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:40 +03:00
Marcelo Tosatti
5a4c928804 KVM: mmu_shrink: kvm_mmu_zap_page requires slots_lock to be held
kvm_mmu_zap_page() needs slots lock held (rmap_remove->gfn_to_memslot,
for example).

Since kvm_lock spinlock is held in mmu_shrink(), do a non-blocking
down_read_trylock().

Untested.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:38 +03:00
Avi Kivity
db475c39ec KVM: MMU: Fix printk format
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:35 +03:00
Avi Kivity
6ada8cca79 KVM: MMU: When debug is enabled, make it a run-time parameter
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:35 +03:00
Avi Kivity
131d82791b KVM: MMU: Avoid page prefetch on SVM
SVM cannot benefit from page prefetching since guest page fault bypass
cannot by made to work there.  Avoid accessing the guest page table in
this case.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:30 +03:00
Avi Kivity
d761a501cf KVM: MMU: Move nonpaging_prefetch_page()
In preparation for next patch. No code change.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:42:30 +03:00
Avi Kivity
1b7fcd3263 KVM: MMU: Fix false flooding when a pte points to page table
The KVM MMU tries to detect when a speculative pte update is not actually
used by demand fault, by checking the accessed bit of the shadow pte.  If
the shadow pte has not been accessed, we deem that page table flooded and
remove the shadow page table, allowing further pte updates to proceed
without emulation.

However, if the pte itself points at a page table and only used for write
operations, the accessed bit will never be set since all access will happen
through the emulator.

This is exactly what happens with kscand on old (2.4.x) HIGHMEM kernels.
The kernel points a kmap_atomic() pte at a page table, and then
proceeds with read-modify-write operations to look at the dirty and accessed
bits.  We get a false flood trigger on the kmap ptes, which results in the
mmu spending all its time setting up and tearing down shadows.

Fix by setting the shadow accessed bit on emulated accesses.

Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:40:50 +03:00
Harvey Harrison
8b2cf73cc1 KVM: add statics were possible, function definition in lapic.h
Noticed by sparse:
arch/x86/kvm/vmx.c:1583:6: warning: symbol 'vmx_disable_intercept_for_msr' was not declared. Should it be static?
arch/x86/kvm/x86.c:3406:5: warning: symbol 'kvm_task_switch_16' was not declared. Should it be static?
arch/x86/kvm/x86.c:3429:5: warning: symbol 'kvm_task_switch_32' was not declared. Should it be static?
arch/x86/kvm/mmu.c:1968:6: warning: symbol 'kvm_mmu_remove_one_alloc_mmu_page' was not declared. Should it be static?
arch/x86/kvm/mmu.c:2014:6: warning: symbol 'mmu_destroy_caches' was not declared. Should it be static?
arch/x86/kvm/lapic.c:862:5: warning: symbol 'kvm_lapic_get_base' was not declared. Should it be static?
arch/x86/kvm/i8254.c:94:5: warning: symbol 'pit_get_gate' was not declared. Should it be static?
arch/x86/kvm/i8254.c:196:5: warning: symbol '__pit_timer_fn' was not declared. Should it be static?
arch/x86/kvm/i8254.c:561:6: warning: symbol '__inject_pit_timer_intr' was not declared. Should it be static?

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
2008-07-20 12:40:46 +03:00