Everywhere we use kvm_for_each_vpcu(), we use an int as the vcpu
index. Unfortunately, we're about to move rework the iterator,
which requires this to be upgrade to an unsigned long.
Let's bite the bullet and repaint all of it in one go.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20211116160403.4074052-7-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
At least on arm64 and x86, the vcpus array is pretty huge (up to
1024 entries on x86) and is mostly empty in the majority of the cases
(running 1k vcpu VMs is not that common).
This mean that we end-up with a 4kB block of unused memory in the
middle of the kvm structure.
Instead of wasting away this memory, let's use an xarray instead,
which gives us almost the same flexibility as a normal array, but
with a reduced memory usage with smaller VMs.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20211116160403.4074052-6-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
All architectures have similar loops iterating over the vcpus,
freeing one vcpu at a time, and eventually wiping the reference
off the vcpus array. They are also inconsistently taking
the kvm->lock mutex when wiping the references from the array.
Make this code common, which will simplify further changes.
The locking is dropped altogether, as this should only be called
when there is no further references on the kvm structure.
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20211116160403.4074052-2-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_is_transparent_hugepage() was removed in commit 205d76ff06 ("KVM:
Remove kvm_is_transparent_hugepage() and PageTransCompoundMap()") but its
declaration in include/linux/kvm_host.h persisted. Drop it.
Fixes: 205d76ff06 (""KVM: Remove kvm_is_transparent_hugepage() and PageTransCompoundMap()")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20211018151407.2107363-1-vkuznets@redhat.com
* Fixes for Xen emulation
* Kill kvm_map_gfn() / kvm_unmap_gfn() and broken gfn_to_pfn_cache
* Fixes for migration of 32-bit nested guests on 64-bit hypervisor
* Compilation fixes
* More SEV cleanups
In commit 7e2175ebd6 ("KVM: x86: Fix recording of guest steal time /
preempted status") I removed the only user of these functions because
it was basically impossible to use them safely.
There are two stages to the GFN->PFN mapping; first through the KVM
memslots to a userspace HVA and then through the page tables to
translate that HVA to an underlying PFN. Invalidations of the former
were being handled correctly, but no attempt was made to use the MMU
notifiers to invalidate the cache when the HVA->GFN mapping changed.
As a prelude to reinventing the gfn_to_pfn_cache with more usable
semantics, rip it out entirely and untangle the implementation of
the unsafe kvm_vcpu_map()/kvm_vcpu_unmap() functions from it.
All current users of kvm_vcpu_map() also look broken right now, and
will be dealt with separately. They broadly fall into two classes:
* Those which map, access the data and immediately unmap. This is
mostly gratuitous and could just as well use the existing user
HVA, and could probably benefit from a gfn_to_hva_cache as they
do so.
* Those which keep the mapping around for a longer time, perhaps
even using the PFN directly from the guest. These will need to
be converted to the new gfn_to_pfn_cache and then kvm_vcpu_map()
can be removed too.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-8-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move x86's perf guest callbacks into common KVM, as they are semantically
identical to arm64's callbacks (the only other such KVM callbacks).
arm64 will convert to the common versions in a future patch.
Implement the necessary arm64 arch hooks now to avoid having to provide
stubs or a temporary #define (from x86) to avoid arm64 compilation errors
when CONFIG_GUEST_PERF_EVENTS=y.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20211111020738.2512932-13-seanjc@google.com
Generalize KVM_REQ_VM_BUGGED so that it can be called even in cases
where it is by design that the VM cannot be operated upon. In this
case any KVM_BUG_ON should still warn, so introduce a new flag
kvm->vm_dead that is separate from kvm->vm_bugged.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
By switching from kfree() to kvfree() in kvm_arch_free_vm() Arm64 can
use the common variant. This can be accomplished by adding another
macro __KVM_HAVE_ARCH_VM_FREE, which will be used only by x86 for now.
Further simplification can be achieved by adding __kvm_arch_free_vm()
doing the common part.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-Id: <20210903130808.30142-5-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
All of the irqfds would to be updated when update the irq
routing, it's too expensive if there're too many irqfds.
However we can reduce the cost by avoid some unnecessary
updates. For irqs of MSI type on X86, the update can be
saved if the msi values are not change.
The vfio migration could receives benefit from this optimi-
zaiton. The test VM has 128 vcpus and 8 VF (with 65 vectors
enabled), so the VM has more than 520 irqfds. We mesure the
cost of the vfio_msix_enable (in QEMU, it would set routing
for each irqfd) for each VF, and we can see the total cost
can be significantly reduced.
Origin Apply this Patch
1st 8 4
2nd 15 5
3rd 22 6
4th 24 6
5th 36 7
6th 44 7
7th 51 8
8th 58 8
Total 258ms 51ms
We're also tring to optimize the QEMU part [1], but it's still
worth to optimize the KVM to gain more benefits.
[1] https://lists.gnu.org/archive/html/qemu-devel/2021-08/msg04215.html
Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Message-Id: <20210827080003.2689-1-longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_MAX_VCPU_ID is not specifying the highest allowed vcpu-id, but the
number of allowed vcpu-ids. This has already led to confusion, so
rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS to make its semantics more
clear
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210913135745.13944-3-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_make_vcpus_request_mask() already disables preemption so just like
kvm_make_all_cpus_request_except() it can be switched to using
pre-allocated per-cpu cpumasks. This allows for improvements for both
users of the function: in Hyper-V emulation code 'tlb_flush' can now be
dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask()
gets rid of dynamic allocation.
cpumask_available() checks in kvm_make_vcpu_request() and
kvm_kick_many_cpus() can now be dropped as they checks for an impossible
condition: kvm_init() makes sure per-cpu masks are allocated.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-9-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There is no user of tlbs_dirty.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-4-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Read vcpu->vcpu_idx directly instead of bouncing through the one-line
wrapper, kvm_vcpu_get_idx(), and drop the wrapper. The wrapper is a
remnant of the original implementation and serves no purpose; remove it
before it gains more users.
Back when kvm_vcpu_get_idx() was added by commit 497d72d80a ("KVM: Add
kvm_vcpu_get_idx to get vcpu index in kvm->vcpus"), the implementation
was more than just a simple wrapper as vcpu->vcpu_idx did not exist and
retrieving the index meant walking over the vCPU array to find the given
vCPU.
When vcpu_idx was introduced by commit 8750e72a79 ("KVM: remember
position in kvm->vcpus array"), the helper was left behind, likely to
avoid extra thrash (but even then there were only two users, the original
arm usage having been removed at some point in the past).
No functional change intended.
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210910183220.2397812-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
- Page ownership tracking between host EL1 and EL2
- Rely on userspace page tables to create large stage-2 mappings
- Fix incompatibility between pKVM and kmemleak
- Fix the PMU reset state, and improve the performance of the virtual PMU
- Move over to the generic KVM entry code
- Address PSCI reset issues w.r.t. save/restore
- Preliminary rework for the upcoming pKVM fixed feature
- A bunch of MM cleanups
- a vGIC fix for timer spurious interrupts
- Various cleanups
-----BEGIN PGP SIGNATURE-----
iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmEnfogPHG1hekBrZXJu
ZWwub3JnAAoJECPQ0LrRPXpDF9oQAINWHN1n30gsxcErMV8gH+XAyhDq2vTjkExQ
Qz5ddo4R5zeVkj0nkunFSK+W3xYz+W97X3I+IaiiHvk5D6dUatj37IyYlazX5iFT
7mbjTAqY7GRxfd6um7uK+CTRCApXY49GGkCVLGA5f+6mQ0JMVXaK9AKlsXKWUQLZ
JvLasUgKkseN6IEJWmPDNBdIeiKBTZloeZMdlM2vSm34HsuirSS5LmshdzJQzSk8
QSEqwXZX50afzJLNlB9Qa6V1tokjZVoYIBk0vAPO83tTh9HIyGL/PFAqBeq2rnWT
M19fFFbx5vizap4ICbpviLmZ5AOywCoBmbPBT79eMAJ53rOqHUJhU1y/3DoiVzxu
LJZI4wmGBQZVivOWOqyEZcNtTAagPLhyrLhMzYulBLwAjfFJmUHdSOxYtx+2Ysvr
SDIPN31FKWrvifTXTqJHDmaaXusi2CNZUOPzVSe2I14SbX+ZX2ny9DltlbRgPNuc
hGJagI5cZc0ngd4mAIzjjNmgBS2B+dSc8dOo71dRNJRLtQLiNHcAyQNJyFme+4xI
NpvpkvzxBAs8rG2X0YIR/Cz3W3yZoCYuQNcoPk7+F/bUTK47VocQCS+gLucHVLbT
H4286EV5n4nZ7E01oJ6uWnDnslPvrx9Sz2fxsrWYkBDR+xrz0EprrGsftFaILprz
Ic43uXfd
=LuHM
-----END PGP SIGNATURE-----
Merge tag 'kvmarm-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 5.15
- Page ownership tracking between host EL1 and EL2
- Rely on userspace page tables to create large stage-2 mappings
- Fix incompatibility between pKVM and kmemleak
- Fix the PMU reset state, and improve the performance of the virtual PMU
- Move over to the generic KVM entry code
- Address PSCI reset issues w.r.t. save/restore
- Preliminary rework for the upcoming pKVM fixed feature
- A bunch of MM cleanups
- a vGIC fix for timer spurious interrupts
- Various cleanups
Add a new stat that counts the number of times a remote TLB flush is
requested, regardless of whether it kicks vCPUs out of guest mode. This
allows us to look at how often flushes are initiated.
Unlike remote_tlb_flush, this one applies to ARM's instruction-set-based
TLB flush implementation, so apply it there too.
Original-by: David Matlack <dmatlack@google.com>
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210817002639.3856694-1-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add three log histogram stats to record the distribution of time spent
on successful polling, failed polling and VCPU wait.
halt_poll_success_hist: Distribution of spent time for a successful poll.
halt_poll_fail_hist: Distribution of spent time for a failed poll.
halt_wait_hist: Distribution of time a VCPU has spent on waiting.
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210802165633.1866976-6-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add simple stats halt_wait_ns to record the time a VCPU has spent on
waiting for all architectures (not just powerpc).
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210802165633.1866976-5-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add new types of KVM stats, linear and logarithmic histogram.
Histogram are very useful for observing the value distribution
of time or size related stats.
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210802165633.1866976-2-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This together with previous patch, ensures that
kvm_zap_gfn_range doesn't race with page fault
running on another vcpu, and will make this page fault code
retry instead.
This is based on a patch suggested by Sean Christopherson:
https://lkml.org/lkml/2021/7/22/1025
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210810205251.424103-5-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Allow archs to create arch-specific nodes under kvm->debugfs_dentry directory
besides the stats fields. The new interface kvm_arch_create_vm_debugfs() is
defined but not yet used. It's called after kvm->debugfs_dentry is created, so
it can be referenced directly in kvm_arch_create_vm_debugfs(). Arch should
define their own versions when they want to create extra debugfs nodes.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210730220455.26054-2-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The memslot for a given gfn is looked up multiple times during page
fault handling. Avoid binary searching for it multiple times by caching
the most recently used slot. There is an existing VM-wide last_used_slot
but that does not work well for cases where vCPUs are accessing memory
in different slots (see performance data below).
Another benefit of caching the most recently use slot (versus looking
up the slot once and passing around a pointer) is speeding up memslot
lookups *across* faults and during spte prefetching.
To measure the performance of this change I ran dirty_log_perf_test with
64 vCPUs and 64 memslots and measured "Populate memory time" and
"Iteration 2 dirty memory time". Tests were ran with eptad=N to force
dirty logging to use fast_page_fault so its performance could be
measured.
Config | Metric | Before | After
---------- | ----------------------------- | ------ | ------
tdp_mmu=Y | Populate memory time | 6.76s | 5.47s
tdp_mmu=Y | Iteration 2 dirty memory time | 2.83s | 0.31s
tdp_mmu=N | Populate memory time | 20.4s | 18.7s
tdp_mmu=N | Iteration 2 dirty memory time | 2.65s | 0.30s
The "Iteration 2 dirty memory time" results are especially compelling
because they are equivalent to running the same test with a single
memslot. In other words, fast_page_fault performance no longer scales
with the number of memslots.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make search_memslots unconditionally search all memslots and move the
last_used_slot logic up one level to __gfn_to_memslot. This is in
preparation for introducing a per-vCPU last_used_slot.
As part of this change convert existing callers of search_memslots to
__gfn_to_memslot to avoid making any functional changes.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
lru_slot is used to keep track of the index of the most-recently used
memslot. The correct acronym would be "mru" but that is not a common
acronym. So call it last_used_slot which is a bit more obvious.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We would like to avoid taking mmu_lock for .invalidate_range_{start,end}()
notifications that are unrelated to KVM. Because mmu_notifier_count
must be modified while holding mmu_lock for write, and must always
be paired across start->end to stay balanced, lock elision must
happen in both or none. Therefore, in preparation for this change,
this patch prevents memslot updates across range_start() and range_end().
Note, technically flag-only memslot updates could be allowed in parallel,
but stalling a memslot update for a relatively short amount of time is
not a scalability issue, and this is all more than complex enough.
A long note on the locking: a previous version of the patch used an rwsem
to block the memslot update while the MMU notifier run, but this resulted
in the following deadlock involving the pseudo-lock tagged as
"mmu_notifier_invalidate_range_start".
======================================================
WARNING: possible circular locking dependency detected
5.12.0-rc3+ #6 Tainted: G OE
------------------------------------------------------
qemu-system-x86/3069 is trying to acquire lock:
ffffffff9c775ca0 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}, at: __mmu_notifier_invalidate_range_end+0x5/0x190
but task is already holding lock:
ffffaff7410a9160 (&kvm->mmu_notifier_slots_lock){.+.+}-{3:3}, at: kvm_mmu_notifier_invalidate_range_start+0x36d/0x4f0 [kvm]
which lock already depends on the new lock.
This corresponds to the following MMU notifier logic:
invalidate_range_start
take pseudo lock
down_read() (*)
release pseudo lock
invalidate_range_end
take pseudo lock (**)
up_read()
release pseudo lock
At point (*) we take the mmu_notifiers_slots_lock inside the pseudo lock;
at point (**) we take the pseudo lock inside the mmu_notifiers_slots_lock.
This could cause a deadlock (ignoring for a second that the pseudo lock
is not a lock):
- invalidate_range_start waits on down_read(), because the rwsem is
held by install_new_memslots
- install_new_memslots waits on down_write(), because the rwsem is
held till (another) invalidate_range_end finishes
- invalidate_range_end sits waits on the pseudo lock, held by
invalidate_range_start.
Removing the fairness of the rwsem breaks the cycle (in lockdep terms,
it would change the *shared* rwsem readers into *shared recursive*
readers), so open-code the wait using a readers count and a
spinlock. This also allows handling blockable and non-blockable
critical section in the same way.
Losing the rwsem fairness does theoretically allow MMU notifiers to
block install_new_memslots forever. Note that mm/mmu_notifier.c's own
retry scheme in mmu_interval_read_begin also uses wait/wake_up
and is likewise not fair.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introduce this safe version of kvm_get_kvm() so that it can be called even
during vm destruction. Use it in kvm_debugfs_open() and remove the verbose
comment. Prepare to be used elsewhere.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210625153214.43106-3-peterx@redhat.com>
[Preserve the comment in kvm_debugfs_open. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Export kvm_make_all_cpus_request() and hoist the request helper
declarations of request up to the KVM_REQ_* definitions in preparation
for adding a "VM bugged" framework. The framework will add KVM_BUG()
and KVM_BUG_ON() as alternatives to full BUG()/BUG_ON() for cases where
KVM has definitely hit a bug (in itself or in silicon) and the VM is all
but guaranteed to be hosed. Marking a VM bugged will trigger a request
to all vCPUs to allow arch code to forcefully evict each vCPU from its
run loop.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-Id: <1d8cbbc8065d831343e70b5dcaea92268145eef1.1625186503.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
To remove code duplication, use the binary stats descriptors in the
implementation of the debugfs interface for statistics. This unifies
the definition of statistics for the binary and debugfs interfaces.
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-8-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a VCPU ioctl to get a statistics file descriptor by which a read
functionality is provided for userspace to read out VCPU stats header,
descriptors and data.
Define VCPU statistics descriptors and header for all architectures.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com> #arm64
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-5-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a VM ioctl to get a statistics file descriptor by which a read
functionality is provided for userspace to read out VM stats header,
descriptors and data.
Define VM statistics descriptors and header for all architectures.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com> #arm64
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-4-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit defines the API for userspace and prepare the common
functionalities to support per VM/VCPU binary stats data readings.
The KVM stats now is only accessible by debugfs, which has some
shortcomings this change series are supposed to fix:
1. The current debugfs stats solution in KVM could be disabled
when kernel Lockdown mode is enabled, which is a potential
rick for production.
2. The current debugfs stats solution in KVM is organized as "one
stats per file", it is good for debugging, but not efficient
for production.
3. The stats read/clear in current debugfs solution in KVM are
protected by the global kvm_lock.
Besides that, there are some other benefits with this change:
1. All KVM VM/VCPU stats can be read out in a bulk by one copy
to userspace.
2. A schema is used to describe KVM statistics. From userspace's
perspective, the KVM statistics are self-describing.
3. With the fd-based solution, a separate telemetry would be able
to read KVM stats in a less privileged environment.
4. After the initial setup by reading in stats descriptors, a
telemetry only needs to read the stats data itself, no more
parsing or setup is needed.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com> #arm64
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-3-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add KVM PM-notifier so that architectures can have arch-specific
VM suspend/resume routines. Such architectures need to select
CONFIG_HAVE_KVM_PM_NOTIFIER and implement kvm_arch_pm_notifier().
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20210606021045.14159-1-senozhatsky@chromium.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a new lock to protect the arch-specific fields of memslots if they
need to be modified in a kvm->srcu read critical section. A future
commit will use this lock to lazily allocate memslot rmaps for x86.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210518173414.450044-5-bgardon@google.com>
[Add Documentation/ hunk. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
array_index_nospec does not work for uint64_t on 32-bit builds.
However, the size of a memory slot must be less than 20 bits wide
on those system, since the memory slot must fit in the user
address space. So just store it in an unsigned long.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM's mechanism for accessing guest memory translates a guest physical
address (gpa) to a host virtual address using the right-shifted gpa
(also known as gfn) and a struct kvm_memory_slot. The translation is
performed in __gfn_to_hva_memslot using the following formula:
hva = slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE
It is expected that gfn falls within the boundaries of the guest's
physical memory. However, a guest can access invalid physical addresses
in such a way that the gfn is invalid.
__gfn_to_hva_memslot is called from kvm_vcpu_gfn_to_hva_prot, which first
retrieves a memslot through __gfn_to_memslot. While __gfn_to_memslot
does check that the gfn falls within the boundaries of the guest's
physical memory or not, a CPU can speculate the result of the check and
continue execution speculatively using an illegal gfn. The speculation
can result in calculating an out-of-bounds hva. If the resulting host
virtual address is used to load another guest physical address, this
is effectively a Spectre gadget consisting of two consecutive reads,
the second of which is data dependent on the first.
Right now it's not clear if there are any cases in which this is
exploitable. One interesting case was reported by the original author
of this patch, and involves visiting guest page tables on x86. Right
now these are not vulnerable because the hva read goes through get_user(),
which contains an LFENCE speculation barrier. However, there are
patches in progress for x86 uaccess.h to mask kernel addresses instead of
using LFENCE; once these land, a guest could use speculation to read
from the VMM's ring 3 address space. Other architectures such as ARM
already use the address masking method, and would be susceptible to
this same kind of data-dependent access gadgets. Therefore, this patch
proactively protects from these attacks by masking out-of-bounds gfns
in __gfn_to_hva_memslot, which blocks speculation of invalid hvas.
Sean Christopherson noted that this patch does not cover
kvm_read_guest_offset_cached. This however is limited to a few bytes
past the end of the cache, and therefore it is unlikely to be useful in
the context of building a chain of data dependent accesses.
Reported-by: Artemiy Margaritov <artemiy.margaritov@gmail.com>
Co-developed-by: Artemiy Margaritov <artemiy.margaritov@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_REQ_UNBLOCK will be used to exit a vcpu from
its inner vcpu halt emulation loop.
Rename KVM_REQ_PENDING_TIMER to KVM_REQ_UNBLOCK, switch
PowerPC to arch specific request bit.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <20210525134321.303768132@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This is inspired by commit 262de4102c (kvm: exit halt polling on
need_resched() as well). Due to PPC implements an arch specific halt
polling logic, we have to the need_resched() check there as well. This
patch adds a helper function that can be shared between book3s and generic
halt-polling loops.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Venkatesh Srinivas <venkateshs@chromium.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Venkatesh Srinivas <venkateshs@chromium.org>
Cc: Jim Mattson <jmattson@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1621339235-11131-1-git-send-email-wanpengli@tencent.com>
[Make the function inline. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the guest enter/exit wrappers to kvm_host.h so that KVM can manage
its context tracking vs. vtime accounting without bleeding too many KVM
details into the context tracking code.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210505002735.1684165-8-seanjc@google.com
Both lock holder vCPU and IPI receiver that has halted are condidate for
boost. However, the PLE handler was originally designed to deal with the
lock holder preemption problem. The Intel PLE occurs when the spinlock
waiter is in kernel mode. This assumption doesn't hold for IPI receiver,
they can be in either kernel or user mode. the vCPU candidate in user mode
will not be boosted even if they should respond to IPIs. Some benchmarks
like pbzip2, swaptions etc do the TLB shootdown in kernel mode and most
of the time they are running in user mode. It can lead to a large number
of continuous PLE events because the IPI sender causes PLE events
repeatedly until the receiver is scheduled while the receiver is not
candidate for a boost.
This patch boosts the vCPU candidiate in user mode which is delivery
interrupt. We can observe the speed of pbzip2 improves 10% in 96 vCPUs
VM in over-subscribe scenario (The host machine is 2 socket, 48 cores,
96 HTs Intel CLX box). There is no performance regression for other
benchmarks like Unixbench spawn (most of the time contend read/write
lock in kernel mode), ebizzy (most of the time contend read/write sem
and TLB shoodtdown in kernel mode).
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1618542490-14756-1-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a capability for userspace to mirror SEV encryption context from
one vm to another. On our side, this is intended to support a
Migration Helper vCPU, but it can also be used generically to support
other in-guest workloads scheduled by the host. The intention is for
the primary guest and the mirror to have nearly identical memslots.
The primary benefits of this are that:
1) The VMs do not share KVM contexts (think APIC/MSRs/etc), so they
can't accidentally clobber each other.
2) The VMs can have different memory-views, which is necessary for post-copy
migration (the migration vCPUs on the target need to read and write to
pages, when the primary guest would VMEXIT).
This does not change the threat model for AMD SEV. Any memory involved
is still owned by the primary guest and its initial state is still
attested to through the normal SEV_LAUNCH_* flows. If userspace wanted
to circumvent SEV, they could achieve the same effect by simply attaching
a vCPU to the primary VM.
This patch deliberately leaves userspace in charge of the memslots for the
mirror, as it already has the power to mess with them in the primary guest.
This patch does not support SEV-ES (much less SNP), as it does not
handle handing off attested VMSAs to the mirror.
For additional context, we need a Migration Helper because SEV PSP
migration is far too slow for our live migration on its own. Using
an in-guest migrator lets us speed this up significantly.
Signed-off-by: Nathan Tempelman <natet@google.com>
Message-Id: <20210408223214.2582277-1-natet@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Abort the walk of coalesced MMIO zones if kvm_io_bus_unregister_dev()
fails to allocate memory for the new instance of the bus. If it can't
instantiate a new bus, unregister_dev() destroys all devices _except_ the
target device. But, it doesn't tell the caller that it obliterated the
bus and invoked the destructor for all devices that were on the bus. In
the coalesced MMIO case, this can result in a deleted list entry
dereference due to attempting to continue iterating on coalesced_zones
after future entries (in the walk) have been deleted.
Opportunistically add curly braces to the for-loop, which encompasses
many lines but sneaks by without braces due to the guts being a single
if statement.
Fixes: f65886606c ("KVM: fix memory leak in kvm_io_bus_unregister_dev()")
Cc: stable@vger.kernel.org
Reported-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210412222050.876100-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_tdp_mmu_zap_collapsible_sptes unnecessarily removes the const
qualifier from its memlsot argument, leading to a compiler warning. Add
the const annotation and pass it to subsequent functions.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210401233736.638171-2-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Yank out the hva-based MMU notifier APIs now that all architectures that
use the notifiers have moved to the gfn-based APIs.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the hva->gfn lookup for MMU notifiers into common code. Every arch
does a similar lookup, and some arch code is all but identical across
multiple architectures.
In addition to consolidating code, this will allow introducing
optimizations that will benefit all architectures without incurring
multiple walks of the memslots, e.g. by taking mmu_lock if and only if a
relevant range exists in the memslots.
The use of __always_inline to avoid indirect call retpolines, as done by
x86, may also benefit other architectures.
Consolidating the lookups also fixes a wart in x86, where the legacy MMU
and TDP MMU each do their own memslot walks.
Lastly, future enhancements to the memslot implementation, e.g. to add an
interval tree to track host address, will need to touch far less arch
specific code.
MIPS, PPC, and arm64 will be converted one at a time in future patches.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the prototypes for the MMU notifier callbacks out of arch code and
into common code. There is no benefit to having each arch replicate the
prototypes since any deviation from the invocation in common code will
explode.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210326021957.1424875-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Track the range being invalidated by mmu_notifier and skip page fault
retries if the fault address is not affected by the in-progress
invalidation. Handle concurrent invalidations by finding the minimal
range which includes all ranges being invalidated. Although the combined
range may include unrelated addresses and cannot be shrunk as individual
invalidation operations complete, it is unlikely the marginal gains of
proper range tracking are worth the additional complexity.
The primary benefit of this change is the reduction in the likelihood of
extreme latency when handing a page fault due to another thread having
been preempted while modifying host virtual addresses.
Signed-off-by: David Stevens <stevensd@chromium.org>
Message-Id: <20210222024522.1751719-3-stevensd@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Current KVM_USER_MEM_SLOTS limits are arch specific (512 on Power, 509 on x86,
32 on s390, 16 on MIPS) but they don't really need to be. Memory slots are
allocated dynamically in KVM when added so the only real limitation is
'id_to_index' array which is 'short'. We don't have any other
KVM_MEM_SLOTS_NUM/KVM_USER_MEM_SLOTS-sized statically defined structures.
Low KVM_USER_MEM_SLOTS can be a limiting factor for some configurations.
In particular, when QEMU tries to start a Windows guest with Hyper-V SynIC
enabled and e.g. 256 vCPUs the limit is hit as SynIC requires two pages per
vCPU and the guest is free to pick any GFN for each of them, this fragments
memslots as QEMU wants to have a separate memslot for each of these pages
(which are supposed to act as 'overlay' pages).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210127175731.2020089-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a read / write lock to be used in place of the MMU spinlock on x86.
The rwlock will enable the TDP MMU to handle page faults, and other
operations in parallel in future commits.
Reviewed-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210202185734.1680553-19-bgardon@google.com>
[Introduce virt/kvm/mmu_lock.h - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Because kvm dirty rings and kvm dirty log is used in an exclusive way,
Let's avoid creating the dirty_bitmap when kvm dirty ring is enabled.
At the meantime, since the dirty_bitmap will be conditionally created
now, we can't use it as a sign of "whether this memory slot enabled
dirty tracking". Change users like that to check against the kvm
memory slot flags.
Note that there still can be chances where the kvm memory slot got its
dirty_bitmap allocated, _if_ the memory slots are created before
enabling of the dirty rings and at the same time with the dirty
tracking capability enabled, they'll still with the dirty_bitmap.
However it should not hurt much (e.g., the bitmaps will always be
freed if they are there), and the real users normally won't trigger
this because dirty bit tracking flag should in most cases only be
applied to kvm slots only before migration starts, that should be far
latter than kvm initializes (VM starts).
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012226.5868-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch is heavily based on previous work from Lei Cao
<lei.cao@stratus.com> and Paolo Bonzini <pbonzini@redhat.com>. [1]
KVM currently uses large bitmaps to track dirty memory. These bitmaps
are copied to userspace when userspace queries KVM for its dirty page
information. The use of bitmaps is mostly sufficient for live
migration, as large parts of memory are be dirtied from one log-dirty
pass to another. However, in a checkpointing system, the number of
dirty pages is small and in fact it is often bounded---the VM is
paused when it has dirtied a pre-defined number of pages. Traversing a
large, sparsely populated bitmap to find set bits is time-consuming,
as is copying the bitmap to user-space.
A similar issue will be there for live migration when the guest memory
is huge while the page dirty procedure is trivial. In that case for
each dirty sync we need to pull the whole dirty bitmap to userspace
and analyse every bit even if it's mostly zeros.
The preferred data structure for above scenarios is a dense list of
guest frame numbers (GFN). This patch series stores the dirty list in
kernel memory that can be memory mapped into userspace to allow speedy
harvesting.
This patch enables dirty ring for X86 only. However it should be
easily extended to other archs as well.
[1] https://patchwork.kernel.org/patch/10471409/
Signed-off-by: Lei Cao <lei.cao@stratus.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012222.5767-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The context will be needed to implement the kvm dirty ring.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012044.5151-5-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_clear_guest_page is not used anymore after "KVM: X86: Don't track dirty
for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]", except from kvm_clear_guest.
We can just inline it in its sole user.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Dirty logging is a key feature of the KVM MMU and must be supported by
the TDP MMU. Add support for both the write protection and PML dirty
logging modes.
Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.
This series can be viewed in Gerrit at:
https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20201014182700.2888246-16-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cache the address space ID just like the slot ID. It will be used in
order to fill in the dirty ring entries.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201014182700.2888246-7-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When updating the stolen time we should always read the current
stolen time from the user provided memory, not from a kernel
cache. If we use a cache then we'll end up resetting stolen time
to zero on the first update after migration.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200804170604.42662-5-drjones@redhat.com
We can use typeof() to avoid the need for the type input.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200804170604.42662-4-drjones@redhat.com
x86:
* Report last CPU for debugging
* Emulate smaller MAXPHYADDR in the guest than in the host
* .noinstr and tracing fixes from Thomas
* nested SVM page table switching optimization and fixes
Generic:
* Unify shadow MMU cache data structures across architectures
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAl8pC+oUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroNcOwgAjomqtEqQNlp7DdZT7VyyklzbxX1/
ud7v+oOJ8K4sFlf64lSthjPo3N9rzZCcw+yOXmuyuITngXOGc3tzIwXpCzpLtuQ1
WO1Ql3B/2dCi3lP5OMmsO1UAZqy9pKLg1dfeYUPk48P5+p7d/NPmk+Em5kIYzKm5
JsaHfCp2EEXomwmljNJ8PQ1vTjIQSSzlgYUBZxmCkaaX7zbEUMtxAQCStHmt8B84
33LczwXBm3viSWrzsoBV37I70+tseugiSGsCfUyupXOvq55d6D9FCqtCb45Hn4Vh
Ik8ggKdalsk/reiGEwNw1/3nr6mRMkHSbl+Mhc4waOIFf9dn0urgQgOaDg==
=YVx0
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"s390:
- implement diag318
x86:
- Report last CPU for debugging
- Emulate smaller MAXPHYADDR in the guest than in the host
- .noinstr and tracing fixes from Thomas
- nested SVM page table switching optimization and fixes
Generic:
- Unify shadow MMU cache data structures across architectures"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
KVM: SVM: Fix sev_pin_memory() error handling
KVM: LAPIC: Set the TDCR settable bits
KVM: x86: Specify max TDP level via kvm_configure_mmu()
KVM: x86/mmu: Rename max_page_level to max_huge_page_level
KVM: x86: Dynamically calculate TDP level from max level and MAXPHYADDR
KVM: VXM: Remove temporary WARN on expected vs. actual EPTP level mismatch
KVM: x86: Pull the PGD's level from the MMU instead of recalculating it
KVM: VMX: Make vmx_load_mmu_pgd() static
KVM: x86/mmu: Add separate helper for shadow NPT root page role calc
KVM: VMX: Drop a duplicate declaration of construct_eptp()
KVM: nSVM: Correctly set the shadow NPT root level in its MMU role
KVM: Using macros instead of magic values
MIPS: KVM: Fix build error caused by 'kvm_run' cleanup
KVM: nSVM: remove nonsensical EXITINFO1 adjustment on nested NPF
KVM: x86: Add a capability for GUEST_MAXPHYADDR < HOST_MAXPHYADDR support
KVM: VMX: optimize #PF injection when MAXPHYADDR does not match
KVM: VMX: Add guest physical address check in EPT violation and misconfig
KVM: VMX: introduce vmx_need_pf_intercept
KVM: x86: update exception bitmap on CPUID changes
KVM: x86: rename update_bp_intercept to update_exception_bitmap
...
Entering a guest is similar to exiting to user space. Pending work like
handling signals, rescheduling, task work etc. needs to be handled before
that.
Provide generic infrastructure to avoid duplication of the same handling
code all over the place.
The transfer to guest mode handling is different from the exit to usermode
handling, e.g. vs. rseq and live patching, so a separate function is used.
The initial list of work items handled is:
TIF_SIGPENDING, TIF_NEED_RESCHED, TIF_NOTIFY_RESUME
Architecture specific TIF flags can be added via defines in the
architecture specific include files.
The calling convention is also different from the syscall/interrupt entry
functions as KVM invokes this from the outer vcpu_run() loop with
interrupts and preemption enabled. To prevent missing a pending work item
it invokes a check for pending TIF work from interrupt disabled code right
before transitioning to guest mode. The lockdep, RCU and tracing state
handling is also done directly around the switch to and from guest mode.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200722220519.833296398@linutronix.de
Move x86's memory cache helpers to common KVM code so that they can be
reused by arm64 and MIPS in future patches.
Suggested-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200703023545.8771-16-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
OVMF booted guest running on shadow pages crashes on TRIPLE FAULT after
enabling paging from SMM. The crash is triggered from mmu_check_root() and
is caused by kvm_is_visible_gfn() searching through memslots with as_id = 0
while vCPU may be in a different context (address space).
Introduce kvm_vcpu_is_visible_gfn() and use it from mmu_check_root().
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200708140023.1476020-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unlike normal 'int' functions returning '0' on success, kvm_setup_async_pf()/
kvm_arch_setup_async_pf() return '1' when a job to handle page fault
asynchronously was scheduled and '0' otherwise. To avoid the confusion
change return type to 'bool'.
No functional change intended.
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200615121334.91300-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].
[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://github.com/KSPP/linux/issues/21
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
'Page not present' event may or may not get injected depending on
guest's state. If the event wasn't injected, there is no need to
inject the corresponding 'page ready' event as the guest may get
confused. E.g. Linux thinks that the corresponding 'page not present'
event wasn't delivered *yet* and allocates a 'dummy entry' for it.
This entry is never freed.
Note, 'wakeup all' events have no corresponding 'page not present'
event and always get injected.
s390 seems to always be able to inject 'page not present', the
change is effectively a nop.
Suggested-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200610175532.779793-2-vkuznets@redhat.com>
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208081
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit b1394e745b ("KVM: x86: fix APIC page invalidation") tried
to fix inappropriate APIC page invalidation by re-introducing arch
specific kvm_arch_mmu_notifier_invalidate_range() and calling it from
kvm_mmu_notifier_invalidate_range_start. However, the patch left a
possible race where the VMCS APIC address cache is updated *before*
it is unmapped:
(Invalidator) kvm_mmu_notifier_invalidate_range_start()
(Invalidator) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD)
(KVM VCPU) vcpu_enter_guest()
(KVM VCPU) kvm_vcpu_reload_apic_access_page()
(Invalidator) actually unmap page
Because of the above race, there can be a mismatch between the
host physical address stored in the APIC_ACCESS_PAGE VMCS field and
the host physical address stored in the EPT entry for the APIC GPA
(0xfee0000). When this happens, the processor will not trap APIC
accesses, and will instead show the raw contents of the APIC-access page.
Because Windows OS periodically checks for unexpected modifications to
the LAPIC register, this will show up as a BSOD crash with BugCheck
CRITICAL_STRUCTURE_CORRUPTION (109) we are currently seeing in
https://bugzilla.redhat.com/show_bug.cgi?id=1751017.
The root cause of the issue is that kvm_arch_mmu_notifier_invalidate_range()
cannot guarantee that no additional references are taken to the pages in
the range before kvm_mmu_notifier_invalidate_range_end(). Fortunately,
this case is supported by the MMU notifier API, as documented in
include/linux/mmu_notifier.h:
* If the subsystem
* can't guarantee that no additional references are taken to
* the pages in the range, it has to implement the
* invalidate_range() notifier to remove any references taken
* after invalidate_range_start().
The fix therefore is to reload the APIC-access page field in the VMCS
from kvm_mmu_notifier_invalidate_range() instead of ..._range_start().
Cc: stable@vger.kernel.org
Fixes: b1394e745b ("KVM: x86: fix APIC page invalidation")
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=197951
Signed-off-by: Eiichi Tsukata <eiichi.tsukata@nutanix.com>
Message-Id: <20200606042627.61070-1-eiichi.tsukata@nutanix.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
After commit 63d0434 ("KVM: x86: move kvm_create_vcpu_debugfs after
last failure point") we are creating the pre-vCPU debugfs files
after the creation of the vCPU file descriptor. This makes it
possible for userspace to reach kvm_vcpu_release before
kvm_create_vcpu_debugfs has finished. The vcpu->debugfs_dentry
then does not have any associated inode anymore, and this causes
a NULL-pointer dereference in debugfs_create_file.
The solution is simply to avoid removing the files; they are
cleaned up when the VM file descriptor is closed (and that must be
after KVM_CREATE_VCPU returns). We can stop storing the dentry
in struct kvm_vcpu too, because it is not needed anywhere after
kvm_create_vcpu_debugfs returns.
Reported-by: syzbot+705f4401d5a93a59b87d@syzkaller.appspotmail.com
Fixes: 63d0434837 ("KVM: x86: move kvm_create_vcpu_debugfs after last failure point")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The use of any sort of waitqueue (simple or regular) for
wait/waking vcpus has always been an overkill and semantically
wrong. Because this is per-vcpu (which is blocked) there is
only ever a single waiting vcpu, thus no need for any sort of
queue.
As such, make use of the rcuwait primitive, with the following
considerations:
- rcuwait already provides the proper barriers that serialize
concurrent waiter and waker.
- Task wakeup is done in rcu read critical region, with a
stable task pointer.
- Because there is no concurrency among waiters, we need
not worry about rcuwait_wait_event() calls corrupting
the wait->task. As a consequence, this saves the locking
done in swait when modifying the queue. This also applies
to per-vcore wait for powerpc kvm-hv.
The x86 tscdeadline_latency test mentioned in 8577370fb0
("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg,
latency is reduced by around 15-20% with this change.
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: kvmarm@lists.cs.columbia.edu
Cc: linux-mips@vger.kernel.org
Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Message-Id: <20200424054837.5138-6-dave@stgolabs.net>
[Avoid extra logic changes. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This allows making request to all other vcpus except the one
specified in the parameter.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Message-Id: <1588771076-73790-2-git-send-email-suravee.suthikulpanit@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_CAP_HALT_POLL is a per-VM capability that lets userspace
control the halt-polling time, allowing halt-polling to be tuned or
disabled on particular VMs.
With dynamic halt-polling, a VM's VCPUs can poll from anywhere from
[0, halt_poll_ns] on each halt. KVM_CAP_HALT_POLL sets the
upper limit on the poll time.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Jon Cargille <jcargill@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20200417221446.108733-1-jcargill@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In earlier versions of kvm, 'kvm_run' was an independent structure
and was not included in the vcpu structure. At present, 'kvm_run'
is already included in the vcpu structure, so the parameter
'kvm_run' is redundant.
This patch simplifies the function definition, removes the extra
'kvm_run' parameter, and extracts it from the 'kvm_vcpu' structure
if necessary.
Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Message-Id: <20200416051057.26526-1-tianjia.zhang@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Create a new function kvm_is_visible_memslot() and use it from
kvm_is_visible_gfn(); use the new function in try_async_pf() too,
to avoid an extra memslot lookup.
Opportunistically squish a multi-line comment into a single-line comment.
Note, the end result, KVM_PFN_NOSLOT, is unchanged.
Cc: Jim Mattson <jmattson@google.com>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The macros VM_STAT and VCPU_STAT are redundantly implemented in multiple
files, each used by a different architecure to initialize the debugfs
entries for statistics. Since they all have the same purpose, they can be
unified in a single common definition in include/linux/kvm_host.h
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20200414155625.20559-1-eesposit@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Check that the resolved slot (somewhat confusingly named 'start') is a
valid/allocated slot before doing the final comparison to see if the
specified gfn resides in the associated slot. The resolved slot can be
invalid if the binary search loop terminated because the search index
was incremented beyond the number of used slots.
This bug has existed since the binary search algorithm was introduced,
but went unnoticed because KVM statically allocated memory for the max
number of slots, i.e. the access would only be truly out-of-bounds if
all possible slots were allocated and the specified gfn was less than
the base of the lowest memslot. Commit 36947254e5 ("KVM: Dynamically
size memslot array based on number of used slots") eliminated the "all
possible slots allocated" condition and made the bug embarrasingly easy
to hit.
Fixes: 9c1a5d3878 ("kvm: optimize GFN to memslot lookup with large slots amount")
Reported-by: syzbot+d889b59b2bb87d4047a2@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200408064059.8957-2-sean.j.christopherson@intel.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pass @opaque to kvm_arch_hardware_setup() and
kvm_arch_check_processor_compat() to allow architecture specific code to
reference @opaque without having to stash it away in a temporary global
variable. This will enable x86 to separate its vendor specific callback
ops, which are passed via @opaque, into "init" and "runtime" ops without
having to stash away the "init" ops.
No functional change intended.
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Tested-by: Cornelia Huck <cohuck@redhat.com> #s390
Acked-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200321202603.19355-2-sean.j.christopherson@intel.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reset the LRU slot if it becomes invalid when deleting a memslot to fix
an out-of-bounds/use-after-free access when searching through memslots.
Explicitly check for there being no used slots in search_memslots(), and
in the caller of s390's approximation variant.
Fixes: 36947254e5 ("KVM: Dynamically size memslot array based on number of used slots")
Reported-by: Qian Cai <cai@lca.pw>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200320205546.2396-2-sean.j.christopherson@intel.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop largepages_enabled, kvm_largepages_enabled() and
kvm_disable_largepages() now that all users are gone.
Note, largepages_enabled was an x86-only flag that got left in common
KVM code when KVM gained support for multiple architectures.
No functional change intended.
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It could take kvm->mmu_lock for an extended period of time when
enabling dirty log for the first time. The main cost is to clear
all the D-bits of last level SPTEs. This situation can benefit from
manual dirty log protect as well, which can reduce the mmu_lock
time taken. The sequence is like this:
1. Initialize all the bits of the dirty bitmap to 1 when enabling
dirty log for the first time
2. Only write protect the huge pages
3. KVM_GET_DIRTY_LOG returns the dirty bitmap info
4. KVM_CLEAR_DIRTY_LOG will clear D-bit for each of the leaf level
SPTEs gradually in small chunks
Under the Intel(R) Xeon(R) Gold 6152 CPU @ 2.10GHz environment,
I did some tests with a 128G windows VM and counted the time taken
of memory_global_dirty_log_start, here is the numbers:
VM Size Before After optimization
128G 460ms 10ms
Signed-off-by: Jay Zhou <jianjay.zhou@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that the memslot logic doesn't assume memslots are always non-NULL,
dynamically size the array of memslots instead of unconditionally
allocating memory for the maximum number of memslots.
Note, because a to-be-deleted memslot must first be invalidated, the
array size cannot be immediately reduced when deleting a memslot.
However, consecutive deletions will realize the memory savings, i.e.
a second deletion will trim the entry.
Tested-by: Christoffer Dall <christoffer.dall@arm.com>
Tested-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Refactor memslot handling to treat the number of used slots as the de
facto size of the memslot array, e.g. return NULL from id_to_memslot()
when an invalid index is provided instead of relying on npages==0 to
detect an invalid memslot. Rework the sorting and walking of memslots
in advance of dynamically sizing memslots to aid bisection and debug,
e.g. with luck, a bug in the refactoring will bisect here and/or hit a
WARN instead of randomly corrupting memory.
Alternatively, a global null/invalid memslot could be returned, i.e. so
callers of id_to_memslot() don't have to explicitly check for a NULL
memslot, but that approach runs the risk of introducing difficult-to-
debug issues, e.g. if the global null slot is modified. Constifying
the return from id_to_memslot() to combat such issues is possible, but
would require a massive refactoring of arch specific code and would
still be susceptible to casting shenanigans.
Add function comments to update_memslots() and search_memslots() to
explicitly (and loudly) state how memslots are sorted.
Opportunistically stuff @hva with a non-canonical value when deleting a
private memslot on x86 to detect bogus usage of the freed slot.
No functional change intended.
Tested-by: Christoffer Dall <christoffer.dall@arm.com>
Tested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rework kvm_get_dirty_log() so that it "returns" the associated memslot
on success. A future patch will rework memslot handling such that
id_to_memslot() can return NULL, returning the memslot makes it more
obvious that the validity of the memslot has been verified, i.e.
precludes the need to add validity checks in the arch code that are
technically unnecessary.
To maintain ordering in s390, move the call to kvm_arch_sync_dirty_log()
from s390's kvm_vm_ioctl_get_dirty_log() to the new kvm_get_dirty_log().
This is a nop for PPC, the only other arch that doesn't select
KVM_GENERIC_DIRTYLOG_READ_PROTECT, as its sync_dirty_log() is empty.
Ideally, moving the sync_dirty_log() call would be done in a separate
patch, but it can't be done in a follow-on patch because that would
temporarily break s390's ordering. Making the move in a preparatory
patch would be functionally correct, but would create an odd scenario
where the moved sync_dirty_log() would operate on a "different" memslot
due to consuming the result of a different id_to_memslot(). The
memslot couldn't actually be different as slots_lock is held, but the
code is confusing enough as it is, i.e. moving sync_dirty_log() in this
patch is the lesser of all evils.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the implementations of KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG
for CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT into common KVM code.
The arch specific implemenations are extremely similar, differing
only in whether the dirty log needs to be sync'd from hardware (x86)
and how the TLBs are flushed. Add new arch hooks to handle sync
and TLB flush; the sync will also be used for non-generic dirty log
support in a future patch (s390).
The ulterior motive for providing a common implementation is to
eliminate the dependency between arch and common code with respect to
the memslot referenced by the dirty log, i.e. to make it obvious in the
code that the validity of the memslot is guaranteed, as a future patch
will rework memslot handling such that id_to_memslot() can return NULL.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that all callers of kvm_free_memslot() pass NULL for @dont, remove
the param from the top-level routine and all arch's implementations.
No functional change intended.
Tested-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop the "const" attribute from @old in kvm_arch_commit_memory_region()
to allow arch specific code to free arch specific resources in the old
memslot without having to cast away the attribute. Freeing resources in
kvm_arch_commit_memory_region() paves the way for simplifying
kvm_free_memslot() by eliminating the last usage of its @dont param.
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove kvm_arch_create_memslot() now that all arch implementations are
effectively nops. Removing kvm_arch_create_memslot() eliminates the
possibility for arch specific code to allocate memory prior to setting
a memslot, which sets the stage for simplifying kvm_free_memslot().
Cc: Janosch Frank <frankja@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reported with "make W=1" due to -Wmissing-prototypes.
Reported-by: Qian Cai <cai@lca.pw>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
From Boris Ostrovsky:
The KVM hypervisor may provide a guest with ability to defer remote TLB
flush when the remote VCPU is not running. When this feature is used,
the TLB flush will happen only when the remote VPCU is scheduled to run
again. This will avoid unnecessary (and expensive) IPIs.
Under certain circumstances, when a guest initiates such deferred action,
the hypervisor may miss the request. It is also possible that the guest
may mistakenly assume that it has already marked remote VCPU as needing
a flush when in fact that request had already been processed by the
hypervisor. In both cases this will result in an invalid translation
being present in a vCPU, potentially allowing accesses to memory locations
in that guest's address space that should not be accessible.
Note that only intra-guest memory is vulnerable.
The five patches address both of these problems:
1. The first patch makes sure the hypervisor doesn't accidentally clear
a guest's remote flush request
2. The rest of the patches prevent the race between hypervisor
acknowledging a remote flush request and guest issuing a new one.
Conflicts:
arch/x86/kvm/x86.c [move from kvm_arch_vcpu_free to kvm_arch_vcpu_destroy]
__kvm_map_gfn()'s call to gfn_to_pfn_memslot() is
* relatively expensive
* in certain cases (such as when done from atomic context) cannot be called
Stashing gfn-to-pfn mapping should help with both cases.
This is part of CVE-2019-3016.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_vcpu_(un)map operates on gfns from any current address space.
In certain cases we want to make sure we are not mapping SMRAM
and for that we can use kvm_(un)map_gfn() that we are introducing
in this patch.
This is part of CVE-2019-3016.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Use kvm_vcpu_gfn_to_hva() when retrieving the host page size so that the
correct set of memslots is used when handling x86 page faults in SMM.
Fixes: 54bf36aac5 ("KVM: x86: use vcpu-specific functions to read/write/translate GFNs")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a helper, is_transparent_hugepage(), to explicitly check whether a
compound page is a THP and use it when populating KVM's secondary MMU.
The explicit check fixes a bug where a remapped compound page, e.g. for
an XDP Rx socket, is mapped into a KVM guest and is mistaken for a THP,
which results in KVM incorrectly creating a huge page in its secondary
MMU.
Fixes: 936a5fe6e6 ("thp: kvm mmu transparent hugepage support")
Reported-by: syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
For ring-based dirty log tracking, it will be more efficient to account
writes during schedule-out or schedule-in to the currently running VCPU.
We would like to do it even if the write doesn't use the current VCPU's
address space, as is the case for cached writes (see commit 4e335d9e7d,
"Revert "KVM: Support vCPU-based gfn->hva cache"", 2017-05-02).
Therefore, add a mechanism to track the currently-loaded kvm_vcpu struct.
There is already something similar in KVM/ARM; one important difference
is that kvm_arch_vcpu_{load,put} have two callers in virt/kvm/kvm_main.c:
we have to update both the architecture-independent vcpu_{load,put} and
the preempt notifiers.
Another change made in the process is to allow using kvm_get_running_vcpu()
in preemptible code. This is allowed because preempt notifiers ensure
that the value does not change even after the VCPU thread is migrated.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove kvm_read_guest_atomic() because it's not used anywhere.
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Marc Zyngier