commit 49f683b41f upstream.
Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the
loads and stores are atomic. In the extremely unlikely scenario the
compiler tears the stores, it's theoretically possible for KVM to attempt
to get a vCPU using an out-of-bounds index, e.g. if the write is split
into multiple 8-bit stores, and is paired with a 32-bit load on a VM with
257 vCPUs:
CPU0 CPU1
last_boosted_vcpu = 0xff;
(last_boosted_vcpu = 0x100)
last_boosted_vcpu[15:8] = 0x01;
i = (last_boosted_vcpu = 0x1ff)
last_boosted_vcpu[7:0] = 0x00;
vcpu = kvm->vcpu_array[0x1ff];
As detected by KCSAN:
BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm]
write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16:
kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm
handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel
vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:?
arch/x86/kvm/vmx/vmx.c:6606) kvm_intel
vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm
kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm
kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm
__se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890)
__x64_sys_ioctl (fs/ioctl.c:890)
x64_sys_call (arch/x86/entry/syscall_64.c:33)
do_syscall_64 (arch/x86/entry/common.c:?)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4:
kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm
handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel
vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:?
arch/x86/kvm/vmx/vmx.c:6606) kvm_intel
vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm
kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm
kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm
__se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890)
__x64_sys_ioctl (fs/ioctl.c:890)
x64_sys_call (arch/x86/entry/syscall_64.c:33)
do_syscall_64 (arch/x86/entry/common.c:?)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
value changed: 0x00000012 -> 0x00000000
Fixes: 217ece6129 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin")
Cc: stable@vger.kernel.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 3d75b8aa5c ]
Always flush the per-vCPU async #PF workqueue when a vCPU is clearing its
completion queue, e.g. when a VM and all its vCPUs is being destroyed.
KVM must ensure that none of its workqueue callbacks is running when the
last reference to the KVM _module_ is put. Gifting a reference to the
associated VM prevents the workqueue callback from dereferencing freed
vCPU/VM memory, but does not prevent the KVM module from being unloaded
before the callback completes.
Drop the misguided VM refcount gifting, as calling kvm_put_kvm() from
async_pf_execute() if kvm_put_kvm() flushes the async #PF workqueue will
result in deadlock. async_pf_execute() can't return until kvm_put_kvm()
finishes, and kvm_put_kvm() can't return until async_pf_execute() finishes:
WARNING: CPU: 8 PID: 251 at virt/kvm/kvm_main.c:1435 kvm_put_kvm+0x2d/0x320 [kvm]
Modules linked in: vhost_net vhost vhost_iotlb tap kvm_intel kvm irqbypass
CPU: 8 PID: 251 Comm: kworker/8:1 Tainted: G W 6.6.0-rc1-e7af8d17224a-x86/gmem-vm #119
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Workqueue: events async_pf_execute [kvm]
RIP: 0010:kvm_put_kvm+0x2d/0x320 [kvm]
Call Trace:
<TASK>
async_pf_execute+0x198/0x260 [kvm]
process_one_work+0x145/0x2d0
worker_thread+0x27e/0x3a0
kthread+0xba/0xe0
ret_from_fork+0x2d/0x50
ret_from_fork_asm+0x11/0x20
</TASK>
---[ end trace 0000000000000000 ]---
INFO: task kworker/8:1:251 blocked for more than 120 seconds.
Tainted: G W 6.6.0-rc1-e7af8d17224a-x86/gmem-vm #119
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/8:1 state:D stack:0 pid:251 ppid:2 flags:0x00004000
Workqueue: events async_pf_execute [kvm]
Call Trace:
<TASK>
__schedule+0x33f/0xa40
schedule+0x53/0xc0
schedule_timeout+0x12a/0x140
__wait_for_common+0x8d/0x1d0
__flush_work.isra.0+0x19f/0x2c0
kvm_clear_async_pf_completion_queue+0x129/0x190 [kvm]
kvm_arch_destroy_vm+0x78/0x1b0 [kvm]
kvm_put_kvm+0x1c1/0x320 [kvm]
async_pf_execute+0x198/0x260 [kvm]
process_one_work+0x145/0x2d0
worker_thread+0x27e/0x3a0
kthread+0xba/0xe0
ret_from_fork+0x2d/0x50
ret_from_fork_asm+0x11/0x20
</TASK>
If kvm_clear_async_pf_completion_queue() actually flushes the workqueue,
then there's no need to gift async_pf_execute() a reference because all
invocations of async_pf_execute() will be forced to complete before the
vCPU and its VM are destroyed/freed. And that in turn fixes the module
unloading bug as __fput() won't do module_put() on the last vCPU reference
until the vCPU has been freed, e.g. if closing the vCPU file also puts the
last reference to the KVM module.
Note that kvm_check_async_pf_completion() may also take the work item off
the completion queue and so also needs to flush the work queue, as the
work will not be seen by kvm_clear_async_pf_completion_queue(). Waiting
on the workqueue could theoretically delay a vCPU due to waiting for the
work to complete, but that's a very, very small chance, and likely a very
small delay. kvm_arch_async_page_present_queued() unconditionally makes a
new request, i.e. will effectively delay entering the guest, so the
remaining work is really just:
trace_kvm_async_pf_completed(addr, cr2_or_gpa);
__kvm_vcpu_wake_up(vcpu);
mmput(mm);
and mmput() can't drop the last reference to the page tables if the vCPU is
still alive, i.e. the vCPU won't get stuck tearing down page tables.
Add a helper to do the flushing, specifically to deal with "wakeup all"
work items, as they aren't actually work items, i.e. are never placed in a
workqueue. Trying to flush a bogus workqueue entry rightly makes
__flush_work() complain (kudos to whoever added that sanity check).
Note, commit 5f6de5cbeb ("KVM: Prevent module exit until all VMs are
freed") *tried* to fix the module refcounting issue by having VMs grab a
reference to the module, but that only made the bug slightly harder to hit
as it gave async_pf_execute() a bit more time to complete before the KVM
module could be unloaded.
Fixes: af585b921e ("KVM: Halt vcpu if page it tries to access is swapped out")
Cc: stable@vger.kernel.org
Cc: David Matlack <dmatlack@google.com>
Reviewed-by: Xu Yilun <yilun.xu@intel.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240110011533.503302-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 9e0f4f2918 ]
kvm_vfio_group_add() creates kvg instance, links it to kv->group_list,
and calls kvm_vfio_file_set_kvm() with kvg->file as an argument after
dropping kv->lock. If we race group addition and deletion calls, kvg
instance may get freed by the time we get around to calling
kvm_vfio_file_set_kvm().
Previous iterations of the code did not reference kvg->file outside of
the critical section, but used a temporary variable. Still, they had
similar problem of the file reference being owned by kvg structure and
potential for kvm_vfio_group_del() dropping it before
kvm_vfio_group_add() had a chance to complete.
Fix this by moving call to kvm_vfio_file_set_kvm() under the protection
of kv->lock. We already call it while holding the same lock when vfio
group is being deleted, so it should be safe here as well.
Fixes: 2fc1bec158 ("kvm: set/clear kvm to/from vfio_group when group add/delete")
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20230714224538.404793-1-dmitry.torokhov@gmail.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit eed3013faa upstream.
Grab a reference to KVM prior to installing VM and vCPU stats file
descriptors to ensure the underlying VM and vCPU objects are not freed
until the last reference to any and all stats fds are dropped.
Note, the stats paths manually invoke fd_install() and so don't need to
grab a reference before creating the file.
Fixes: ce55c04945 ("KVM: stats: Support binary stats retrieval for a VCPU")
Fixes: fcfe1baedd ("KVM: stats: Support binary stats retrieval for a VM")
Reported-by: Zheng Zhang <zheng.zhang@email.ucr.edu>
Closes: https://lore.kernel.org/all/CAC_GQSr3xzZaeZt85k_RCBd5kfiOve8qXo7a81Cq53LuVQ5r=Q@mail.gmail.com
Cc: stable@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Message-Id: <20230711230131.648752-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2230f9e117 upstream.
We run into guest hang in edk2 firmware when KSM is kept as running on
the host. The edk2 firmware is waiting for status 0x80 from QEMU's pflash
device (TYPE_PFLASH_CFI01) during the operation of sector erasing or
buffered write. The status is returned by reading the memory region of
the pflash device and the read request should have been forwarded to QEMU
and emulated by it. Unfortunately, the read request is covered by an
illegal stage2 mapping when the guest hang issue occurs. The read request
is completed with QEMU bypassed and wrong status is fetched. The edk2
firmware runs into an infinite loop with the wrong status.
The illegal stage2 mapping is populated due to same page sharing by KSM
at (C) even the associated memory slot has been marked as invalid at (B)
when the memory slot is requested to be deleted. It's notable that the
active and inactive memory slots can't be swapped when we're in the middle
of kvm_mmu_notifier_change_pte() because kvm->mn_active_invalidate_count
is elevated, and kvm_swap_active_memslots() will busy loop until it reaches
to zero again. Besides, the swapping from the active to the inactive memory
slots is also avoided by holding &kvm->srcu in __kvm_handle_hva_range(),
corresponding to synchronize_srcu_expedited() in kvm_swap_active_memslots().
CPU-A CPU-B
----- -----
ioctl(kvm_fd, KVM_SET_USER_MEMORY_REGION)
kvm_vm_ioctl_set_memory_region
kvm_set_memory_region
__kvm_set_memory_region
kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE)
kvm_invalidate_memslot
kvm_copy_memslot
kvm_replace_memslot
kvm_swap_active_memslots (A)
kvm_arch_flush_shadow_memslot (B)
same page sharing by KSM
kvm_mmu_notifier_invalidate_range_start
:
kvm_mmu_notifier_change_pte
kvm_handle_hva_range
__kvm_handle_hva_range
kvm_set_spte_gfn (C)
:
kvm_mmu_notifier_invalidate_range_end
Fix the issue by skipping the invalid memory slot at (C) to avoid the
illegal stage2 mapping so that the read request for the pflash's status
is forwarded to QEMU and emulated by it. In this way, the correct pflash's
status can be returned from QEMU to break the infinite loop in the edk2
firmware.
We tried a git-bisect and the first problematic commit is cd4c718352 ("
KVM: arm64: Convert to the gfn-based MMU notifier callbacks"). With this,
clean_dcache_guest_page() is called after the memory slots are iterated
in kvm_mmu_notifier_change_pte(). clean_dcache_guest_page() is called
before the iteration on the memory slots before this commit. This change
literally enlarges the racy window between kvm_mmu_notifier_change_pte()
and memory slot removal so that we're able to reproduce the issue in a
practical test case. However, the issue exists since commit d5d8184d35
("KVM: ARM: Memory virtualization setup").
Cc: stable@vger.kernel.org # v3.9+
Fixes: d5d8184d35 ("KVM: ARM: Memory virtualization setup")
Reported-by: Shuai Hu <hshuai@redhat.com>
Reported-by: Zhenyu Zhang <zhenyzha@redhat.com>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Message-Id: <20230615054259.14911-1-gshan@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit afb2acb2e3 upstream.
In kvm_vm_ioctl_create_vcpu(), add vcpu to vcpu_array iff it's safe to
access vcpu via kvm_get_vcpu() and kvm_for_each_vcpu(), i.e. when there's
no failure path requiring vcpu removal and destruction. Such order is
important because vcpu_array accessors may end up referencing vcpu at
vcpu_array[0] even before online_vcpus is set to 1.
When online_vcpus=0, any call to kvm_get_vcpu() goes through
array_index_nospec() and ends with an attempt to xa_load(vcpu_array, 0):
int num_vcpus = atomic_read(&kvm->online_vcpus);
i = array_index_nospec(i, num_vcpus);
return xa_load(&kvm->vcpu_array, i);
Similarly, when online_vcpus=0, a kvm_for_each_vcpu() does not iterate over
an "empty" range, but actually [0, ULONG_MAX]:
xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \
(atomic_read(&kvm->online_vcpus) - 1))
In both cases, such online_vcpus=0 edge case, even if leading to
unnecessary calls to XArray API, should not be an issue; requesting
unpopulated indexes/ranges is handled by xa_load() and xa_for_each_range().
However, this means that when the first vCPU is created and inserted in
vcpu_array *and* before online_vcpus is incremented, code calling
kvm_get_vcpu()/kvm_for_each_vcpu() already has access to that first vCPU.
This should not pose a problem assuming that once a vcpu is stored in
vcpu_array, it will remain there, but that's not the case:
kvm_vm_ioctl_create_vcpu() first inserts to vcpu_array, then requests a
file descriptor. If create_vcpu_fd() fails, newly inserted vcpu is removed
from the vcpu_array, then destroyed:
vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT);
kvm_get_kvm(kvm);
r = create_vcpu_fd(vcpu);
if (r < 0) {
xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx);
kvm_put_kvm_no_destroy(kvm);
goto unlock_vcpu_destroy;
}
atomic_inc(&kvm->online_vcpus);
This results in a possible race condition when a reference to a vcpu is
acquired (via kvm_get_vcpu() or kvm_for_each_vcpu()) moments before said
vcpu is destroyed.
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Message-Id: <20230510140410.1093987-2-mhal@rbox.co>
Cc: stable@vger.kernel.org
Fixes: c5b0775491 ("KVM: Convert the kvm->vcpus array to a xarray", 2021-12-08)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2b01281273 upstream.
Register /dev/kvm, i.e. expose KVM to userspace, only after all other
setup has completed. Once /dev/kvm is exposed, userspace can start
invoking KVM ioctls, creating VMs, etc... If userspace creates a VM
before KVM is done with its configuration, bad things may happen, e.g.
KVM will fail to properly migrate vCPU state if a VM is created before
KVM has registered preemption notifiers.
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20221130230934.1014142-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 51cdc8bc12 ]
Currently it is possible that the final put of a KVM reference comes from
vfio during its device close operation. This occurs while the vfio group
lock is held; however, if the vfio device is still in the kvm device list,
then the following call chain could result in a deadlock:
VFIO holds group->group_lock/group_rwsem
-> kvm_put_kvm
-> kvm_destroy_vm
-> kvm_destroy_devices
-> kvm_vfio_destroy
-> kvm_vfio_file_set_kvm
-> vfio_file_set_kvm
-> try to hold group->group_lock/group_rwsem
The key function is the kvm_destroy_devices() which triggers destroy cb
of kvm_device_ops. It calls back to vfio and try to hold group_lock. So
if this path doesn't call back to vfio, this dead lock would be fixed.
Actually, there is a way for it. KVM provides another point to free the
kvm-vfio device which is the point when the device file descriptor is
closed. This can be achieved by providing the release cb instead of the
destroy cb. Also rename kvm_vfio_destroy() to be kvm_vfio_release().
/*
* Destroy is responsible for freeing dev.
*
* Destroy may be called before or after destructors are called
* on emulated I/O regions, depending on whether a reference is
* held by a vcpu or other kvm component that gets destroyed
* after the emulated I/O.
*/
void (*destroy)(struct kvm_device *dev);
/*
* Release is an alternative method to free the device. It is
* called when the device file descriptor is closed. Once
* release is called, the destroy method will not be called
* anymore as the device is removed from the device list of
* the VM. kvm->lock is held.
*/
void (*release)(struct kvm_device *dev);
Fixes: 421cfe6596 ("vfio: remove VFIO_GROUP_NOTIFY_SET_KVM")
Reported-by: Alex Williamson <alex.williamson@redhat.com>
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Link: https://lore.kernel.org/r/20230114000351.115444-1-mjrosato@linux.ibm.com
Link: https://lore.kernel.org/r/20230120150528.471752-1-yi.l.liu@intel.com
[aw: update comment as well, s/destroy/release/]
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This brings in a few important fixes for Xen emulation.
While nobody should be enabling it, the bug effectively
allows userspace to read arbitrary memory.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In the case where a GPC is refreshed to a different location within the
same page, we didn't bother to update it. Mostly we don't need to, but
since the ->khva field also includes the offset within the page, that
does have to be updated.
Fixes: 3ba2c95ea1 ("KVM: Do not incorporate page offset into gfn=>pfn cache user address")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Cc: stable@kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Obey kvm.halt_poll_ns in VMs not using KVM_CAP_HALT_POLL on every halt,
rather than just sampling the module parameter when the VM is first
created. This restore the original behavior of kvm.halt_poll_ns for VMs
that have not opted into KVM_CAP_HALT_POLL.
Notably, this change restores the ability for admins to disable or
change the maximum halt-polling time system wide for VMs not using
KVM_CAP_HALT_POLL.
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Fixes: acd05785e4 ("kvm: add capability for halt polling")
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Avoid re-reading kvm->max_halt_poll_ns multiple times during
halt-polling except when it is explicitly useful, e.g. to check if the
max time changed across a halt. kvm->max_halt_poll_ns can be changed at
any time by userspace via KVM_CAP_HALT_POLL.
This bug is unlikely to cause any serious side-effects. In the worst
case one halt polls for shorter or longer than it should, and then is
fixed up on the next halt. Furthmore, this is still possible since
kvm->max_halt_poll_ns are not synchronized with halts.
Fixes: acd05785e4 ("kvm: add capability for halt polling")
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cap vcpu->halt_poll_ns based on the max halt polling time just before
halting, rather than after the last halt. This arguably provides better
accuracy if an admin disables halt polling in between halts, although
the improvement is nominal.
A side-effect of this change is that grow_halt_poll_ns() no longer needs
to access vcpu->kvm->max_halt_poll_ns, which will be useful in a future
commit where the max halt polling time can come from the module parameter
halt_poll_ns instead.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20221117001657.1067231-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* Fix the pKVM stage-1 walker erronously using the stage-2 accessor
* Correctly convert vcpu->kvm to a hyp pointer when generating
an exception in a nVHE+MTE configuration
* Check that KVM_CAP_DIRTY_LOG_* are valid before enabling them
* Fix SMPRI_EL1/TPIDR2_EL0 trapping on VHE
* Document the boot requirements for FGT when entering the kernel
at EL1
There are two capabilities related to ring-based dirty page tracking:
KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL. Both are
supported by x86. However, arm64 supports KVM_CAP_DIRTY_LOG_RING_ACQ_REL
only when the feature is supported on arm64. The userspace doesn't have
to enable the advertised capability, meaning KVM_CAP_DIRTY_LOG_RING can
be enabled on arm64 by userspace and it's wrong.
Fix it by double checking if the capability has been advertised prior to
enabling it. It's rejected to enable the capability if it hasn't been
advertised.
Fixes: 17601bfed9 ("KVM: Add KVM_CAP_DIRTY_LOG_RING_ACQ_REL capability and config option")
Reported-by: Sean Christopherson <seanjc@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221031003621.164306-4-gshan@redhat.com
Reject kvm_gpc_check() and kvm_gpc_refresh() if the cache is inactive.
Not checking the active flag during refresh is particularly egregious, as
KVM can end up with a valid, inactive cache, which can lead to a variety
of use-after-free bugs, e.g. consuming a NULL kernel pointer or missing
an mmu_notifier invalidation due to the cache not being on the list of
gfns to invalidate.
Note, "active" needs to be set if and only if the cache is on the list
of caches, i.e. is reachable via mmu_notifier events. If a relevant
mmu_notifier event occurs while the cache is "active" but not on the
list, KVM will not acquire the cache's lock and so will not serailize
the mmu_notifier event with active users and/or kvm_gpc_refresh().
A race between KVM_XEN_ATTR_TYPE_SHARED_INFO and KVM_XEN_HVM_EVTCHN_SEND
can be exploited to trigger the bug.
1. Deactivate shinfo cache:
kvm_xen_hvm_set_attr
case KVM_XEN_ATTR_TYPE_SHARED_INFO
kvm_gpc_deactivate
kvm_gpc_unmap
gpc->valid = false
gpc->khva = NULL
gpc->active = false
Result: active = false, valid = false
2. Cause cache refresh:
kvm_arch_vm_ioctl
case KVM_XEN_HVM_EVTCHN_SEND
kvm_xen_hvm_evtchn_send
kvm_xen_set_evtchn
kvm_xen_set_evtchn_fast
kvm_gpc_check
return -EWOULDBLOCK because !gpc->valid
kvm_xen_set_evtchn_fast
return -EWOULDBLOCK
kvm_gpc_refresh
hva_to_pfn_retry
gpc->valid = true
gpc->khva = not NULL
Result: active = false, valid = true
3. Race ioctl KVM_XEN_HVM_EVTCHN_SEND against ioctl
KVM_XEN_ATTR_TYPE_SHARED_INFO:
kvm_arch_vm_ioctl
case KVM_XEN_HVM_EVTCHN_SEND
kvm_xen_hvm_evtchn_send
kvm_xen_set_evtchn
kvm_xen_set_evtchn_fast
read_lock gpc->lock
kvm_xen_hvm_set_attr case
KVM_XEN_ATTR_TYPE_SHARED_INFO
mutex_lock kvm->lock
kvm_xen_shared_info_init
kvm_gpc_activate
gpc->khva = NULL
kvm_gpc_check
[ Check passes because gpc->valid is
still true, even though gpc->khva
is already NULL. ]
shinfo = gpc->khva
pending_bits = shinfo->evtchn_pending
CRASH: test_and_set_bit(..., pending_bits)
Fixes: 982ed0de47 ("KVM: Reinstate gfn_to_pfn_cache with invalidation support")
Cc: stable@vger.kernel.org
Reported-by: : Michal Luczaj <mhal@rbox.co>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20221013211234.1318131-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the gfn_to_pfn_cache lock initialization to another helper and
call the new helper during VM/vCPU creation. There are race
conditions possible due to kvm_gfn_to_pfn_cache_init()'s
ability to re-initialize the cache's locks.
For example: a race between ioctl(KVM_XEN_HVM_EVTCHN_SEND) and
kvm_gfn_to_pfn_cache_init() leads to a corrupted shinfo gpc lock.
(thread 1) | (thread 2)
|
kvm_xen_set_evtchn_fast |
read_lock_irqsave(&gpc->lock, ...) |
| kvm_gfn_to_pfn_cache_init
| rwlock_init(&gpc->lock)
read_unlock_irqrestore(&gpc->lock, ...) |
Rename "cache_init" and "cache_destroy" to activate+deactivate to
avoid implying that the cache really is destroyed/freed.
Note, there more races in the newly named kvm_gpc_activate() that will
be addressed separately.
Fixes: 982ed0de47 ("KVM: Reinstate gfn_to_pfn_cache with invalidation support")
Cc: stable@vger.kernel.org
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
[sean: call out that this is a bug fix]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20221013211234.1318131-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Although simple_attr_open() fails only with -ENOMEM with current code
base, it would be nicer to return retval of simple_attr_open() directly
in kvm_debugfs_open().
No functional change intended.
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Message-Id: <69d64d93accd1f33691b8a383ae555baee80f943.1665975828.git.houwenlong.hwl@antgroup.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We will introduce the first architecture specific compat vm ioctl in the
next patch. Add all necessary boilerplate to allow architectures to
override compat vm ioctls when necessary.
Signed-off-by: Alexander Graf <graf@amazon.com>
Message-Id: <20221017184541.2658-2-graf@amazon.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
- Prune private items from vfio_pci_core.h to a new internal header,
fix missed function rename, and refactor vfio-pci interrupt defines.
(Jason Gunthorpe)
- Create consistent naming and handling of ioctls with a function per
ioctl for vfio-pci and vfio group handling, use proper type args
where available. (Jason Gunthorpe)
- Implement a set of low power device feature ioctls allowing userspace
to make use of power states such as D3cold where supported.
(Abhishek Sahu)
- Remove device counter on vfio groups, which had restricted the page
pinning interface to singleton groups to account for limitations in
the type1 IOMMU backend. Document usage as limited to emulated IOMMU
devices, ie. traditional mdev devices where this restriction is
consistent. (Jason Gunthorpe)
- Correct function prefix in hisi_acc driver incurred during previous
refactoring. (Shameer Kolothum)
- Correct typo and remove redundant warning triggers in vfio-fsl driver.
(Christophe JAILLET)
- Introduce device level DMA dirty tracking uAPI and implementation in
the mlx5 variant driver (Yishai Hadas & Joao Martins)
- Move much of the vfio_device life cycle management into vfio core,
simplifying and avoiding duplication across drivers. This also
facilitates adding a struct device to vfio_device which begins the
introduction of device rather than group level user support and fills
a gap allowing userspace identify devices as vfio capable without
implicit knowledge of the driver. (Kevin Tian & Yi Liu)
- Split vfio container handling to a separate file, creating a more
well defined API between the core and container code, masking IOMMU
backend implementation from the core, allowing for an easier future
transition to an iommufd based implementation of the same.
(Jason Gunthorpe)
- Attempt to resolve race accessing the iommu_group for a device
between vfio releasing DMA ownership and removal of the device from
the IOMMU driver. Follow-up with support to allow vfio_group to
exist with NULL iommu_group pointer to support existing userspace
use cases of holding the group file open. (Jason Gunthorpe)
- Fix error code and hi/lo register manipulation issues in the hisi_acc
variant driver, along with various code cleanups. (Longfang Liu)
- Fix a prior regression in GVT-g group teardown, resulting in
unreleased resources. (Jason Gunthorpe)
- A significant cleanup and simplification of the mdev interface,
consolidating much of the open coded per driver sysfs interface
support into the mdev core. (Christoph Hellwig)
- Simplification of tracking and locking around vfio_groups that
fall out from previous refactoring. (Jason Gunthorpe)
- Replace trivial open coded f_ops tests with new helper.
(Alex Williamson)
-----BEGIN PGP SIGNATURE-----
iQJPBAABCAA5FiEEQvbATlQL0amee4qQI5ubbjuwiyIFAmNGz2AbHGFsZXgud2ls
bGlhbXNvbkByZWRoYXQuY29tAAoJECObm247sIsiatYQAI+7bFjVsTKwCnWUhp/A
WnFmLpnh/OsBIYiXRbXGZBgIO4iPmMyFkxqjnv6e8H1WnKhLbuPy/xCaAvPrtI8b
YKCpzdrDnfrPfB4+0cyGLJx15Jqd3sOZy097kl2lQJTscELTjJxTl0uB/Fbf/s38
t1K2nIhBm+sGK3rTf3JjY4Jc7vDbwX7HQt6rUVEbd3NoyLJV1T/HdeSgwSMdyiED
WwkRZ0z/vU0hEDk5wk1ZyltkiUzdCSws3C8T0J39xRObPLHR1vYgKO8aeZhfQb4p
luD1fzGRMt3JinSXCPPm5HfADXq2Rozx7Y7a454fvCa7lpX4MNAgaQdfIzI64lZj
cMgSYAIskVq4vxCkO4bKec4FYrzJoxBMJwiXZvOZ4mF5SL4UIDwerMqQTA3fvtQ+
puS6x+/DF9XXHrEewEX7teg6QYPQueneSS+fWeFpMGzDXSjdQB6qV+rMWS297t+4
1KyITxkOxcZQ4+j1OLPGtxsRLKtWApawoNTpRMlaD+hSExxHLbUmKexOLXzuAoVP
nhbjud+jzEbpCnwps24Og/iEBdRYJcl2KwEeSRPI856YRDrNa9jPtiDlsAtKZOK2
gJnOixSss6R+wgVVYIyMDZ8tsvO+UDQruvqQ2kFku1FOlO86pvwD6UUVuTVosdNc
fktw6Dx90N3fdb/o8jjAjssx
=Z8+P
-----END PGP SIGNATURE-----
Merge tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio
Pull VFIO updates from Alex Williamson:
- Prune private items from vfio_pci_core.h to a new internal header,
fix missed function rename, and refactor vfio-pci interrupt defines
(Jason Gunthorpe)
- Create consistent naming and handling of ioctls with a function per
ioctl for vfio-pci and vfio group handling, use proper type args
where available (Jason Gunthorpe)
- Implement a set of low power device feature ioctls allowing userspace
to make use of power states such as D3cold where supported (Abhishek
Sahu)
- Remove device counter on vfio groups, which had restricted the page
pinning interface to singleton groups to account for limitations in
the type1 IOMMU backend. Document usage as limited to emulated IOMMU
devices, ie. traditional mdev devices where this restriction is
consistent (Jason Gunthorpe)
- Correct function prefix in hisi_acc driver incurred during previous
refactoring (Shameer Kolothum)
- Correct typo and remove redundant warning triggers in vfio-fsl driver
(Christophe JAILLET)
- Introduce device level DMA dirty tracking uAPI and implementation in
the mlx5 variant driver (Yishai Hadas & Joao Martins)
- Move much of the vfio_device life cycle management into vfio core,
simplifying and avoiding duplication across drivers. This also
facilitates adding a struct device to vfio_device which begins the
introduction of device rather than group level user support and fills
a gap allowing userspace identify devices as vfio capable without
implicit knowledge of the driver (Kevin Tian & Yi Liu)
- Split vfio container handling to a separate file, creating a more
well defined API between the core and container code, masking IOMMU
backend implementation from the core, allowing for an easier future
transition to an iommufd based implementation of the same (Jason
Gunthorpe)
- Attempt to resolve race accessing the iommu_group for a device
between vfio releasing DMA ownership and removal of the device from
the IOMMU driver. Follow-up with support to allow vfio_group to exist
with NULL iommu_group pointer to support existing userspace use cases
of holding the group file open (Jason Gunthorpe)
- Fix error code and hi/lo register manipulation issues in the hisi_acc
variant driver, along with various code cleanups (Longfang Liu)
- Fix a prior regression in GVT-g group teardown, resulting in
unreleased resources (Jason Gunthorpe)
- A significant cleanup and simplification of the mdev interface,
consolidating much of the open coded per driver sysfs interface
support into the mdev core (Christoph Hellwig)
- Simplification of tracking and locking around vfio_groups that fall
out from previous refactoring (Jason Gunthorpe)
- Replace trivial open coded f_ops tests with new helper (Alex
Williamson)
* tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio: (77 commits)
vfio: More vfio_file_is_group() use cases
vfio: Make the group FD disassociate from the iommu_group
vfio: Hold a reference to the iommu_group in kvm for SPAPR
vfio: Add vfio_file_is_group()
vfio: Change vfio_group->group_rwsem to a mutex
vfio: Remove the vfio_group->users and users_comp
vfio/mdev: add mdev available instance checking to the core
vfio/mdev: consolidate all the description sysfs into the core code
vfio/mdev: consolidate all the available_instance sysfs into the core code
vfio/mdev: consolidate all the name sysfs into the core code
vfio/mdev: consolidate all the device_api sysfs into the core code
vfio/mdev: remove mtype_get_parent_dev
vfio/mdev: remove mdev_parent_dev
vfio/mdev: unexport mdev_bus_type
vfio/mdev: remove mdev_from_dev
vfio/mdev: simplify mdev_type handling
vfio/mdev: embedd struct mdev_parent in the parent data structure
vfio/mdev: make mdev.h standalone includable
drm/i915/gvt: simplify vgpu configuration management
drm/i915/gvt: fix a memory leak in intel_gvt_init_vgpu_types
...
SPAPR exists completely outside the normal iommu driver framework, the
groups it creates are fake and are only created to enable VFIO's uAPI.
Thus, it does not need to follow the iommu core rule that the iommu_group
will only be touched while a driver is attached.
Carry a group reference into KVM and have KVM directly manage the lifetime
of this object independently of VFIO. This means KVM no longer relies on
the vfio group file being valid to maintain the group reference.
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v2-15417f29324e+1c-vfio_group_disassociate_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
This replaces uses of vfio_file_iommu_group() which were only detecting if
the file is a VFIO file with no interest in the actual group.
The only remaning user of vfio_file_iommu_group() is in KVM for the SPAPR
stuff. It passes the iommu_group into the arch code through kvm for some
reason.
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v2-15417f29324e+1c-vfio_group_disassociate_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
- Fixes for single-stepping in the presence of an async
exception as well as the preservation of PSTATE.SS
- Better handling of AArch32 ID registers on AArch64-only
systems
- Fixes for the dirty-ring API, allowing it to work on
architectures with relaxed memory ordering
- Advertise the new kvmarm mailing list
- Various minor cleanups and spelling fixes
-----BEGIN PGP SIGNATURE-----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=aNPK
-----END PGP SIGNATURE-----
Merge tag 'kvmarm-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for v6.1
- Fixes for single-stepping in the presence of an async
exception as well as the preservation of PSTATE.SS
- Better handling of AArch32 ID registers on AArch64-only
systems
- Fixes for the dirty-ring API, allowing it to work on
architectures with relaxed memory ordering
- Advertise the new kvmarm mailing list
- Various minor cleanups and spelling fixes
In order to differenciate between architectures that require no extra
synchronisation when accessing the dirty ring and those who do,
add a new capability (KVM_CAP_DIRTY_LOG_RING_ACQ_REL) that identify
the latter sort. TSO architectures can obviously advertise both, while
relaxed architectures must only advertise the ACQ_REL version.
This requires some configuration symbol rejigging, with HAVE_KVM_DIRTY_RING
being only indirectly selected by two top-level config symbols:
- HAVE_KVM_DIRTY_RING_TSO for strongly ordered architectures (x86)
- HAVE_KVM_DIRTY_RING_ACQ_REL for weakly ordered architectures (arm64)
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20220926145120.27974-3-maz@kernel.org
The current implementation of the dirty ring has an implicit requirement
that stores to the dirty ring from userspace must be:
- be ordered with one another
- visible from another CPU executing a ring reset
While these implicit requirements work well for x86 (and any other
TSO-like architecture), they do not work for more relaxed architectures
such as arm64 where stores to different addresses can be freely
reordered, and loads from these addresses not observing writes from
another CPU unless the required barriers (or acquire/release semantics)
are used.
In order to start fixing this, upgrade the ring reset accesses:
- the kvm_dirty_gfn_harvested() helper now uses acquire semantics
so it is ordered after all previous writes, including that from
userspace
- the kvm_dirty_gfn_set_invalid() helper now uses release semantics
so that the next_slot and next_offset reads don't drift past
the entry invalidation
This is only a partial fix as the userspace side also need upgrading.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20220926145120.27974-2-maz@kernel.org
KVM_REQ_UNHALT is now unnecessary because it is replaced by the return
value of kvm_vcpu_block/kvm_vcpu_halt. Remove it.
No functional change intended.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20220921003201.1441511-13-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When alloc_cpumask_var_node() fails for a certain cpu, there might be some
allocated cpumasks for percpu cpu_kick_mask. We should free these cpumasks
or memoryleak will occur.
Fixes: baff59ccdc ("KVM: Pre-allocate cpumasks for kvm_make_all_cpus_request_except()")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Link: https://lore.kernel.org/r/20220823063414.59778-1-linmiaohe@huawei.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The variable is initialized but it is only used after its assignment.
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Li kunyu <kunyu@nfschina.com>
Message-Id: <20220819021535.483702-1-kunyu@nfschina.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The variable is initialized but it is only used after its assignment.
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Li kunyu <kunyu@nfschina.com>
Message-Id: <20220819022804.483914-1-kunyu@nfschina.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The motivation of this renaming is to make these variables and related
helper functions less mmu_notifier bound and can also be used for non
mmu_notifier based page invalidation. mmu_invalidate_* was chosen to
better describe the purpose of 'invalidating' a page that those
variables are used for.
- mmu_notifier_seq/range_start/range_end are renamed to
mmu_invalidate_seq/range_start/range_end.
- mmu_notifier_retry{_hva} helper functions are renamed to
mmu_invalidate_retry{_hva}.
- mmu_notifier_count is renamed to mmu_invalidate_in_progress to
avoid confusion with mn_active_invalidate_count.
- While here, also update kvm_inc/dec_notifier_count() to
kvm_mmu_invalidate_begin/end() to match the change for
mmu_notifier_count.
No functional change intended.
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Message-Id: <20220816125322.1110439-3-chao.p.peng@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Invoke kvm_coalesced_mmio_init() from kvm_create_vm() now that allocating
and initializing coalesced MMIO objects is separate from registering any
associated devices. Moving coalesced MMIO cleans up the last oddity
where KVM does VM creation/initialization after kvm_create_vm(), and more
importantly after kvm_arch_post_init_vm() is called and the VM is added
to the global vm_list, i.e. after the VM is fully created as far as KVM
is concerned.
Originally, kvm_coalesced_mmio_init() was called by kvm_create_vm(), but
the original implementation was completely devoid of error handling.
Commit 6ce5a090a9 ("KVM: coalesced_mmio: fix kvm_coalesced_mmio_init()'s
error handling" fixed the various bugs, and in doing so rightly moved the
call to after kvm_create_vm() because kvm_coalesced_mmio_init() also
registered the coalesced MMIO device. Commit 2b3c246a68 ("KVM: Make
coalesced mmio use a device per zone") cleaned up that mess by having
each zone register a separate device, i.e. moved device registration to
its logical home in kvm_vm_ioctl_register_coalesced_mmio(). As a result,
kvm_coalesced_mmio_init() is now a "pure" initialization helper and can
be safely called from kvm_create_vm().
Opportunstically drop the #ifdef, KVM provides stubs for
kvm_coalesced_mmio_{init,free}() when CONFIG_KVM_MMIO=n (s390).
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220816053937.2477106-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unconditionally get a reference to the /dev/kvm module when creating a VM
instead of using try_get_module(), which will fail if the module is in
the process of being forcefully unloaded. The error handling when
try_get_module() fails doesn't properly unwind all that has been done,
e.g. doesn't call kvm_arch_pre_destroy_vm() and doesn't remove the VM
from the global list. Not removing VMs from the global list tends to be
fatal, e.g. leads to use-after-free explosions.
The obvious alternative would be to add proper unwinding, but the
justification for using try_get_module(), "rmmod --wait", is completely
bogus as support for "rmmod --wait", i.e. delete_module() without
O_NONBLOCK, was removed by commit 3f2b9c9cdf ("module: remove rmmod
--wait option.") nearly a decade ago.
It's still possible for try_get_module() to fail due to the module dying
(more like being killed), as the module will be tagged MODULE_STATE_GOING
by "rmmod --force", i.e. delete_module(..., O_TRUNC), but playing nice
with forced unloading is an exercise in futility and gives a falsea sense
of security. Using try_get_module() only prevents acquiring _new_
references, it doesn't magically put the references held by other VMs,
and forced unloading doesn't wait, i.e. "rmmod --force" on KVM is all but
guaranteed to cause spectacular fireworks; the window where KVM will fail
try_get_module() is tiny compared to the window where KVM is building and
running the VM with an elevated module refcount.
Addressing KVM's inability to play nice with "rmmod --force" is firmly
out-of-scope. Forcefully unloading any module taints kernel (for obvious
reasons) _and_ requires the kernel to be built with
CONFIG_MODULE_FORCE_UNLOAD=y, which is off by default and comes with the
amusing disclaimer that it's "mainly for kernel developers and desperate
users". In other words, KVM is free to scoff at bug reports due to using
"rmmod --force" while VMs may be running.
Fixes: 5f6de5cbeb ("KVM: Prevent module exit until all VMs are freed")
Cc: stable@vger.kernel.org
Cc: David Matlack <dmatlack@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220816053937.2477106-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Properly unwind VM creation if kvm_create_vm_debugfs() fails. A recent
change to invoke kvm_create_vm_debug() in kvm_create_vm() was led astray
by buggy try_get_module() handling adding by commit 5f6de5cbeb ("KVM:
Prevent module exit until all VMs are freed"). The debugfs error path
effectively inherits the bad error path of try_module_get(), e.g. KVM
leaves the to-be-free VM on vm_list even though KVM appears to do the
right thing by calling module_put() and falling through.
Opportunistically hoist kvm_create_vm_debugfs() above the call to
kvm_arch_post_init_vm() so that the "post-init" arch hook is actually
invoked after the VM is initialized (ignoring kvm_coalesced_mmio_init()
for the moment). x86 is the only non-nop implementation of the post-init
hook, and it doesn't allocate/initialize any objects that are reachable
via debugfs code (spawns a kthread worker for the NX huge page mitigation).
Leave the buggy try_get_module() alone for now, it will be fixed in a
separate commit.
Fixes: b74ed7a68e ("KVM: Actually create debugfs in kvm_create_vm()")
Reported-by: syzbot+744e173caec2e1627ee0@syzkaller.appspotmail.com
Cc: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Message-Id: <20220816053937.2477106-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Doing debugfs creation after vm creation leaves things in a
quasi-initialized state for a while. This is further complicated by the
fact that we tear down debugfs from kvm_destroy_vm(). Align debugfs and
stats init/destroy with the vm init/destroy pattern to avoid any
headaches.
Note the fix for a benign mistake in error handling for calls to
kvm_arch_create_vm_debugfs() rolled in. Since all implementations of
the function return 0 unconditionally it isn't actually a bug at
the moment.
Lastly, tear down debugfs/stats data in the kvm_create_vm_debugfs()
error path. Previously it was safe to assume that kvm_destroy_vm() would
take out the garbage, that is no longer the case.
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220720092259.3491733-6-oliver.upton@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
At the time the VM fd is used in kvm_create_vm_debugfs(), the fd has
been allocated but not yet installed. It is only really useful as an
identifier in strings for the VM (such as debugfs).
Treat it exactly as such by passing the string name of the fd to
kvm_create_vm_debugfs(), futureproofing against possible misuse of the
VM fd.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220720092259.3491733-5-oliver.upton@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Allocate a VM's fd at the very beginning of kvm_dev_ioctl_create_vm() so
that KVM can use the fd value to generate strigns, e.g. for debugfs,
when creating and initializing the VM.
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220720092259.3491733-4-oliver.upton@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Initialize stats_id alongside other kvm_vcpu fields to make it more
difficult to unintentionally access stats_id before it's set.
No functional change intended.
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220720092259.3491733-3-oliver.upton@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Initialize stats_id alongside other struct kvm fields to make it more
difficult to unintentionally access stats_id before it's set. While at
it, move the format string to the first line of the call and fix the
indentation of the second line.
No functional change intended.
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220720092259.3491733-2-oliver.upton@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM/s390, KVM/x86 and common infrastructure changes for 5.20
x86:
* Permit guests to ignore single-bit ECC errors
* Fix races in gfn->pfn cache refresh; do not pin pages tracked by the cache
* Intel IPI virtualization
* Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS
* PEBS virtualization
* Simplify PMU emulation by just using PERF_TYPE_RAW events
* More accurate event reinjection on SVM (avoid retrying instructions)
* Allow getting/setting the state of the speaker port data bit
* Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls are inconsistent
* "Notify" VM exit (detect microarchitectural hangs) for Intel
* Cleanups for MCE MSR emulation
s390:
* add an interface to provide a hypervisor dump for secure guests
* improve selftests to use TAP interface
* enable interpretive execution of zPCI instructions (for PCI passthrough)
* First part of deferred teardown
* CPU Topology
* PV attestation
* Minor fixes
Generic:
* new selftests API using struct kvm_vcpu instead of a (vm, id) tuple
x86:
* Use try_cmpxchg64 instead of cmpxchg64
* Bugfixes
* Ignore benign host accesses to PMU MSRs when PMU is disabled
* Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior
* x86/MMU: Allow NX huge pages to be disabled on a per-vm basis
* Port eager page splitting to shadow MMU as well
* Enable CMCI capability by default and handle injected UCNA errors
* Expose pid of vcpu threads in debugfs
* x2AVIC support for AMD
* cleanup PIO emulation
* Fixes for LLDT/LTR emulation
* Don't require refcounted "struct page" to create huge SPTEs
x86 cleanups:
* Use separate namespaces for guest PTEs and shadow PTEs bitmasks
* PIO emulation
* Reorganize rmap API, mostly around rmap destruction
* Do not workaround very old KVM bugs for L0 that runs with nesting enabled
* new selftests API for CPUID
The kvm_mmu_topup_memory_cache() always uses GFP_KERNEL_ACCOUNT for
memory allocation which prevents it's use in atomic context. To address
this limitation of kvm_mmu_topup_memory_cache(), we add gfp_custom flag
in struct kvm_mmu_memory_cache. When the gfp_custom flag is set to some
GFP_xyz flags, the kvm_mmu_topup_memory_cache() will use that instead of
GFP_KERNEL_ACCOUNT.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
Add a new debugfs file to expose the pid of each vcpu threads. This
is very helpful for userland tools to get the vcpu pids without
worrying about thread naming conventions of the VMM.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Message-Id: <20220523190327.2658-1-vineeth@bitbyteword.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Allow the capacity of the kvm_mmu_memory_cache struct to be chosen at
declaration time rather than being fixed for all declarations. This will
be used in a follow-up commit to declare an cache in x86 with a capacity
of 512+ objects without having to increase the capacity of all caches in
KVM.
This change requires each cache now specify its capacity at runtime,
since the cache struct itself no longer has a fixed capacity known at
compile time. To protect against someone accidentally defining a
kvm_mmu_memory_cache struct directly (without the extra storage), this
commit includes a WARN_ON() in kvm_mmu_topup_memory_cache().
In order to support different capacities, this commit changes the
objects pointer array to be dynamically allocated the first time the
cache is topped-up.
While here, opportunistically clean up the stack-allocated
kvm_mmu_memory_cache structs in riscv and arm64 to use designated
initializers.
No functional change intended.
Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220516232138.1783324-22-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop the unnecessary initialization of the local 'pfn' variable in
hva_to_pfn(). First and foremost, '0' is not an invalid pfn, it's a
perfectly valid pfn on most architectures. I.e. if hva_to_pfn() were to
return an "uninitializd" pfn, it would actually be interpeted as a legal
pfn by most callers.
Second, hva_to_pfn() can't return an uninitialized pfn as hva_to_pfn()
explicitly sets pfn to an error value (or returns an error value directly)
if a helper returns failure, and all helpers set the pfn on success.
The zeroing of 'pfn' was introduced by commit 2fc843117d ("KVM:
reorganize hva_to_pfn"), probably to avoid "uninitialized variable"
warnings on statements that return pfn. However, no compiler seems
to produce them, making the initialization unnecessary.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rename and refactor kvm_is_reserved_pfn() to kvm_pfn_to_refcounted_page()
to better reflect what KVM is actually checking, and to eliminate extra
pfn_to_page() lookups. The kvm_release_pfn_*() an kvm_try_get_pfn()
helpers in particular benefit from "refouncted" nomenclature, as it's not
all that obvious why KVM needs to get/put refcounts for some PG_reserved
pages (ZERO_PAGE and ZONE_DEVICE).
Add a comment to call out that the list of exceptions to PG_reserved is
all but guaranteed to be incomplete. The list has mostly been compiled
by people throwing noodles at KVM and finding out they stick a little too
well, e.g. the ZERO_PAGE's refcount overflowed and ZONE_DEVICE pages
didn't get freed.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Operate on a 'struct page' instead of a pfn when checking if a page is a
ZONE_DEVICE page, and rename the helper accordingly. Generally speaking,
KVM doesn't actually care about ZONE_DEVICE memory, i.e. shouldn't do
anything special for ZONE_DEVICE memory. Rather, KVM wants to treat
ZONE_DEVICE memory like regular memory, and the need to identify
ZONE_DEVICE memory only arises as an exception to PG_reserved pages. In
other words, KVM should only ever check for ZONE_DEVICE memory after KVM
has already verified that there is a struct page associated with the pfn.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop helpers to convert a gfn/gpa to a 'struct page' in the context of a
vCPU. KVM doesn't require that guests be backed by 'struct page' memory,
thus any use of helpers that assume 'struct page' is bound to be flawed,
as was the case for the recently removed last user in x86's nested VMX.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop a WARN_ON() if kvm_pfn_to_page() encounters a "reserved" pfn, which
in this context means a struct page that has PG_reserved but is not a/the
ZERO_PAGE and is not a ZONE_DEVICE page. The usage, via gfn_to_page(),
in x86 is safe as gfn_to_page() is used only to retrieve a page from
KVM-controlled memslot, but the usage in PPC and s390 operates on
arbitrary gfns and thus memslots that can be backed by incompatible
memory.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Invert the order of KVM's page/pfn release helpers so that the "inner"
helper operates on a page instead of a pfn. As pointed out by Linus[*],
converting between struct page and a pfn isn't necessarily cheap, and
that's not even counting the overhead of is_error_noslot_pfn() and
kvm_is_reserved_pfn(). Even if the checks were dirt cheap, there's no
reason to convert from a page to a pfn and back to a page, just to mark
the page dirty/accessed or to put a reference to the page.
Opportunistically drop a stale declaration of kvm_set_page_accessed()
from kvm_host.h (there was no implementation).
No functional change intended.
[*] https://lore.kernel.org/all/CAHk-=wifQimj2d6npq-wCi5onYPjzQg4vyO4tFcPJJZr268cRw@mail.gmail.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220429010416.2788472-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
