summaryrefslogtreecommitdiff
path: root/virt/kvm/async_pf.c
diff options
context:
space:
mode:
authorSean Christopherson <seanjc@google.com>2024-01-09 17:15:30 -0800
committerSean Christopherson <seanjc@google.com>2024-02-06 11:02:18 -0800
commit3d75b8aa5c29058a512db29da7cbee8052724157 (patch)
treea10ccdec56dfb2bcf00911386a9236743e145210 /virt/kvm/async_pf.c
parent41bccc98fb7931d63d03f326a746ac4d429c1dd3 (diff)
KVM: Always flush async #PF workqueue when vCPU is being destroyed
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 5f6de5cbebee ("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: af585b921e5d ("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>
Diffstat (limited to 'virt/kvm/async_pf.c')
-rw-r--r--virt/kvm/async_pf.c31
1 files changed, 26 insertions, 5 deletions
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index e033c79d528e..28658b9e0d96 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -87,7 +87,27 @@ static void async_pf_execute(struct work_struct *work)
__kvm_vcpu_wake_up(vcpu);
mmput(mm);
- kvm_put_kvm(vcpu->kvm);
+}
+
+static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
+{
+ /*
+ * The async #PF is "done", but KVM must wait for the work item itself,
+ * i.e. async_pf_execute(), to run to completion. If KVM is a module,
+ * KVM must ensure *no* code owned by the KVM (the module) can be run
+ * after the last call to module_put(). Note, flushing the work item
+ * is always required when the item is taken off the completion queue.
+ * E.g. even if the vCPU handles the item in the "normal" path, the VM
+ * could be terminated before async_pf_execute() completes.
+ *
+ * Wake all events skip the queue and go straight done, i.e. don't
+ * need to be flushed (but sanity check that the work wasn't queued).
+ */
+ if (work->wakeup_all)
+ WARN_ON_ONCE(work->work.func);
+ else
+ flush_work(&work->work);
+ kmem_cache_free(async_pf_cache, work);
}
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
@@ -114,7 +134,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
#else
if (cancel_work_sync(&work->work)) {
mmput(work->mm);
- kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
kmem_cache_free(async_pf_cache, work);
}
#endif
@@ -126,7 +145,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
list_first_entry(&vcpu->async_pf.done,
typeof(*work), link);
list_del(&work->link);
- kmem_cache_free(async_pf_cache, work);
+
+ spin_unlock(&vcpu->async_pf.lock);
+ kvm_flush_and_free_async_pf_work(work);
+ spin_lock(&vcpu->async_pf.lock);
}
spin_unlock(&vcpu->async_pf.lock);
@@ -151,7 +173,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
list_del(&work->queue);
vcpu->async_pf.queued--;
- kmem_cache_free(async_pf_cache, work);
+ kvm_flush_and_free_async_pf_work(work);
}
}
@@ -186,7 +208,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
work->arch = *arch;
work->mm = current->mm;
mmget(work->mm);
- kvm_get_kvm(work->vcpu->kvm);
INIT_WORK(&work->work, async_pf_execute);