diff options
| author | Keith Busch <kbusch@kernel.org> | 2025-01-23 07:35:43 -0800 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2025-01-24 10:53:56 -0500 |
| commit | 931656b9e2ff7029aee0b36e17780621948a6ac1 (patch) | |
| tree | 6f2c1558a03bc4ed547b12bd33e614fd014201ba /arch/x86/kvm | |
| parent | 86eb1aef7279ec68fe9b7a44685efc09aa56a8f0 (diff) | |
| download | linux-stable-931656b9e2ff7029aee0b36e17780621948a6ac1.tar.gz linux-stable-931656b9e2ff7029aee0b36e17780621948a6ac1.tar.bz2 linux-stable-931656b9e2ff7029aee0b36e17780621948a6ac1.zip | |
kvm: defer huge page recovery vhost task to later
Some libraries want to ensure they are single threaded before forking,
so making the kernel's kvm huge page recovery process a vhost task of
the user process breaks those. The minijail library used by crosvm is
one such affected application.
Defer the task to after the first VM_RUN call, which occurs after the
parent process has forked all its jailed processes. This needs to happen
only once for the kvm instance, so introduce some general-purpose
infrastructure for that, too. It's similar in concept to pthread_once;
except it is actually usable, because the callback takes a parameter.
Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Alyssa Ross <hi@alyssa.is>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250123153543.2769928-1-kbusch@meta.com>
[Move call_once API to include/linux. - Paolo]
Cc: stable@vger.kernel.org
Fixes: d96c77bd4eeb ("KVM: x86: switch hugepage recovery thread to vhost_task")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kvm')
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 18 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 7 |
2 files changed, 19 insertions, 6 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 26b4ba7e7cb5..a45ae60e84ab 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7447,20 +7447,28 @@ static bool kvm_nx_huge_page_recovery_worker(void *data) return true; } -int kvm_mmu_post_init_vm(struct kvm *kvm) +static void kvm_mmu_start_lpage_recovery(struct once *once) { - if (nx_hugepage_mitigation_hard_disabled) - return 0; + struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); + struct kvm *kvm = container_of(ka, struct kvm, arch); kvm->arch.nx_huge_page_last = get_jiffies_64(); kvm->arch.nx_huge_page_recovery_thread = vhost_task_create( kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, kvm, "kvm-nx-lpage-recovery"); + if (kvm->arch.nx_huge_page_recovery_thread) + vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + if (nx_hugepage_mitigation_hard_disabled) + return 0; + + call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery); if (!kvm->arch.nx_huge_page_recovery_thread) return -ENOMEM; - - vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6e248152fa13..6d4a6734b2d6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11471,6 +11471,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; int r; + r = kvm_mmu_post_init_vm(vcpu->kvm); + if (r) + return r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; @@ -12748,7 +12752,8 @@ out: int kvm_arch_post_init_vm(struct kvm *kvm) { - return kvm_mmu_post_init_vm(kvm); + once_init(&kvm->arch.nx_once); + return 0; } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) |