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: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
Changelog:
v2:
* Reworded the git commit as suggested by Sean
* Dropped the me->kvm->last_boosted_vcpu in favor of
kvm->last_boosted_vcpu as suggested by Sean
v1:
* https://lore.kernel.org/all/20240509090146.146153-1-leitao@xxxxxxxxxx/
---
virt/kvm/kvm_main.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ff0a20565f90..d9ce063c76f9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4066,12 +4066,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
struct kvm *kvm = me->kvm;
struct kvm_vcpu *vcpu;
- int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
+ int last_boosted_vcpu;
unsigned long i;
int yielded = 0;
int try = 3;
int pass;
+ last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu);
kvm_vcpu_set_in_spin_loop(me, true);
/*
* We boost the priority of a VCPU that is runnable but not
@@ -4109,7 +4110,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
yielded = kvm_vcpu_yield_to(vcpu);
if (yielded > 0) {
- kvm->last_boosted_vcpu = i;
+ WRITE_ONCE(kvm->last_boosted_vcpu, i);
break;
} else if (yielded < 0) {
try--;
--
2.43.0
