From: Wanpeng Li <[email protected]>
The below test case can cause infinite loop in kvm when ept=0.
#include <unistd.h>
#include <sys/syscall.h>
#include <string.h>
#include <stdint.h>
#include <linux/kvm.h>
#include <fcntl.h>
#include <sys/ioctl.h>
long r[5];
int main()
{
r[2] = open("/dev/kvm", O_RDONLY);
r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
r[4] = ioctl(r[3], KVM_CREATE_VCPU, 7);
ioctl(r[4], KVM_RUN, 0);
}
It doesn't setup the memory regions, mmu_alloc_shadow/direct_roots() in
kvm return 1 when kvm fails to allocate root page table which can result
in beblow infinite loop:
vcpu_run() {
for (;;) {
r = vcpu_enter_guest()::kvm_mmu_reload() returns 1
if (r <= 0)
break;
if (need_resched())
cond_resched();
}
}
This patch fixes it by returning -ENOSPC when there is no available kvm mmu
page for root page table.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Fixes: 26eeb53cf0f (KVM: MMU: Bail out immediately if there is no available mmu page)
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/mmu.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index c9aaa18..89da688 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if(make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, 0, 0,
vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
@@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
@@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
@@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->kvm->mmu_lock);
if (make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
- return 1;
+ return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
0, ACC_ALL);
--
2.7.4
From: Wanpeng Li <[email protected]>
*** Guest State ***
CR0: actual=0x0000000000000030, shadow=0x0000000060000010, gh_mask=fffffffffffffff7
CR4: actual=0x0000000000002050, shadow=0x0000000000000000, gh_mask=ffffffffffffe871
CR3 = 0x00000000fffbc000
RSP = 0x0000000000000000 RIP = 0x0000000000000000
RFLAGS=0x00000000 DR7 = 0x0000000000000400
^^^^^^^^^^
The failed vmentry is triggered by the following testcase when ept=Y:
#include <unistd.h>
#include <sys/syscall.h>
#include <string.h>
#include <stdint.h>
#include <linux/kvm.h>
#include <fcntl.h>
#include <sys/ioctl.h>
long r[5];
int main()
{
r[2] = open("/dev/kvm", O_RDONLY);
r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
r[4] = ioctl(r[3], KVM_CREATE_VCPU, 7);
struct kvm_regs regs = {
.rflags = 0,
};
ioctl(r[4], KVM_SET_REGS, ®s);
ioctl(r[4], KVM_RUN, 0);
}
X86 RFLAGS bit 1 is fixed set, userspace can simply clearing bit 1
of RFLAGS with KVM_SET_REGS ioctl which results in vmentry fails.
This patch fixes it by catching userspace set RFLAGS w/o the fixes
bit and bailing out immediately.
Suggested-by: Jim Mattson <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Cc: Jim Mattson <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
virt/kvm/kvm_main.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c01cff0..7100833 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2602,6 +2602,11 @@ static long kvm_vcpu_ioctl(struct file *filp,
r = PTR_ERR(kvm_regs);
goto out;
}
+ r = -EINVAL;
+ if (!(kvm_regs->rflags & X86_EFLAGS_FIXED)) {
+ kfree(kvm_regs);
+ goto out;
+ }
r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
kfree(kvm_regs);
break;
--
2.7.4
On 05/12/2017 07:21, Wanpeng Li wrote:
> From: Wanpeng Li <[email protected]>
>
> The below test case can cause infinite loop in kvm when ept=0.
>
> #include <unistd.h>
> #include <sys/syscall.h>
> #include <string.h>
> #include <stdint.h>
> #include <linux/kvm.h>
> #include <fcntl.h>
> #include <sys/ioctl.h>
>
> long r[5];
> int main()
> {
> r[2] = open("/dev/kvm", O_RDONLY);
> r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
> r[4] = ioctl(r[3], KVM_CREATE_VCPU, 7);
> ioctl(r[4], KVM_RUN, 0);
> }
>
> It doesn't setup the memory regions, mmu_alloc_shadow/direct_roots() in
> kvm return 1 when kvm fails to allocate root page table which can result
> in beblow infinite loop:
>
> vcpu_run() {
> for (;;) {
> r = vcpu_enter_guest()::kvm_mmu_reload() returns 1
> if (r <= 0)
> break;
> if (need_resched())
> cond_resched();
> }
> }
>
> This patch fixes it by returning -ENOSPC when there is no available kvm mmu
> page for root page table.
>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Radim Krčmář <[email protected]>
> Fixes: 26eeb53cf0f (KVM: MMU: Bail out immediately if there is no available mmu page)
> Signed-off-by: Wanpeng Li <[email protected]>
> ---
> arch/x86/kvm/mmu.c | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index c9aaa18..89da688 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
> spin_lock(&vcpu->kvm->mmu_lock);
> if(make_mmu_pages_available(vcpu) < 0) {
> spin_unlock(&vcpu->kvm->mmu_lock);
> - return 1;
> + return -ENOSPC;
> }
> sp = kvm_mmu_get_page(vcpu, 0, 0,
> vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
> @@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
> spin_lock(&vcpu->kvm->mmu_lock);
> if (make_mmu_pages_available(vcpu) < 0) {
> spin_unlock(&vcpu->kvm->mmu_lock);
> - return 1;
> + return -ENOSPC;
> }
> sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
> i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
> @@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
> spin_lock(&vcpu->kvm->mmu_lock);
> if (make_mmu_pages_available(vcpu) < 0) {
> spin_unlock(&vcpu->kvm->mmu_lock);
> - return 1;
> + return -ENOSPC;
> }
> sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
> vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
> @@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
> spin_lock(&vcpu->kvm->mmu_lock);
> if (make_mmu_pages_available(vcpu) < 0) {
> spin_unlock(&vcpu->kvm->mmu_lock);
> - return 1;
> + return -ENOSPC;
> }
> sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
> 0, ACC_ALL);
>
Queued, thanks.