From: Paolo Bonzini <pbonzini@xxxxxxxxxx>
commit e61ab42de874c5af8c5d98b327c77a374d9e7da1 upstream.
It is error-prone that code after vmexit cannot access percpu data
because GSBASE has not been restored yet. It forces MSR_IA32_SPEC_CTRL
save/restore to happen very late, after the predictor untraining
sequence, and it gets in the way of return stack depth tracking
(a retbleed mitigation that is in linux-next as of 2022-11-09).
As a first step towards fixing that, move the VMCB VMSAVE/VMLOAD to
assembly, essentially undoing commit fb0c4a4fee5a ("KVM: SVM: move
VMLOAD/VMSAVE to C code", 2021-03-15). The reason for that commit was
that it made it simpler to use a different VMCB for VMLOAD/VMSAVE versus
VMRUN; but that is not a big hassle anymore thanks to the kvm-asm-offsets
machinery and other related cleanups.
The idea on how to number the exception tables is stolen from
a prototype patch by Peter Zijlstra.
Cc: stable@xxxxxxxxxxxxxxx
Fixes: a149180fbcf3 ("x86: Add magic AMD return-thunk")
Link: <https://lore.kernel.org/all/f571e404-e625-bae1-10e9-449b2eb4cbd8@xxxxxxxxxx/>
Reviewed-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/kvm-asm-offsets.c | 1
arch/x86/kvm/svm/svm.c | 9 -------
arch/x86/kvm/svm/vmenter.S | 49 +++++++++++++++++++++++++++++++----------
3 files changed, 39 insertions(+), 20 deletions(-)
--- a/arch/x86/kvm/kvm-asm-offsets.c
+++ b/arch/x86/kvm/kvm-asm-offsets.c
@@ -16,6 +16,7 @@ static void __used common(void)
BLANK();
OFFSET(SVM_vcpu_arch_regs, vcpu_svm, vcpu.arch.regs);
OFFSET(SVM_current_vmcb, vcpu_svm, current_vmcb);
+ OFFSET(SVM_vmcb01, vcpu_svm, vmcb01);
OFFSET(KVM_VMCB_pa, kvm_vmcb_info, pa);
}
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3923,16 +3923,7 @@ static noinstr void svm_vcpu_enter_exit(
} else {
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
- /*
- * Use a single vmcb (vmcb01 because it's always valid) for
- * context switching guest state via VMLOAD/VMSAVE, that way
- * the state doesn't need to be copied between vmcb01 and
- * vmcb02 when switching vmcbs for nested virtualization.
- */
- vmload(svm->vmcb01.pa);
__svm_vcpu_run(svm);
- vmsave(svm->vmcb01.pa);
-
vmload(__sme_page_pa(sd->save_area));
}
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -28,6 +28,8 @@
#define VCPU_R15 (SVM_vcpu_arch_regs + __VCPU_REGS_R15 * WORD_SIZE)
#endif
+#define SVM_vmcb01_pa (SVM_vmcb01 + KVM_VMCB_pa)
+
.section .noinstr.text, "ax"
/**
@@ -55,6 +57,16 @@ SYM_FUNC_START(__svm_vcpu_run)
mov %_ASM_ARG1, %_ASM_DI
.endif
+ /*
+ * Use a single vmcb (vmcb01 because it's always valid) for
+ * context switching guest state via VMLOAD/VMSAVE, that way
+ * the state doesn't need to be copied between vmcb01 and
+ * vmcb02 when switching vmcbs for nested virtualization.
+ */
+ mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+1: vmload %_ASM_AX
+2:
+
/* Get svm->current_vmcb->pa into RAX. */
mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
@@ -80,16 +92,11 @@ SYM_FUNC_START(__svm_vcpu_run)
/* Enter guest mode */
sti
-1: vmrun %_ASM_AX
-
-2: cli
-
-#ifdef CONFIG_RETPOLINE
- /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
- FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
-#endif
+3: vmrun %_ASM_AX
+4:
+ cli
- /* "POP" @svm to RAX. */
+ /* Pop @svm to RAX while it's the only available register. */
pop %_ASM_AX
/* Save all guest registers. */
@@ -110,6 +117,18 @@ SYM_FUNC_START(__svm_vcpu_run)
mov %r15, VCPU_R15(%_ASM_AX)
#endif
+ /* @svm can stay in RDI from now on. */
+ mov %_ASM_AX, %_ASM_DI
+
+ mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+5: vmsave %_ASM_AX
+6:
+
+#ifdef CONFIG_RETPOLINE
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+#endif
+
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
* untrained as soon as we exit the VM and are back to the
@@ -159,11 +178,19 @@ SYM_FUNC_START(__svm_vcpu_run)
pop %_ASM_BP
RET
-3: cmpb $0, kvm_rebooting
+10: cmpb $0, kvm_rebooting
jne 2b
ud2
+30: cmpb $0, kvm_rebooting
+ jne 4b
+ ud2
+50: cmpb $0, kvm_rebooting
+ jne 6b
+ ud2
- _ASM_EXTABLE(1b, 3b)
+ _ASM_EXTABLE(1b, 10b)
+ _ASM_EXTABLE(3b, 30b)
+ _ASM_EXTABLE(5b, 50b)
SYM_FUNC_END(__svm_vcpu_run)
