KVM: x86: smm: preserve interrupt shadow in SMRAM

When #SMI is asserted, the CPU can be in interrupt shadow due to sti or
mov ss.

It is not mandatory in  Intel/AMD prm to have the #SMI blocked during the
shadow, and on top of that, since neither SVM nor VMX has true support
for SMI window, waiting for one instruction would mean single stepping
the guest.

Instead, allow #SMI in this case, but both reset the interrupt window and
stash its value in SMRAM to restore it on exit from SMM.

This fixes rare failures seen mostly on windows guests on VMX, when #SMI
falls on the sti instruction which mainfest in VM entry failure due
to EFLAGS.IF not being set, but STI interrupt window still being set
in the VMCS.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20221025124741.228045-24-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index e3ecb1f..a9c1c2a 100644 (file)
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -27,7 +27,9 @@ static void check_smram_offsets(void)
        CHECK_SMRAM32_OFFSET(io_restart_rsi,            0xFF0C);
        CHECK_SMRAM32_OFFSET(io_restart_rip,            0xFF10);
        CHECK_SMRAM32_OFFSET(cr4,                       0xFF14);
-       CHECK_SMRAM32_OFFSET(reserved3,                 0xFF18);
+       CHECK_SMRAM32_OFFSET(reserved2,                 0xFF18);
+       CHECK_SMRAM32_OFFSET(int_shadow,                0xFF1A);
+       CHECK_SMRAM32_OFFSET(reserved3,                 0xFF1B);
        CHECK_SMRAM32_OFFSET(ds,                        0xFF2C);
        CHECK_SMRAM32_OFFSET(fs,                        0xFF38);
        CHECK_SMRAM32_OFFSET(gs,                        0xFF44);
@@ -73,7 +75,9 @@ static void check_smram_offsets(void)
        CHECK_SMRAM64_OFFSET(reserved1,                 0xFEC4);
        CHECK_SMRAM64_OFFSET(io_inst_restart,           0xFEC8);
        CHECK_SMRAM64_OFFSET(auto_hlt_restart,          0xFEC9);
-       CHECK_SMRAM64_OFFSET(reserved2,                 0xFECA);
+       CHECK_SMRAM64_OFFSET(amd_nmi_mask,              0xFECA);
+       CHECK_SMRAM64_OFFSET(int_shadow,                0xFECB);
+       CHECK_SMRAM64_OFFSET(reserved2,                 0xFECC);
        CHECK_SMRAM64_OFFSET(efer,                      0xFED0);
        CHECK_SMRAM64_OFFSET(svm_guest_flag,            0xFED8);
        CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa,        0xFEE0);
@@ -219,6 +223,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu,
        smram->cr4 = kvm_read_cr4(vcpu);
        smram->smm_revision = 0x00020000;
        smram->smbase = vcpu->arch.smbase;
+
+       smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
 }
 
 #ifdef CONFIG_X86_64
@@ -268,6 +274,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu,
        enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
        enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
        enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+       smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
 }
 #endif
 
@@ -313,6 +321,8 @@ void enter_smm(struct kvm_vcpu *vcpu)
        kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
        kvm_rip_write(vcpu, 0x8000);
 
+       static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
        cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
        static_call(kvm_x86_set_cr0)(vcpu, cr0);
        vcpu->arch.cr0 = cr0;
@@ -460,7 +470,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 {
        struct kvm_vcpu *vcpu = ctxt->vcpu;
        struct desc_ptr dt;
-       int i;
+       int i, r;
 
        ctxt->eflags =  smstate->eflags | X86_EFLAGS_FIXED;
        ctxt->_eip =  smstate->eip;
@@ -494,8 +504,16 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 
        vcpu->arch.smbase = smstate->smbase;
 
-       return rsm_enter_protected_mode(vcpu, smstate->cr0,
+       r = rsm_enter_protected_mode(vcpu, smstate->cr0,
                                        smstate->cr3, smstate->cr4);
+
+       if (r != X86EMUL_CONTINUE)
+               return r;
+
+       static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+       ctxt->interruptibility = (u8)smstate->int_shadow;
+
+       return r;
 }
 
 #ifdef CONFIG_X86_64
@@ -545,6 +563,9 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
        rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS);
        rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS);
 
+       static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+       ctxt->interruptibility = (u8)smstate->int_shadow;
+
        return X86EMUL_CONTINUE;
 }
 #endif

diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h
index 5202174..a1cf2ac 100644 (file)
--- a/arch/x86/kvm/smm.h
+++ b/arch/x86/kvm/smm.h
@@ -31,7 +31,9 @@ struct kvm_smram_state_32 {
        u32 cr4;
 
        /* A20M#, CPL, shutdown and other reserved/undocumented fields */
-       u32 reserved3[5];
+       u16 reserved2;
+       u8 int_shadow; /* KVM extension */
+       u8 reserved3[17];
 
        struct kvm_smm_seg_state_32 ds;
        struct kvm_smm_seg_state_32 fs;
@@ -95,7 +97,9 @@ struct kvm_smram_state_64 {
        u32 reserved1;
        u8 io_inst_restart;
        u8 auto_hlt_restart;
-       u8 reserved2[6];
+       u8 amd_nmi_mask; /* Documented in AMD BKDG as NMI mask, not used by KVM */
+       u8 int_shadow;
+       u32 reserved2;
 
        u64 efer;