kvm: x86: fix RSM when PCID is non-zero

rsm_load_state_64() and rsm_enter_protected_mode() load CR3, then
CR4 & ~PCIDE, then CR0, then CR4.

However, setting CR4.PCIDE fails if CR3[11:0] != 0.  It's probably easier
in the long run to replace rsm_enter_protected_mode() with an emulator
callback that sets all the special registers (like KVM_SET_SREGS would
do).  For now, set the PCID field of CR3 only after CR4.PCIDE is 1.

Reported-by: Laszlo Ersek <lersek@redhat.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Fixes: 660a5d517aaab9187f93854425c4c63f4a09195c
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index abe74f7..b514b2b 100644 (file)
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2390,9 +2390,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 }
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
-                                    u64 cr0, u64 cr4)
+                                   u64 cr0, u64 cr3, u64 cr4)
 {
        int bad;
+       u64 pcid;
+
+       /* In order to later set CR4.PCIDE, CR3[11:0] must be zero.  */
+       pcid = 0;
+       if (cr4 & X86_CR4_PCIDE) {
+               pcid = cr3 & 0xfff;
+               cr3 &= ~0xfff;
+       }
+
+       bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+       if (bad)
+               return X86EMUL_UNHANDLEABLE;
 
        /*
         * First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2411,6 +2423,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
                bad = ctxt->ops->set_cr(ctxt, 4, cr4);
                if (bad)
                        return X86EMUL_UNHANDLEABLE;
+               if (pcid) {
+                       bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+                       if (bad)
+                               return X86EMUL_UNHANDLEABLE;
+               }
+
        }
 
        return X86EMUL_CONTINUE;
@@ -2421,11 +2439,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
        struct desc_struct desc;
        struct desc_ptr dt;
        u16 selector;
-       u32 val, cr0, cr4;
+       u32 val, cr0, cr3, cr4;
        int i;
 
        cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-       ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+       cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
        ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
        ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
 
@@ -2467,14 +2485,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 
        ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
 
-       return rsm_enter_protected_mode(ctxt, cr0, cr4);
+       return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
 static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 {
        struct desc_struct desc;
        struct desc_ptr dt;
-       u64 val, cr0, cr4;
+       u64 val, cr0, cr3, cr4;
        u32 base3;
        u16 selector;
        int i, r;
@@ -2491,7 +2509,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
        ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
        cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-       ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+       cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
        cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
        ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
        val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2519,7 +2537,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
        dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
        ctxt->ops->set_gdt(ctxt, &dt);
 
-       r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+       r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
        if (r != X86EMUL_CONTINUE)
                return r;