x86: vMCE emulation

This patch provides virtual MCE support to guest. It emulates a simple
and clean MCE MSRs interface to guest by faking caps to guest if needed
and masking caps if unnecessary:
1. Providing a well-defined MCG_CAP to guest, filter out un-necessary
   caps and provide only guest needed caps;
2. Disabling MCG_CTL to avoid model specific;
3. Sticking all 1's to MCi_CTL to guest to avoid model specific;
4. Enabling CMCI cap but never really inject to guest to prevent
   polling periodically;
5. Masking MSCOD field of MCi_STATUS to avoid model specific;
6. Keeping natural semantics by per-vcpu instead of per-domain
   variables;
7. Using bank1 and reserving bank0 to work around 'bank0 quirk' of some
   very old processors;
8. Cleaning some vMCE# injection logic which shared by Intel and AMD
   but useless under new vMCE implement;
9. Keeping compatilbe w/ old xen version which has been backported to
   SLES11 SP2, so that old vMCE would not blocked when migrate to new
   vMCE;

Signed-off-by: Liu, Jinsong <jinsong.liu@intel.com>

- make printing consistent (and non-exploitable)
- fix return values of intel_mce_{rd,wr}msr() for out of range banks
- miscellaneous cleanup

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Committed-by: Jan Beulich <jbeulich@suse.com>

1 files changed, 19 insertions, 12 deletions

diff --git a/xen/include/asm-x86/mce.h b/xen/include/asm-x86/mce.h
index 922c94ac6a..a4eea47782 100644
--- a/xen/include/asm-x86/mce.h
+++ b/xen/include/asm-x86/mce.h
@@ -3,28 +3,35 @@
 #ifndef _XEN_X86_MCE_H
 #define _XEN_X86_MCE_H
 
-/* This entry is for recording bank nodes for the impacted domain,
- * put into impact_header list. */
-struct bank_entry {
-    struct list_head list;
-    uint16_t bank;
+/*
+ * Emulate 2 banks for guest
+ * Bank0: reserved for 'bank0 quirk' occur at some very old processors:
+ *   1). Intel cpu whose family-model value < 06-1A;
+ *   2). AMD K7
+ * Bank1: used to transfer error info to guest
+ */
+#define GUEST_MC_BANK_NUM 2
+
+/* Filter MSCOD model specific error code to guest */
+#define MCi_STATUS_MSCOD_MASK (~(0xffffULL << 16))
+
+/* No mci_ctl since it stick all 1's */
+struct vmce_bank {
     uint64_t mci_status;
     uint64_t mci_addr;
     uint64_t mci_misc;
+    uint64_t mci_ctl2;
 };
 
-struct domain_mca_msrs
-{
-    /* Guest should not change below values after DOM boot up */
+/* No mcg_ctl since it not expose to guest */
+struct vmce {
+    uint64_t mcg_cap;
     uint64_t mcg_status;
-    uint16_t nr_injection;
-    struct list_head impact_header;
     spinlock_t lock;
+    struct vmce_bank bank[GUEST_MC_BANK_NUM];
 };
 
 /* Guest vMCE MSRs virtualization */
-extern int vmce_init_msr(struct domain *d);
-extern void vmce_destroy_msr(struct domain *d);
 extern void vmce_init_vcpu(struct vcpu *);
 extern int vmce_restore_vcpu(struct vcpu *, uint64_t caps);
 extern int vmce_wrmsr(uint32_t msr, uint64_t val);