KVM: Add PV MSR to enable asynchronous page faults delivery.

Guest enables async PF vcpu functionality using this MSR.

Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

3 files changed, 42 insertions, 2 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c3076bcf5ef7..0d7039804b4c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -419,6 +419,8 @@ struct kvm_vcpu_arch {
         struct {
                 bool halted;
                 gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+                struct gfn_to_hva_cache data;
+                u64 msr_val;
         } apf;
 };
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index e3faaaf4301e..8662ae0a035c 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -20,6 +20,7 @@
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
+#define KVM_FEATURE_ASYNC_PF            4
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -32,9 +33,12 @@
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+#define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 
 #define KVM_MAX_MMU_OP_BATCH           32
 
+#define KVM_ASYNC_PF_ENABLED                    (1 << 0)
+
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
 #define KVM_MMU_OP_FLUSH_TLB            2
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd254779d1cc..063c07296764 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -783,12 +783,12 @@ EXPORT_SYMBOL_GPL(kvm_get_dr);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN     7
+#define KVM_SAVE_MSRS_BEGIN     8
 static u32 msrs_to_save[] = {
         MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
         MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
         HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
-        HV_X64_MSR_APIC_ASSIST_PAGE,
+        HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN,
         MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
         MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -1425,6 +1425,29 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
         return 0;
 }
 
+static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
+{
+        gpa_t gpa = data & ~0x3f;
+
+        /* Bits 1:5 are resrved, Should be zero */
+        if (data & 0x3e)
+                return 1;
+
+        vcpu->arch.apf.msr_val = data;
+
+        if (!(data & KVM_ASYNC_PF_ENABLED)) {
+                kvm_clear_async_pf_completion_queue(vcpu);
+                kvm_async_pf_hash_reset(vcpu);
+                return 0;
+        }
+
+        if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+                return 1;
+
+        kvm_async_pf_wakeup_all(vcpu);
+        return 0;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
         switch (msr) {
@@ -1506,6 +1529,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
                 }
                 break;
         }
+        case MSR_KVM_ASYNC_PF_EN:
+                if (kvm_pv_enable_async_pf(vcpu, data))
+                        return 1;
+                break;
         case MSR_IA32_MCG_CTL:
         case MSR_IA32_MCG_STATUS:
         case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
@@ -1782,6 +1809,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
         case MSR_KVM_SYSTEM_TIME_NEW:
                 data = vcpu->arch.time;
                 break;
+        case MSR_KVM_ASYNC_PF_EN:
+                data = vcpu->arch.apf.msr_val;
+                break;
         case MSR_IA32_P5_MC_ADDR:
         case MSR_IA32_P5_MC_TYPE:
         case MSR_IA32_MCG_CAP:
@@ -1929,6 +1959,7 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_DEBUGREGS:
         case KVM_CAP_X86_ROBUST_SINGLESTEP:
         case KVM_CAP_XSAVE:
+        case KVM_CAP_ASYNC_PF:
                 r = 1;
                 break;
         case KVM_CAP_COALESCED_MMIO:
@@ -5792,6 +5823,8 @@ free_vcpu:
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+        vcpu->arch.apf.msr_val = 0;
+
         vcpu_load(vcpu);
         kvm_mmu_unload(vcpu);
         vcpu_put(vcpu);
@@ -5811,6 +5844,7 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
         vcpu->arch.dr7 = DR7_FIXED_1;
 
         kvm_make_request(KVM_REQ_EVENT, vcpu);
+        vcpu->arch.apf.msr_val = 0;
 
         kvm_clear_async_pf_completion_queue(vcpu);
         kvm_async_pf_hash_reset(vcpu);