nested vmx: emulate MSR bitmaps

In nested vmx virtualization for MSR bitmaps, L0 hypervisor will trap
all the VM exit from L2 guest by disable the MSR_BITMAP feature. When
handling this VM exit, L0 hypervisor judges whether L1 hypervisor uses
MSR_BITMAP feature and the corresponding bit is set to 1. If so, L0
will inject such VM exit into L1 hypervisor; otherwise, L0 will be
responsible for handling this VM exit.

Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Committed-by: Keir Fraser <keir@xen.org>

diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index 0fbdd751c0cd5f67c9419bbd0362bc6f7a0b8127..205e70556b78e5373fac1b7c658c322c465f4628 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -673,6 +673,34 @@ void vmx_disable_intercept_for_msr(struct vcpu *v, u32 msr, int type)
     }
 }
 
+/*
+ * access_type: read == 0, write == 1
+ */
+int vmx_check_msr_bitmap(unsigned long *msr_bitmap, u32 msr, int access_type)
+{
+    int ret = 1;
+    if ( !msr_bitmap )
+        return 1;
+
+    if ( msr <= 0x1fff )
+    {
+        if ( access_type == 0 )
+            ret = test_bit(msr, msr_bitmap + 0x000/BYTES_PER_LONG); /* read-low */
+        else if ( access_type == 1 )
+            ret = test_bit(msr, msr_bitmap + 0x800/BYTES_PER_LONG); /* write-low */
+    }
+    else if ( (msr >= 0xc0000000) && (msr <= 0xc0001fff) )
+    {
+        msr &= 0x1fff;
+        if ( access_type == 0 )
+            ret = test_bit(msr, msr_bitmap + 0x400/BYTES_PER_LONG); /* read-high */
+        else if ( access_type == 1 )
+            ret = test_bit(msr, msr_bitmap + 0xc00/BYTES_PER_LONG); /* write-high */
+    }
+    return ret;
+}
+
+
 /*
  * Switch VMCS between layer 1 & 2 guest
  */

diff --git a/xen/arch/x86/hvm/vmx/vvmx.c b/xen/arch/x86/hvm/vmx/vvmx.c
index ed47780a67d74d9cca32fb93045842c36455b725..719bfce0eff52130bb7b19bbfcdefd140c15f734 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vvmx.c
+++ b/xen/arch/x86/hvm/vmx/vvmx.c
@@ -48,6 +48,7 @@ int nvmx_vcpu_initialise(struct vcpu *v)
     nvmx->intr.error_code = 0;
     nvmx->iobitmap[0] = NULL;
     nvmx->iobitmap[1] = NULL;
+    nvmx->msrbitmap = NULL;
     return 0;
 out:
     return -ENOMEM;
@@ -561,6 +562,17 @@ static void __clear_current_vvmcs(struct vcpu *v)
         __vmpclear(virt_to_maddr(nvcpu->nv_n2vmcx));
 }
 
+static void __map_msr_bitmap(struct vcpu *v)
+{
+    struct nestedvmx *nvmx = &vcpu_2_nvmx(v);
+    unsigned long gpa;
+
+    if ( nvmx->msrbitmap )
+        hvm_unmap_guest_frame (nvmx->msrbitmap); 
+    gpa = __get_vvmcs(vcpu_nestedhvm(v).nv_vvmcx, MSR_BITMAP);
+    nvmx->msrbitmap = hvm_map_guest_frame_ro(gpa >> PAGE_SHIFT);
+}
+
 static void __map_io_bitmap(struct vcpu *v, u64 vmcs_reg)
 {
     struct nestedvmx *nvmx = &vcpu_2_nvmx(v);
@@ -597,6 +609,10 @@ static void nvmx_purge_vvmcs(struct vcpu *v)
             nvmx->iobitmap[i] = NULL;
         }
     }
+    if ( nvmx->msrbitmap ) {
+        hvm_unmap_guest_frame(nvmx->msrbitmap);
+        nvmx->msrbitmap = NULL;
+    }
 }
 
 u64 nvmx_get_tsc_offset(struct vcpu *v)
@@ -1153,6 +1169,7 @@ int nvmx_handle_vmptrld(struct cpu_user_regs *regs)
         nvcpu->nv_vvmcx = hvm_map_guest_frame_rw(gpa >> PAGE_SHIFT);
         nvcpu->nv_vvmcxaddr = gpa;
         map_io_bitmap_all (v);
+        __map_msr_bitmap(v);
     }
 
     vmreturn(regs, VMSUCCEED);
@@ -1270,6 +1287,9 @@ int nvmx_handle_vmwrite(struct cpu_user_regs *regs)
               vmcs_encoding == IO_BITMAP_B_HIGH )
         __map_io_bitmap (v, IO_BITMAP_B);
 
+    if ( vmcs_encoding == MSR_BITMAP || vmcs_encoding == MSR_BITMAP_HIGH )
+        __map_msr_bitmap(v);
+
     vmreturn(regs, VMSUCCEED);
     return X86EMUL_OKAY;
 }
@@ -1320,6 +1340,7 @@ int nvmx_msr_read_intercept(unsigned int msr, u64 *msr_content)
                CPU_BASED_RDTSC_EXITING |
                CPU_BASED_MONITOR_TRAP_FLAG |
                CPU_BASED_VIRTUAL_NMI_PENDING |
+               CPU_BASED_ACTIVATE_MSR_BITMAP |
                CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
         /* bit 1, 4-6,8,13-16,26 must be 1 (refer G4 of SDM) */
         tmp = ( (1<<26) | (0xf << 13) | 0x100 | (0x7 << 4) | 0x2);
@@ -1497,8 +1518,6 @@ int nvmx_n2_vmexit_handler(struct cpu_user_regs *regs,
     case EXIT_REASON_TRIPLE_FAULT:
     case EXIT_REASON_TASK_SWITCH:
     case EXIT_REASON_CPUID:
-    case EXIT_REASON_MSR_READ:
-    case EXIT_REASON_MSR_WRITE:
     case EXIT_REASON_VMCALL:
     case EXIT_REASON_VMCLEAR:
     case EXIT_REASON_VMLAUNCH:
@@ -1514,6 +1533,22 @@ int nvmx_n2_vmexit_handler(struct cpu_user_regs *regs,
         /* inject to L1 */
         nvcpu->nv_vmexit_pending = 1;
         break;
+    case EXIT_REASON_MSR_READ:
+    case EXIT_REASON_MSR_WRITE:
+    {
+        int status;
+        ctrl = __n2_exec_control(v);
+        if ( ctrl & CPU_BASED_ACTIVATE_MSR_BITMAP )
+        {
+            status = vmx_check_msr_bitmap(nvmx->msrbitmap, regs->ecx,
+                         !!(exit_reason == EXIT_REASON_MSR_WRITE));
+            if ( status )
+                nvcpu->nv_vmexit_pending = 1;
+        }
+        else
+            nvcpu->nv_vmexit_pending = 1;
+        break;
+    }
     case EXIT_REASON_IO_INSTRUCTION:
         ctrl = __n2_exec_control(v);
         if ( ctrl & CPU_BASED_ACTIVATE_IO_BITMAP )

diff --git a/xen/include/asm-x86/hvm/vmx/vmcs.h b/xen/include/asm-x86/hvm/vmx/vmcs.h
index cc92f6964343793bb6b8d51a1763898b231577e2..14ac7736a052106c1f6e9fd303afcf93809faf76 100644 (file)
--- a/xen/include/asm-x86/hvm/vmx/vmcs.h
+++ b/xen/include/asm-x86/hvm/vmx/vmcs.h
@@ -427,6 +427,7 @@ int vmx_add_host_load_msr(u32 msr);
 void vmx_vmcs_switch(struct vmcs_struct *from, struct vmcs_struct *to);
 void vmx_set_eoi_exit_bitmap(struct vcpu *v, u8 vector);
 void vmx_clear_eoi_exit_bitmap(struct vcpu *v, u8 vector);
+int vmx_check_msr_bitmap(unsigned long *msr_bitmap, u32 msr, int access_type);
 
 #endif /* ASM_X86_HVM_VMX_VMCS_H__ */
 

diff --git a/xen/include/asm-x86/hvm/vmx/vvmx.h b/xen/include/asm-x86/hvm/vmx/vvmx.h
index b9137b83f8c4efbf931de0085042691965d2ef12..067fbe413e2c41544674af8ce95b715aa78f3a87 100644 (file)
--- a/xen/include/asm-x86/hvm/vmx/vvmx.h
+++ b/xen/include/asm-x86/hvm/vmx/vvmx.h
@@ -26,6 +26,7 @@
 struct nestedvmx {
     paddr_t    vmxon_region_pa;
     void       *iobitmap[2];           /* map (va) of L1 guest I/O bitmap */
+    void       *msrbitmap;             /* map (va) of L1 guest MSR bitmap */
     /* deferred nested interrupt */
     struct {
         unsigned long intr_info;