KVM: vmx: Allow the guest to run with dirty debug registers

When not running in guest-debug mode (i.e. the guest controls the debug
registers, having to take an exit for each DR access is a waste of time.
If the guest gets into a state where each context switch causes DR to be
saved and restored, this can take away as much as 40% of the execution
time from the guest.

If the guest is running with vcpu->arch.db == vcpu->arch.eff_db, we
can let it write freely to the debug registers and reload them on the
next exit.  We still need to exit on the first access, so that the
KVM_DEBUGREG_WONT_EXIT flag is set in switch_db_regs; after that, further
accesses to the debug registers will not cause a vmexit.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 37 insertions, 1 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b2a913bb07e0..a9940ec9e215 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -43,6 +43,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/debugreg.h>
 #include <asm/kexec.h>
 
 #include "trace.h"
@@ -2850,7 +2851,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
                       vmx_capability.ept, vmx_capability.vpid);
         }
 
-        min = 0;
+        min = VM_EXIT_SAVE_DEBUG_CONTROLS;
 #ifdef CONFIG_X86_64
         min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
@@ -5084,6 +5085,22 @@ static int handle_dr(struct kvm_vcpu *vcpu)
                 }
         }
 
+        if (vcpu->guest_debug == 0) {
+                u32 cpu_based_vm_exec_control;
+
+                cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+                cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
+                vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+
+                /*
+                 * No more DR vmexits; force a reload of the debug registers
+                 * and reenter on this instruction.  The next vmexit will
+                 * retrieve the full state of the debug registers.
+                 */
+                vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT;
+                return 1;
+        }
+
         exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
         dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
         reg = DEBUG_REG_ACCESS_REG(exit_qualification);
@@ -5110,6 +5127,24 @@ static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
 {
 }
 
+static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+        u32 cpu_based_vm_exec_control;
+
+        get_debugreg(vcpu->arch.db[0], 0);
+        get_debugreg(vcpu->arch.db[1], 1);
+        get_debugreg(vcpu->arch.db[2], 2);
+        get_debugreg(vcpu->arch.db[3], 3);
+        get_debugreg(vcpu->arch.dr6, 6);
+        vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
+
+        vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
+
+        cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+        cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
+        vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+}
+
 static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
         vmcs_writel(GUEST_DR7, val);
@@ -8628,6 +8663,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
         .get_dr6 = vmx_get_dr6,
         .set_dr6 = vmx_set_dr6,
         .set_dr7 = vmx_set_dr7,
+        .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
         .cache_reg = vmx_cache_reg,
         .get_rflags = vmx_get_rflags,
         .set_rflags = vmx_set_rflags,