KVM: Allow not-present guest page faults to bypass kvm

There are two classes of page faults trapped by kvm:
 - host page faults, where the fault is needed to allow kvm to install
   the shadow pte or update the guest accessed and dirty bits
 - guest page faults, where the guest has faulted and kvm simply injects
   the fault back into the guest to handle

The second class, guest page faults, is pure overhead.  We can eliminate
some of it on vmx using the following evil trick:
 - when we set up a shadow page table entry, if the corresponding guest pte
   is not present, set up the shadow pte as not present
 - if the guest pte _is_ present, mark the shadow pte as present but also
   set one of the reserved bits in the shadow pte
 - tell the vmx hardware not to trap faults which have the present bit clear

With this, normal page-not-present faults go directly to the guest,
bypassing kvm entirely.

Unfortunately, this trick only works on Intel hardware, as AMD lacks a
way to discriminate among page faults based on error code.  It is also
a little risky since it uses reserved bits which might become unreserved
in the future, so a module parameter is provided to disable it.

Signed-off-by: Avi Kivity <avi@qumranet.com>

1 files changed, 9 insertions, 2 deletions

diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 8eb49e055ec0..27a3318fa6c2 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
+#include <linux/moduleparam.h>
 
 #include <asm/io.h>
 #include <asm/desc.h>
@@ -33,6 +34,9 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+static int bypass_guest_pf = 1;
+module_param(bypass_guest_pf, bool, 0);
+
 struct vmcs {
 	u32 revision_id;
 	u32 abort;
@@ -1535,8 +1539,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	}
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
 
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
+	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
 	vmcs_write32(CR3_TARGET_COUNT, 0);           /* 22.2.1 */
 
 	vmcs_writel(HOST_CR0, read_cr0());  /* 22.2.3 */
@@ -2582,6 +2586,9 @@ static int __init vmx_init(void)
 	if (r)
 		goto out1;
 
+	if (bypass_guest_pf)
+		kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
+
 	return 0;
 
 out1: