x86/vvmx: make updating shadow EPTP value more efficient

At the moment, the shadow EPTP value is written unconditionally in
ept_handle_violation().

Instead, write the value on vmentry to the guest; but only write it if
the value needs updating.

To detect this, add a flag to the nestedvcpu struct, stale_np2m, to
indicate when such an action is necessary.  Set it when the nested p2m
changes or when the np2m is flushed by an IPI, and clear it when we
write the new value.

Since an IPI invalidating the p2m may happen between
nvmx_switch_guest() and vmx_vmenter, but we can't perform the vmwrite
with interrupts disabled, check the flag just before entering the
guest and restart the vmentry if it's set.

Signed-off-by: Sergey Dyasli <sergey.dyasli@citrix.com>
Signed-off-by: George Dunlap <george.dunlap@citrix.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Jun Nakajima <jun.nakajima@intel.com>

diff --git a/xen/arch/x86/hvm/nestedhvm.c b/xen/arch/x86/hvm/nestedhvm.c
index f2f7469d86a1dc5d2a700e61086b7dda3b9e57a6..74a464d16201298ae21b51f6d1e32882e3e5944f 100644 (file)
--- a/xen/arch/x86/hvm/nestedhvm.c
+++ b/xen/arch/x86/hvm/nestedhvm.c
@@ -56,6 +56,7 @@ nestedhvm_vcpu_reset(struct vcpu *v)
     nv->nv_vvmcxaddr = INVALID_PADDR;
     nv->nv_flushp2m = 0;
     nv->nv_p2m = NULL;
+    nv->stale_np2m = false;
 
     hvm_asid_flush_vcpu_asid(&nv->nv_n2asid);
 
@@ -107,6 +108,7 @@ nestedhvm_flushtlb_ipi(void *info)
      */
     hvm_asid_flush_core();
     vcpu_nestedhvm(v).nv_p2m = NULL;
+    vcpu_nestedhvm(v).stale_np2m = true;
 }
 
 void

diff --git a/xen/arch/x86/hvm/vmx/entry.S b/xen/arch/x86/hvm/vmx/entry.S
index 53eedc63631c99639c62c65c66739bade7b8dda1..47cd67426053b090804ef365d4bf82cd739a539b 100644 (file)
--- a/xen/arch/x86/hvm/vmx/entry.S
+++ b/xen/arch/x86/hvm/vmx/entry.S
@@ -79,6 +79,8 @@ UNLIKELY_END(realmode)
 
         mov  %rsp,%rdi
         call vmx_vmenter_helper
+        test %al, %al
+        jz .Lvmx_vmentry_restart
         mov  VCPU_hvm_guest_cr2(%rbx),%rax
 
         pop  %r15
@@ -117,6 +119,10 @@ ENTRY(vmx_asm_do_vmentry)
         GET_CURRENT(bx)
         jmp  .Lvmx_do_vmentry
 
+.Lvmx_vmentry_restart:
+        sti
+        jmp  .Lvmx_do_vmentry
+
 .Lvmx_goto_emulator:
         sti
         mov  %rsp,%rdi

diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 9cfa9b6965898f918af295d6064ec21a6ed5eb02..a5c2bd71cd2151243166f3bfde8a17b521ecd1a5 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -3249,12 +3249,6 @@ static void ept_handle_violation(ept_qual_t q, paddr_t gpa)
     case 0:         // Unhandled L1 EPT violation
         break;
     case 1:         // This violation is handled completly
-        /*Current nested EPT maybe flushed by other vcpus, so need
-         * to re-set its shadow EPTP pointer.
-         */
-        if ( nestedhvm_vcpu_in_guestmode(current) &&
-                        nestedhvm_paging_mode_hap(current ) )
-            __vmwrite(EPT_POINTER, get_shadow_eptp(current));
         return;
     case -1:        // This vioaltion should be injected to L1 VMM
         vcpu_nestedhvm(current).nv_vmexit_pending = 1;
@@ -4203,13 +4197,18 @@ static void lbr_fixup(void)
         bdw_erratum_bdf14_fixup();
 }
 
-void vmx_vmenter_helper(const struct cpu_user_regs *regs)
+/* Returns false if the vmentry has to be restarted */
+bool vmx_vmenter_helper(const struct cpu_user_regs *regs)
 {
     struct vcpu *curr = current;
     u32 new_asid, old_asid;
     struct hvm_vcpu_asid *p_asid;
     bool_t need_flush;
 
+    /* Shadow EPTP can't be updated here because irqs are disabled */
+     if ( nestedhvm_vcpu_in_guestmode(curr) && vcpu_nestedhvm(curr).stale_np2m )
+         return false;
+
     if ( curr->domain->arch.hvm_domain.pi_ops.do_resume )
         curr->domain->arch.hvm_domain.pi_ops.do_resume(curr);
 
@@ -4270,6 +4269,8 @@ void vmx_vmenter_helper(const struct cpu_user_regs *regs)
     __vmwrite(GUEST_RIP,    regs->rip);
     __vmwrite(GUEST_RSP,    regs->rsp);
     __vmwrite(GUEST_RFLAGS, regs->rflags | X86_EFLAGS_MBS);
+
+    return true;
 }
 
 /*

diff --git a/xen/arch/x86/hvm/vmx/vvmx.c b/xen/arch/x86/hvm/vmx/vvmx.c
index 2f468e6ced3f7b11aae51f547e8db6a313216efc..3f596dc698677aa9688ebf4765a9ea1dd841a133 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vvmx.c
+++ b/xen/arch/x86/hvm/vmx/vvmx.c
@@ -1405,12 +1405,34 @@ static void virtual_vmexit(struct cpu_user_regs *regs)
     vmsucceed(regs);
 }
 
+static void nvmx_eptp_update(void)
+{
+    struct vcpu *curr = current;
+
+    if ( !nestedhvm_vcpu_in_guestmode(curr) ||
+          vcpu_nestedhvm(curr).nv_vmexit_pending ||
+         !vcpu_nestedhvm(curr).stale_np2m ||
+         !nestedhvm_paging_mode_hap(curr) )
+        return;
+
+    /*
+     * Interrupts are enabled here, so we need to clear stale_np2m
+     * before we do the vmwrite.  If we do it in the other order, an
+     * and IPI comes in changing the shadow eptp after the vmwrite,
+     * we'll complete the vmenter with a stale eptp value.
+     */
+    vcpu_nestedhvm(curr).stale_np2m = false;
+    __vmwrite(EPT_POINTER, get_shadow_eptp(curr));
+}
+
 void nvmx_switch_guest(void)
 {
     struct vcpu *v = current;
     struct nestedvcpu *nvcpu = &vcpu_nestedhvm(v);
     struct cpu_user_regs *regs = guest_cpu_user_regs();
 
+    nvmx_eptp_update();
+
     /*
      * A pending IO emulation may still be not finished. In this case, no
      * virtual vmswitch is allowed. Or else, the following IO emulation will

diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 0bd7342bdd4178cf6630d9dccbe775159c5748a5..6d7932ff87ac86738713c135ed0b737c5e8aa584 100644 (file)
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1830,6 +1830,12 @@ static void assign_np2m(struct vcpu *v, struct p2m_domain *p2m)
     cpumask_set_cpu(v->processor, p2m->dirty_cpumask);
 }
 
+static void nvcpu_flush(struct vcpu *v)
+{
+    hvm_asid_flush_vcpu(v);
+    vcpu_nestedhvm(v).stale_np2m = true;
+}
+
 struct p2m_domain *
 p2m_get_nestedp2m_locked(struct vcpu *v)
 {
@@ -1853,7 +1859,7 @@ p2m_get_nestedp2m_locked(struct vcpu *v)
         if ( p2m->np2m_base == np2m_base || p2m->np2m_base == P2M_BASE_EADDR )
         {
             if ( p2m->np2m_base == P2M_BASE_EADDR )
-                hvm_asid_flush_vcpu(v);
+                nvcpu_flush(v);
             p2m->np2m_base = np2m_base;
             assign_np2m(v, p2m);
             nestedp2m_unlock(d);
@@ -1869,7 +1875,7 @@ p2m_get_nestedp2m_locked(struct vcpu *v)
     p2m_flush_table(p2m);
     p2m_lock(p2m);
     p2m->np2m_base = np2m_base;
-    hvm_asid_flush_vcpu(v);
+    nvcpu_flush(v);
     assign_np2m(v, p2m);
     nestedp2m_unlock(d);
 

diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
index 6c54773f1c02316cb275916bd80ee4061c76cda9..27330242e3ea85794a0787978346b1feb0e2e111 100644 (file)
--- a/xen/include/asm-x86/hvm/vcpu.h
+++ b/xen/include/asm-x86/hvm/vcpu.h
@@ -115,6 +115,7 @@ struct nestedvcpu {
 
     bool_t nv_flushp2m; /* True, when p2m table must be flushed */
     struct p2m_domain *nv_p2m; /* used p2m table for this vcpu */
+    bool stale_np2m; /* True when p2m_base in VMCx02 is no longer valid */
 
     struct hvm_vcpu_asid nv_n2asid;