x86/HVM: extend LAPIC shortcuts around P2M lookups

... to all internally handled MMIO regions. It is in particular the
HPET page that, e.g. on Windows Server 2012 R2, can get heavily
accessed, and hence avoiding the unnecessary lookups is rather
beneficial (in the reported case a 40+-vCPU guest would previously not
have booted at all while with hvm_hap_nested_page_fault() shortcut
alone it was able to boot up in 18 minutes [i.e. still room for
improvement]).

Note the apparently unrelated addition of a is_hvm_vcpu() check to the
__hvm_copy() code: Afaict for PVH this shortcut should never have taken
effect (since there's no LAPIC in that case).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Tim Deegan <tim@xen.org>

diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index e8344066764ffd8fc9718c807b1984d589a8352d..31629e729cc50c52a7688c6cfbc719fd99f4bb5d 100644 (file)
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -2779,11 +2779,14 @@ int hvm_hap_nested_page_fault(paddr_t gpa,
         }
     }
 
-    /* For the benefit of 32-bit WinXP (& older Windows) on AMD CPUs,
-     * a fast path for LAPIC accesses, skipping the p2m lookup. */
+    /*
+     * No need to do the P2M lookup for internally handled MMIO, benefiting
+     * - 32-bit WinXP (& older Windows) on AMD CPUs for LAPIC accesses,
+     * - newer Windows (like Server 2012) for HPET accesses.
+     */
     if ( !nestedhvm_vcpu_in_guestmode(v)
          && is_hvm_vcpu(v)
-         && gfn == PFN_DOWN(vlapic_base_address(vcpu_vlapic(v))) )
+         && hvm_mmio_internal(gpa) )
     {
         if ( !handle_mmio() )
             hvm_inject_hw_exception(TRAP_gp_fault, 0);
@@ -3892,7 +3895,9 @@ static enum hvm_copy_result __hvm_copy(
 
     while ( todo > 0 )
     {
-        count = min_t(int, PAGE_SIZE - (addr & ~PAGE_MASK), todo);
+        paddr_t gpa = addr & ~PAGE_MASK;
+
+        count = min_t(int, PAGE_SIZE - gpa, todo);
 
         if ( flags & HVMCOPY_virt )
         {
@@ -3907,16 +3912,22 @@ static enum hvm_copy_result __hvm_copy(
                     hvm_inject_page_fault(pfec, addr);
                 return HVMCOPY_bad_gva_to_gfn;
             }
+            gpa |= (paddr_t)gfn << PAGE_SHIFT;
         }
         else
         {
             gfn = addr >> PAGE_SHIFT;
+            gpa = addr;
         }
 
-        /* For the benefit of 32-bit WinXP (& older Windows) on AMD CPUs,
-         * a fast path for LAPIC accesses, skipping the p2m lookup. */
+        /*
+         * No need to do the P2M lookup for internally handled MMIO, benefiting
+         * - 32-bit WinXP (& older Windows) on AMD CPUs for LAPIC accesses,
+         * - newer Windows (like Server 2012) for HPET accesses.
+         */
         if ( !nestedhvm_vcpu_in_guestmode(curr)
-             && gfn == PFN_DOWN(vlapic_base_address(vcpu_vlapic(curr))) )
+             && is_hvm_vcpu(curr)
+             && hvm_mmio_internal(gpa) )
             return HVMCOPY_bad_gfn_to_mfn;
 
         page = get_page_from_gfn(curr->domain, gfn, &p2mt, P2M_UNSHARE);

diff --git a/xen/arch/x86/hvm/intercept.c b/xen/arch/x86/hvm/intercept.c
index 7cc13b5edd229c25b83066192fb8f456bd123a17..797eedf33f6c49ff0fe953ace59b48f9ba3cfd01 100644 (file)
--- a/xen/arch/x86/hvm/intercept.c
+++ b/xen/arch/x86/hvm/intercept.c
@@ -163,6 +163,18 @@ static int hvm_mmio_access(struct vcpu *v,
     return rc;
 }
 
+bool_t hvm_mmio_internal(paddr_t gpa)
+{
+    struct vcpu *curr = current;
+    unsigned int i;
+
+    for ( i = 0; i < HVM_MMIO_HANDLER_NR; ++i )
+        if ( hvm_mmio_handlers[i]->check_handler(curr, gpa) )
+            return 1;
+
+    return 0;
+}
+
 int hvm_mmio_intercept(ioreq_t *p)
 {
     struct vcpu *v = current;

diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
index 8228ab8cd759e3b88e1915ae90a509c97c739c2a..c7ac5664604e81f57e2c1f79e608544c862b6127 100644 (file)
--- a/xen/include/asm-x86/hvm/io.h
+++ b/xen/include/asm-x86/hvm/io.h
@@ -91,6 +91,7 @@ static inline int hvm_buffered_io_intercept(ioreq_t *p)
     return hvm_io_intercept(p, HVM_BUFFERED_IO);
 }
 
+bool_t hvm_mmio_internal(paddr_t gpa);
 int hvm_mmio_intercept(ioreq_t *p);
 int hvm_buffered_io_send(ioreq_t *p);