KVM: MMU: Consolidate two guest pte reads in kvm_mmu_pte_write()

kvm_mmu_pte_write() reads guest ptes in two different occasions, both to
allow a 32-bit pae guest to update a pte with 4-byte writes.  Consolidate
these into a single read, which also allows us to consolidate another read
from an invlpg speculating a gpte into the shadow page table.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4455ddb..91f8b17 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2560,36 +2560,11 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 }
 
 static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-                                         const u8 *new, int bytes)
+                                         u64 gpte)
 {
        gfn_t gfn;
-       int r;
-       u64 gpte = 0;
        pfn_t pfn;
 
-       if (bytes != 4 && bytes != 8)
-               return;
-
-       /*
-        * Assume that the pte write on a page table of the same type
-        * as the current vcpu paging mode.  This is nearly always true
-        * (might be false while changing modes).  Note it is verified later
-        * by update_pte().
-        */
-       if (is_pae(vcpu)) {
-               /* Handle a 32-bit guest writing two halves of a 64-bit gpte */
-               if ((bytes == 4) && (gpa % 4 == 0)) {
-                       r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8);
-                       if (r)
-                               return;
-                       memcpy((void *)&gpte + (gpa % 8), new, 4);
-               } else if ((bytes == 8) && (gpa % 8 == 0)) {
-                       memcpy((void *)&gpte, new, 8);
-               }
-       } else {
-               if ((bytes == 4) && (gpa % 4 == 0))
-                       memcpy((void *)&gpte, new, 4);
-       }
        if (!is_present_gpte(gpte))
                return;
        gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
@@ -2640,7 +2615,34 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        int r;
 
        pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
-       mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
+
+       switch (bytes) {
+       case 4:
+               gentry = *(const u32 *)new;
+               break;
+       case 8:
+               gentry = *(const u64 *)new;
+               break;
+       default:
+               gentry = 0;
+               break;
+       }
+
+       /*
+        * Assume that the pte write on a page table of the same type
+        * as the current vcpu paging mode.  This is nearly always true
+        * (might be false while changing modes).  Note it is verified later
+        * by update_pte().
+        */
+       if (is_pae(vcpu) && bytes == 4) {
+               /* Handle a 32-bit guest writing two halves of a 64-bit gpte */
+               gpa &= ~(gpa_t)7;
+               r = kvm_read_guest(vcpu->kvm, gpa, &gentry, 8);
+               if (r)
+                       gentry = 0;
+       }
+
+       mmu_guess_page_from_pte_write(vcpu, gpa, gentry);
        spin_lock(&vcpu->kvm->mmu_lock);
        kvm_mmu_access_page(vcpu, gfn);
        kvm_mmu_free_some_pages(vcpu);
@@ -2705,20 +2707,11 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
                                continue;
                }
                spte = &sp->spt[page_offset / sizeof(*spte)];
-               if ((gpa & (pte_size - 1)) || (bytes < pte_size)) {
-                       gentry = 0;
-                       r = kvm_read_guest_atomic(vcpu->kvm,
-                                                 gpa & ~(u64)(pte_size - 1),
-                                                 &gentry, pte_size);
-                       new = (const void *)&gentry;
-                       if (r < 0)
-                               new = NULL;
-               }
                while (npte--) {
                        entry = *spte;
                        mmu_pte_write_zap_pte(vcpu, sp, spte);
-                       if (new)
-                               mmu_pte_write_new_pte(vcpu, sp, spte, new);
+                       if (gentry)
+                               mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
                        mmu_pte_write_flush_tlb(vcpu, entry, *spte);
                        ++spte;
                }