KVM: MMU: Simplify hash table indexing

[linux-2.6-omap-h63xx.git] / arch / x86 / kvm / mmu.c

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d8172aabc660de7503c43b697fea470d81f7eb9a..6f8392d4034ec8601061139030b3312a75be5d0a 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -222,8 +222,7 @@ static int is_io_pte(unsigned long pte)
 
 static int is_rmap_pte(u64 pte)
 {
-       return pte != shadow_trap_nonpresent_pte
-               && pte != shadow_notrap_nonpresent_pte;
+       return is_shadow_present_pte(pte);
 }
 
 static gfn_t pse36_gfn_delta(u32 gpte)
@@ -560,7 +559,7 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static unsigned kvm_page_table_hashfn(gfn_t gfn)
 {
-       return gfn;
+       return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
 }
 
 static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
@@ -664,7 +663,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
        struct hlist_node *node;
 
        pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
-       index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+       index = kvm_page_table_hashfn(gfn);
        bucket = &kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry(sp, node, bucket, hash_link)
                if (sp->gfn == gfn && !sp->role.metaphysical) {
@@ -702,7 +701,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
        }
        pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
                 gfn, role.word);
-       index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+       index = kvm_page_table_hashfn(gfn);
        bucket = &vcpu->kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry(sp, node, bucket, hash_link)
                if (sp->gfn == gfn && sp->role.word == role.word) {
@@ -841,7 +840,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
        pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
        r = 0;
-       index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+       index = kvm_page_table_hashfn(gfn);
        bucket = &kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
                if (sp->gfn == gfn && !sp->role.metaphysical) {
@@ -893,14 +892,25 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                         int *ptwrite, gfn_t gfn, struct page *page)
 {
        u64 spte;
-       int was_rmapped = is_rmap_pte(*shadow_pte);
+       int was_rmapped = 0;
        int was_writeble = is_writeble_pte(*shadow_pte);
+       hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
        pgprintk("%s: spte %llx access %x write_fault %d"
                 " user_fault %d gfn %lx\n",
                 __FUNCTION__, *shadow_pte, pt_access,
                 write_fault, user_fault, gfn);
 
+       if (is_rmap_pte(*shadow_pte)) {
+               if (host_pfn != page_to_pfn(page)) {
+                       pgprintk("hfn old %lx new %lx\n",
+                                host_pfn, page_to_pfn(page));
+                       rmap_remove(vcpu->kvm, shadow_pte);
+               }
+               else
+                       was_rmapped = 1;
+       }
+
        /*
         * We don't set the accessed bit, since we sometimes want to see
         * whether the guest actually used the pte (in order to detect
@@ -1319,8 +1329,7 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
 static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
                                  struct kvm_mmu_page *sp,
                                  u64 *spte,
-                                 const void *new, int bytes,
-                                 int offset_in_pte)
+                                 const void *new)
 {
        if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
                ++vcpu->kvm->stat.mmu_pde_zapped;
@@ -1329,9 +1338,9 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
 
        ++vcpu->kvm->stat.mmu_pte_updated;
        if (sp->role.glevels == PT32_ROOT_LEVEL)
-               paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+               paging32_update_pte(vcpu, sp, spte, new);
        else
-               paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+               paging64_update_pte(vcpu, sp, spte, new);
 }
 
 static bool need_remote_flush(u64 old, u64 new)
@@ -1402,7 +1411,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        up_read(&current->mm->mmap_sem);
 
        vcpu->arch.update_pte.gfn = gfn;
-       vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn);
+       vcpu->arch.update_pte.page = page;
 }
 
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -1413,7 +1422,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        struct hlist_node *node, *n;
        struct hlist_head *bucket;
        unsigned index;
-       u64 entry;
+       u64 entry, gentry;
        u64 *spte;
        unsigned offset = offset_in_page(gpa);
        unsigned pte_size;
@@ -1423,6 +1432,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        int level;
        int flooded = 0;
        int npte;
+       int r;
 
        pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
        mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
@@ -1440,7 +1450,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
                vcpu->arch.last_pt_write_count = 1;
                vcpu->arch.last_pte_updated = NULL;
        }
-       index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+       index = kvm_page_table_hashfn(gfn);
        bucket = &vcpu->kvm->arch.mmu_page_hash[index];
        hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
                if (sp->gfn != gfn || sp->role.metaphysical)
@@ -1486,11 +1496,20 @@ 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);
-                       mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes,
-                                             page_offset & (pte_size - 1));
+                       if (new)
+                               mmu_pte_write_new_pte(vcpu, sp, spte, new);
                        mmu_pte_write_flush_tlb(vcpu, entry, *spte);
                        ++spte;
                }