KVM: x86: make FNAME(fetch) and __direct_map more similar

commit 3fcf2d1bdeb6a513523cb2c77012a6b047aa859c upstream.

These two functions are basically doing the same thing through
kvm_mmu_get_page, link_shadow_page and mmu_set_spte; yet, for historical
reasons, their code looks very different.  This patch tries to take the
best of each and make them very similar, so that it is easy to understand
changes that apply to both of them.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[bwh: Backported to 4.9: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2cf1ff7e3af7a385371041411f12c5bd4c9a6d57..bf370b63928ecbca273fc78a6350c67da1b793d9 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2757,40 +2757,39 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
        __direct_pte_prefetch(vcpu, sp, sptep);
 }
 
-static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
-                       int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
+                       int map_writable, int level, kvm_pfn_t pfn,
+                       bool prefault)
 {
-       struct kvm_shadow_walk_iterator iterator;
+       struct kvm_shadow_walk_iterator it;
        struct kvm_mmu_page *sp;
-       int emulate = 0;
-       gfn_t pseudo_gfn;
+       int ret;
+       gfn_t gfn = gpa >> PAGE_SHIFT;
+       gfn_t base_gfn = gfn;
 
        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
-               return 0;
+               return RET_PF_RETRY;
 
-       for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
-               if (iterator.level == level) {
-                       emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
-                                              write, level, gfn, pfn, prefault,
-                                              map_writable);
-                       direct_pte_prefetch(vcpu, iterator.sptep);
-                       ++vcpu->stat.pf_fixed;
+       for_each_shadow_entry(vcpu, gpa, it) {
+               base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+               if (it.level == level)
                        break;
-               }
 
-               drop_large_spte(vcpu, iterator.sptep);
-               if (!is_shadow_present_pte(*iterator.sptep)) {
-                       u64 base_addr = iterator.addr;
+               drop_large_spte(vcpu, it.sptep);
+               if (!is_shadow_present_pte(*it.sptep)) {
+                       sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr,
+                                             it.level - 1, true, ACC_ALL);
 
-                       base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
-                       pseudo_gfn = base_addr >> PAGE_SHIFT;
-                       sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
-                                             iterator.level - 1, 1, ACC_ALL);
-
-                       link_shadow_page(vcpu, iterator.sptep, sp);
+                       link_shadow_page(vcpu, it.sptep, sp);
                }
        }
-       return emulate;
+
+       ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL,
+                          write, level, base_gfn, pfn, prefault,
+                          map_writable);
+       direct_pte_prefetch(vcpu, it.sptep);
+       ++vcpu->stat.pf_fixed;
+       return ret;
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
@@ -3062,8 +3061,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
        make_mmu_pages_available(vcpu);
        if (likely(!force_pt_level))
                transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-       r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
-
+       r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault);
 out_unlock:
        spin_unlock(&vcpu->kvm->mmu_lock);
        kvm_release_pfn_clean(pfn);
@@ -3598,8 +3596,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
        make_mmu_pages_available(vcpu);
        if (likely(!force_pt_level))
                transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-       r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
-
+       r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault);
 out_unlock:
        spin_unlock(&vcpu->kvm->mmu_lock);
        kvm_release_pfn_clean(pfn);

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3763edaa01a4b18501c6e907aec4b72e030a0607..c0d87ba4217d5f08dd7aad93e6eefc8e363e6782 100644 (file)
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -579,6 +579,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
        struct kvm_shadow_walk_iterator it;
        unsigned direct_access, access = gw->pt_access;
        int top_level, ret;
+       gfn_t base_gfn;
 
        direct_access = gw->pte_access;
 
@@ -623,31 +624,29 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                        link_shadow_page(vcpu, it.sptep, sp);
        }
 
-       for (;
-            shadow_walk_okay(&it) && it.level > hlevel;
-            shadow_walk_next(&it)) {
-               gfn_t direct_gfn;
+       base_gfn = gw->gfn;
 
+       for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
                clear_sp_write_flooding_count(it.sptep);
+               base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+               if (it.level == hlevel)
+                       break;
+
                validate_direct_spte(vcpu, it.sptep, direct_access);
 
                drop_large_spte(vcpu, it.sptep);
 
-               if (is_shadow_present_pte(*it.sptep))
-                       continue;
-
-               direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
-
-               sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
-                                     true, direct_access);
-               link_shadow_page(vcpu, it.sptep, sp);
+               if (!is_shadow_present_pte(*it.sptep)) {
+                       sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
+                                             it.level - 1, true, direct_access);
+                       link_shadow_page(vcpu, it.sptep, sp);
+               }
        }
 
-       clear_sp_write_flooding_count(it.sptep);
        ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
-                          it.level, gw->gfn, pfn, prefault, map_writable);
+                          it.level, base_gfn, pfn, prefault, map_writable);
        FNAME(pte_prefetch)(vcpu, gw, it.sptep);
-
+       ++vcpu->stat.pf_fixed;
        return ret;
 
 out_gpte_changed:
@@ -810,7 +809,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
                transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
        r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
                         level, pfn, map_writable, prefault);
-       ++vcpu->stat.pf_fixed;
        kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock: