KVM: fix tracing kvm_try_async_get_page

[karo-tx-linux.git] / arch / x86 / kvm / mmu.c

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4ab04de5a76af12fae67d60c9bf4bf8df0437f9e..272e3020003043a8add639d123675e7b0d507caf 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -196,7 +196,6 @@ static struct percpu_counter kvm_total_used_mmu_pages;
 
 static u64 __read_mostly shadow_trap_nonpresent_pte;
 static u64 __read_mostly shadow_notrap_nonpresent_pte;
-static u64 __read_mostly shadow_base_present_pte;
 static u64 __read_mostly shadow_nx_mask;
 static u64 __read_mostly shadow_x_mask;        /* mutual exclusive with nx_mask */
 static u64 __read_mostly shadow_user_mask;
@@ -215,12 +214,6 @@ void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);
 
-void kvm_mmu_set_base_ptes(u64 base_pte)
-{
-       shadow_base_present_pte = base_pte;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
-
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
                u64 dirty_mask, u64 nx_mask, u64 x_mask)
 {
@@ -1975,7 +1968,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
         * whether the guest actually used the pte (in order to detect
         * demand paging).
         */
-       spte = shadow_base_present_pte;
+       spte = PT_PRESENT_MASK;
        if (!speculative)
                spte |= shadow_accessed_mask;
        if (!dirty)
@@ -2076,6 +2069,16 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
                                 spte_to_pfn(*sptep), pfn);
                        drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
                        kvm_flush_remote_tlbs(vcpu->kvm);
+               /*
+                * If we overwrite a writable spte with a read-only one,
+                * drop it and flush remote TLBs. Otherwise rmap_write_protect
+                * will find a read-only spte, even though the writable spte
+                * might be cached on a CPU's TLB.
+                */
+               } else if (is_writable_pte(*sptep) &&
+                         (!(pte_access & ACC_WRITE_MASK) || !dirty)) {
+                       drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
+                       kvm_flush_remote_tlbs(vcpu->kvm);
                } else
                        was_rmapped = 1;
        }
@@ -2213,7 +2216,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 }
 
 static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
-                       int level, gfn_t gfn, pfn_t pfn)
+                       int map_writable, int level, gfn_t gfn, pfn_t pfn)
 {
        struct kvm_shadow_walk_iterator iterator;
        struct kvm_mmu_page *sp;
@@ -2222,9 +2225,13 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 
        for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
                if (iterator.level == level) {
-                       mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
+                       unsigned pte_access = ACC_ALL;
+
+                       if (!map_writable)
+                               pte_access &= ~ACC_WRITE_MASK;
+                       mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
                                     0, write, 1, &pt_write,
-                                    level, gfn, pfn, false, true);
+                                    level, gfn, pfn, false, map_writable);
                        direct_pte_prefetch(vcpu, iterator.sptep);
                        ++vcpu->stat.pf_fixed;
                        break;
@@ -2285,6 +2292,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
        int level;
        pfn_t pfn;
        unsigned long mmu_seq;
+       bool map_writable;
 
        level = mapping_level(vcpu, gfn);
 
@@ -2299,7 +2307,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 
        mmu_seq = vcpu->kvm->mmu_notifier_seq;
        smp_rmb();
-       pfn = gfn_to_pfn(vcpu->kvm, gfn);
+       pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, &map_writable);
 
        /* mmio */
        if (is_error_pfn(pfn))
@@ -2309,7 +2317,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
        if (mmu_notifier_retry(vcpu, mmu_seq))
                goto out_unlock;
        kvm_mmu_free_some_pages(vcpu);
-       r = __direct_map(vcpu, v, write, level, gfn, pfn);
+       r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn);
        spin_unlock(&vcpu->kvm->mmu_lock);
 
 
@@ -2570,7 +2578,7 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
 }
 
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
-                               u32 error_code)
+                               u32 error_code, bool no_apf)
 {
        gfn_t gfn;
        int r;
@@ -2589,9 +2597,10 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
                             error_code & PFERR_WRITE_MASK, gfn);
 }
 
-int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 {
        struct kvm_arch_async_pf arch;
+       arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
        arch.gfn = gfn;
 
        return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
@@ -2606,20 +2615,20 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu)
        return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
-static bool try_async_pf(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva,
-                        pfn_t *pfn)
+static bool try_async_pf(struct kvm_vcpu *vcpu, bool no_apf, gfn_t gfn,
+                        gva_t gva, pfn_t *pfn, bool write, bool *writable)
 {
        bool async;
 
-       *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async);
+       *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable);
 
        if (!async)
                return false; /* *pfn has correct page already */
 
        put_page(pfn_to_page(*pfn));
 
-       if (can_do_async_pf(vcpu)) {
-               trace_kvm_try_async_get_page(async, *pfn);
+       if (!no_apf && can_do_async_pf(vcpu)) {
+               trace_kvm_try_async_get_page(gva, gfn);
                if (kvm_find_async_pf_gfn(vcpu, gfn)) {
                        trace_kvm_async_pf_doublefault(gva, gfn);
                        kvm_make_request(KVM_REQ_APF_HALT, vcpu);
@@ -2628,19 +2637,21 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva,
                        return true;
        }
 
-       *pfn = gfn_to_pfn(vcpu->kvm, gfn);
+       *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable);
 
        return false;
 }
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
-                               u32 error_code)
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+                         bool no_apf)
 {
        pfn_t pfn;
        int r;
        int level;
        gfn_t gfn = gpa >> PAGE_SHIFT;
        unsigned long mmu_seq;
+       int write = error_code & PFERR_WRITE_MASK;
+       bool map_writable;
 
        ASSERT(vcpu);
        ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));
@@ -2656,7 +2667,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
        mmu_seq = vcpu->kvm->mmu_notifier_seq;
        smp_rmb();
 
-       if (try_async_pf(vcpu, gfn, gpa, &pfn))
+       if (try_async_pf(vcpu, no_apf, gfn, gpa, &pfn, write, &map_writable))
                return 0;
 
        /* mmio */
@@ -2666,7 +2677,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
        if (mmu_notifier_retry(vcpu, mmu_seq))
                goto out_unlock;
        kvm_mmu_free_some_pages(vcpu);
-       r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
+       r = __direct_map(vcpu, gpa, write, map_writable,
                         level, gfn, pfn);
        spin_unlock(&vcpu->kvm->mmu_lock);
 
@@ -3319,7 +3330,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
        int r;
        enum emulation_result er;
 
-       r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code);
+       r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
        if (r < 0)
                goto out;