KVM: MMU: Emulate #PF error code of reserved bits violation

Detect, indicate, and propagate page faults where reserved bits are set.
Take care to handle the different paging modes, each of which has different
sets of reserved bits.

[avi: fix pte reserved bits for efer.nxe=0]

Signed-off-by: Eddie Dong <eddie.dong@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8351c4d..548b97d 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -261,6 +261,7 @@ struct kvm_mmu {
        union kvm_mmu_page_role base_role;
 
        u64 *pae_root;
+       u64 rsvd_bits_mask[2][4];
 };
 
 struct kvm_vcpu_arch {
@@ -791,5 +792,6 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 
 #endif /* _ASM_X86_KVM_HOST_H */

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8aac67c..b2c8e28 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -126,6 +126,7 @@ module_param(oos_shadow, bool, 0644);
 #define PFERR_PRESENT_MASK (1U << 0)
 #define PFERR_WRITE_MASK (1U << 1)
 #define PFERR_USER_MASK (1U << 2)
+#define PFERR_RSVD_MASK (1U << 3)
 #define PFERR_FETCH_MASK (1U << 4)
 
 #define PT_DIRECTORY_LEVEL 2
@@ -179,6 +180,11 @@ static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mt_mask;
 
+static inline u64 rsvd_bits(int s, int e)
+{
+       return ((1ULL << (e - s + 1)) - 1) << s;
+}
+
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 {
        shadow_trap_nonpresent_pte = trap_pte;
@@ -2151,6 +2157,14 @@ static void paging_free(struct kvm_vcpu *vcpu)
        nonpaging_free(vcpu);
 }
 
+static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level)
+{
+       int bit7;
+
+       bit7 = (gpte >> 7) & 1;
+       return (gpte & vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0;
+}
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -2159,6 +2173,55 @@ static void paging_free(struct kvm_vcpu *vcpu)
 #include "paging_tmpl.h"
 #undef PTTYPE
 
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
+{
+       struct kvm_mmu *context = &vcpu->arch.mmu;
+       int maxphyaddr = cpuid_maxphyaddr(vcpu);
+       u64 exb_bit_rsvd = 0;
+
+       if (!is_nx(vcpu))
+               exb_bit_rsvd = rsvd_bits(63, 63);
+       switch (level) {
+       case PT32_ROOT_LEVEL:
+               /* no rsvd bits for 2 level 4K page table entries */
+               context->rsvd_bits_mask[0][1] = 0;
+               context->rsvd_bits_mask[0][0] = 0;
+               if (is_cpuid_PSE36())
+                       /* 36bits PSE 4MB page */
+                       context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+               else
+                       /* 32 bits PSE 4MB page */
+                       context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+               context->rsvd_bits_mask[1][0] = ~0ull;
+               break;
+       case PT32E_ROOT_LEVEL:
+               context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 62);              /* PDE */
+               context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 62);      /* PTE */
+               context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 62) |
+                       rsvd_bits(13, 20);              /* large page */
+               context->rsvd_bits_mask[1][0] = ~0ull;
+               break;
+       case PT64_ROOT_LEVEL:
+               context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+               context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+               context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+               context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 51);
+               context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+               context->rsvd_bits_mask[1][2] = context->rsvd_bits_mask[0][2];
+               context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+                       rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20);
+               context->rsvd_bits_mask[1][0] = ~0ull;
+               break;
+       }
+}
+
 static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
 {
        struct kvm_mmu *context = &vcpu->arch.mmu;
@@ -2179,6 +2242,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
 
 static int paging64_init_context(struct kvm_vcpu *vcpu)
 {
+       reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
        return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
 }
 
@@ -2186,6 +2250,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu)
 {
        struct kvm_mmu *context = &vcpu->arch.mmu;
 
+       reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
        context->new_cr3 = paging_new_cr3;
        context->page_fault = paging32_page_fault;
        context->gva_to_gpa = paging32_gva_to_gpa;
@@ -2201,6 +2266,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu)
 
 static int paging32E_init_context(struct kvm_vcpu *vcpu)
 {
+       reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
        return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
 }
 
@@ -2221,12 +2287,15 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
                context->gva_to_gpa = nonpaging_gva_to_gpa;
                context->root_level = 0;
        } else if (is_long_mode(vcpu)) {
+               reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
                context->gva_to_gpa = paging64_gva_to_gpa;
                context->root_level = PT64_ROOT_LEVEL;
        } else if (is_pae(vcpu)) {
+               reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
                context->gva_to_gpa = paging64_gva_to_gpa;
                context->root_level = PT32E_ROOT_LEVEL;
        } else {
+               reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
                context->gva_to_gpa = paging32_gva_to_gpa;
                context->root_level = PT32_ROOT_LEVEL;
        }

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index eae9499..09782a9 100644 (file)
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -123,6 +123,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
        gfn_t table_gfn;
        unsigned index, pt_access, pte_access;
        gpa_t pte_gpa;
+       int rsvd_fault = 0;
 
        pgprintk("%s: addr %lx\n", __func__, addr);
 walk:
@@ -157,6 +158,10 @@ walk:
                if (!is_present_pte(pte))
                        goto not_present;
 
+               rsvd_fault = is_rsvd_bits_set(vcpu, pte, walker->level);
+               if (rsvd_fault)
+                       goto access_error;
+
                if (write_fault && !is_writeble_pte(pte))
                        if (user_fault || is_write_protection(vcpu))
                                goto access_error;
@@ -232,6 +237,8 @@ err:
                walker->error_code |= PFERR_USER_MASK;
        if (fetch_fault)
                walker->error_code |= PFERR_FETCH_MASK;
+       if (rsvd_fault)
+               walker->error_code |= PFERR_RSVD_MASK;
        return 0;
 }
 

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5bbcad3..df86668 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3017,6 +3017,16 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
        return best;
 }
 
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
+{
+       struct kvm_cpuid_entry2 *best;
+
+       best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+       if (best)
+               return best->eax & 0xff;
+       return 36;
+}
+
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
        u32 function, index;