KVM: x86/mmu: Configure max page level during hardware setup

Configure the max page level during hardware setup to avoid a retpoline
in the page fault handler.  Drop ->get_lpage_level() as the page fault
handler was the last user.

No functional change intended.

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c9b721140f5963f60e2c8401424aff0dee05d92d..c817987c599e83e34980a678010d2cea6427812e 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1155,7 +1155,6 @@ struct kvm_x86_ops {
        int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
        int (*get_tdp_level)(struct kvm_vcpu *vcpu);
        u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
-       int (*get_lpage_level)(void);
 
        void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -1510,7 +1509,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush);
 
-void kvm_configure_mmu(bool enable_tdp);
+void kvm_configure_mmu(bool enable_tdp, int tdp_page_level);
 
 static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
                                  struct x86_exception *exception)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 724bc8051117217b43b3edb43093db4009e17a1c..554546948e8791ceabd3b4882986a9c0b6880f37 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -87,6 +87,8 @@ __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
  */
 bool tdp_enabled = false;
 
+static int max_page_level __read_mostly;
+
 enum {
        AUDIT_PRE_PAGE_FAULT,
        AUDIT_POST_PAGE_FAULT,
@@ -3282,7 +3284,7 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
        if (!slot)
                return PT_PAGE_TABLE_LEVEL;
 
-       max_level = min(max_level, kvm_x86_ops->get_lpage_level());
+       max_level = min(max_level, max_page_level);
        for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) {
                linfo = lpage_info_slot(gfn, slot, max_level);
                if (!linfo->disallow_lpage)
@@ -5559,9 +5561,23 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva);
 
-void kvm_configure_mmu(bool enable_tdp)
+void kvm_configure_mmu(bool enable_tdp, int tdp_page_level)
 {
        tdp_enabled = enable_tdp;
+
+       /*
+        * max_page_level reflects the capabilities of KVM's MMU irrespective
+        * of kernel support, e.g. KVM may be capable of using 1GB pages when
+        * the kernel is not.  But, KVM never creates a page size greater than
+        * what is used by the kernel for any given HVA, i.e. the kernel's
+        * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust().
+        */
+       if (tdp_enabled)
+               max_page_level = tdp_page_level;
+       else if (boot_cpu_has(X86_FEATURE_GBPAGES))
+               max_page_level = PT_PDPE_LEVEL;
+       else
+               max_page_level = PT_DIRECTORY_LEVEL;
 }
 EXPORT_SYMBOL_GPL(kvm_configure_mmu);
 

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 422ee02afe8cb7d36d125da478d13e2057e63884..5e3261ec8c59fe10d77520419cf2ce18550bc469 100644 (file)
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1458,7 +1458,7 @@ static __init int svm_hardware_setup(void)
        if (npt_enabled && !npt)
                npt_enabled = false;
 
-       kvm_configure_mmu(npt_enabled);
+       kvm_configure_mmu(npt_enabled, PT_PDPE_LEVEL);
        pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
 
        if (nrips) {
@@ -6064,11 +6064,6 @@ static void svm_set_supported_cpuid(struct kvm_cpuid_entry2 *entry)
        }
 }
 
-static int svm_get_lpage_level(void)
-{
-       return PT_PDPE_LEVEL;
-}
-
 static bool svm_has_wbinvd_exit(void)
 {
        return true;
@@ -7426,8 +7421,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
        .get_exit_info = svm_get_exit_info,
 
-       .get_lpage_level = svm_get_lpage_level,
-
        .cpuid_update = svm_cpuid_update,
 
        .set_supported_cpuid = svm_set_supported_cpuid,

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b4ae305646fef6bedc2cdaf7e67742ac5e008895..066c97ceebbf43e183060bb8ea72a5f02e03d6f3 100644 (file)
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6913,15 +6913,6 @@ exit:
        return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
 }
 
-static int vmx_get_lpage_level(void)
-{
-       if (enable_ept && !cpu_has_vmx_ept_1g_page())
-               return PT_DIRECTORY_LEVEL;
-       else
-               /* For shadow and EPT supported 1GB page */
-               return PT_PDPE_LEVEL;
-}
-
 static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx)
 {
        /*
@@ -7653,7 +7644,7 @@ static __init int hardware_setup(void)
 {
        unsigned long host_bndcfgs;
        struct desc_ptr dt;
-       int r, i;
+       int r, i, ept_lpage_level;
 
        rdmsrl_safe(MSR_EFER, &host_efer);
 
@@ -7746,7 +7737,16 @@ static __init int hardware_setup(void)
 
        if (enable_ept)
                vmx_enable_tdp();
-       kvm_configure_mmu(enable_ept);
+
+       if (!enable_ept)
+               ept_lpage_level = 0;
+       else if (cpu_has_vmx_ept_1g_page())
+               ept_lpage_level = PT_PDPE_LEVEL;
+       else if (cpu_has_vmx_ept_2m_page())
+               ept_lpage_level = PT_DIRECTORY_LEVEL;
+       else
+               ept_lpage_level = PT_PAGE_TABLE_LEVEL;
+       kvm_configure_mmu(enable_ept, ept_lpage_level);
 
        /*
         * Only enable PML when hardware supports PML feature, and both EPT
@@ -7924,8 +7924,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
        .get_exit_info = vmx_get_exit_info,
 
-       .get_lpage_level = vmx_get_lpage_level,
-
        .cpuid_update = vmx_cpuid_update,
        .set_supported_cpuid = vmx_set_supported_cpuid,