Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "This includes a fix for two oopses, one on PPC and on x86.

  The rest is fixes for bugs with newer Intel processors"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm/fpu: Enable eager restore kvm FPU for MPX
  Revert "KVM: x86: drop fpu_activate hook"
  kvm: fix crash in kvm_vcpu_reload_apic_access_page
  KVM: MMU: fix SMAP virtualization
  KVM: MMU: fix CR4.SMEP=1, CR0.WP=0 with shadow pages
  KVM: MMU: fix smap permission check
  KVM: PPC: Book3S HV: Fix list traversal in error case

11 files changed, 74 insertions, 19 deletions

diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 53838d9c6295..c59bd9bc41ef 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -169,6 +169,10 @@ Shadow pages contain the following information:
     Contains the value of cr4.smep && !cr0.wp for which the page is valid
     (pages for which this is true are different from other pages; see the
     treatment of cr0.wp=0 below).
+  role.smap_andnot_wp:
+    Contains the value of cr4.smap && !cr0.wp for which the page is valid
+    (pages for which this is true are different from other pages; see the
+    treatment of cr0.wp=0 below).
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
@@ -344,10 +348,16 @@ on fault type:
 
 (user write faults generate a #PF)
 
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it.  We handle this by also setting spte.nx.  If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+  the kernel may now execute it.  We handle this by also setting spte.nx.
+  If we get a user fetch or read fault, we'll change spte.u=1 and
+  spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+  page, it can not be reused when CR4.SMAP is enabled. We set
+  CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+  here we do not care the case that CR4.SMAP is enabled since KVM will
+  directly inject #PF to guest due to failed permission check.
 
 To prevent an spte that was converted into a kernel page with cr0.wp=0
 from being written by the kernel after cr0.wp has changed to 1, we make
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48d3c5d2ecc9..df81caab7383 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
  */
 static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu, *vnext;
 	int i;
 	int srcu_idx;
 
@@ -1982,7 +1982,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	if ((threads_per_core > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+		list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+					 arch.run_list) {
 			vcpu->arch.ret = -EBUSY;
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dea2e7e962e3..f4a555beef19 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -207,6 +207,7 @@ union kvm_mmu_page_role {
 		unsigned nxe:1;
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
+		unsigned smap_andnot_wp:1;
 	};
 };
 
@@ -400,6 +401,7 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	struct fpu guest_fpu;
+	bool eager_fpu;
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -743,6 +745,7 @@ struct kvm_x86_ops {
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	void (*fpu_activate)(struct kvm_vcpu *vcpu);
 	void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 59b69f6a2844..1d08ad3582d0 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,8 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/i387.h> /* For use_eager_fpu.  Ugh! */
+#include <asm/fpu-internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/xsave.h>
 #include "cpuid.h"
@@ -95,6 +97,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
+	vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu);
+
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
 	 * address checks; exit if it is ever changed.
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c3b1ad9fca81..496b3695d3d3 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -117,4 +117,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d43867c33bc4..44a7d2515497 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3736,8 +3736,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+				      struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3918,6 +3918,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 {
 	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	MMU_WARN_ON(VALID_PAGE(context->root_hpa));
@@ -3936,6 +3937,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 	context->base_role.cr0_wp  = is_write_protection(vcpu);
 	context->base_role.smep_andnot_wp
 		= smep && !is_write_protection(vcpu);
+	context->base_role.smap_andnot_wp
+		= smap && !is_write_protection(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -4207,12 +4210,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
-	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
 	bool remote_flush, local_flush, zap_page;
+	union kvm_mmu_page_role mask = (union kvm_mmu_page_role) {
+		.cr0_wp = 1,
+		.cr4_pae = 1,
+		.nxe = 1,
+		.smep_andnot_wp = 1,
+		.smap_andnot_wp = 1,
+	};
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
@@ -4238,7 +4247,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
-	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index c7d65637c851..0ada65ecddcf 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -71,8 +71,6 @@ enum {
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-		bool ept);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
@@ -166,6 +164,8 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 
+	WARN_ON(pfec & PFERR_RSVD_MASK);
+
 	return (mmu->permissions[index] >> pte_access) & 1;
 }
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index fd49c867b25a..6e6d115fe9b5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 					      mmu_is_nested(vcpu));
 		if (likely(r != RET_MMIO_PF_INVALID))
 			return r;
+
+		/*
+		 * page fault with PFEC.RSVD  = 1 is caused by shadow
+		 * page fault, should not be used to walk guest page
+		 * table.
+		 */
+		error_code &= ~PFERR_RSVD_MASK;
 	};
 
 	r = mmu_topup_memory_caches(vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ce741b8650f6..9afa233b5482 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4381,6 +4381,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.fpu_activate = svm_fpu_activate,
 	.fpu_deactivate = svm_fpu_deactivate,
 
 	.tlb_flush = svm_flush_tlb,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b61687bd79..2d73807f0d31 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10185,6 +10185,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
+	.fpu_activate = vmx_fpu_activate,
 	.fpu_deactivate = vmx_fpu_deactivate,
 
 	.tlb_flush = vmx_flush_tlb,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c73efcd03e29..ea306adbbc13 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -702,8 +702,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
-				   X86_CR4_PAE | X86_CR4_SMEP;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP;
+
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
@@ -744,9 +745,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
-		update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
 	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
 		kvm_update_cpuid(vcpu);
 
@@ -6197,6 +6195,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 		return;
 
 	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return;
 	kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
 
 	/*
@@ -7060,7 +7060,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	fpu_save_init(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+	if (!vcpu->arch.eager_fpu)
+		kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+
 	trace_kvm_fpu(0);
 }
 
@@ -7076,11 +7078,21 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 						unsigned int id)
 {
+	struct kvm_vcpu *vcpu;
+
 	if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
 		printk_once(KERN_WARNING
 		"kvm: SMP vm created on host with unstable TSC; "
 		"guest TSC will not be reliable\n");
-	return kvm_x86_ops->vcpu_create(kvm, id);
+
+	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+	/*
+	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
+	 * deactivated soon if it doesn't.
+	 */
+	kvm_x86_ops->fpu_activate(vcpu);
+	return vcpu;
 }
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)