5 files changed, 63 insertions, 32 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index afa7bbb596cd..0aefb626fa8f 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,7 +16,6 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
-#include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
 #include "cpuid.h"
@@ -114,8 +113,7 @@ 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);
 
-	if (use_eager_fpu())
-		kvm_x86_ops->fpu_activate(vcpu);
+	kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d9c7e986b4e4..87c5880ba3b7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4405,7 +4405,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 }
 
 static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-			      const u8 *new, int bytes)
+			      const u8 *new, int bytes,
+			      struct kvm_page_track_notifier_node *node)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
@@ -4617,11 +4618,19 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 	init_kvm_mmu(vcpu);
 }
 
+static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
+			struct kvm_memory_slot *slot,
+			struct kvm_page_track_notifier_node *node)
+{
+	kvm_mmu_invalidate_zap_all_pages(kvm);
+}
+
 void kvm_mmu_init_vm(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
 
 	node->track_write = kvm_mmu_pte_write;
+	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
 	kvm_page_track_register_notifier(kvm, node);
 }
 
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index b431539c3714..4a1c13eaa518 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -106,6 +106,7 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
 			kvm_flush_remote_tlbs(kvm);
 }
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
 
 /*
  * remove the guest page from the tracking pool which stops the interception
@@ -135,6 +136,7 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
@@ -181,6 +183,7 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
 	spin_unlock(&kvm->mmu_lock);
 }
+EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
 
 /*
  * stop receiving the event interception. It is the opposed operation of
@@ -199,6 +202,7 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 	spin_unlock(&kvm->mmu_lock);
 	synchronize_srcu(&head->track_srcu);
 }
+EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
 
 /*
  * Notify the node that write access is intercepted and write emulation is
@@ -222,6 +226,31 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	idx = srcu_read_lock(&head->track_srcu);
 	hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
 		if (n->track_write)
-			n->track_write(vcpu, gpa, new, bytes);
+			n->track_write(vcpu, gpa, new, bytes, n);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
+
+/*
+ * Notify the node that memory slot is being removed or moved so that it can
+ * drop write-protection for the pages in the memory slot.
+ *
+ * The node should figure out it has any write-protected pages in this slot
+ * by itself.
+ */
+void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
+		if (n->track_flush_slot)
+			n->track_flush_slot(kvm, slot, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5382b82462fc..3980da515fd0 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2145,12 +2145,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #endif
 	if (vmx->host_state.msr_host_bndcfgs)
 		wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs);
-	/*
-	 * If the FPU is not active (through the host task or
-	 * the guest vcpu), then restore the cr0.TS bit.
-	 */
-	if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
-		stts();
 	load_gdt(this_cpu_ptr(&host_gdt));
 }
 
@@ -4845,9 +4839,11 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
-	unsigned long cr4;
+	unsigned long cr0, cr4;
 
-	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
+	cr0 = read_cr0();
+	WARN_ON(cr0 & X86_CR0_TS);
+	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 04c5d96b1d67..2912684ff902 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2071,6 +2071,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
 		return;
 
+	vcpu->arch.st.steal.preempted = 0;
+
 	if (vcpu->arch.st.steal.version & 1)
 		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
 
@@ -2826,8 +2828,22 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 }
 
+static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
+		return;
+
+	vcpu->arch.st.steal.preempted = 1;
+
+	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+			&vcpu->arch.st.steal.preempted,
+			offsetof(struct kvm_steal_time, preempted),
+			sizeof(vcpu->arch.st.steal.preempted));
+}
+
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	kvm_steal_time_set_preempted(vcpu);
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -5081,11 +5097,6 @@ static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
 {
 	preempt_disable();
 	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-	/*
-	 * CR0.TS may reference the host fpu state, not the guest fpu state,
-	 * so it may be clear at this point.
-	 */
-	clts();
 }
 
 static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
@@ -7407,25 +7418,13 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded) {
-		vcpu->fpu_counter = 0;
+	if (!vcpu->guest_fpu_loaded)
 		return;
-	}
 
 	vcpu->guest_fpu_loaded = 0;
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	/*
-	 * If using eager FPU mode, or if the guest is a frequent user
-	 * of the FPU, just leave the FPU active for next time.
-	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
-	 * the FPU in bursts will revert to loading it on demand.
-	 */
-	if (!use_eager_fpu()) {
-		if (++vcpu->fpu_counter < 5)
-			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
-	}
 	trace_kvm_fpu(0);
 }
 
@@ -8176,7 +8175,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
-	kvm_mmu_invalidate_zap_all_pages(kvm);
+	kvm_page_track_flush_slot(kvm, slot);
 }
 
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)