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

Pull KVM fixes from Paolo Bonzini:
 "The important fixes are for two bugs introduced by the merge window.

  On top of this, add a couple of WARN_ONs and stop spamming dmesg on
  pretty much every boot of a virtual machine"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: warn on more invariant breakage
  kvm: fix sorting of memslots with base_gfn == 0
  kvm: x86: drop severity of "generation wraparound" message
  kvm: x86: vmx: reorder some msr writing

3 files changed, 65 insertions, 51 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 10fbed126b1..f83fc6c5e0b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4448,7 +4448,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * zap all shadow pages.
 	 */
 	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
-		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index feb852b0459..d4c58d88483 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5840,53 +5840,10 @@ static __init int hardware_setup(void)
 	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
 	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
 
-	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
-	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
-
-	memcpy(vmx_msr_bitmap_legacy_x2apic,
-			vmx_msr_bitmap_legacy, PAGE_SIZE);
-	memcpy(vmx_msr_bitmap_longmode_x2apic,
-			vmx_msr_bitmap_longmode, PAGE_SIZE);
-
-	if (enable_apicv) {
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			vmx_disable_intercept_msr_read_x2apic(msr);
-
-		/* According SDM, in x2apic mode, the whole id reg is used.
-		 * But in KVM, it only use the highest eight bits. Need to
-		 * intercept it */
-		vmx_enable_intercept_msr_read_x2apic(0x802);
-		/* TMCCT */
-		vmx_enable_intercept_msr_read_x2apic(0x839);
-		/* TPR */
-		vmx_disable_intercept_msr_write_x2apic(0x808);
-		/* EOI */
-		vmx_disable_intercept_msr_write_x2apic(0x80b);
-		/* SELF-IPI */
-		vmx_disable_intercept_msr_write_x2apic(0x83f);
-	}
-
-	if (enable_ept) {
-		kvm_mmu_set_mask_ptes(0ull,
-			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
-			(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
-			0ull, VMX_EPT_EXECUTABLE_MASK);
-		ept_set_mmio_spte_mask();
-		kvm_enable_tdp();
-	} else
-		kvm_disable_tdp();
-
-	update_ple_window_actual_max();
-
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
 		goto out7;
-    }
+	}
 
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
@@ -5945,6 +5902,49 @@ static __init int hardware_setup(void)
 	if (nested)
 		nested_vmx_setup_ctls_msrs();
 
+	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
+
+	memcpy(vmx_msr_bitmap_legacy_x2apic,
+			vmx_msr_bitmap_legacy, PAGE_SIZE);
+	memcpy(vmx_msr_bitmap_longmode_x2apic,
+			vmx_msr_bitmap_longmode, PAGE_SIZE);
+
+	if (enable_apicv) {
+		for (msr = 0x800; msr <= 0x8ff; msr++)
+			vmx_disable_intercept_msr_read_x2apic(msr);
+
+		/* According SDM, in x2apic mode, the whole id reg is used.
+		 * But in KVM, it only use the highest eight bits. Need to
+		 * intercept it */
+		vmx_enable_intercept_msr_read_x2apic(0x802);
+		/* TMCCT */
+		vmx_enable_intercept_msr_read_x2apic(0x839);
+		/* TPR */
+		vmx_disable_intercept_msr_write_x2apic(0x808);
+		/* EOI */
+		vmx_disable_intercept_msr_write_x2apic(0x80b);
+		/* SELF-IPI */
+		vmx_disable_intercept_msr_write_x2apic(0x83f);
+	}
+
+	if (enable_ept) {
+		kvm_mmu_set_mask_ptes(0ull,
+			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
+			(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
+			0ull, VMX_EPT_EXECUTABLE_MASK);
+		ept_set_mmio_spte_mask();
+		kvm_enable_tdp();
+	} else
+		kvm_disable_tdp();
+
+	update_ple_window_actual_max();
+
 	return alloc_kvm_area();
 
 out7:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f5283438ee0..1cc6e2e1998 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -671,6 +671,7 @@ static void update_memslots(struct kvm_memslots *slots,
 
 	WARN_ON(mslots[i].id != id);
 	if (!new->npages) {
+		WARN_ON(!mslots[i].npages);
 		new->base_gfn = 0;
 		if (mslots[i].npages)
 			slots->used_slots--;
@@ -687,12 +688,25 @@ static void update_memslots(struct kvm_memslots *slots,
 		slots->id_to_index[mslots[i].id] = i;
 		i++;
 	}
-	while (i > 0 &&
-	       new->base_gfn > mslots[i - 1].base_gfn) {
-		mslots[i] = mslots[i - 1];
-		slots->id_to_index[mslots[i].id] = i;
-		i--;
-	}
+
+	/*
+	 * The ">=" is needed when creating a slot with base_gfn == 0,
+	 * so that it moves before all those with base_gfn == npages == 0.
+	 *
+	 * On the other hand, if new->npages is zero, the above loop has
+	 * already left i pointing to the beginning of the empty part of
+	 * mslots, and the ">=" would move the hole backwards in this
+	 * case---which is wrong.  So skip the loop when deleting a slot.
+	 */
+	if (new->npages) {
+		while (i > 0 &&
+		       new->base_gfn >= mslots[i - 1].base_gfn) {
+			mslots[i] = mslots[i - 1];
+			slots->id_to_index[mslots[i].id] = i;
+			i--;
+		}
+	} else
+		WARN_ON_ONCE(i != slots->used_slots);
 
 	mslots[i] = *new;
 	slots->id_to_index[mslots[i].id] = i;