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

Pull KVM fixes from Paolo Bonzini:
 - Fix for a Haswell regression in nested virtualization, introduced
   during the merge window.
 - A fix from Oleg to async page faults.
 - A bunch of small ARM changes.
 - A trivial patch to use the new MSI-X API introduced during the merge
   window.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: ARM: vgic: Fix the overlap check action about setting the GICD & GICC base address.
  KVM: arm/arm64: vgic: fix GICD_ICFGR register accesses
  KVM: async_pf: mm->mm_users can not pin apf->mm
  KVM: ARM: vgic: Fix sgi dispatch problem
  MAINTAINERS: co-maintainance of KVM/{arm,arm64}
  arm: KVM: fix possible misalignment of PGDs and bounce page
  KVM: x86: Check for host supported fields in shadow vmcs
  kvm: Use pci_enable_msix_exact() instead of pci_enable_msix()
  ARM: KVM: disable KVM in Kconfig on big-endian systems

3 files changed, 51 insertions, 19 deletions

diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 466bd299b1a8aa..4be5bb150bddde 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,7 +23,7 @@ config KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
-	depends on ARM_VIRT_EXT && ARM_LPAE
+	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
 	---help---
 	  Support hosting virtualized guest machines. You will also
 	  need to select one or more of the processor modules below.
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 80bb1e6c2c2906..16f804938b8fea 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -293,14 +295,14 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		kfree(boot_hyp_pgd);
+		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
 		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
-	kfree(init_bounce_page);
+	free_page((unsigned long)init_bounce_page);
 	init_bounce_page = NULL;
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -330,7 +332,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		kfree(hyp_pgd);
+		free_pages((unsigned long)hyp_pgd, pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -1024,7 +1026,7 @@ int kvm_mmu_init(void)
 		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
 		phys_addr_t phys_base;
 
-		init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
 		if (!init_bounce_page) {
 			kvm_err("Couldn't allocate HYP init bounce page\n");
 			err = -ENOMEM;
@@ -1050,8 +1052,9 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
 		err = -ENOMEM;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1f68c5831924d1..33e8c028842fb4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -503,7 +503,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 				[number##_HIGH] = VMCS12_OFFSET(name)+4
 
 
-static const unsigned long shadow_read_only_fields[] = {
+static unsigned long shadow_read_only_fields[] = {
 	/*
 	 * We do NOT shadow fields that are modified when L0
 	 * traps and emulates any vmx instruction (e.g. VMPTRLD,
@@ -526,10 +526,10 @@ static const unsigned long shadow_read_only_fields[] = {
 	GUEST_LINEAR_ADDRESS,
 	GUEST_PHYSICAL_ADDRESS
 };
-static const int max_shadow_read_only_fields =
+static int max_shadow_read_only_fields =
 	ARRAY_SIZE(shadow_read_only_fields);
 
-static const unsigned long shadow_read_write_fields[] = {
+static unsigned long shadow_read_write_fields[] = {
 	GUEST_RIP,
 	GUEST_RSP,
 	GUEST_CR0,
@@ -558,7 +558,7 @@ static const unsigned long shadow_read_write_fields[] = {
 	HOST_FS_SELECTOR,
 	HOST_GS_SELECTOR
 };
-static const int max_shadow_read_write_fields =
+static int max_shadow_read_write_fields =
 	ARRAY_SIZE(shadow_read_write_fields);
 
 static const unsigned short vmcs_field_to_offset_table[] = {
@@ -3009,6 +3009,41 @@ static void free_kvm_area(void)
 	}
 }
 
+static void init_vmcs_shadow_fields(void)
+{
+	int i, j;
+
+	/* No checks for read only fields yet */
+
+	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
+		switch (shadow_read_write_fields[i]) {
+		case GUEST_BNDCFGS:
+			if (!vmx_mpx_supported())
+				continue;
+			break;
+		default:
+			break;
+		}
+
+		if (j < i)
+			shadow_read_write_fields[j] =
+				shadow_read_write_fields[i];
+		j++;
+	}
+	max_shadow_read_write_fields = j;
+
+	/* shadowed fields guest access without vmexit */
+	for (i = 0; i < max_shadow_read_write_fields; i++) {
+		clear_bit(shadow_read_write_fields[i],
+			  vmx_vmwrite_bitmap);
+		clear_bit(shadow_read_write_fields[i],
+			  vmx_vmread_bitmap);
+	}
+	for (i = 0; i < max_shadow_read_only_fields; i++)
+		clear_bit(shadow_read_only_fields[i],
+			  vmx_vmread_bitmap);
+}
+
 static __init int alloc_kvm_area(void)
 {
 	int cpu;
@@ -3039,6 +3074,8 @@ static __init int hardware_setup(void)
 		enable_vpid = 0;
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
+	if (enable_shadow_vmcs)
+		init_vmcs_shadow_fields();
 
 	if (!cpu_has_vmx_ept() ||
 	    !cpu_has_vmx_ept_4levels()) {
@@ -8803,14 +8840,6 @@ static int __init vmx_init(void)
 
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
-	/* shadowed read/write fields */
-	for (i = 0; i < max_shadow_read_write_fields; i++) {
-		clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap);
-		clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap);
-	}
-	/* shadowed read only fields */
-	for (i = 0; i < max_shadow_read_only_fields; i++)
-		clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap);
 
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O