summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorPaolo Bonzini <pbonzini@redhat.com>2022-04-08 12:30:04 -0400
committerPaolo Bonzini <pbonzini@redhat.com>2022-04-08 12:30:04 -0400
commita44e2c207c30a5780c4ad0cc3579b8715cebf52e (patch)
treecabd396cf79b33d707f2d974ce7f811a334a4173 /arch
parent5593473a1e6c743764b08e3b6071cb43b5cfa6c4 (diff)
parent21db83846683d3987666505a3ec38f367708199a (diff)
Merge tag 'kvmarm-fixes-5.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 fixes for 5.18, take #1 - Some PSCI fixes after introducing PSCIv1.1 and SYSTEM_RESET2 - Fix the MMU write-lock not being taken on THP split - Fix mixed-width VM handling - Fix potential UAF when debugfs registration fails - Various selftest updates for all of the above
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h27
-rw-r--r--arch/arm64/include/asm/kvm_host.h10
-rw-r--r--arch/arm64/kvm/mmu.c11
-rw-r--r--arch/arm64/kvm/psci.c31
-rw-r--r--arch/arm64/kvm/reset.c65
-rw-r--r--arch/arm64/kvm/vgic/vgic-debug.c10
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c2
7 files changed, 101 insertions, 55 deletions
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index d62405ce3e6d..7496deab025a 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -43,10 +43,22 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
+#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.hcr_el2 & HCR_RW);
}
+#else
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED,
+ &kvm->arch.flags));
+
+ return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+}
+#endif
static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
{
@@ -72,15 +84,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
vcpu->arch.hcr_el2 |= HCR_TVM;
}
- if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+ if (vcpu_el1_is_32bit(vcpu))
vcpu->arch.hcr_el2 &= ~HCR_RW;
-
- /*
- * TID3: trap feature register accesses that we virtualise.
- * For now this is conditional, since no AArch32 feature regs
- * are currently virtualised.
- */
- if (!vcpu_el1_is_32bit(vcpu))
+ else
+ /*
+ * TID3: trap feature register accesses that we virtualise.
+ * For now this is conditional, since no AArch32 feature regs
+ * are currently virtualised.
+ */
vcpu->arch.hcr_el2 |= HCR_TID3;
if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e3b25dc6c367..94a27a7520f4 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -127,6 +127,16 @@ struct kvm_arch {
#define KVM_ARCH_FLAG_MTE_ENABLED 1
/* At least one vCPU has ran in the VM */
#define KVM_ARCH_FLAG_HAS_RAN_ONCE 2
+ /*
+ * The following two bits are used to indicate the guest's EL1
+ * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
+ * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
+ * Otherwise, the guest's EL1 register width has not yet been
+ * determined yet.
+ */
+#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3
+#define KVM_ARCH_FLAG_EL1_32BIT 4
+
unsigned long flags;
/*
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0d19259454d8..53ae2c0640bc 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1079,7 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
gfn_t gfn;
kvm_pfn_t pfn;
bool logging_active = memslot_is_logging(memslot);
- bool logging_perm_fault = false;
+ bool use_read_lock = false;
unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
unsigned long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1114,7 +1114,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (logging_active) {
force_pte = true;
vma_shift = PAGE_SHIFT;
- logging_perm_fault = (fault_status == FSC_PERM && write_fault);
+ use_read_lock = (fault_status == FSC_PERM && write_fault &&
+ fault_granule == PAGE_SIZE);
} else {
vma_shift = get_vma_page_shift(vma, hva);
}
@@ -1218,7 +1219,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* logging dirty logging, only acquire read lock for permission
* relaxation.
*/
- if (logging_perm_fault)
+ if (use_read_lock)
read_lock(&kvm->mmu_lock);
else
write_lock(&kvm->mmu_lock);
@@ -1268,6 +1269,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
} else {
+ WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n");
+
ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
__pfn_to_phys(pfn), prot,
memcache);
@@ -1280,7 +1283,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
}
out_unlock:
- if (logging_perm_fault)
+ if (use_read_lock)
read_unlock(&kvm->mmu_lock);
else
write_unlock(&kvm->mmu_lock);
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 372da09a2fab..baac2b405f23 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -215,15 +215,11 @@ static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn)
{
- switch(fn) {
- case PSCI_0_2_FN64_CPU_SUSPEND:
- case PSCI_0_2_FN64_CPU_ON:
- case PSCI_0_2_FN64_AFFINITY_INFO:
- /* Disallow these functions for 32bit guests */
- if (vcpu_mode_is_32bit(vcpu))
- return PSCI_RET_NOT_SUPPORTED;
- break;
- }
+ /*
+ * Prevent 32 bit guests from calling 64 bit PSCI functions.
+ */
+ if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu))
+ return PSCI_RET_NOT_SUPPORTED;
return 0;
}
@@ -235,10 +231,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
unsigned long val;
int ret = 1;
- val = kvm_psci_check_allowed_function(vcpu, psci_fn);
- if (val)
- goto out;
-
switch (psci_fn) {
case PSCI_0_2_FN_PSCI_VERSION:
/*
@@ -306,7 +298,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
break;
}
-out:
smccc_set_retval(vcpu, val, 0, 0, 0);
return ret;
}
@@ -318,9 +309,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
unsigned long val;
int ret = 1;
- if (minor > 1)
- return -EINVAL;
-
switch(psci_fn) {
case PSCI_0_2_FN_PSCI_VERSION:
val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1;
@@ -426,6 +414,15 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
*/
int kvm_psci_call(struct kvm_vcpu *vcpu)
{
+ u32 psci_fn = smccc_get_function(vcpu);
+ unsigned long val;
+
+ val = kvm_psci_check_allowed_function(vcpu, psci_fn);
+ if (val) {
+ smccc_set_retval(vcpu, val, 0, 0, 0);
+ return 1;
+ }
+
switch (kvm_psci_version(vcpu)) {
case KVM_ARM_PSCI_1_1:
return kvm_psci_1_x_call(vcpu, 1);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index ecc40c8cd6f6..6c70c6f61c70 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -181,27 +181,51 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
return 0;
}
-static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
+/**
+ * kvm_set_vm_width() - set the register width for the guest
+ * @vcpu: Pointer to the vcpu being configured
+ *
+ * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED
+ * in the VM flags based on the vcpu's requested register width, the HW
+ * capabilities and other options (such as MTE).
+ * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be
+ * consistent with the value of the FLAG_EL1_32BIT bit in the flags.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int kvm_set_vm_width(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *tmp;
+ struct kvm *kvm = vcpu->kvm;
bool is32bit;
- unsigned long i;
is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
+
+ lockdep_assert_held(&kvm->lock);
+
+ if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) {
+ /*
+ * The guest's register width is already configured.
+ * Make sure that the vcpu is consistent with it.
+ */
+ if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags))
+ return 0;
+
+ return -EINVAL;
+ }
+
if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
- return false;
+ return -EINVAL;
/* MTE is incompatible with AArch32 */
- if (kvm_has_mte(vcpu->kvm) && is32bit)
- return false;
+ if (kvm_has_mte(kvm) && is32bit)
+ return -EINVAL;
- /* Check that the vcpus are either all 32bit or all 64bit */
- kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
- if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit)
- return false;
- }
+ if (is32bit)
+ set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
- return true;
+ set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags);
+
+ return 0;
}
/**
@@ -230,10 +254,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
u32 pstate;
mutex_lock(&vcpu->kvm->lock);
- reset_state = vcpu->arch.reset_state;
- WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+ ret = kvm_set_vm_width(vcpu);
+ if (!ret) {
+ reset_state = vcpu->arch.reset_state;
+ WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+ }
mutex_unlock(&vcpu->kvm->lock);
+ if (ret)
+ return ret;
+
/* Reset PMU outside of the non-preemptible section */
kvm_pmu_vcpu_reset(vcpu);
@@ -260,14 +290,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
}
}
- if (!vcpu_allowed_register_width(vcpu)) {
- ret = -EINVAL;
- goto out;
- }
-
switch (vcpu->arch.target) {
default:
- if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
+ if (vcpu_el1_is_32bit(vcpu)) {
pstate = VCPU_RESET_PSTATE_SVC;
} else {
pstate = VCPU_RESET_PSTATE_EL1;
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index f38c40a76251..78cde687383c 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -82,7 +82,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter)
static void *vgic_debug_start(struct seq_file *s, loff_t *pos)
{
- struct kvm *kvm = (struct kvm *)s->private;
+ struct kvm *kvm = s->private;
struct vgic_state_iter *iter;
mutex_lock(&kvm->lock);
@@ -110,7 +110,7 @@ out:
static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct kvm *kvm = (struct kvm *)s->private;
+ struct kvm *kvm = s->private;
struct vgic_state_iter *iter = kvm->arch.vgic.iter;
++*pos;
@@ -122,7 +122,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
static void vgic_debug_stop(struct seq_file *s, void *v)
{
- struct kvm *kvm = (struct kvm *)s->private;
+ struct kvm *kvm = s->private;
struct vgic_state_iter *iter;
/*
@@ -229,8 +229,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq,
static int vgic_debug_show(struct seq_file *s, void *v)
{
- struct kvm *kvm = (struct kvm *)s->private;
- struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
+ struct kvm *kvm = s->private;
+ struct vgic_state_iter *iter = v;
struct vgic_irq *irq;
struct kvm_vcpu *vcpu = NULL;
unsigned long flags;
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 089fc2ffcb43..2e13402be3bd 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -2143,7 +2143,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id,
void *ptr, void *opaque)
{
- struct its_device *dev = (struct its_device *)opaque;
+ struct its_device *dev = opaque;
struct its_collection *collection;
struct kvm *kvm = its->dev->kvm;
struct kvm_vcpu *vcpu = NULL;