From: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
Unmap/flush shadow stage 2 page tables for the nested VMs as well as the
stage 2 page table for the guest hypervisor.
Note: A bunch of the code in mmu.c relating to MMU notifiers is
currently dealt with in an extremely abrupt way, for example by clearing
out an entire shadow stage-2 table. This will be handled in a more
efficient way using the reverse mapping feature in a later version of
the patch series.
Signed-off-by: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
Signed-off-by: Jintack Lim <jintack.lim@xxxxxxxxxx>
Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx>
---
arch/arm64/include/asm/kvm_mmu.h | 3 +++
arch/arm64/include/asm/kvm_nested.h | 3 +++
arch/arm64/kvm/mmu.c | 30 ++++++++++++++++++----
arch/arm64/kvm/nested.c | 39 +++++++++++++++++++++++++++++
4 files changed, 70 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 5c6fb2fb8287..6017645312c5 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -170,6 +170,8 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr);
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+ phys_addr_t addr, phys_addr_t end);
void __init free_hyp_pgds(void);
void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
@@ -179,6 +181,7 @@ void kvm_uninit_stage2_mmu(struct kvm *kvm);
void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
phys_addr_t pa, unsigned long size, bool writable);
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index cbcddc2e8379..0b3f764f44e8 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -112,6 +112,9 @@ extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
struct kvm_s2_trans *trans);
extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
+extern void kvm_nested_s2_wp(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_flush(struct kvm *kvm);
int handle_wfx_nested(struct kvm_vcpu *vcpu, bool is_wfe);
extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index b885a02200a1..35c196a69e3b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -333,13 +333,19 @@ void kvm_unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
__unmap_stage2_range(mmu, start, size, true);
}
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu,
+ phys_addr_t addr, phys_addr_t end)
+{
+ stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
+}
+
static void stage2_flush_memslot(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
- stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush);
+ kvm_stage2_flush_range(&kvm->arch.mmu, addr, end);
}
/**
@@ -362,6 +368,8 @@ static void stage2_flush_vm(struct kvm *kvm)
kvm_for_each_memslot(memslot, bkt, slots)
stage2_flush_memslot(kvm, memslot);
+ kvm_nested_s2_flush(kvm);
+
write_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
}
@@ -1040,6 +1048,8 @@ void stage2_unmap_vm(struct kvm *kvm)
kvm_for_each_memslot(memslot, bkt, slots)
stage2_unmap_memslot(kvm, memslot);
+ kvm_nested_s2_unmap(kvm);
+
write_unlock(&kvm->mmu_lock);
mmap_read_unlock(current->mm);
srcu_read_unlock(&kvm->srcu, idx);
@@ -1139,12 +1149,12 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
}
/**
- * stage2_wp_range() - write protect stage2 memory region range
+ * kvm_stage2_wp_range() - write protect stage2 memory region range
* @mmu: The KVM stage-2 MMU pointer
* @addr: Start address of range
* @end: End address of range
*/
-static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
}
@@ -1175,7 +1185,8 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
- stage2_wp_range(&kvm->arch.mmu, start, end);
+ kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
+ kvm_nested_s2_wp(kvm);
write_unlock(&kvm->mmu_lock);
kvm_flush_remote_tlbs_memslot(kvm, memslot);
}
@@ -1229,7 +1240,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
lockdep_assert_held_write(&kvm->mmu_lock);
- stage2_wp_range(&kvm->arch.mmu, start, end);
+ kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
/*
* Eager-splitting is done when manual-protect is set. We
@@ -1241,6 +1252,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
*/
if (kvm_dirty_log_manual_protect_and_init_set(kvm))
kvm_mmu_split_huge_pages(kvm, start, end);
+
+ kvm_nested_s2_wp(kvm);
}
static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
@@ -1878,6 +1891,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
(range->end - range->start) << PAGE_SHIFT,
range->may_block);
+ kvm_nested_s2_unmap(kvm);
return false;
}
@@ -1912,6 +1926,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
PAGE_SIZE, __pfn_to_phys(pfn),
KVM_PGTABLE_PROT_R, NULL, 0);
+ kvm_nested_s2_unmap(kvm);
return false;
}
@@ -1925,6 +1940,10 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
range->start << PAGE_SHIFT,
size, true);
+ /*
+ * TODO: Handle nested_mmu structures here using the reverse mapping in
+ * a later version of patch series.
+ */
}
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -2182,6 +2201,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
write_lock(&kvm->mmu_lock);
kvm_unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+ kvm_nested_s2_unmap(kvm);
write_unlock(&kvm->mmu_lock);
}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index e4203d106b71..58e8a3dc5fef 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -520,6 +520,45 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
return kvm_inject_nested_sync(vcpu, esr_el2);
}
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ if (kvm_s2_mmu_valid(mmu))
+ kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu));
+ }
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_unmap(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ if (kvm_s2_mmu_valid(mmu))
+ kvm_unmap_stage2_range(mmu, 0, kvm_phys_size(mmu));
+ }
+}
+
+/* expects kvm->mmu_lock to be held */
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+ struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+ if (kvm_s2_mmu_valid(mmu))
+ kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu));
+ }
+}
+
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
int i;
--
2.39.2
