KVM: arm64: nv: Unmap/flush shadow stage 2 page tables

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@linaro.org>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240614144552.2773592-5-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 87cc941cfd150c7b01ff74d70d6b118b2aefe724..216ca424bb1684865589648e964a59afd6b36c2f 100644 (file)
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -167,6 +167,8 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
 void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_flush_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);
 
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 82e0484ca26bfeebc664c4e97d5bf31febf2f2d1..6f770405574f311336c15cb176e678dd81a9dade 100644 (file)
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -113,6 +113,9 @@ 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 kvm_init_nv_sysregs(struct kvm *kvm);
 

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 5aed2e9d380d0813db675a0992683db201a76570..4ed93a384255ec27f80219b9298767cc609ff16e 100644 (file)
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -333,13 +333,18 @@ void kvm_stage2_unmap_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 +367,8 @@ 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);
 }
@@ -1035,6 +1042,8 @@ 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);
@@ -1134,12 +1143,12 @@ 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);
 }
@@ -1170,7 +1179,8 @@ 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);
 }
@@ -1224,7 +1234,7 @@ 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
@@ -1236,6 +1246,8 @@ 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 +1890,7 @@ 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;
 }
 
@@ -1891,6 +1904,10 @@ 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)
@@ -2141,6 +2158,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
        write_lock(&kvm->mmu_lock);
        kvm_stage2_unmap_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 2a8821674b10d21cbba7f7f3b9f887b916ec77d4..114a3f59c28b218937fa6b9f0a483335ac307c23 100644 (file)
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -527,6 +527,48 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
        return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+       int i;
+
+       lockdep_assert_held_write(&kvm->mmu_lock);
+
+       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));
+       }
+}
+
+void kvm_nested_s2_unmap(struct kvm *kvm)
+{
+       int i;
+
+       lockdep_assert_held_write(&kvm->mmu_lock);
+
+       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_unmap_range(mmu, 0, kvm_phys_size(mmu));
+       }
+}
+
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+       int i;
+
+       lockdep_assert_held_write(&kvm->mmu_lock);
+
+       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;