[PATCH v3 2/4] KVM: arm64: nv: Do not block when unmapping stage-2 if disallowed

[Oliver Upton <oliver.upton@linux.dev>]

Right now the nested code allows unmap operations on a shadow stage-2 to
block unconditionally. This is wrong in a couple places, such as a
non-blocking MMU notifier or on the back of a sched_in() notifier as
part of shadow MMU recycling.

Carry through whether or not blocking is allowed to
kvm_pgtable_stage2_unmap(). This 'fixes' an issue where stage-2 MMU
reclaim would precipitate a stack overflow from a pile of kvm_sched_in()
callbacks, all trying to recycle a stage-2 MMU.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_mmu.h    |  3 ++-
 arch/arm64/include/asm/kvm_nested.h |  2 +-
 arch/arm64/kvm/mmu.c                | 15 ++++++++-------
 arch/arm64/kvm/nested.c             |  6 +++---
 arch/arm64/kvm/sys_regs.c           |  6 +++---
 5 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index cd4087fbda9a..66d93e320ec8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 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_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block);
 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);
 
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index e8bc6d67aba2..e74b90dcfac4 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -124,7 +124,7 @@ 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_unmap(struct kvm *kvm, bool may_block);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
 unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a509b63bd4dd..0f7658aefa1a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 				   may_block));
 }
 
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block)
 {
-	__unmap_stage2_range(mmu, start, size, true);
+	__unmap_stage2_range(mmu, start, size, may_block);
 }
 
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
-	kvm_nested_s2_unmap(kvm);
+	kvm_nested_s2_unmap(kvm, true);
 
 	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
@@ -1912,7 +1913,7 @@ 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);
+	kvm_nested_s2_unmap(kvm, range->may_block);
 	return false;
 }
 
@@ -2179,8 +2180,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	write_lock(&kvm->mmu_lock);
-	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
-	kvm_nested_s2_unmap(kvm);
+	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
+	kvm_nested_s2_unmap(kvm, true);
 	write_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index df670c14e1c6..58d3b998793a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -634,7 +634,7 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 
 	/* Clear the old state */
 	if (kvm_s2_mmu_valid(s2_mmu))
-		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu), false);
 
 	/*
 	 * The virtual VMID (modulo CnP) will be used as a key when matching
@@ -745,7 +745,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
 	}
 }
 
-void kvm_nested_s2_unmap(struct kvm *kvm)
+void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
 {
 	int i;
 
@@ -755,7 +755,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
 		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));
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
 	}
 }
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index dad88e31f953..e0c7cc16466e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2903,7 +2903,7 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	 * Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
 	 * corresponding VMIDs.
 	 */
-	kvm_nested_s2_unmap(vcpu->kvm);
+	kvm_nested_s2_unmap(vcpu->kvm, true);
 
 	write_unlock(&vcpu->kvm->mmu_lock);
 
@@ -2955,7 +2955,7 @@ union tlbi_info {
 static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
 			       const union tlbi_info *info)
 {
-	kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
+	kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
 }
 
 static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -3050,7 +3050,7 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
 	max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
 	base_addr &= ~(max_size - 1);
 
-	kvm_stage2_unmap_range(mmu, base_addr, max_size);
+	kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
 }
 
 static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
-- 
2.47.0.rc0.187.ge670bccf7e-goog