Merge tag 'kvmarm-fixes-5.10-5' of...

Merge tag 'kvmarm-fixes-5.10-5' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

kvm/arm64 fixes for 5.10, take #5

- Don't leak page tables on PTE update
- Correctly invalidate TLBs on table to block transition
- Only update permissions if the fault level matches the
  expected mapping size

arch/arm64/include/asm/esr.h

@@ -104,6 +104,7 @@
 /* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
 #define ESR_ELx_FSC		(0x3F)
 #define ESR_ELx_FSC_TYPE	(0x3C)
+#define ESR_ELx_FSC_LEVEL	(0x03)
 #define ESR_ELx_FSC_EXTABT	(0x10)
 #define ESR_ELx_FSC_SERROR	(0x11)
 #define ESR_ELx_FSC_ACCESS	(0x08)

arch/arm64/include/asm/kvm_emulate.h

@@ -350,6 +350,11 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
+static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+}
+
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {

arch/arm64/kvm/hyp/pgtable.c

@@ -470,6 +470,15 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
 		return false;
 
+	/*
+	 * If the PTE was already valid, drop the refcount on the table
+	 * early, as it will be bumped-up again in stage2_map_walk_leaf().
+	 * This ensures that the refcount stays constant across a valid to
+	 * valid PTE update.
+	 */
+	if (kvm_pte_valid(*ptep))
+		put_page(virt_to_page(ptep));
+
 	if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level))
 		goto out;
 
@@ -493,7 +502,13 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
 		return 0;
 
 	kvm_set_invalid_pte(ptep);
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, 0);
+
+	/*
+	 * Invalidate the whole stage-2, as we may have numerous leaf
+	 * entries below us which would otherwise need invalidating
+	 * individually.
+	 */
+	kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu);
 	data->anchor = ptep;
 	return 0;
 }

arch/arm64/kvm/mmu.c

@@ -754,10 +754,12 @@ 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);
-	unsigned long vma_pagesize;
+	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;
 	struct kvm_pgtable *pgt;
 
+	fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
@@ -896,7 +898,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
 		prot |= KVM_PGTABLE_PROT_X;
 
-	if (fault_status == FSC_PERM && !(logging_active && writable)) {
+	/*
+	 * Under the premise of getting a FSC_PERM fault, we just need to relax
+	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
+	 * kvm_pgtable_stage2_map() should be called to change block size.
+	 */
+	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,