Merge branch kvm-arm64/s1ptw-write-fault into kvmarm-master/fixes

* kvm-arm64/s1ptw-write-fault:
: .
: Fix S1PTW fault handling that was until then always taken
: as a write. From the cover letter:
:
: `Recent developments on the EFI front have resulted in guests that
: simply won't boot if the page tables are in a read-only memslot and
: that you're a bit unlucky in the way S2 gets paged in... The core
: issue is related to the fact that we treat a S1PTW as a write, which
: is close enough to what needs to be done. Until to get to RO memslots.
:
: The first patch fixes this and is definitely a stable candidate. It
: splits the faulting of page tables in two steps (RO translation fault,
: followed by a writable permission fault -- should it even happen).
: The second one documents the slightly odd behaviour of PTW writes to
: RO memslot, which do not result in a KVM_MMIO exit. The last patch is
: totally optional, only tangentially related, and randomly repainting
: stuff (maybe that's contagious, who knows)."
:
: .
KVM: arm64: Convert FSC_* over to ESR_ELx_FSC_*
KVM: arm64: Document the behaviour of S1PTW faults on RO memslots
KVM: arm64: Fix S1PTW handling on RO memslots

Signed-off-by: Marc Zyngier <[e-mail]>

Documentation/virt/kvm/api.rst

···
 mmap() that affects the region will be made visible immediately.  Another
 example is madvise(MADV_DROP).
 
+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.
 
 4.36 KVM_SET_TSS_ADDR
 ---------------------

arch/arm64/include/asm/esr.h

···
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
 #define ESR_ELx_FSC_PERM	(0x0C)
+#define ESR_ELx_FSC_SEA_TTW0	(0x14)
+#define ESR_ELx_FSC_SEA_TTW1	(0x15)
+#define ESR_ELx_FSC_SEA_TTW2	(0x16)
+#define ESR_ELx_FSC_SEA_TTW3	(0x17)
+#define ESR_ELx_FSC_SECC	(0x18)
+#define ESR_ELx_FSC_SECC_TTW0	(0x1c)
+#define ESR_ELx_FSC_SECC_TTW1	(0x1d)
+#define ESR_ELx_FSC_SECC_TTW2	(0x1e)
+#define ESR_ELx_FSC_SECC_TTW3	(0x1f)
 
 /* ISS field definitions for Data Aborts */
 #define ESR_ELx_ISV_SHIFT	(24)

arch/arm64/include/asm/kvm_arm.h

···
 				 BIT(18) |		\
 				 GENMASK(16, 15))
 
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT	ESR_ELx_FSC_FAULT
-#define FSC_ACCESS	ESR_ELx_FSC_ACCESS
-#define FSC_PERM	ESR_ELx_FSC_PERM
-#define FSC_SEA		ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0	(0x14)
-#define FSC_SEA_TTW1	(0x15)
-#define FSC_SEA_TTW2	(0x16)
-#define FSC_SEA_TTW3	(0x17)
-#define FSC_SECC	(0x18)
-#define FSC_SECC_TTW0	(0x1c)
-#define FSC_SECC_TTW1	(0x1d)
-#define FSC_SECC_TTW2	(0x1e)
-#define FSC_SECC_TTW3	(0x1f)
-
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*

arch/arm64/include/asm/kvm_emulate.h

···
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
-	case FSC_SEA:
-	case FSC_SEA_TTW0:
-	case FSC_SEA_TTW1:
-	case FSC_SEA_TTW2:
-	case FSC_SEA_TTW3:
-	case FSC_SECC:
-	case FSC_SECC_TTW0:
-	case FSC_SECC_TTW1:
-	case FSC_SECC_TTW2:
-	case FSC_SECC_TTW3:
+	case ESR_ELx_FSC_EXTABT:
+	case ESR_ELx_FSC_SEA_TTW0:
+	case ESR_ELx_FSC_SEA_TTW1:
+	case ESR_ELx_FSC_SEA_TTW2:
+	case ESR_ELx_FSC_SEA_TTW3:
+	case ESR_ELx_FSC_SECC:
+	case ESR_ELx_FSC_SECC_TTW0:
+	case ESR_ELx_FSC_SECC_TTW1:
+	case ESR_ELx_FSC_SECC_TTW2:
+	case ESR_ELx_FSC_SECC_TTW3:
 		return true;
 	default:
 		return false;
···
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_abt_iss1tw(vcpu))
-		return true;
+	if (kvm_vcpu_abt_iss1tw(vcpu)) {
+		/*
+		 * Only a permission fault on a S1PTW should be
+		 * considered as a write. Otherwise, page tables baked
+		 * in a read-only memslot will result in an exception
+		 * being delivered in the guest.
+		 *
+		 * The drawback is that we end-up faulting twice if the
+		 * guest is using any of HW AF/DB: a translation fault
+		 * to map the page containing the PT (read only at
+		 * first), then a permission fault to allow the flags
+		 * to be set.
+		 */
+		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+		case ESR_ELx_FSC_PERM:
+			return true;
+		default:
+			return false;
+		}
+	}
 
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;

arch/arm64/kvm/hyp/include/hyp/fault.h

···
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {

arch/arm64/kvm/hyp/include/hyp/switch.h

···
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);

arch/arm64/kvm/mmu.c

···
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
-	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
···
 	 * only exception to this is when dirty logging is enabled at runtime
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
-	if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+	if (fault_status != ESR_ELx_FSC_PERM ||
+	    (logging_active && write_fault)) {
 		ret = kvm_mmu_topup_memory_cache(memcache,
 						 kvm_mmu_cache_min_pages(kvm));
 		if (ret)
···
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+		if (fault_status ==  ESR_ELx_FSC_PERM &&
+		    fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
···
 								   &fault_ipa);
 	}
 
-	if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (kvm_vma_mte_allowed(vma)) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
···
 	 * 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)
+	if (fault_status == ESR_ELx_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,
···
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
-	if (fault_status == FSC_FAULT) {
+	if (fault_status == ESR_ELx_FSC_FAULT) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
···
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
-	    fault_status != FSC_ACCESS) {
+	if (fault_status != ESR_ELx_FSC_FAULT &&
+	    fault_status != ESR_ELx_FSC_PERM &&
+	    fault_status != ESR_ELx_FSC_ACCESS) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
···
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
 
-	if (fault_status == FSC_ACCESS) {
+	if (fault_status == ESR_ELx_FSC_ACCESS) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;