Add helper functions which operate directly on an ESR value rather than
trying to access the register itself.

These mirror equivalent KVM vCPU wrappers in kvm_emulate.h and allow those
wrappers and KVM's stage-2 fault handling to operate on a plain ESR value.

This is needed to later generate a synthetic fault for the stage-2 page
table pre-faulting mechanism.

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/include/asm/esr.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index f816f5d77f1a..9c0205983d9a 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -437,6 +437,50 @@
 #ifndef __ASSEMBLER__
 #include <asm/types.h>
 
+static __always_inline u8 esr_get_ec(unsigned long esr)
+{
+	return ESR_ELx_EC(esr);
+}
+
+static __always_inline bool esr_trap_is_iabt(unsigned long esr)
+{
+	return esr_get_ec(esr) == ESR_ELx_EC_IABT_LOW;
+}
+
+static __always_inline bool esr_abt_is_s1ptw(unsigned long esr)
+{
+	return esr & ESR_ELx_S1PTW;
+}
+
+/* Always check for S1PTW *before* using this. */
+static __always_inline bool esr_dabt_is_write(unsigned long esr)
+{
+	return esr & ESR_ELx_WNR;
+}
+
+static __always_inline bool esr_dabt_is_cm(unsigned long esr)
+{
+	return esr & ESR_ELx_CM;
+}
+
+static __always_inline bool esr_abt_is_exec_fault(unsigned long esr)
+{
+	return esr_trap_is_iabt(esr) && !esr_abt_is_s1ptw(esr);
+}
+
+static __always_inline bool esr_abt_is_sea(unsigned long esr)
+{
+	switch (esr & ESR_ELx_FSC) {
+	case ESR_ELx_FSC_EXTABT:
+	case ESR_ELx_FSC_SEA_TTW(-1) ... ESR_ELx_FSC_SEA_TTW(3):
+	case ESR_ELx_FSC_SECC:
+	case ESR_ELx_FSC_SECC_TTW(-1) ... ESR_ELx_FSC_SECC_TTW(3):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline unsigned long esr_brk_comment(unsigned long esr)
 {
 	return esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;

-- 
2.55.0

Convert kvm_vcpu_* ESR wrappers in kvm_emulate.h and the stage-2 abort
handling logic in mmu.c to use the newly introduced ESR helpers.

kvm_is_write_fault() is split in two, with esr_abt_is_write_fault()
handling the esr parts of the operation and kvm_is_write_fault() wraps it.

Introduce/modify kvm_s2_fault_is_{perm,exec,write}(),
kvm_s2_perm_fault_granule() so the abort path reads the ESR from a single
place.

This is to allow a later change to permit stage 2 pre-faulting via a
synthetic ESR value.

Remove now-unused kvm_vcpu_dabt_is_cm(), kvm_vcpu_trap_is_exec_fault() and
kvm_vcpu_trap_get_perm_fault_granule().

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 52 +++++++-----------------
 arch/arm64/kvm/mmu.c                 | 76 ++++++++++++++++++++++--------------
 2 files changed, 61 insertions(+), 67 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a3c1928bdf74..a3b272265554 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -411,18 +411,13 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 
 static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
+	return esr_abt_is_s1ptw(kvm_vcpu_get_esr(vcpu));
 }
 
 /* Always check for S1PTW *before* using this. */
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
-}
-
-static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
-{
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM);
+	return esr_dabt_is_write(kvm_vcpu_get_esr(vcpu));
 }
 
 static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
@@ -438,17 +433,12 @@ static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu
 
 static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
 {
-	return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
+	return esr_get_ec(kvm_vcpu_get_esr(vcpu));
 }
 
 static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
-}
-
-static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
-{
-	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+	return esr_trap_is_iabt(kvm_vcpu_get_esr(vcpu));
 }
 
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
@@ -468,26 +458,9 @@ bool kvm_vcpu_trap_is_translation_fault(const struct kvm_vcpu *vcpu)
 	return esr_fsc_is_translation_fault(kvm_vcpu_get_esr(vcpu));
 }
 
-static inline
-u64 kvm_vcpu_trap_get_perm_fault_granule(const struct kvm_vcpu *vcpu)
-{
-	unsigned long esr = kvm_vcpu_get_esr(vcpu);
-
-	BUG_ON(!esr_fsc_is_permission_fault(esr));
-	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(esr & ESR_ELx_FSC_LEVEL));
-}
-
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
-	switch (kvm_vcpu_trap_get_fault(vcpu)) {
-	case ESR_ELx_FSC_EXTABT:
-	case ESR_ELx_FSC_SEA_TTW(-1) ... ESR_ELx_FSC_SEA_TTW(3):
-	case ESR_ELx_FSC_SECC:
-	case ESR_ELx_FSC_SECC_TTW(-1) ... ESR_ELx_FSC_SECC_TTW(3):
-		return true;
-	default:
-		return false;
-	}
+	return esr_abt_is_sea(kvm_vcpu_get_esr(vcpu));
 }
 
 static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
@@ -496,9 +469,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 	return ESR_ELx_SYS64_ISS_RT(esr);
 }
 
-static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+static inline bool esr_abt_is_write_fault(unsigned long esr)
 {
-	if (kvm_vcpu_abt_iss1tw(vcpu)) {
+	if (esr_abt_is_s1ptw(esr)) {
 		/*
 		 * Only a permission fault on a S1PTW should be
 		 * considered as a write. Otherwise, page tables baked
@@ -511,13 +484,18 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 		 * first), then a permission fault to allow the flags
 		 * to be set.
 		 */
-		return kvm_vcpu_trap_is_permission_fault(vcpu);
+		return esr_fsc_is_permission_fault(esr);
 	}
 
-	if (kvm_vcpu_trap_is_iabt(vcpu))
+	if (esr_trap_is_iabt(esr))
 		return false;
 
-	return kvm_vcpu_dabt_iswrite(vcpu);
+	return esr_dabt_is_write(esr);
+}
+
+static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	return esr_abt_is_write_fault(kvm_vcpu_get_esr(vcpu));
 }
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 74e7e7f7564c..d1a6e25c3095 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1605,10 +1605,35 @@ struct kvm_s2_fault_desc {
 	unsigned long		hva;
 };
 
+static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
+{
+	return esr_fsc_is_permission_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+}
+
+static bool kvm_s2_fault_is_exec(const struct kvm_s2_fault_desc *s2fd)
+{
+	return esr_abt_is_exec_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+}
+
+static bool kvm_s2_fault_is_write(const struct kvm_s2_fault_desc *s2fd)
+{
+	return esr_abt_is_write_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+}
+
+static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
+{
+	u64 level;
+
+	if (!kvm_s2_fault_is_perm(s2fd))
+		return 0;
+	level = kvm_vcpu_get_esr(s2fd->vcpu) & ESR_ELx_FSC_LEVEL;
+	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
+}
+
 static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 {
 	bool write_fault, exec_fault;
-	bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu);
+	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt;
@@ -1632,8 +1657,8 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	else
 		gfn = s2fd->fault_ipa >> PAGE_SHIFT;
 
-	write_fault = kvm_is_write_fault(s2fd->vcpu);
-	exec_fault = kvm_vcpu_trap_is_exec_fault(s2fd->vcpu);
+	write_fault = kvm_s2_fault_is_write(s2fd);
+	exec_fault = kvm_s2_fault_is_exec(s2fd);
 
 	VM_WARN_ON_ONCE(write_fault && exec_fault);
 
@@ -1840,11 +1865,6 @@ static short kvm_s2_resolve_vma_size(const struct kvm_s2_fault_desc *s2fd,
 	return vma_shift;
 }
 
-static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
-{
-	return kvm_vcpu_trap_is_permission_fault(s2fd->vcpu);
-}
-
 static int kvm_s2_fault_get_vma_info(const struct kvm_s2_fault_desc *s2fd,
 				     struct kvm_s2_fault_vma_info *s2vi)
 {
@@ -1910,7 +1930,7 @@ static int kvm_s2_fault_pin_pfn(const struct kvm_s2_fault_desc *s2fd,
 		return ret;
 
 	s2vi->pfn = __kvm_faultin_pfn(s2fd->memslot, get_canonical_gfn(s2fd, s2vi),
-				      kvm_is_write_fault(s2fd->vcpu) ? FOLL_WRITE : 0,
+				      kvm_s2_fault_is_write(s2fd) ? FOLL_WRITE : 0,
 				      &s2vi->map_writable, &s2vi->page);
 	if (unlikely(is_error_noslot_pfn(s2vi->pfn))) {
 		if (s2vi->pfn == KVM_PFN_ERR_HWPOISON) {
@@ -1968,7 +1988,7 @@ static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
 {
 	struct kvm *kvm = s2fd->vcpu->kvm;
 
-	if (kvm_vcpu_trap_is_exec_fault(s2fd->vcpu) && s2vi->map_non_cacheable)
+	if (kvm_s2_fault_is_exec(s2fd) && s2vi->map_non_cacheable)
 		return -ENOEXEC;
 
 	/*
@@ -1986,13 +2006,13 @@ static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
 
 	if (s2vi->map_writable && (s2vi->device ||
 				   !memslot_is_logging(s2fd->memslot) ||
-				   kvm_is_write_fault(s2fd->vcpu)))
+				   kvm_s2_fault_is_write(s2fd)))
 		*prot |= KVM_PGTABLE_PROT_W;
 
 	if (s2fd->nested)
 		*prot = adjust_nested_fault_perms(s2fd->nested, *prot);
 
-	if (kvm_vcpu_trap_is_exec_fault(s2fd->vcpu))
+	if (kvm_s2_fault_is_exec(s2fd))
 		*prot |= KVM_PGTABLE_PROT_X;
 
 	if (s2vi->map_non_cacheable)
@@ -2034,8 +2054,7 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 	if (mmu_invalidate_retry(kvm, s2vi->mmu_seq))
 		goto out_unlock;
 
-	perm_fault_granule = (kvm_s2_fault_is_perm(s2fd) ?
-			      kvm_vcpu_trap_get_perm_fault_granule(s2fd->vcpu) : 0);
+	perm_fault_granule = kvm_s2_perm_fault_granule(s2fd);
 	mapping_size = s2vi->vma_pagesize;
 	pfn = s2vi->pfn;
 	gfn = s2vi->gfn;
@@ -2103,7 +2122,7 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 
 static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 {
-	bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu);
+	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
 	struct kvm_s2_fault_vma_info s2vi = {};
 	enum kvm_pgtable_prot prot;
 	void *memcache;
@@ -2250,7 +2269,7 @@ int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s2_trans nested_trans, *nested = NULL;
-	unsigned long esr;
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
 	phys_addr_t fault_ipa; /* The address we faulted on */
 	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
 	struct kvm_memory_slot *memslot;
@@ -2259,11 +2278,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	if (kvm_vcpu_abt_issea(vcpu))
+	if (esr_abt_is_sea(esr))
 		return kvm_handle_guest_sea(vcpu);
 
-	esr = kvm_vcpu_get_esr(vcpu);
-
 	/*
 	 * The fault IPA should be reliable at this point as we're not dealing
 	 * with an SEA.
@@ -2272,7 +2289,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
 		return -EFAULT;
 
-	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+	is_iabt = esr_trap_is_iabt(esr);
 
 	if (esr_fsc_is_translation_fault(esr)) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
@@ -2289,7 +2306,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), esr,
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
@@ -2298,9 +2315,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	    !esr_fsc_is_access_flag_fault(esr) &&
 	    !esr_fsc_is_excl_atomic_fault(esr)) {
 		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),
-			(unsigned long)kvm_vcpu_get_esr(vcpu));
+			esr_get_ec(esr),
+			(unsigned long)(esr & ESR_ELx_FSC),
+			(unsigned long)esr);
 		return -EFAULT;
 	}
 
@@ -2349,7 +2366,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn = ipa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
-	write_fault = kvm_is_write_fault(vcpu);
+	write_fault = esr_abt_is_write_fault(esr);
 	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
 		/*
 		 * The guest has put either its instructions or its page-tables
@@ -2362,7 +2379,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (kvm_vcpu_abt_iss1tw(vcpu)) {
+		if (esr_abt_is_s1ptw(esr)) {
 			ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			goto out_unlock;
 		}
@@ -2377,7 +2394,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		 * So let's assume that the guest is just being
 		 * cautious, and skip the instruction.
 		 */
-		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
+		if (kvm_is_error_hva(hva) && esr_dabt_is_cm(esr)) {
 			kvm_incr_pc(vcpu);
 			ret = 1;
 			goto out_unlock;
@@ -2414,9 +2431,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	if (kvm_vm_is_protected(vcpu->kvm)) {
 		ret = pkvm_mem_abort(&s2fd);
 	} else {
-		VM_WARN_ON_ONCE(kvm_vcpu_trap_is_permission_fault(vcpu) &&
-				!write_fault &&
-				!kvm_vcpu_trap_is_exec_fault(vcpu));
+		VM_WARN_ON_ONCE(kvm_s2_fault_is_perm(&s2fd) && !write_fault &&
+				!kvm_s2_fault_is_exec(&s2fd));
 
 		if (kvm_slot_has_gmem(memslot))
 			ret = gmem_abort(&s2fd);

-- 
2.55.0

kvm_handle_guest_abort() establishes a kvm_s2_fault_desc data structure,
s2fd, to store and propagate state to either pkvm_mem_abort(), gmem_abort()
or user_mem_abort() handlers.

Each of these, however, examines the Exception Syndrome Register (ESR) via
s2fd->vcpu.

Introduce an s2fd->esr field to abstract this and propagate it to callers.

The value of this (beyond refactoring) is to be able to later generate
faults with a synthetic esr, specifically to implement stage 2 page table
pre-faulting.

Abort handlers which use kvm_s2_fault_desc - gmem_abort() and
user_mem_abort() - now only reference s2fd->esr and do not look it up in
any other way, which makes it safe to pass a synthetic s2fd->esr value to
these functions.

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/kvm/mmu.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d1a6e25c3095..8303121e3332 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1603,21 +1603,22 @@ struct kvm_s2_fault_desc {
 	struct kvm_s2_trans	*nested;
 	struct kvm_memory_slot	*memslot;
 	unsigned long		hva;
+	unsigned long		esr;
 };
 
 static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
 {
-	return esr_fsc_is_permission_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+	return esr_fsc_is_permission_fault(s2fd->esr);
 }
 
 static bool kvm_s2_fault_is_exec(const struct kvm_s2_fault_desc *s2fd)
 {
-	return esr_abt_is_exec_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+	return esr_abt_is_exec_fault(s2fd->esr);
 }
 
 static bool kvm_s2_fault_is_write(const struct kvm_s2_fault_desc *s2fd)
 {
-	return esr_abt_is_write_fault(kvm_vcpu_get_esr(s2fd->vcpu));
+	return esr_abt_is_write_fault(s2fd->esr);
 }
 
 static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
@@ -1626,7 +1627,7 @@ static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
 
 	if (!kvm_s2_fault_is_perm(s2fd))
 		return 0;
-	level = kvm_vcpu_get_esr(s2fd->vcpu) & ESR_ELx_FSC_LEVEL;
+	level = s2fd->esr & ESR_ELx_FSC_LEVEL;
 	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
 }
 
@@ -1997,7 +1998,7 @@ static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
 	 * and trigger the exception here. Since the memslot is valid, inject
 	 * the fault back to the guest.
 	 */
-	if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(s2fd->vcpu))) {
+	if (esr_fsc_is_excl_atomic_fault(s2fd->esr)) {
 		kvm_inject_dabt_excl_atomic(s2fd->vcpu, kvm_vcpu_get_hfar(s2fd->vcpu));
 		return 1;
 	}
@@ -2426,6 +2427,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		.nested		= nested,
 		.memslot	= memslot,
 		.hva		= hva,
+		.esr		= esr,
 	};
 
 	if (kvm_vm_is_protected(vcpu->kvm)) {

-- 
2.55.0

kvm_handle_guest_abort() establishes a kvm_s2_fault_desc data structure,
s2fd, to store and propagate state to either pkvm_mem_abort(), gmem_abort()
or user_mem_abort() handlers.

Each of these, however, examines the state of the stage 2 MMU via
vcpu->arch.hw_mmu.

Introduce an s2fd->mmu field to abstract this and propagate it to callers.

Similar to adding the esr field, this allows injection of synthetic faults
with the ultimate intention of implementing stage 2 page table
pre-faulting.

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/kvm/mmu.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8303121e3332..f402481e8a4e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1604,6 +1604,7 @@ struct kvm_s2_fault_desc {
 	struct kvm_memory_slot	*memslot;
 	unsigned long		hva;
 	unsigned long		esr;
+	struct kvm_s2_mmu	*mmu;
 };
 
 static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
@@ -1637,7 +1638,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
-	struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt;
+	struct kvm_pgtable *pgt = s2fd->mmu->pgt;
 	unsigned long mmu_seq;
 	struct page *page;
 	struct kvm *kvm = s2fd->vcpu->kvm;
@@ -1735,7 +1736,7 @@ static int pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 {
 	unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;
 	struct kvm_vcpu *vcpu = s2fd->vcpu;
-	struct kvm_pgtable *pgt = vcpu->arch.hw_mmu->pgt;
+	struct kvm_pgtable *pgt = s2fd->mmu->pgt;
 	struct mm_struct *mm = current->mm;
 	struct kvm *kvm = vcpu->kvm;
 	void *hyp_memcache;
@@ -2050,7 +2051,7 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 	int ret;
 
 	kvm_fault_lock(kvm);
-	pgt = s2fd->vcpu->arch.hw_mmu->pgt;
+	pgt = s2fd->mmu->pgt;
 	ret = -EAGAIN;
 	if (mmu_invalidate_retry(kvm, s2vi->mmu_seq))
 		goto out_unlock;
@@ -2271,6 +2272,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s2_trans nested_trans, *nested = NULL;
 	unsigned long esr = kvm_vcpu_get_esr(vcpu);
+	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 	phys_addr_t fault_ipa; /* The address we faulted on */
 	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
 	struct kvm_memory_slot *memslot;
@@ -2300,7 +2302,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 
 		/* Falls between the IPA range and the PARange? */
-		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
+		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(mmu->vtcr))) {
 			fault_ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(vcpu));
 
 			return kvm_inject_sea(vcpu, is_iabt, fault_ipa);
@@ -2337,8 +2339,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	 * nothing to walk and we treat it as a 1:1 before going through the
 	 * canonical translation.
 	 */
-	if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) &&
-	    vcpu->arch.hw_mmu->nested_stage2_enabled) {
+	if (kvm_is_nested_s2_mmu(vcpu->kvm, mmu) &&
+	    mmu->nested_stage2_enabled) {
 		u32 esr;
 
 		ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
@@ -2413,7 +2415,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	}
 
 	/* Userspace should not be able to register out-of-bounds IPAs */
-	VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
+	VM_BUG_ON(ipa >= kvm_phys_size(mmu));
 
 	if (esr_fsc_is_access_flag_fault(esr)) {
 		handle_access_fault(vcpu, fault_ipa);
@@ -2428,6 +2430,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		.memslot	= memslot,
 		.hva		= hva,
 		.esr		= esr,
+		.mmu		= mmu,
 	};
 
 	if (kvm_vm_is_protected(vcpu->kvm)) {

-- 
2.55.0

When stage 2 page tables fault the net result may either be that a page is
mapped, an error occurred or the fault should be retried (-EAGAIN).

When a fault succeeds it may be upgraded to a PMD size via
transparent_hugepage_adjust().

In order to support KVM pre-faulting the outcome of the fault and the
mapping size must be recorded.

Track the mapping size via new kvm_s2_fault_result struct, which is
threaded through gmem_abort(), user_mem_abort() and kvm_s2_fault_map().

PKVM and SEA aren't relevant to synthetic pre-faulting so neither
kvm_inject_sea() nor pkvm_mem_abort() are altered.

Actual hardware faulting doesn't require this information, so
kvm_handle_guest_abort() simply passes NULL kvm_s2_fault_result to
gmem_abort() and user_mem_abort().

A non-NULL result also tells the abort handlers that the caller is
pre-faulting rather than a vcpu, in which case -EAGAIN is propagated to the
caller to allow the pre-fault to be retried.

No functional change intended.

Suggested-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/kvm/mmu.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index f402481e8a4e..13541218cadb 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1607,6 +1607,10 @@ struct kvm_s2_fault_desc {
 	struct kvm_s2_mmu	*mmu;
 };
 
+struct kvm_s2_fault_result {
+	unsigned long mapping_size;
+};
+
 static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
 {
 	return esr_fsc_is_permission_fault(s2fd->esr);
@@ -1632,7 +1636,8 @@ static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
 	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
 }
 
-static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
+static int gmem_abort(const struct kvm_s2_fault_desc *s2fd,
+		      struct kvm_s2_fault_result *result)
 {
 	bool write_fault, exec_fault;
 	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
@@ -1714,7 +1719,13 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	if ((prot & KVM_PGTABLE_PROT_W) && !ret)
 		mark_page_dirty_in_slot(kvm, s2fd->memslot, gfn);
 
-	return ret != -EAGAIN ? ret : 0;
+	if (ret == -EAGAIN)
+		return result ? ret : 0;
+
+	if (result && !ret)
+		result->mapping_size = PAGE_SIZE;
+
+	return ret;
 }
 
 struct kvm_s2_fault_vma_info {
@@ -2038,7 +2049,8 @@ static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
 static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 			    const struct kvm_s2_fault_vma_info *s2vi,
 			    enum kvm_pgtable_prot prot,
-			    void *memcache)
+			    void *memcache,
+			    struct kvm_s2_fault_result *result)
 {
 	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
 	bool writable = prot & KVM_PGTABLE_PROT_W;
@@ -2117,12 +2129,17 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
 		mark_page_dirty_in_slot(kvm, s2fd->memslot, gpa_to_gfn(ipa));
 	}
 
-	if (ret != -EAGAIN)
-		return ret;
-	return 0;
+	if (ret == -EAGAIN)
+		return result ? ret : 0;
+
+	if (result && !ret)
+		result->mapping_size = mapping_size;
+
+	return ret;
 }
 
-static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd)
+static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd,
+			  struct kvm_s2_fault_result *result)
 {
 	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
 	struct kvm_s2_fault_vma_info s2vi = {};
@@ -2161,7 +2178,7 @@ static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 		return ret;
 	}
 
-	return kvm_s2_fault_map(s2fd, &s2vi, prot, memcache);
+	return kvm_s2_fault_map(s2fd, &s2vi, prot, memcache, result);
 }
 
 /* Resolve the access fault by making the page young again. */
@@ -2440,9 +2457,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 				!kvm_s2_fault_is_exec(&s2fd));
 
 		if (kvm_slot_has_gmem(memslot))
-			ret = gmem_abort(&s2fd);
+			ret = gmem_abort(&s2fd, NULL);
 		else
-			ret = user_mem_abort(&s2fd);
+			ret = user_mem_abort(&s2fd, NULL);
 	}
 
 	if (ret == 0)

-- 
2.55.0

topup_mmu_memcache() sizes the page-table cache from
vcpu->arch.hw_mmu, which is the MMU that faulted.

Pass the target s2fd->mmu instead, so the mmu used can be controlled by the
caller.

For a guest abort this is vcpu->arch.hw_mmu, so this commit introduces no
functional change in practice.

However, it's necessary for a future change which introduces stage 2
pre-faulting which must always target the canonical MMU regardless of the
vCPU's last-run context.

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/kvm/mmu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 13541218cadb..8c23fef4ecf8 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1554,9 +1554,9 @@ static void *get_mmu_memcache(struct kvm_vcpu *vcpu)
 		return &vcpu->arch.pkvm_memcache;
 }
 
-static int topup_mmu_memcache(struct kvm_vcpu *vcpu, void *memcache)
+static int topup_mmu_memcache(struct kvm_s2_mmu *mmu, void *memcache)
 {
-	int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+	int min_pages = kvm_mmu_cache_min_pages(mmu);
 
 	if (!is_protected_kvm_enabled())
 		return kvm_mmu_topup_memory_cache(memcache, min_pages);
@@ -1654,7 +1654,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd,
 
 	if (!perm_fault) {
 		memcache = get_mmu_memcache(s2fd->vcpu);
-		ret = topup_mmu_memcache(s2fd->vcpu, memcache);
+		ret = topup_mmu_memcache(s2fd->mmu, memcache);
 		if (ret)
 			return ret;
 	}
@@ -1755,7 +1755,7 @@ static int pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
 	int ret;
 
 	hyp_memcache = get_mmu_memcache(vcpu);
-	ret = topup_mmu_memcache(vcpu, hyp_memcache);
+	ret = topup_mmu_memcache(s2fd->mmu, hyp_memcache);
 	if (ret)
 		return -ENOMEM;
 
@@ -2159,7 +2159,7 @@ static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd,
 	memcache = get_mmu_memcache(s2fd->vcpu);
 	if (!perm_fault || memslot_is_logging(s2fd->memslot) ||
 	    is_protected_kvm_enabled()) {
-		ret = topup_mmu_memcache(s2fd->vcpu, memcache);
+		ret = topup_mmu_memcache(s2fd->mmu, memcache);
 		if (ret)
 			return ret;
 	}

-- 
2.55.0

Currently kvm_s2_fault_pin_pfn() handles a poisoned page directly by
sending a SIGBUS signal itself.

This is an odd place to do it, the caller should decide what to do with
errors, so move the handling to the sole caller, user_mem_abort().

This lays the foundation for stage 2 pre-faulting which, arising from a
synthetic fault, should not send a signal.

In order to do so, check to see if user_mem_abort()'s caller has set result
- i.e. whether it wants to be informed about the outcome of the fault
handling.

If it does, then it is implied that it should handle the -EHWPOISON error
itself. This is the case for pre-faulting.

Otherwise this is real hardware, so send the signal.

No functional change intended.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/kvm/mmu.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c23fef4ecf8..eae085a622ff 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1946,10 +1946,8 @@ static int kvm_s2_fault_pin_pfn(const struct kvm_s2_fault_desc *s2fd,
 				      kvm_s2_fault_is_write(s2fd) ? FOLL_WRITE : 0,
 				      &s2vi->map_writable, &s2vi->page);
 	if (unlikely(is_error_noslot_pfn(s2vi->pfn))) {
-		if (s2vi->pfn == KVM_PFN_ERR_HWPOISON) {
-			kvm_send_hwpoison_signal(s2fd->hva, __ffs(s2vi->vma_pagesize));
-			return 0;
-		}
+		if (s2vi->pfn == KVM_PFN_ERR_HWPOISON)
+			return -EHWPOISON;
 		return -EFAULT;
 	}
 
@@ -2169,6 +2167,13 @@ static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd,
 	 * get block mapping for device MMIO region.
 	 */
 	ret = kvm_s2_fault_pin_pfn(s2fd, &s2vi);
+	if (ret == -EHWPOISON) {
+		/* If result is specified, let the caller handle this. */
+		if (result)
+			return -EHWPOISON;
+		kvm_send_hwpoison_signal(s2fd->hva, __ffs(s2vi.vma_pagesize));
+		return 0;
+	}
 	if (ret != 1)
 		return ret;
 

-- 
2.55.0

From: Jack Thomson <jackabt@amazon.com>

Allow callers of kvm_pgtable_get_leaf() to specify the page-table walk
flags, in preparation for performing walks under the MMU read lock.

Reading a stage-2 leaf while only holding the read lock requires
KVM_PGTABLE_WALK_SHARED: parallel faults (which also only hold the read
lock) can unlink table pages and free them via RCU, so the walker must
be inside an RCU read-side critical section, which the shared walk flag
provides via kvm_pgtable_walk_begin().

All existing callers either hold the write lock, walk with interrupts
disabled, or run at hyp where shared walks are rejected; they keep the
current behaviour by passing no flags.

No functional change intended.

Signed-off-by: Jack Thomson <jackabt@amazon.com>
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/include/asm/kvm_pgtable.h  |  5 ++++-
 arch/arm64/kvm/hyp/nvhe/mem_protect.c | 10 +++++-----
 arch/arm64/kvm/hyp/pgtable.c          |  5 +++--
 arch/arm64/kvm/mmu.c                  |  2 +-
 arch/arm64/kvm/nested.c               |  2 +-
 5 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 41a8687938eb..d0167f7dfbee 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -859,6 +859,8 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
  * @addr:	Input address for the start of the walk.
  * @ptep:	Pointer to storage for the retrieved PTE.
  * @level:	Pointer to storage for the level of the retrieved PTE.
+ * @flags:	Flags to control the page-table walk
+ *		(see struct kvm_pgtable_visit_ctx).
  *
  * The offset of @addr within a page is ignored.
  *
@@ -869,7 +871,8 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, s8 *level);
+			 kvm_pte_t *ptep, s8 *level,
+			 enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 39aa8911f62c..23a57312b981 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -532,7 +532,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 	int ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
-	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level, 0);
 	if (ret)
 		return ret;
 
@@ -910,7 +910,7 @@ static int get_valid_guest_pte(struct pkvm_hyp_vm *vm, u64 ipa, kvm_pte_t *ptep,
 	s8 level;
 	int ret;
 
-	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
 	if (ret)
 		return ret;
 	if (guest_pte_is_poisoned(pte))
@@ -959,7 +959,7 @@ int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu)
 	ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(&hyp_vcpu->vcpu));
 
 	guest_lock_component(vm);
-	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
 	if (ret)
 		goto unlock;
 
@@ -1315,7 +1315,7 @@ static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm,
 		return -EPERM;
 	}
 
-	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level, 0);
 	if (ret)
 		return ret;
 
@@ -1544,7 +1544,7 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
 	s8 level;
 	int ret;
 
-	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
 	if (ret)
 		return ret;
 	if (!kvm_pte_valid(pte))
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index b74dd5ce1efd..347eec3957d6 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -298,12 +298,13 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
 }
 
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, s8 *level)
+			 kvm_pte_t *ptep, s8 *level,
+			 enum kvm_pgtable_walk_flags flags)
 {
 	struct leaf_walk_data data;
 	struct kvm_pgtable_walker walker = {
 		.cb	= leaf_walker,
-		.flags	= KVM_PGTABLE_WALK_LEAF,
+		.flags	= flags | KVM_PGTABLE_WALK_LEAF,
 		.arg	= &data,
 	};
 	int ret;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index eae085a622ff..9c922b498adb 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -866,7 +866,7 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	 * IPI-ing threads).
 	 */
 	local_irq_save(flags);
-	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
+	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level, 0);
 	local_irq_restore(flags);
 
 	if (ret)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 17123f0b6dab..3488d5ad225b 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -654,7 +654,7 @@ static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
 		return 0;
 
 	tmp &= ~(sz - 1);
-	if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
+	if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL, 0))
 		goto again;
 	if (!(pte & PTE_VALID))
 		goto again;

-- 
2.55.0

Implement KVM stage 2 page table pre-faulting for the arm64 architecture,
with the core of the implementation in kvm_arch_vcpu_pre_fault_memory().

Pre-fault by first trying a page table walk under the MMU read lock then,
if it fails, injecting a synthetic data abort at the page table level
at which the page table walk failed.

This is necessarily racey as reclaim might happen at any time. Successfully
pre-faulting can therefore only guarantee that each GPA was observed to be
mapped at least once.

Protected KVM (pKVM) is not supported at all because pKVM creates VMs and
vCPUs when first run, meaning any attempt to pre-fault prior to this cannot
succeed.

A retry mechanic is implemented when user_mem_abort() or gmem_abort() fail
to map memory due to a benign failure where a hardware abort would not
result in an error.

An invalid memslot (i.e. a memslot with the KVM_MEMSLOT_INVALID flag set)
results in the operation returning -EAGAIN without a retry mechanic,
because an invalid memslot means the pre-fault operation raced with memslot
reclaim, and since the SRCU lock is held, progress cannot be made, and the
user must retry.

This work is based with gratitude on Jack Thomson's original series, its
previous revisions and the feedback they received.

Link: https://patch.msgid.link/20260612162354.73378-1-jackabt.amazon@gmail.com/
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 arch/arm64/include/asm/kvm_pkvm.h |   2 +-
 arch/arm64/kvm/Kconfig            |   1 +
 arch/arm64/kvm/arm.c              |   1 +
 arch/arm64/kvm/mmu.c              | 141 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 144 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index beea00e693a0..4d6e5765e9e5 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -44,9 +44,9 @@ static inline bool kvm_pkvm_ext_allowed(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
 		return true;
 	case KVM_CAP_ARM_MTE:
-		return false;
 	case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
 	case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES:
+	case KVM_CAP_PRE_FAULT_MEMORY:
 		return false;
 	default:
 		return !kvm || !kvm_vm_is_protected(kvm);
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 449154f9a485..71233068b7cb 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -37,6 +37,7 @@ menuconfig KVM
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	select KVM_GUEST_MEMFD
+	select KVM_GENERIC_PRE_FAULT_MEMORY
 	help
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index ccae82c1242b..58ac70f31d84 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -393,6 +393,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_COUNTER_OFFSET:
 	case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS:
 	case KVM_CAP_ARM_SEA_TO_USER:
+	case KVM_CAP_PRE_FAULT_MEMORY:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 9c922b498adb..17f1f6d36f2b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cleanup.h>
 #include <linux/mman.h>
 #include <linux/kvm_host.h>
 #include <linux/io.h>
@@ -2835,3 +2836,143 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
 
 	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
 }
+
+/*
+ * Try to walk to the specified GPA in canonical mmu - if unmapped returns 0, if
+ * mapped returns the granule size, otherwise returns an error.
+ */
+static long kvm_walk_s2(struct kvm_pgtable *pgt,
+			gpa_t gpa, s8 *level)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	kvm_pte_t pte;
+	long ret;
+
+	guard(read_lock)(&kvm->mmu_lock);
+
+	ret = kvm_pgtable_get_leaf(pgt, gpa, &pte, level,
+				   KVM_PGTABLE_WALK_SHARED);
+	if (ret)
+		return ret;
+	/* Unpopulated, must fault. */
+	if (!kvm_pte_valid(pte))
+		return 0;
+	return kvm_granule_size(*level);
+}
+
+/* Synthesised data abort at specified page table level. */
+#define PRE_FAULT_ESR(level)				\
+	 ((ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT) |	\
+	  ESR_ELx_IL | ESR_ELx_FSC_FAULT_L(level))
+
+/* Retrieve either a read-only or a read/write hva. */
+static hva_t gfn_to_hva_memslot_read(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return gfn_to_hva_memslot_prot(slot, gfn, /*writable=*/NULL);
+}
+
+static long __pre_fault_s2(struct kvm_s2_mmu *mmu, struct kvm_vcpu *vcpu,
+			   gpa_t gpa, struct kvm_memory_slot *memslot, s8 level)
+{
+	const bool is_gmem = kvm_slot_has_gmem(memslot);
+	const gfn_t gfn = gpa_to_gfn(gpa);
+	const hva_t hva = is_gmem ? 0 : gfn_to_hva_memslot_read(memslot, gfn);
+	const struct kvm_s2_fault_desc s2fd = {
+		.vcpu		= vcpu,
+		.fault_ipa	= gpa,
+		.nested		= NULL,
+		.memslot	= memslot,
+		.hva		= hva,
+		.esr		= PRE_FAULT_ESR(level),
+		.mmu		= mmu,
+	};
+	struct kvm_s2_fault_result result = {};
+	long ret;
+
+	if (kvm_is_error_hva(hva))
+		return -EFAULT;
+
+	if (is_gmem)
+		ret = gmem_abort(&s2fd, &result);
+	else
+		ret = user_mem_abort(&s2fd, &result);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+	return result.mapping_size;
+}
+
+static long pre_fault_s2(struct kvm_s2_mmu *mmu, struct kvm_vcpu *vcpu,
+			 gpa_t gpa, struct kvm_memory_slot *memslot)
+{
+	s8 level;
+	long ret;
+
+	/* Try a walk first. */
+	ret = kvm_walk_s2(mmu->pgt, gpa, &level);
+	if (ret)
+		return ret;
+	/* OK, have to fault page in. */
+	return __pre_fault_s2(mmu, vcpu, gpa, memslot, level);
+}
+
+static unsigned long
+pre_fault_bytes_consumed(gpa_t gpa, unsigned long granule_size,
+			 unsigned long bytes_remaining)
+{
+	/* Granules are always a power-of-2. */
+	const unsigned long granule_bytes_remaining =
+		granule_size - (gpa % granule_size);
+
+	return min(granule_bytes_remaining, bytes_remaining);
+}
+
+/* If you lose the race this many times, time to give up. */
+#define MAX_PRE_FAULT_RETRIES 3
+
+/**
+ * kvm_arch_vcpu_pre_fault_memory - pre-fault stage-2 page tables for the
+ * specified GPA.
+ * @vcpu:	The VCPU pointer
+ * @range:	{gpa, size, flags} tuple
+ *
+ * The mapping performed is always best-effort - faulting in is necessarily
+ * racey. The ranges faulted in are canonical, nested page tables are ignored.
+ *
+ * @range->gpa specifies the GPA to pre-fault, @range->size specifies how many
+ * bytes remain to be pre-faulted and @range->flags is reserved and must be 0.
+ *
+ * Returns: the number of bytes the pre-fault consumed, or an error.
+ */
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+				    struct kvm_pre_fault_memory *range)
+{
+	struct kvm *kvm = vcpu->kvm;
+	const u64 bytes_remaining = range->size;
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu; /* Canonical. */
+	struct kvm_memory_slot *memslot;
+	const gpa_t gpa = range->gpa;
+	int num_retries = 0;
+	long ret;
+
+	/*
+	 * pKVM is unsupported as their vCPUs are instantiated on first run and
+	 * pre-faulting only running vCPUs would be inconsistent and confusing.
+	 */
+	if (is_protected_kvm_enabled())
+		return -EOPNOTSUPP;
+
+	memslot = gfn_to_memslot(kvm, gpa_to_gfn(gpa));
+	if (!memslot)
+		return -ENOENT;
+	/* SRCU must be released for progress and only userland can do that. */
+	if (memslot->flags & KVM_MEMSLOT_INVALID)
+		return -EAGAIN;
+
+	do {
+		ret = pre_fault_s2(mmu, vcpu, gpa, memslot);
+	} while (ret == -EAGAIN && num_retries++ < MAX_PRE_FAULT_RETRIES);
+
+	if (IS_ERR_VALUE(ret))
+		return ret;
+	return pre_fault_bytes_consumed(gpa, ret, bytes_remaining);
+}

-- 
2.55.0

Update the KVM API documentation to reflect the fact that arm64 now
supports this functionality.

Also document error values and arm64-specific behaviour.

Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 Documentation/virt/kvm/api.rst | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 4988c32df4bf..fb7f8baca970 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6485,7 +6485,7 @@ See KVM_SET_USER_MEMORY_REGION2 for additional details.
 ---------------------------
 
 :Capability: KVM_CAP_PRE_FAULT_MEMORY
-:Architectures: none
+:Architectures: x86, s390, arm64
 :Type: vcpu ioctl
 :Parameters: struct kvm_pre_fault_memory (in/out)
 :Returns: 0 if at least one page is processed, < 0 on error
@@ -6493,12 +6493,14 @@ See KVM_SET_USER_MEMORY_REGION2 for additional details.
 Errors:
 
   ========== ===============================================================
+  EAGAIN     A race occurred before progress was made, but a retry may succeed.
   EINVAL     The specified `gpa` and `size` were invalid (e.g. not
              page aligned, causes an overflow, or size is zero), or the VM
              is UCONTROL (s390).
   ENOENT     The specified `gpa` is outside defined memslots.
   EINTR      An unmasked signal is pending and no page was processed.
   EFAULT     The parameter address was invalid.
+  EHWPOISON  A poisoned host page was encountered.
   EOPNOTSUPP Mapping memory for a GPA is unsupported by the
              hypervisor, and/or for the current vCPU state/mode.
   EIO        unexpected error conditions (also causes a WARN)
@@ -6518,7 +6520,17 @@ Errors:
 KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory
 for the current vCPU state.  KVM maps memory as if the vCPU generated a
 stage-2 read page fault, e.g. faults in memory as needed, but doesn't break
-CoW.  On x86, KVM does not mark any newly created stage-2 PTE as Accessed.
+CoW.  On arm64, KVM marks newly created stage-2 PTEs as Accessed, as it
+does for any stage-2 fault, but leaves the Accessed state of existing PTEs
+unchanged.  On x86, KVM does not mark any newly created stage-2 PTE as
+Accessed, and for s390 it is not applicable.
+
+On arm64, a GPA is interpreted as an IPA, and never interpreted as the IPA
+of a nested guest. Pre-faulting only populates canonical stage 2 page
+tables.
+
+The feature is not supported on arm64 if the protected KVM (pKVM) feature
+is enabled.
 
 In the case of confidential VM types where there is an initial set up of
 private guest memory before the guest is 'finalized'/measured, this ioctl
@@ -6533,7 +6545,7 @@ When the ioctl returns, the input values are updated to point to the
 remaining range.  If `size` > 0 on return, the caller can just issue
 the ioctl again with the same `struct kvm_map_memory` argument.
 
-Shadow page tables cannot support this ioctl because they
+On x86, shadow page tables cannot support this ioctl because they
 are indexed by virtual address or nested guest physical address.
 Calling this ioctl when the guest is using shadow page tables (for
 example because it is running a nested guest with nested page tables)

-- 
2.55.0

From: Jack Thomson <jackabt@amazon.com>

Enable the pre_fault_memory_test to run on arm64 by making it work with
different guest page sizes and testing multiple guest configurations.

Add an assert on the exit reason, comparing against UCALL_EXIT_REASON so
the check is portable, as arm64 exits with KVM_EXIT_MMIO while x86 uses
KVM_EXIT_IO.

Signed-off-by: Jack Thomson <jackabt@amazon.com>
[ljs: merge conflict resolution with commit c847704619da, commit message
 accuracy fixup]
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   1 +
 .../testing/selftests/kvm/pre_fault_memory_test.c  | 117 +++++++++++++++++----
 2 files changed, 96 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 5f8d17ee5f67..66a9a4e62888 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -199,6 +199,7 @@ TEST_GEN_PROGS_arm64 += guest_memfd_test
 TEST_GEN_PROGS_arm64 += mmu_stress_test
 TEST_GEN_PROGS_arm64 += rseq_test
 TEST_GEN_PROGS_arm64 += steal_time
+TEST_GEN_PROGS_arm64 += pre_fault_memory_test
 
 TEST_GEN_PROGS_s390 = $(TEST_GEN_PROGS_COMMON)
 TEST_GEN_PROGS_s390 += s390/memop
diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index a0fcae3cb7a8..ee77c51cc566 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -12,19 +12,29 @@
 #include <processor.h>
 #include <pthread.h>
 #include <ucall_common.h>
+#include <guest_modes.h>
 
 /* Arbitrarily chosen values */
-#define TEST_SIZE		(SZ_2M + PAGE_SIZE)
-#define TEST_NPAGES		(TEST_SIZE / PAGE_SIZE)
+#define TEST_BASE_SIZE		SZ_2M
 #define TEST_SLOT		10
 
+/* Storage of test info to share with guest code */
+struct test_config {
+	u64 page_size;
+	u64 test_size;
+	u64 test_num_pages;
+};
+
+static struct test_config test_config;
+
 static void guest_code(u64 base_gva)
 {
 	volatile u64 val __used;
+	struct test_config *config = &test_config;
 	int i;
 
-	for (i = 0; i < TEST_NPAGES; i++) {
-		u64 *src = (u64 *)(base_gva + i * PAGE_SIZE);
+	for (i = 0; i < config->test_num_pages; i++) {
+		u64 *src = (u64 *)(base_gva + i * config->page_size);
 
 		val = *src;
 	}
@@ -57,7 +67,7 @@ static void *delete_slot_worker(void *__data)
 		cpu_relax();
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa,
-				    TEST_SLOT, TEST_NPAGES, data->flags);
+				    TEST_SLOT, test_config.test_num_pages, data->flags);
 
 	return NULL;
 }
@@ -150,8 +160,8 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
 	/*
 	 * Assert success if prefaulting the entire range should succeed, i.e.
 	 * complete with no bytes remaining.  Otherwise prefaulting should have
-	 * failed due to ENOENT (due to RET_PF_EMULATE for emulated MMIO when
-	 * no memslot exists).
+	 * failed due to ENOENT (no memslot exists for the GPA; on x86 this
+	 * surfaces via RET_PF_EMULATE).
 	 */
 	if (!expected_left)
 		TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
@@ -160,39 +170,72 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
 					  KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
 }
 
-static void __test_pre_fault_memory(unsigned long vm_type, bool private)
+struct test_params {
+	unsigned long vm_type;
+	bool private;
+};
+
+static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
 {
-	gpa_t gpa, gva, alignment, guest_page_size;
+	gpa_t gpa, gva, alignment, guest_page_size, host_page_size;
+	struct test_params *p = arg;
 	const struct vm_shape shape = {
-		.mode = VM_MODE_DEFAULT,
-		.type = vm_type,
+		.mode = guest_mode,
+		.type = p->vm_type,
 	};
 	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
 	struct kvm_vm *vm;
 	struct ucall uc;
 
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(guest_mode));
+
 	vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
 
-	alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size;
-	gpa = (vm->max_gfn - TEST_NPAGES) * guest_page_size;
+	guest_page_size = vm_guest_mode_params[guest_mode].page_size;
+	host_page_size = getpagesize();
+
+	test_config.page_size = guest_page_size;
+	test_config.test_size = align_up(TEST_BASE_SIZE + test_config.page_size,
+					 host_page_size);
+	test_config.test_num_pages = vm_calc_num_guest_pages(vm->mode, test_config.test_size);
+
+	gpa = (vm->max_gfn - test_config.test_num_pages) * test_config.page_size;
 	alignment = SZ_2M;
+	alignment = max(alignment, host_page_size);
 	gpa = align_down(gpa, alignment);
 	gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, TEST_SLOT,
-				    TEST_NPAGES, private ? KVM_MEM_GUEST_MEMFD : 0);
-	virt_map(vm, gva, gpa, TEST_NPAGES);
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    gpa, TEST_SLOT, test_config.test_num_pages,
+				    p->private ? KVM_MEM_GUEST_MEMFD : 0);
+	virt_map(vm, gva, gpa, test_config.test_num_pages);
 
-	if (private)
-		vm_mem_set_private(vm, gpa, TEST_SIZE);
+	if (p->private)
+		vm_mem_set_private(vm, gpa, test_config.test_size);
 
-	pre_fault_memory(vcpu, gpa, 0, SZ_2M, 0, private);
-	pre_fault_memory(vcpu, gpa, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private);
-	pre_fault_memory(vcpu, gpa, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private);
+	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+	/* Retry the same range after the first prefault attempt. */
+	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+	pre_fault_memory(vcpu, gpa,
+			 test_config.test_size - host_page_size,
+			 host_page_size * 2, host_page_size, p->private);
+	pre_fault_memory(vcpu, gpa, test_config.test_size,
+			 host_page_size, host_page_size, p->private);
 
 	vcpu_args_set(vcpu, 1, gva);
+
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, test_config);
+
 	vcpu_run(vcpu);
 
+	run = vcpu->run;
+	TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
+		    "Wanted %s, got exit reason: %u (%s)",
+		    exit_reason_str(UCALL_EXIT_REASON),
+		    run->exit_reason, exit_reason_str(run->exit_reason));
+
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
 		REPORT_GUEST_ASSERT(uc);
@@ -209,16 +252,46 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 
 static void test_pre_fault_memory(unsigned long vm_type, bool private)
 {
+	struct test_params p = {
+		.vm_type = vm_type,
+		.private = private,
+	};
+
 	if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) {
 		pr_info("Skipping tests for vm_type 0x%lx\n", vm_type);
 		return;
 	}
 
-	__test_pre_fault_memory(vm_type, private);
+	for_each_guest_mode(__test_pre_fault_memory, &p);
+}
+
+static void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-h] [-m mode]\n", name);
+	puts("");
+	guest_modes_help();
+	puts("");
 }
 
 int main(int argc, char *argv[])
 {
+	int opt;
+
+	guest_modes_append_default();
+
+	while ((opt = getopt(argc, argv, "hm:")) != -1) {
+		switch (opt) {
+		case 'm':
+			guest_modes_cmdline(optarg);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			exit(0);
+		}
+	}
+
 	TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
 
 	test_pre_fault_memory(0, false);

-- 
2.55.0

From: Jack Thomson <jackabt@amazon.com>

Add a -s option to specify different memory backing types for the
pre-fault tests (e.g. anonymous, hugetlb), allowing testing of the
pre-fault functionality across different memory configurations.

Signed-off-by: Jack Thomson <jackabt@amazon.com>
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 .../testing/selftests/kvm/pre_fault_memory_test.c  | 51 +++++++++++++++-------
 1 file changed, 36 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index ee77c51cc566..702c72bbfa96 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -46,6 +46,7 @@ struct slot_worker_data {
 	struct kvm_vm *vm;
 	gpa_t gpa;
 	u32 flags;
+	enum vm_mem_backing_src_type mem_backing_src;
 	bool worker_ready;
 	bool prefault_ready;
 	bool recreate_slot;
@@ -66,14 +67,16 @@ static void *delete_slot_worker(void *__data)
 	while (!READ_ONCE(data->recreate_slot))
 		cpu_relax();
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa,
+	vm_userspace_mem_region_add(vm, data->mem_backing_src, data->gpa,
 				    TEST_SLOT, test_config.test_num_pages, data->flags);
 
 	return NULL;
 }
 
 static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
-			     u64 size, u64 expected_left, bool private)
+			     u64 size, u64 expected_left,
+			     enum vm_mem_backing_src_type mem_backing_src,
+			     bool private)
 {
 	struct kvm_pre_fault_memory range = {
 		.gpa = base_gpa + offset,
@@ -84,6 +87,7 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
 		.vm = vcpu->vm,
 		.gpa = base_gpa,
 		.flags = private ? KVM_MEM_GUEST_MEMFD : 0,
+		.mem_backing_src = mem_backing_src,
 	};
 	bool slot_recreated = false;
 	pthread_t slot_worker;
@@ -173,11 +177,13 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
 struct test_params {
 	unsigned long vm_type;
 	bool private;
+	enum vm_mem_backing_src_type mem_backing_src;
 };
 
 static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
 {
 	gpa_t gpa, gva, alignment, guest_page_size, host_page_size;
+	gpa_t backing_src_pagesz, mem_page_size;
 	struct test_params *p = arg;
 	const struct vm_shape shape = {
 		.mode = guest_mode,
@@ -189,24 +195,28 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
 	struct ucall uc;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(guest_mode));
+	pr_info("Testing memory backing src type: %s\n",
+		vm_mem_backing_src_alias(p->mem_backing_src)->name);
 
 	vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
 
 	guest_page_size = vm_guest_mode_params[guest_mode].page_size;
 	host_page_size = getpagesize();
+	backing_src_pagesz = get_backing_src_pagesz(p->mem_backing_src);
+	mem_page_size = max(host_page_size, backing_src_pagesz);
 
 	test_config.page_size = guest_page_size;
 	test_config.test_size = align_up(TEST_BASE_SIZE + test_config.page_size,
-					 host_page_size);
+					 mem_page_size);
 	test_config.test_num_pages = vm_calc_num_guest_pages(vm->mode, test_config.test_size);
 
 	gpa = (vm->max_gfn - test_config.test_num_pages) * test_config.page_size;
 	alignment = SZ_2M;
-	alignment = max(alignment, host_page_size);
+	alignment = max(alignment, mem_page_size);
 	gpa = align_down(gpa, alignment);
 	gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+	vm_userspace_mem_region_add(vm, p->mem_backing_src,
 				    gpa, TEST_SLOT, test_config.test_num_pages,
 				    p->private ? KVM_MEM_GUEST_MEMFD : 0);
 	virt_map(vm, gva, gpa, test_config.test_num_pages);
@@ -214,14 +224,18 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
 	if (p->private)
 		vm_mem_set_private(vm, gpa, test_config.test_size);
 
-	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0,
+			 p->mem_backing_src, p->private);
 	/* Retry the same range after the first prefault attempt. */
-	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+	pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0,
+			 p->mem_backing_src, p->private);
 	pre_fault_memory(vcpu, gpa,
 			 test_config.test_size - host_page_size,
-			 host_page_size * 2, host_page_size, p->private);
+			 host_page_size * 2, host_page_size,
+			 p->mem_backing_src, p->private);
 	pre_fault_memory(vcpu, gpa, test_config.test_size,
-			 host_page_size, host_page_size, p->private);
+			 host_page_size, host_page_size,
+			 p->mem_backing_src, p->private);
 
 	vcpu_args_set(vcpu, 1, gva);
 
@@ -250,11 +264,13 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
 	kvm_vm_free(vm);
 }
 
-static void test_pre_fault_memory(unsigned long vm_type, bool private)
+static void test_pre_fault_memory(unsigned long vm_type, enum vm_mem_backing_src_type backing_src,
+				  bool private)
 {
 	struct test_params p = {
 		.vm_type = vm_type,
 		.private = private,
+		.mem_backing_src = backing_src,
 	};
 
 	if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) {
@@ -268,23 +284,28 @@ static void test_pre_fault_memory(unsigned long vm_type, bool private)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-m mode]\n", name);
+	printf("usage: %s [-h] [-m mode] [-s mem-type]\n", name);
 	puts("");
 	guest_modes_help();
+	backing_src_help("-s");
 	puts("");
 }
 
 int main(int argc, char *argv[])
 {
+	enum vm_mem_backing_src_type backing = DEFAULT_VM_MEM_SRC;
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:s:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
+		case 's':
+			backing = parse_backing_src_type(optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -294,10 +315,10 @@ int main(int argc, char *argv[])
 
 	TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
 
-	test_pre_fault_memory(0, false);
+	test_pre_fault_memory(0, backing, false);
 #ifdef __x86_64__
-	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, false);
-	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, true);
+	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, false);
+	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, true);
 #endif
 	return 0;
 }

-- 
2.55.0

Add an arm64 nested-virtualisation selftest for KVM_PRE_FAULT_MEMORY.

The guest enters vEL2, sets up its EL2 translation configuration into the
real EL1 registers then ERETs to vEL1 and exits to userspace so its vCPU
last-run context is nested backed by a shadow stage 2 MMU.

The test then asserts that pre-faulting ignores that and instead targets
the canonical stage 2 page tables only.

Userspace cannot observe a mistargeted pre-fault, so simply assert that the
pre-faulting works correctly when the last-run context was nested.

Based on a patch by Jack Thomson with gratitude. The test here is
simplified and focused on what can be asserted.

Link: https://lore.kernel.org/kvmarm/20260612162354.73378-6-jackabt.amazon@gmail.com/
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   1 +
 .../selftests/kvm/arm64/nv_pre_fault_memory_test.c | 158 +++++++++++++++++++++
 2 files changed, 159 insertions(+)

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 66a9a4e62888..1e0edd0f99f7 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -173,6 +173,7 @@ TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
 TEST_GEN_PROGS_arm64 += arm64/hello_el2
 TEST_GEN_PROGS_arm64 += arm64/host_sve
 TEST_GEN_PROGS_arm64 += arm64/hypercalls
+TEST_GEN_PROGS_arm64 += arm64/nv_pre_fault_memory_test
 TEST_GEN_PROGS_arm64 += arm64/external_aborts
 TEST_GEN_PROGS_arm64 += arm64/mmio_sign_ext
 TEST_GEN_PROGS_arm64 += arm64/page_fault_test
diff --git a/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c b/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c
new file mode 100644
index 000000000000..09c1db303856
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * nv_pre_fault_memory_test - Test KVM_PRE_FAULT_MEMORY on a vCPU whose
+ * last-run context is nested.
+ *
+ * The guest enters vEL2, sets up its EL2 translation configuration into the
+ * real EL1 registers then ERETs to vEL1 and exits to userspace so its vCPU
+ * last-run context is nested backed by a shadow stage 2 MMU.
+ *
+ * Assert that pre-faulting ignores that and targets the canonical stage-2
+ * page tables only.
+ */
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+#include "ucall.h"
+
+#include <asm/sysreg.h>
+#include <linux/sizes.h>
+
+#define TEST_MEM_SLOT		10
+#define TEST_MEM_SIZE		SZ_2M
+#define TEST_MEM_GPA		SZ_1G
+
+static void guest_el1_code(void)
+{
+	u64 offset;
+
+	GUEST_ASSERT_EQ(get_current_el(), 1);
+
+	/* Exit to userspace with the vEL1 (nested) context live. */
+	GUEST_SYNC(1);
+
+	/*
+	 * Touch the prefaulted range. vstage-2 is disabled, so the shadow
+	 * stage-2 is a 1:1 view of the canonical IPA space.
+	 */
+	for (offset = 0; offset < TEST_MEM_SIZE; offset += SZ_4K)
+		READ_ONCE(*(u64 *)(TEST_MEM_GPA + offset));
+
+	GUEST_DONE();
+}
+
+static void guest_code(void)
+{
+	u64 sp;
+
+	GUEST_ASSERT_EQ(get_current_el(), 2);
+
+	/*
+	 * Mirror the EL2 translation regime into the real EL1 registers so
+	 * that vEL1 runs on the test's stage-1 page tables. With E2H=1, the
+	 * _EL1 accessors read the EL2 registers, and the _EL12 accessors
+	 * write the real EL1 registers.
+	 */
+	write_sysreg_s(read_sysreg(sctlr_el1), SYS_SCTLR_EL12);
+	write_sysreg_s(read_sysreg(tcr_el1), SYS_TCR_EL12);
+	write_sysreg_s(read_sysreg(ttbr0_el1), SYS_TTBR0_EL12);
+	write_sysreg_s(read_sysreg(mair_el1), SYS_MAIR_EL12);
+	write_sysreg_s(read_sysreg(cpacr_el1), SYS_CPACR_EL12);
+
+	/* Run vEL1 on the same stack. */
+	asm volatile("mov %0, sp" : "=r"(sp));
+	write_sysreg(sp, sp_el1);
+
+	/*
+	 * Drop TGE so that vEL1 is a nested context rather than host EL0.
+	 * KVM backs it with a shadow stage-2 MMU even though vstage-2 is
+	 * disabled (HCR_EL2.VM=0).
+	 */
+	write_sysreg(read_sysreg(hcr_el2) & ~HCR_EL2_TGE, hcr_el2);
+	isb();
+
+	write_sysreg(PSR_MODE_EL1h | PSR_F_BIT | PSR_I_BIT | PSR_A_BIT |
+		     PSR_D_BIT, spsr_el2);
+	write_sysreg((u64)guest_el1_code, elr_el2);
+	asm volatile("eret");
+
+	GUEST_ASSERT(false);
+}
+
+static void pre_fault(struct kvm_vcpu *vcpu, u64 gpa, u64 size)
+{
+	struct kvm_pre_fault_memory range = {
+		.gpa = gpa,
+		.size = size,
+	};
+	int ret;
+
+	do {
+		ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
+	} while ((!ret && range.size) ||
+		 (ret < 0 && (errno == EINTR || errno == EAGAIN)));
+
+	TEST_ASSERT(!ret, "KVM_PRE_FAULT_MEMORY failed, ret: %d errno: %d",
+		    ret, errno);
+	TEST_ASSERT_EQ(range.size, 0);
+}
+
+int main(void)
+{
+	struct kvm_vcpu_init init;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	u64 npages;
+
+	TEST_REQUIRE(test_supports_el2());
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
+
+	vm = vm_create(1);
+
+	kvm_get_default_vcpu_target(vm, &init);
+	init.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2);
+	vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code);
+	kvm_arch_vm_finalize_vcpus(vm);
+
+	npages = TEST_MEM_SIZE / vm->page_size;
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, TEST_MEM_GPA,
+				    TEST_MEM_SLOT, npages, 0);
+	virt_map(vm, TEST_MEM_GPA, TEST_MEM_GPA, npages);
+
+	/* Run the guest until it has ERET'd from vEL2 to vEL1. */
+	vcpu_run(vcpu);
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_SYNC:
+		TEST_ASSERT_EQ(uc.args[1], 1);
+		break;
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	default:
+		TEST_FAIL("Unhandled ucall: %ld", uc.cmd);
+	}
+
+	/*
+	 * The vCPU's last-run context is vEL1, so its hw_mmu is a shadow
+	 * stage-2 MMU.
+	 *
+	 * Pre-faulting must ignore that and populate the canonical stage-2.
+	 */
+	pre_fault(vcpu, TEST_MEM_GPA, TEST_MEM_SIZE);
+
+	/* Resume at vEL1 and touch the prefaulted range. */
+	vcpu_run(vcpu);
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	default:
+		TEST_FAIL("Unhandled ucall: %ld", uc.cmd);
+	}
+
+	kvm_vm_free(vm);
+	return 0;
+}

-- 
2.55.0