Merge tag 'kvmarm-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 6.8

- LPA2 support, adding 52bit IPA/PA capability for 4kB and 16kB
  base granule sizes. Branch shared with the arm64 tree.

- Large Fine-Grained Trap rework, bringing some sanity to the
  feature, although there is more to come. This comes with
  a prefix branch shared with the arm64 tree.

- Some additional Nested Virtualization groundwork, mostly
  introducing the NV2 VNCR support and retargetting the NV
  support to that version of the architecture.

- A small set of vgic fixes and associated cleanups.

6 files changed, 86 insertions, 45 deletions

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index c42d683102c7..cf20e44e86f2 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -119,8 +119,8 @@ enum {
 /* Access flag update enable/disable */
 #define TCR_EL1_HA		(1ULL << 39)
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k);
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k);
 
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
index b691df33e64e..63f5167397cc 100644
--- a/tools/testing/selftests/kvm/include/guest_modes.h
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -11,8 +11,8 @@ struct guest_mode {
 
 extern struct guest_mode guest_modes[NUM_VM_MODES];
 
-#define guest_mode_append(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+#define guest_mode_append(mode, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ (enabled), (enabled) }; \
 })
 
 void guest_modes_append_default(void);
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 4c8a05cbc20c..9e5afc472c14 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -172,6 +172,7 @@ static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm,
 
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
+	VM_MODE_P52V48_16K,
 	VM_MODE_P52V48_64K,
 	VM_MODE_P48V48_4K,
 	VM_MODE_P48V48_16K,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6fe12e985ba5..41c776b642c0 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -12,6 +12,7 @@
 #include "kvm_util.h"
 #include "processor.h"
 #include <linux/bitfield.h>
+#include <linux/sizes.h>
 
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -58,13 +59,25 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
 	return (gva >> vm->page_shift) & mask;
 }
 
+static inline bool use_lpa2_pte_format(struct kvm_vm *vm)
+{
+	return (vm->page_size == SZ_4K || vm->page_size == SZ_16K) &&
+	    (vm->pa_bits > 48 || vm->va_bits > 48);
+}
+
 static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
 {
 	uint64_t pte;
 
-	pte = pa & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	if (use_lpa2_pte_format(vm)) {
+		pte = pa & GENMASK(49, vm->page_shift);
+		pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
+		attrs &= ~GENMASK(9, 8);
+	} else {
+		pte = pa & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+	}
 	pte |= attrs;
 
 	return pte;
@@ -74,9 +87,14 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
 {
 	uint64_t pa;
 
-	pa = pte & GENMASK(47, vm->page_shift);
-	if (vm->page_shift == 16)
-		pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	if (use_lpa2_pte_format(vm)) {
+		pa = pte & GENMASK(49, vm->page_shift);
+		pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+	} else {
+		pa = pte & GENMASK(47, vm->page_shift);
+		if (vm->page_shift == 16)
+			pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+	}
 
 	return pa;
 }
@@ -266,9 +284,6 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure base granule size */
 	switch (vm->mode) {
-	case VM_MODE_P52V48_4K:
-		TEST_FAIL("AArch64 does not support 4K sized pages "
-			  "with 52-bit physical address ranges");
 	case VM_MODE_PXXV48_4K:
 		TEST_FAIL("AArch64 does not support 4K sized pages "
 			  "with ANY-bit physical address ranges");
@@ -278,12 +293,14 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P36V48_64K:
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V47_16K:
 		tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
 		break;
+	case VM_MODE_P52V48_4K:
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P36V48_4K:
@@ -297,6 +314,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure output size */
 	switch (vm->mode) {
+	case VM_MODE_P52V48_4K:
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P52V48_64K:
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
@@ -325,6 +344,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
 	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
 	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+	if (use_lpa2_pte_format(vm))
+		tcr_el1 |= (1ul << 59) /* DS */;
 
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
@@ -492,12 +513,24 @@ uint32_t guest_get_vcpuid(void)
 	return read_sysreg(tpidr_el1);
 }
 
-void aarch64_get_supported_page_sizes(uint32_t ipa,
-				      bool *ps4k, bool *ps16k, bool *ps64k)
+static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran,
+				uint32_t not_sup_val, uint32_t ipa52_min_val)
+{
+	if (gran == not_sup_val)
+		return 0;
+	else if (gran >= ipa52_min_val && vm_ipa >= 52)
+		return 52;
+	else
+		return min(vm_ipa, 48U);
+}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
+					uint32_t *ipa16k, uint32_t *ipa64k)
 {
 	struct kvm_vcpu_init preferred_init;
 	int kvm_fd, vm_fd, vcpu_fd, err;
 	uint64_t val;
+	uint32_t gran;
 	struct kvm_one_reg reg = {
 		.id	= KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
 		.addr	= (uint64_t)&val,
@@ -518,9 +551,17 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val) != 0xf;
-	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val) == 0;
-	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val) != 0;
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
+					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
+					ID_AA64MMFR0_EL1_TGRAN64_IMP);
+
+	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
+					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 
 	close(vcpu_fd);
 	close(vm_fd);
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 1df3ce4b16fd..b04901e55138 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -14,37 +14,33 @@ struct guest_mode guest_modes[NUM_VM_MODES];
 void guest_modes_append_default(void)
 {
 #ifndef __aarch64__
-	guest_mode_append(VM_MODE_DEFAULT, true, true);
+	guest_mode_append(VM_MODE_DEFAULT, true);
 #else
 	{
 		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-		bool ps4k, ps16k, ps64k;
+		uint32_t ipa4k, ipa16k, ipa64k;
 		int i;
 
-		aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k);
+		aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k);
 
-		vm_mode_default = NUM_VM_MODES;
+		guest_mode_append(VM_MODE_P52V48_4K, ipa4k >= 52);
+		guest_mode_append(VM_MODE_P52V48_16K, ipa16k >= 52);
+		guest_mode_append(VM_MODE_P52V48_64K, ipa64k >= 52);
 
-		if (limit >= 52)
-			guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k);
-		if (limit >= 48) {
-			guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k);
-		}
-		if (limit >= 40) {
-			guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k);
-			if (ps4k)
-				vm_mode_default = VM_MODE_P40V48_4K;
-		}
-		if (limit >= 36) {
-			guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k);
-			guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k);
-			guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k);
-			guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k);
-		}
+		guest_mode_append(VM_MODE_P48V48_4K, ipa4k >= 48);
+		guest_mode_append(VM_MODE_P48V48_16K, ipa16k >= 48);
+		guest_mode_append(VM_MODE_P48V48_64K, ipa64k >= 48);
+
+		guest_mode_append(VM_MODE_P40V48_4K, ipa4k >= 40);
+		guest_mode_append(VM_MODE_P40V48_16K, ipa16k >= 40);
+		guest_mode_append(VM_MODE_P40V48_64K, ipa64k >= 40);
+
+		guest_mode_append(VM_MODE_P36V48_4K, ipa4k >= 36);
+		guest_mode_append(VM_MODE_P36V48_16K, ipa16k >= 36);
+		guest_mode_append(VM_MODE_P36V48_64K, ipa64k >= 36);
+		guest_mode_append(VM_MODE_P36V47_16K, ipa16k >= 36);
+
+		vm_mode_default = ipa4k >= 40 ? VM_MODE_P40V48_4K : NUM_VM_MODES;
 
 		/*
 		 * Pick the first supported IPA size if the default
@@ -72,7 +68,7 @@ void guest_modes_append_default(void)
 		close(kvm_fd);
 		/* Starting with z13 we have 47bits of physical address */
 		if (info.ibc >= 0x30)
-			guest_mode_append(VM_MODE_P47V64_4K, true, true);
+			guest_mode_append(VM_MODE_P47V64_4K, true);
 	}
 #endif
 #ifdef __riscv
@@ -80,9 +76,9 @@ void guest_modes_append_default(void)
 		unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
 
 		if (sz >= 52)
-			guest_mode_append(VM_MODE_P52V48_4K, true, true);
+			guest_mode_append(VM_MODE_P52V48_4K, true);
 		if (sz >= 48)
-			guest_mode_append(VM_MODE_P48V48_4K, true, true);
+			guest_mode_append(VM_MODE_P48V48_4K, true);
 	}
 #endif
 }
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 17a978b8a2c4..e066d584c656 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -148,6 +148,7 @@ const char *vm_guest_mode_string(uint32_t i)
 {
 	static const char * const strings[] = {
 		[VM_MODE_P52V48_4K]	= "PA-bits:52,  VA-bits:48,  4K pages",
+		[VM_MODE_P52V48_16K]	= "PA-bits:52,  VA-bits:48, 16K pages",
 		[VM_MODE_P52V48_64K]	= "PA-bits:52,  VA-bits:48, 64K pages",
 		[VM_MODE_P48V48_4K]	= "PA-bits:48,  VA-bits:48,  4K pages",
 		[VM_MODE_P48V48_16K]	= "PA-bits:48,  VA-bits:48, 16K pages",
@@ -173,6 +174,7 @@ const char *vm_guest_mode_string(uint32_t i)
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_16K]	= { 52, 48,  0x4000, 14 },
 	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
 	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
 	[VM_MODE_P48V48_16K]	= { 48, 48,  0x4000, 14 },
@@ -251,6 +253,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	case VM_MODE_P36V48_64K:
 		vm->pgtable_levels = 3;
 		break;
+	case VM_MODE_P52V48_16K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P36V48_16K: