Merge tag 'kvmarm-fixes-6.15-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64: First batch of fixes for 6.15

 - Rework heuristics for resolving the fault IPA (HPFAR_EL2 v. re-walk
   stage-1 page tables) to align with the architecture. This avoids
   possibly taking an SEA at EL2 on the page table walk or using an
   architecturally UNKNOWN fault IPA.

 - Use acquire/release semantics in the KVM FF-A proxy to avoid reading
   a stale value for the FF-A version.

 - Fix KVM guest driver to match PV CPUID hypercall ABI.

 - Use Inner Shareable Normal Write-Back mappings at stage-1 in KVM
   selftests, which is the only memory type for which atomic
   instructions are architecturally guaranteed to work.

3 files changed, 96 insertions, 33 deletions

diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index ec33a8f9c908..dc6559dad9d8 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -199,7 +199,7 @@ static bool guest_set_ha(void)
 	if (hadbs == 0)
 		return false;
 
-	tcr = read_sysreg(tcr_el1) | TCR_EL1_HA;
+	tcr = read_sysreg(tcr_el1) | TCR_HA;
 	write_sysreg(tcr, tcr_el1);
 	isb();
 
diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h
index 1e8d0d531fbd..b0fc0f945766 100644
--- a/tools/testing/selftests/kvm/include/arm64/processor.h
+++ b/tools/testing/selftests/kvm/include/arm64/processor.h
@@ -62,6 +62,67 @@
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |				\
 	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
 
+/* TCR_EL1 specific flags */
+#define TCR_T0SZ_OFFSET	0
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+
+#define TCR_IRGN0_SHIFT	8
+#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA	(UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT	10
+#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA	(UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT		12
+#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT		14
+#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_IPS_SHIFT		32
+#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
+#define TCR_IPS_52_BITS	(UL(6) << TCR_IPS_SHIFT)
+#define TCR_IPS_48_BITS	(UL(5) << TCR_IPS_SHIFT)
+#define TCR_IPS_40_BITS	(UL(2) << TCR_IPS_SHIFT)
+#define TCR_IPS_36_BITS	(UL(1) << TCR_IPS_SHIFT)
+
+#define TCR_HA			(UL(1) << 39)
+#define TCR_DS			(UL(1) << 59)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t)	((t) << 2)
+#define PTE_ATTRINDX_MASK	GENMASK(4, 2)
+#define PTE_ATTRINDX_SHIFT	2
+
+#define PTE_VALID		BIT(0)
+#define PGD_TYPE_TABLE		BIT(1)
+#define PUD_TYPE_TABLE		BIT(1)
+#define PMD_TYPE_TABLE		BIT(1)
+#define PTE_TYPE_PAGE		BIT(1)
+
+#define PTE_SHARED		(UL(3) << 8) /* SH[1:0], inner shareable */
+#define PTE_AF			BIT(10)
+
+#define PTE_ADDR_MASK(page_shift)	GENMASK(47, (page_shift))
+#define PTE_ADDR_51_48			GENMASK(15, 12)
+#define PTE_ADDR_51_48_SHIFT		12
+#define PTE_ADDR_MASK_LPA2(page_shift)	GENMASK(49, (page_shift))
+#define PTE_ADDR_51_50_LPA2		GENMASK(9, 8)
+#define PTE_ADDR_51_50_LPA2_SHIFT	8
+
 void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
 struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  struct kvm_vcpu_init *init, void *guest_code);
@@ -102,12 +163,6 @@ enum {
 			   (v) == VECTOR_SYNC_LOWER_64    || \
 			   (v) == VECTOR_SYNC_LOWER_32)
 
-/* Access flag */
-#define PTE_AF			(1ULL << 10)
-
-/* Access flag update enable/disable */
-#define TCR_EL1_HA		(1ULL << 39)
-
 void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 					uint32_t *ipa16k, uint32_t *ipa64k);
 
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 7ba3aa3755f3..9d69904cb608 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -72,13 +72,13 @@ static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
 	uint64_t pte;
 
 	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);
+		pte = pa & PTE_ADDR_MASK_LPA2(vm->page_shift);
+		pte |= FIELD_GET(GENMASK(51, 50), pa) << PTE_ADDR_51_50_LPA2_SHIFT;
+		attrs &= ~PTE_ADDR_51_50_LPA2;
 	} else {
-		pte = pa & GENMASK(47, vm->page_shift);
+		pte = pa & PTE_ADDR_MASK(vm->page_shift);
 		if (vm->page_shift == 16)
-			pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+			pte |= FIELD_GET(GENMASK(51, 48), pa) << PTE_ADDR_51_48_SHIFT;
 	}
 	pte |= attrs;
 
@@ -90,12 +90,12 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
 	uint64_t pa;
 
 	if (use_lpa2_pte_format(vm)) {
-		pa = pte & GENMASK(49, vm->page_shift);
-		pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+		pa = pte & PTE_ADDR_MASK_LPA2(vm->page_shift);
+		pa |= FIELD_GET(PTE_ADDR_51_50_LPA2, pte) << 50;
 	} else {
-		pa = pte & GENMASK(47, vm->page_shift);
+		pa = pte & PTE_ADDR_MASK(vm->page_shift);
 		if (vm->page_shift == 16)
-			pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+			pa |= FIELD_GET(PTE_ADDR_51_48, pte) << 48;
 	}
 
 	return pa;
@@ -128,7 +128,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 			 uint64_t flags)
 {
-	uint8_t attr_idx = flags & 7;
+	uint8_t attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT);
+	uint64_t pg_attr;
 	uint64_t *ptep;
 
 	TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -147,18 +148,21 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
 	if (!*ptep)
-		*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+		*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+				 PGD_TYPE_TABLE | PTE_VALID);
 
 	switch (vm->pgtable_levels) {
 	case 4:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
 		if (!*ptep)
-			*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+			*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+					 PUD_TYPE_TABLE | PTE_VALID);
 		/* fall through */
 	case 3:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
 		if (!*ptep)
-			*ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+			*ptep = addr_pte(vm, vm_alloc_page_table(vm),
+					 PMD_TYPE_TABLE | PTE_VALID);
 		/* fall through */
 	case 2:
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
@@ -167,7 +171,11 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
-	*ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3);  /* AF */
+	pg_attr = PTE_AF | PTE_ATTRINDX(attr_idx) | PTE_TYPE_PAGE | PTE_VALID;
+	if (!use_lpa2_pte_format(vm))
+		pg_attr |= PTE_SHARED;
+
+	*ptep = addr_pte(vm, paddr, pg_attr);
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -293,20 +301,20 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P48V48_64K:
 	case VM_MODE_P40V48_64K:
 	case VM_MODE_P36V48_64K:
-		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= TCR_TG0_64K;
 		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 */
+		tcr_el1 |= TCR_TG0_16K;
 		break;
 	case VM_MODE_P52V48_4K:
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P36V48_4K:
-		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= TCR_TG0_4K;
 		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
@@ -319,35 +327,35 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	case VM_MODE_P52V48_4K:
 	case VM_MODE_P52V48_16K:
 	case VM_MODE_P52V48_64K:
-		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		tcr_el1 |= TCR_IPS_52_BITS;
 		ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
 		break;
 	case VM_MODE_P48V48_4K:
 	case VM_MODE_P48V48_16K:
 	case VM_MODE_P48V48_64K:
-		tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+		tcr_el1 |= TCR_IPS_48_BITS;
 		break;
 	case VM_MODE_P40V48_4K:
 	case VM_MODE_P40V48_16K:
 	case VM_MODE_P40V48_64K:
-		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		tcr_el1 |= TCR_IPS_40_BITS;
 		break;
 	case VM_MODE_P36V48_4K:
 	case VM_MODE_P36V48_16K:
 	case VM_MODE_P36V48_64K:
 	case VM_MODE_P36V47_16K:
-		tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+		tcr_el1 |= TCR_IPS_36_BITS;
 		break;
 	default:
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
 	}
 
-	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
-	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
-	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
-	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+	sctlr_el1 |= SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_I;
+
+	tcr_el1 |= TCR_IRGN0_WBWA | TCR_ORGN0_WBWA | TCR_SH0_INNER;
+	tcr_el1 |= TCR_T0SZ(vm->va_bits);
 	if (use_lpa2_pte_format(vm))
-		tcr_el1 |= (1ul << 59) /* DS */;
+		tcr_el1 |= TCR_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);