Merge branch kvm-arm64/hyp-stack-guard into kvmarm-master/next

* kvm-arm64/hyp-stack-guard:
  : .
  : Harden the EL2 stack by providing stack guards, courtesy of
  : Kalesh Singh.
  : .
  KVM: arm64: Symbolize the nVHE HYP addresses
  KVM: arm64: Detect and handle hypervisor stack overflows
  KVM: arm64: Add guard pages for pKVM (protected nVHE) hypervisor stack
  KVM: arm64: Add guard pages for KVM nVHE hypervisor stack
  KVM: arm64: Introduce pkvm_alloc_private_va_range()
  KVM: arm64: Introduce hyp_alloc_private_va_range()

Signed-off-by: Marc Zyngier <maz@kernel.org>

9 files changed, 214 insertions, 68 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e7cb8a4d2e81..cee02ea86159 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1479,7 +1479,6 @@ static void cpu_prepare_hyp_mode(int cpu)
 	tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET;
 	params->tcr_el2 = tcr;
 
-	params->stack_hyp_va = kern_hyp_va(per_cpu(kvm_arm_hyp_stack_page, cpu) + PAGE_SIZE);
 	params->pgd_pa = kvm_mmu_get_httbr();
 	if (is_protected_kvm_enabled())
 		params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS;
@@ -1929,14 +1928,46 @@ static int init_hyp_mode(void)
 	 * Map the Hyp stack pages
 	 */
 	for_each_possible_cpu(cpu) {
+		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
-					  PAGE_HYP);
+		unsigned long hyp_addr;
 
+		/*
+		 * Allocate a contiguous HYP private VA range for the stack
+		 * and guard page. The allocation is also aligned based on
+		 * the order of its size.
+		 */
+		err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
+		if (err) {
+			kvm_err("Cannot allocate hyp stack guard page\n");
+			goto out_err;
+		}
+
+		/*
+		 * Since the stack grows downwards, map the stack to the page
+		 * at the higher address and leave the lower guard page
+		 * unbacked.
+		 *
+		 * Any valid stack address now has the PAGE_SHIFT bit as 1
+		 * and addresses corresponding to the guard page have the
+		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+		 */
+		err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE,
+					    __pa(stack_page), PAGE_HYP);
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
 			goto out_err;
 		}
+
+		/*
+		 * Save the stack PA in nvhe_init_params. This will be needed
+		 * to recreate the stack mapping in protected nVHE mode.
+		 * __hyp_pa() won't do the right thing there, since the stack
+		 * has been mapped in the flexible private VA space.
+		 */
+		params->stack_pa = __pa(stack_page);
+
+		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
 	}
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 7726b01dc09a..c9f1310e2e5f 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -322,13 +322,8 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 	u64 elr_in_kimg = __phys_to_kimg(elr_phys);
 	u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt;
 	u64 mode = spsr & PSR_MODE_MASK;
+	u64 panic_addr = elr_virt + hyp_offset;
 
-	/*
-	 * The nVHE hyp symbols are not included by kallsyms to avoid issues
-	 * with aliasing. That means that the symbols cannot be printed with the
-	 * "%pS" format specifier, so fall back to the vmlinux address if
-	 * there's no better option.
-	 */
 	if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
 		kvm_err("Invalid host exception to nVHE hyp!\n");
 	} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
@@ -348,9 +343,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 		if (file)
 			kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
 		else
-			kvm_err("nVHE hyp BUG at: %016llx!\n", elr_virt + hyp_offset);
+			kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr,
+					(void *)panic_addr);
 	} else {
-		kvm_err("nVHE hyp panic at: %016llx!\n", elr_virt + hyp_offset);
+		kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr,
+				(void *)panic_addr);
 	}
 
 	/*
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index 2d08510c6cc1..42d8eb9bfe72 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -19,8 +19,10 @@ int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back);
 int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot);
 int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
 int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot);
-unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
-					    enum kvm_pgtable_prot prot);
+int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
+				  enum kvm_pgtable_prot prot,
+				  unsigned long *haddr);
+int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr);
 
 static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size,
 				     unsigned long *start, unsigned long *end)
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 727c979b2b69..20bf1327e6b9 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -153,6 +153,18 @@ SYM_FUNC_END(__host_hvc)
 
 .macro invalid_host_el2_vect
 	.align 7
+
+	/*
+	 * Test whether the SP has overflowed, without corrupting a GPR.
+	 * nVHE hypervisor stacks are aligned so that the PAGE_SHIFT bit
+	 * of SP should always be 1.
+	 */
+	add	sp, sp, x0			// sp' = sp + x0
+	sub	x0, sp, x0			// x0' = sp' - x0 = (sp + x0) - x0 = sp
+	tbz	x0, #PAGE_SHIFT, .L__hyp_sp_overflow\@
+	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
+	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
+
 	/* If a guest is loaded, panic out of it. */
 	stp	x0, x1, [sp, #-16]!
 	get_loaded_vcpu x0, x1
@@ -165,6 +177,18 @@ SYM_FUNC_END(__host_hvc)
 	 * been partially clobbered by __host_enter.
 	 */
 	b	hyp_panic
+
+.L__hyp_sp_overflow\@:
+	/*
+	 * Reset SP to the top of the stack, to allow handling the hyp_panic.
+	 * This corrupts the stack but is ok, since we won't be attempting
+	 * any unwinding here.
+	 */
+	ldr_this_cpu	x0, kvm_init_params + NVHE_INIT_STACK_HYP_VA, x1
+	mov	sp, x0
+
+	b	hyp_panic_bad_stack
+	ASM_BUG()
 .endm
 
 .macro invalid_host_el1_vect
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 5e2197db0d32..3cea4b6ac23e 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -160,7 +160,23 @@ static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ct
 	DECLARE_REG(size_t, size, host_ctxt, 2);
 	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);
 
-	cpu_reg(host_ctxt, 1) = __pkvm_create_private_mapping(phys, size, prot);
+	/*
+	 * __pkvm_create_private_mapping() populates a pointer with the
+	 * hypervisor start address of the allocation.
+	 *
+	 * However, handle___pkvm_create_private_mapping() hypercall crosses the
+	 * EL1/EL2 boundary so the pointer would not be valid in this context.
+	 *
+	 * Instead pass the allocation address as the return value (or return
+	 * ERR_PTR() on failure).
+	 */
+	unsigned long haddr;
+	int err = __pkvm_create_private_mapping(phys, size, prot, &haddr);
+
+	if (err)
+		haddr = (unsigned long)ERR_PTR(err);
+
+	cpu_reg(host_ctxt, 1) = haddr;
 }
 
 static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index cdbe8e246418..96193cb31a39 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -37,36 +37,60 @@ static int __pkvm_create_mappings(unsigned long start, unsigned long size,
 	return err;
 }
 
-unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
-					    enum kvm_pgtable_prot prot)
+/**
+ * pkvm_alloc_private_va_range - Allocates a private VA range.
+ * @size:	The size of the VA range to reserve.
+ * @haddr:	The hypervisor virtual start address of the allocation.
+ *
+ * The private virtual address (VA) range is allocated above __io_map_base
+ * and aligned based on the order of @size.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr)
 {
-	unsigned long addr;
-	int err;
+	unsigned long base, addr;
+	int ret = 0;
 
 	hyp_spin_lock(&pkvm_pgd_lock);
 
-	size = PAGE_ALIGN(size + offset_in_page(phys));
-	addr = __io_map_base;
-	__io_map_base += size;
+	/* Align the allocation based on the order of its size */
+	addr = ALIGN(__io_map_base, PAGE_SIZE << get_order(size));
 
-	/* Are we overflowing on the vmemmap ? */
-	if (__io_map_base > __hyp_vmemmap) {
-		__io_map_base -= size;
-		addr = (unsigned long)ERR_PTR(-ENOMEM);
-		goto out;
-	}
+	/* The allocated size is always a multiple of PAGE_SIZE */
+	base = addr + PAGE_ALIGN(size);
 
-	err = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, size, phys, prot);
-	if (err) {
-		addr = (unsigned long)ERR_PTR(err);
-		goto out;
+	/* Are we overflowing on the vmemmap ? */
+	if (!addr || base > __hyp_vmemmap)
+		ret = -ENOMEM;
+	else {
+		__io_map_base = base;
+		*haddr = addr;
 	}
 
-	addr = addr + offset_in_page(phys);
-out:
 	hyp_spin_unlock(&pkvm_pgd_lock);
 
-	return addr;
+	return ret;
+}
+
+int __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
+				  enum kvm_pgtable_prot prot,
+				  unsigned long *haddr)
+{
+	unsigned long addr;
+	int err;
+
+	size = PAGE_ALIGN(size + offset_in_page(phys));
+	err = pkvm_alloc_private_va_range(size, &addr);
+	if (err)
+		return err;
+
+	err = __pkvm_create_mappings(addr, size, phys, prot);
+	if (err)
+		return err;
+
+	*haddr = addr + offset_in_page(phys);
+	return err;
 }
 
 int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot)
@@ -146,7 +170,8 @@ int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot)
 int hyp_map_vectors(void)
 {
 	phys_addr_t phys;
-	void *bp_base;
+	unsigned long bp_base;
+	int ret;
 
 	if (!kvm_system_needs_idmapped_vectors()) {
 		__hyp_bp_vect_base = __bp_harden_hyp_vecs;
@@ -154,13 +179,12 @@ int hyp_map_vectors(void)
 	}
 
 	phys = __hyp_pa(__bp_harden_hyp_vecs);
-	bp_base = (void *)__pkvm_create_private_mapping(phys,
-							__BP_HARDEN_HYP_VECS_SZ,
-							PAGE_HYP_EXEC);
-	if (IS_ERR_OR_NULL(bp_base))
-		return PTR_ERR(bp_base);
+	ret = __pkvm_create_private_mapping(phys, __BP_HARDEN_HYP_VECS_SZ,
+					    PAGE_HYP_EXEC, &bp_base);
+	if (ret)
+		return ret;
 
-	__hyp_bp_vect_base = bp_base;
+	__hyp_bp_vect_base = (void *)bp_base;
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 27af337f9fea..e8d4ea2fcfa0 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -99,17 +99,42 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 		return ret;
 
 	for (i = 0; i < hyp_nr_cpus; i++) {
+		struct kvm_nvhe_init_params *params = per_cpu_ptr(&kvm_init_params, i);
+		unsigned long hyp_addr;
+
 		start = (void *)kern_hyp_va(per_cpu_base[i]);
 		end = start + PAGE_ALIGN(hyp_percpu_size);
 		ret = pkvm_create_mappings(start, end, PAGE_HYP);
 		if (ret)
 			return ret;
 
-		end = (void *)per_cpu_ptr(&kvm_init_params, i)->stack_hyp_va;
-		start = end - PAGE_SIZE;
-		ret = pkvm_create_mappings(start, end, PAGE_HYP);
+		/*
+		 * Allocate a contiguous HYP private VA range for the stack
+		 * and guard page. The allocation is also aligned based on
+		 * the order of its size.
+		 */
+		ret = pkvm_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr);
+		if (ret)
+			return ret;
+
+		/*
+		 * Since the stack grows downwards, map the stack to the page
+		 * at the higher address and leave the lower guard page
+		 * unbacked.
+		 *
+		 * Any valid stack address now has the PAGE_SHIFT bit as 1
+		 * and addresses corresponding to the guard page have the
+		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+		 */
+		hyp_spin_lock(&pkvm_pgd_lock);
+		ret = kvm_pgtable_hyp_map(&pkvm_pgtable, hyp_addr + PAGE_SIZE,
+					PAGE_SIZE, params->stack_pa, PAGE_HYP);
+		hyp_spin_unlock(&pkvm_pgd_lock);
 		if (ret)
 			return ret;
+
+		/* Update stack_hyp_va to end of the stack's private VA range */
+		params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE);
 	}
 
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index caace61ea459..978f1b94fb25 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -377,7 +377,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return exit_code;
 }
 
-void __noreturn hyp_panic(void)
+asmlinkage void __noreturn hyp_panic(void)
 {
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
@@ -399,6 +399,11 @@ void __noreturn hyp_panic(void)
 	unreachable();
 }
 
+asmlinkage void __noreturn hyp_panic_bad_stack(void)
+{
+	hyp_panic();
+}
+
 asmlinkage void kvm_unexpected_el2_exception(void)
 {
 	return __kvm_unexpected_el2_exception();
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 5400fc020164..f5651a05b6a8 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -258,8 +258,8 @@ static bool kvm_host_owns_hyp_mappings(void)
 	return true;
 }
 
-static int __create_hyp_mappings(unsigned long start, unsigned long size,
-				 unsigned long phys, enum kvm_pgtable_prot prot)
+int __create_hyp_mappings(unsigned long start, unsigned long size,
+			  unsigned long phys, enum kvm_pgtable_prot prot)
 {
 	int err;
 
@@ -457,23 +457,22 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	return 0;
 }
 
-static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
-					unsigned long *haddr,
-					enum kvm_pgtable_prot prot)
+
+/**
+ * hyp_alloc_private_va_range - Allocates a private VA range.
+ * @size:	The size of the VA range to reserve.
+ * @haddr:	The hypervisor virtual start address of the allocation.
+ *
+ * The private virtual address (VA) range is allocated below io_map_base
+ * and aligned based on the order of @size.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
 {
 	unsigned long base;
 	int ret = 0;
 
-	if (!kvm_host_owns_hyp_mappings()) {
-		base = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
-					 phys_addr, size, prot);
-		if (IS_ERR_OR_NULL((void *)base))
-			return PTR_ERR((void *)base);
-		*haddr = base;
-
-		return 0;
-	}
-
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
 	/*
@@ -484,8 +483,10 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
 	 *
 	 * The allocated size is always a multiple of PAGE_SIZE.
 	 */
-	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
-	base = io_map_base - size;
+	base = io_map_base - PAGE_ALIGN(size);
+
+	/* Align the allocation based on the order of its size */
+	base = ALIGN_DOWN(base, PAGE_SIZE << get_order(size));
 
 	/*
 	 * Verify that BIT(VA_BITS - 1) hasn't been flipped by
@@ -495,19 +496,40 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
 	if ((base ^ io_map_base) & BIT(VA_BITS - 1))
 		ret = -ENOMEM;
 	else
-		io_map_base = base;
+		*haddr = io_map_base = base;
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 
+	return ret;
+}
+
+static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
+					unsigned long *haddr,
+					enum kvm_pgtable_prot prot)
+{
+	unsigned long addr;
+	int ret = 0;
+
+	if (!kvm_host_owns_hyp_mappings()) {
+		addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
+					 phys_addr, size, prot);
+		if (IS_ERR_VALUE(addr))
+			return addr;
+		*haddr = addr;
+
+		return 0;
+	}
+
+	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
+	ret = hyp_alloc_private_va_range(size, &addr);
 	if (ret)
-		goto out;
+		return ret;
 
-	ret = __create_hyp_mappings(base, size, phys_addr, prot);
+	ret = __create_hyp_mappings(addr, size, phys_addr, prot);
 	if (ret)
-		goto out;
+		return ret;
 
-	*haddr = base + offset_in_page(phys_addr);
-out:
+	*haddr = addr + offset_in_page(phys_addr);
 	return ret;
 }