Merge branch kvm-arm64/pkvm-selftest-6.16 into kvm-arm64/pkvm-np-thp-6.16

* kvm-arm64/pkvm-selftest-6.16:
: .
: pKVM selftests covering the memory ownership transitions by
: Quentin Perret. From the initial cover letter:
:
: "We have recently found a bug [1] in the pKVM memory ownership
: transitions by code inspection, but it could have been caught with a
: test.
:
: Introduce a boot-time selftest exercising all the known pKVM memory
: transitions and importantly checks the rejection of illegal transitions.
:
: The new test is hidden behind a new Kconfig option separate from
: CONFIG_EL2_NVHE_DEBUG on purpose as that has side effects on the
: transition checks ([1] doesn't reproduce with EL2 debug enabled).
:
: [1] https://lore.kernel.org/kvmarm/[e-mail]/"
: .
KVM: arm64: Extend pKVM selftest for np-guests
KVM: arm64: Selftest for pKVM transitions
KVM: arm64: Don't WARN from __pkvm_host_share_guest()
KVM: arm64: Add .hyp.data section

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

arch/arm64/include/asm/kvm_pkvm.h

···
 	return res;
 }
 
+#ifdef CONFIG_NVHE_EL2_DEBUG
+static inline unsigned long pkvm_selftest_pages(void) { return 32; }
+#else
+static inline unsigned long pkvm_selftest_pages(void) { return 0; }
+#endif
+
 #define KVM_FFA_MBOX_NR_PAGES	1
 
 static inline unsigned long hyp_ffa_proxy_pages(void)

arch/arm64/include/asm/sections.h

···
 extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
 extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];
+extern char __hyp_data_start[], __hyp_data_end[];
 extern char __hyp_rodata_start[], __hyp_rodata_end[];
 extern char __hyp_reloc_begin[], __hyp_reloc_end[];
 extern char __hyp_bss_start[], __hyp_bss_end[];

arch/arm64/kernel/image-vars.h

···
 KVM_NVHE_ALIAS(__hyp_text_end);
 KVM_NVHE_ALIAS(__hyp_bss_start);
 KVM_NVHE_ALIAS(__hyp_bss_end);
+KVM_NVHE_ALIAS(__hyp_data_start);
+KVM_NVHE_ALIAS(__hyp_data_end);
 KVM_NVHE_ALIAS(__hyp_rodata_start);
 KVM_NVHE_ALIAS(__hyp_rodata_end);
 

arch/arm64/kernel/vmlinux.lds.S

···
 	*(__kvm_ex_table)					\
 	__stop___kvm_ex_table = .;
 
-#define HYPERVISOR_DATA_SECTIONS				\
+#define HYPERVISOR_RODATA_SECTIONS				\
 	HYP_SECTION_NAME(.rodata) : {				\
 		. = ALIGN(PAGE_SIZE);				\
 		__hyp_rodata_start = .;				\
···
 		*(HYP_SECTION_NAME(.rodata))			\
 		. = ALIGN(PAGE_SIZE);				\
 		__hyp_rodata_end = .;				\
+	}
+
+#define HYPERVISOR_DATA_SECTION					\
+	HYP_SECTION_NAME(.data) : {				\
+		. = ALIGN(PAGE_SIZE);				\
+		__hyp_data_start = .;				\
+		*(HYP_SECTION_NAME(.data))			\
+		. = ALIGN(PAGE_SIZE);				\
+		__hyp_data_end = .;				\
 	}
 
 #define HYPERVISOR_PERCPU_SECTION				\
···
 #define SBSS_ALIGN			PAGE_SIZE
 #else /* CONFIG_KVM */
 #define HYPERVISOR_EXTABLE
-#define HYPERVISOR_DATA_SECTIONS
+#define HYPERVISOR_RODATA_SECTIONS
+#define HYPERVISOR_DATA_SECTION
 #define HYPERVISOR_PERCPU_SECTION
 #define HYPERVISOR_RELOC_SECTION
 #define SBSS_ALIGN			0
···
 	/* everything from this point to __init_begin will be marked RO NX */
 	RO_DATA(PAGE_SIZE)
 
-	HYPERVISOR_DATA_SECTIONS
+	HYPERVISOR_RODATA_SECTIONS
 
 	.got : { *(.got) }
 	/*
···
 	_data = .;
 	_sdata = .;
 	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
+
+	HYPERVISOR_DATA_SECTION
 
 	/*
 	 * Data written with the MMU off but read with the MMU on requires

arch/arm64/kvm/arm.c

···
 		goto out_err;
 	}
 
+	err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_start),
+				  kvm_ksym_ref(__hyp_data_end), PAGE_HYP);
+	if (err) {
+		kvm_err("Cannot map .hyp.data section\n");
+		goto out_err;
+	}
+
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
 				  kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
 	if (err) {

arch/arm64/kvm/hyp/include/nvhe/mem_protect.h

···
 	else
 		write_sysreg(0, vttbr_el2);
 }
+
+#ifdef CONFIG_NVHE_EL2_DEBUG
+void pkvm_ownership_selftest(void *base);
+#else
+static inline void pkvm_ownership_selftest(void *base) { }
+#endif
 #endif /* __KVM_NVHE_MEM_PROTECT__ */

arch/arm64/kvm/hyp/nvhe/hyp.lds.S

···
 	BEGIN_HYP_SECTION(.data..percpu)
 		PERCPU_INPUT(L1_CACHE_BYTES)
 	END_HYP_SECTION
+
 	HYP_SECTION(.bss)
+	HYP_SECTION(.data)
 }

arch/arm64/kvm/hyp/nvhe/mem_protect.c

···
 		if (page->host_share_guest_count)
 			break;
 		/* Only host to np-guest multi-sharing is tolerated */
-		WARN_ON(1);
 		fallthrough;
 	default:
 		ret = -EPERM;
···
 
 	return 0;
 }
+
+#ifdef CONFIG_NVHE_EL2_DEBUG
+struct pkvm_expected_state {
+	enum pkvm_page_state host;
+	enum pkvm_page_state hyp;
+	enum pkvm_page_state guest[2]; /* [ gfn, gfn + 1 ] */
+};
+
+static struct pkvm_expected_state selftest_state;
+static struct hyp_page *selftest_page;
+
+static struct pkvm_hyp_vm selftest_vm = {
+	.kvm = {
+		.arch = {
+			.mmu = {
+				.arch = &selftest_vm.kvm.arch,
+				.pgt = &selftest_vm.pgt,
+			},
+		},
+	},
+};
+
+static struct pkvm_hyp_vcpu selftest_vcpu = {
+	.vcpu = {
+		.arch = {
+			.hw_mmu = &selftest_vm.kvm.arch.mmu,
+		},
+		.kvm = &selftest_vm.kvm,
+	},
+};
+
+static void init_selftest_vm(void *virt)
+{
+	struct hyp_page *p = hyp_virt_to_page(virt);
+	int i;
+
+	selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
+	WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt));
+
+	for (i = 0; i < pkvm_selftest_pages(); i++) {
+		if (p[i].refcount)
+			continue;
+		p[i].refcount = 1;
+		hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i]));
+	}
+}
+
+static u64 selftest_ipa(void)
+{
+	return BIT(selftest_vm.pgt.ia_bits - 1);
+}
+
+static void assert_page_state(void)
+{
+	void *virt = hyp_page_to_virt(selftest_page);
+	u64 size = PAGE_SIZE << selftest_page->order;
+	struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu;
+	u64 phys = hyp_virt_to_phys(virt);
+	u64 ipa[2] = { selftest_ipa(), selftest_ipa() + PAGE_SIZE };
+
+	host_lock_component();
+	WARN_ON(__host_check_page_state_range(phys, size, selftest_state.host));
+	host_unlock_component();
+
+	hyp_lock_component();
+	WARN_ON(__hyp_check_page_state_range(phys, size, selftest_state.hyp));
+	hyp_unlock_component();
+
+	guest_lock_component(&selftest_vm);
+	WARN_ON(__guest_check_page_state_range(vcpu, ipa[0], size, selftest_state.guest[0]));
+	WARN_ON(__guest_check_page_state_range(vcpu, ipa[1], size, selftest_state.guest[1]));
+	guest_unlock_component(&selftest_vm);
+}
+
+#define assert_transition_res(res, fn, ...)		\
+	do {						\
+		WARN_ON(fn(__VA_ARGS__) != res);	\
+		assert_page_state();			\
+	} while (0)
+
+void pkvm_ownership_selftest(void *base)
+{
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_RWX;
+	void *virt = hyp_alloc_pages(&host_s2_pool, 0);
+	struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu;
+	struct pkvm_hyp_vm *vm = &selftest_vm;
+	u64 phys, size, pfn, gfn;
+
+	WARN_ON(!virt);
+	selftest_page = hyp_virt_to_page(virt);
+	selftest_page->refcount = 0;
+	init_selftest_vm(base);
+
+	size = PAGE_SIZE << selftest_page->order;
+	phys = hyp_virt_to_phys(virt);
+	pfn = hyp_phys_to_pfn(phys);
+	gfn = hyp_phys_to_pfn(selftest_ipa());
+
+	selftest_state.host = PKVM_NOPAGE;
+	selftest_state.hyp = PKVM_PAGE_OWNED;
+	selftest_state.guest[0] = selftest_state.guest[1] = PKVM_NOPAGE;
+	assert_page_state();
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+
+	selftest_state.host = PKVM_PAGE_OWNED;
+	selftest_state.hyp = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
+
+	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+	selftest_state.hyp = PKVM_PAGE_SHARED_BORROWED;
+	assert_transition_res(0,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+
+	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
+	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
+	hyp_unpin_shared_mem(virt, virt + size);
+	WARN_ON(hyp_page_count(virt) != 1);
+	assert_transition_res(-EBUSY,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+
+	hyp_unpin_shared_mem(virt, virt + size);
+	assert_page_state();
+	WARN_ON(hyp_page_count(virt));
+
+	selftest_state.host = PKVM_PAGE_OWNED;
+	selftest_state.hyp = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_unshare_hyp, pfn);
+
+	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+	selftest_state.hyp = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, vm);
+	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
+
+	selftest_state.host = PKVM_PAGE_OWNED;
+	selftest_state.hyp = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_unshare_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
+
+	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+	selftest_state.guest[0] = PKVM_PAGE_SHARED_BORROWED;
+	assert_transition_res(0,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, vcpu, prot);
+	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
+	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
+	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
+	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
+
+	selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED;
+	assert_transition_res(0,	__pkvm_host_share_guest, pfn, gfn + 1, vcpu, prot);
+	WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2);
+
+	selftest_state.guest[0] = PKVM_NOPAGE;
+	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn, vm);
+
+	selftest_state.guest[1] = PKVM_NOPAGE;
+	selftest_state.host = PKVM_PAGE_OWNED;
+	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn + 1, vm);
+
+	selftest_state.host = PKVM_NOPAGE;
+	selftest_state.hyp = PKVM_PAGE_OWNED;
+	assert_transition_res(0,	__pkvm_host_donate_hyp, pfn, 1);
+
+	selftest_page->refcount = 1;
+	hyp_put_page(&host_s2_pool, virt);
+}
+#endif

arch/arm64/kvm/hyp/nvhe/setup.c

···
 static void *vm_table_base;
 static void *hyp_pgt_base;
 static void *host_s2_pgt_base;
+static void *selftest_base;
 static void *ffa_proxy_pages;
 static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
 static struct hyp_pool hpool;
···
 	unsigned long nr_pages;
 
 	hyp_early_alloc_init(virt, size);
+
+	nr_pages = pkvm_selftest_pages();
+	selftest_base = hyp_early_alloc_contig(nr_pages);
+	if (nr_pages && !selftest_base)
+		return -ENOMEM;
 
 	nr_pages = hyp_vmemmap_pages(sizeof(struct hyp_page));
 	vmemmap_base = hyp_early_alloc_contig(nr_pages);
···
 		return ret;
 
 	ret = pkvm_create_mappings(__hyp_text_start, __hyp_text_end, PAGE_HYP_EXEC);
+	if (ret)
+		return ret;
+
+	ret = pkvm_create_mappings(__hyp_data_start, __hyp_data_end, PAGE_HYP);
 	if (ret)
 		return ret;
 
···
 		goto out;
 
 	pkvm_hyp_vm_table_init(vm_table_base);
+
+	pkvm_ownership_selftest(selftest_base);
 out:
 	/*
 	 * We tail-called to here from handle___pkvm_init() and will not return,

arch/arm64/kvm/pkvm.c

···
 	hyp_mem_pages += host_s2_pgtable_pages();
 	hyp_mem_pages += hyp_vm_table_pages();
 	hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE);
+	hyp_mem_pages += pkvm_selftest_pages();
 	hyp_mem_pages += hyp_ffa_proxy_pages();
 
 	/*
···
 	 * at, which would end badly once inaccessible.
 	 */
 	kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
+	kmemleak_free_part(__hyp_data_start, __hyp_data_end - __hyp_data_start);
 	kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start);
 	kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);