1 files changed, 195 insertions, 179 deletions

diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 354b11e27c07..89b6e7840002 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/time_namespace.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
@@ -28,25 +29,18 @@
 #include <asm/signal32.h>
 #include <asm/vdso.h>
 
-extern char vdso_start[], vdso_end[];
-#ifdef CONFIG_COMPAT_VDSO
-extern char vdso32_start[], vdso32_end[];
-#endif /* CONFIG_COMPAT_VDSO */
+enum vdso_abi {
+	VDSO_ABI_AA64,
+	VDSO_ABI_AA32,
+};
 
-/* vdso_lookup arch_index */
-enum arch_vdso_type {
-	ARM64_VDSO = 0,
-#ifdef CONFIG_COMPAT_VDSO
-	ARM64_VDSO32 = 1,
-#endif /* CONFIG_COMPAT_VDSO */
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
 };
-#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_TYPES		(ARM64_VDSO32 + 1)
-#else
-#define VDSO_TYPES		(ARM64_VDSO + 1)
-#endif /* CONFIG_COMPAT_VDSO */
 
-struct __vdso_abi {
+struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
 	const char *vdso_code_end;
@@ -57,14 +51,14 @@ struct __vdso_abi {
 	struct vm_special_mapping *cm;
 };
 
-static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
-	{
+static struct vdso_abi_info vdso_info[] __ro_after_init = {
+	[VDSO_ABI_AA64] = {
 		.name = "vdso",
 		.vdso_code_start = vdso_start,
 		.vdso_code_end = vdso_end,
 	},
 #ifdef CONFIG_COMPAT_VDSO
-	{
+	[VDSO_ABI_AA32] = {
 		.name = "vdso32",
 		.vdso_code_start = vdso32_start,
 		.vdso_code_end = vdso32_end,
@@ -75,78 +69,133 @@ static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
 /*
  * The vDSO data page.
  */
-static union {
-	struct vdso_data	data[CS_BASES];
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
 struct vdso_data *vdso_data = vdso_data_store.data;
 
-static int __vdso_remap(enum arch_vdso_type arch_index,
-			const struct vm_special_mapping *sm,
-			struct vm_area_struct *new_vma)
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
 {
-	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
-	unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
-				  vdso_lookup[arch_index].vdso_code_start;
-
-	if (vdso_size != new_size)
-		return -EINVAL;
-
 	current->mm->context.vdso = (void *)new_vma->vm_start;
 
 	return 0;
 }
 
-static int __vdso_init(enum arch_vdso_type arch_index)
+static int __init __vdso_init(enum vdso_abi abi)
 {
 	int i;
 	struct page **vdso_pagelist;
 	unsigned long pfn;
 
-	if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+	if (memcmp(vdso_info[abi].vdso_code_start, "\177ELF", 4)) {
 		pr_err("vDSO is not a valid ELF object!\n");
 		return -EINVAL;
 	}
 
-	vdso_lookup[arch_index].vdso_pages = (
-			vdso_lookup[arch_index].vdso_code_end -
-			vdso_lookup[arch_index].vdso_code_start) >>
+	vdso_info[abi].vdso_pages = (
+			vdso_info[abi].vdso_code_end -
+			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages,
 				sizeof(struct page *),
 				GFP_KERNEL);
 	if (vdso_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
 
+	for (i = 0; i < vdso_info[abi].vdso_pages; i++)
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
 
-	/* Grab the vDSO code pages. */
-	pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+	vdso_info[abi].cm->pages = vdso_pagelist;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
 
-	for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+	mmap_read_lock(mm);
 
-	vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
-	vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+	for_each_vma(vmi, vma) {
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+			zap_vma_pages(vma);
+#ifdef CONFIG_COMPAT_VDSO
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+			zap_vma_pages(vma);
+#endif
+	}
 
+	mmap_read_unlock(mm);
 	return 0;
 }
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
 
-static int __setup_additional_pages(enum arch_vdso_type arch_index,
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
 				    int uses_interp)
 {
 	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	unsigned long gp_flags = 0;
 	void *ret;
 
-	vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
+	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -154,18 +203,21 @@ static int __setup_additional_pages(enum arch_vdso_type arch_index,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
-				       vdso_lookup[arch_index].dm);
+	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
+				       VM_READ|VM_MAYREAD|VM_PFNMAP,
+				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
 		goto up_fail;
 
-	vdso_base += PAGE_SIZE;
+	if (system_supports_bti_kernel())
+		gp_flags = VM_ARM64_BTI;
+
+	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
-				       VM_READ|VM_EXEC|
+				       VM_READ|VM_EXEC|gp_flags|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       vdso_lookup[arch_index].cm);
+				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
 		goto up_fail;
 
@@ -180,52 +232,42 @@ up_fail:
 /*
  * Create and map the vectors page for AArch32 tasks.
  */
-#ifdef CONFIG_COMPAT_VDSO
-static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
-		struct vm_area_struct *new_vma)
+enum aarch32_map {
+	AA32_MAP_VECTORS, /* kuser helpers */
+	AA32_MAP_SIGPAGE,
+	AA32_MAP_VVAR,
+	AA32_MAP_VDSO,
+};
+
+static struct page *aarch32_vectors_page __ro_after_init;
+static struct page *aarch32_sig_page __ro_after_init;
+
+static int aarch32_sigpage_mremap(const struct vm_special_mapping *sm,
+				  struct vm_area_struct *new_vma)
 {
-	return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+	current->mm->context.sigpage = (void *)new_vma->vm_start;
+
+	return 0;
 }
-#endif /* CONFIG_COMPAT_VDSO */
 
-/*
- * aarch32_vdso_pages:
- * 0 - kuser helpers
- * 1 - sigreturn code
- * or (CONFIG_COMPAT_VDSO):
- * 0 - kuser helpers
- * 1 - vdso data
- * 2 - vdso code
- */
-#define C_VECTORS	0
-#ifdef CONFIG_COMPAT_VDSO
-#define C_VVAR		1
-#define C_VDSO		2
-#define C_PAGES		(C_VDSO + 1)
-#else
-#define C_SIGPAGE	1
-#define C_PAGES		(C_SIGPAGE + 1)
-#endif /* CONFIG_COMPAT_VDSO */
-static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
-static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
-	{
+static struct vm_special_mapping aarch32_vdso_maps[] = {
+	[AA32_MAP_VECTORS] = {
 		.name	= "[vectors]", /* ABI */
-		.pages	= &aarch32_vdso_pages[C_VECTORS],
+		.pages	= &aarch32_vectors_page,
 	},
-#ifdef CONFIG_COMPAT_VDSO
-	{
+	[AA32_MAP_SIGPAGE] = {
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_sig_page,
+		.mremap	= aarch32_sigpage_mremap,
+	},
+	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
+		.fault = vvar_fault,
 	},
-	{
+	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
-		.mremap = aarch32_vdso_mremap,
-	},
-#else
-	{
-		.name	= "[sigpage]", /* ABI */
-		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+		.mremap = vdso_mremap,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -237,69 +279,59 @@ static int aarch32_alloc_kuser_vdso_page(void)
 	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
 		return 0;
 
-	vdso_page = get_zeroed_page(GFP_ATOMIC);
+	vdso_page = get_zeroed_page(GFP_KERNEL);
 	if (!vdso_page)
 		return -ENOMEM;
 
 	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
 	       kuser_sz);
-	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
-	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	aarch32_vectors_page = virt_to_page((void *)vdso_page);
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
-	int ret;
-
-	vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
-	vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
-
-	ret = __vdso_init(ARM64_VDSO32);
-	if (ret)
-		return ret;
-
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret) {
-		unsigned long c_vvar =
-			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]);
-		unsigned long c_vdso =
-			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]);
-
-		free_page(c_vvar);
-		free_page(c_vdso);
-	}
-
-	return ret;
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+#define COMPAT_SIGPAGE_POISON_WORD	0xe7fddef1
+static int aarch32_alloc_sigpage(void)
 {
 	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
 	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
-	unsigned long sigpage;
-	int ret;
+	__le32 poison = cpu_to_le32(COMPAT_SIGPAGE_POISON_WORD);
+	void *sigpage;
 
-	sigpage = get_zeroed_page(GFP_ATOMIC);
+	sigpage = (void *)__get_free_page(GFP_KERNEL);
 	if (!sigpage)
 		return -ENOMEM;
 
-	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
-	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
-	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+	memset32(sigpage, (__force u32)poison, PAGE_SIZE / sizeof(poison));
+	memcpy(sigpage, __aarch32_sigret_code_start, sigret_sz);
+	aarch32_sig_page = virt_to_page(sigpage);
+	return 0;
+}
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret)
-		free_page(sigpage);
+static int __init __aarch32_alloc_vdso_pages(void)
+{
 
-	return ret;
+	if (!IS_ENABLED(CONFIG_COMPAT_VDSO))
+		return 0;
+
+	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
+
+	return __vdso_init(VDSO_ABI_AA32);
 }
-#endif /* CONFIG_COMPAT_VDSO */
 
 static int __init aarch32_alloc_vdso_pages(void)
 {
-	return __aarch32_alloc_vdso_pages();
+	int ret;
+
+	ret = __aarch32_alloc_vdso_pages();
+	if (ret)
+		return ret;
+
+	ret = aarch32_alloc_sigpage();
+	if (ret)
+		return ret;
+
+	return aarch32_alloc_kuser_vdso_page();
 }
 arch_initcall(aarch32_alloc_vdso_pages);
 
@@ -317,12 +349,11 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
 				       VM_READ | VM_EXEC |
 				       VM_MAYREAD | VM_MAYEXEC,
-				       &aarch32_vdso_spec[C_VECTORS]);
+				       &aarch32_vdso_maps[AA32_MAP_VECTORS]);
 
 	return PTR_ERR_OR_ZERO(ret);
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 static int aarch32_sigreturn_setup(struct mm_struct *mm)
 {
 	unsigned long addr;
@@ -341,63 +372,53 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
 				       VM_MAYWRITE | VM_MAYEXEC,
-				       &aarch32_vdso_spec[C_SIGPAGE]);
+				       &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
 	if (IS_ERR(ret))
 		goto out;
 
-	mm->context.vdso = (void *)addr;
+	mm->context.sigpage = (void *)addr;
 
 out:
 	return PTR_ERR_OR_ZERO(ret);
 }
-#endif /* !CONFIG_COMPAT_VDSO */
 
 int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	int ret;
 
-	if (down_write_killable(&mm->mmap_sem))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
 	ret = aarch32_kuser_helpers_setup(mm);
 	if (ret)
 		goto out;
 
-#ifdef CONFIG_COMPAT_VDSO
-	ret = __setup_additional_pages(ARM64_VDSO32,
-				       mm,
-				       bprm,
-				       uses_interp);
-#else
-	ret = aarch32_sigreturn_setup(mm);
-#endif /* CONFIG_COMPAT_VDSO */
+	if (IS_ENABLED(CONFIG_COMPAT_VDSO)) {
+		ret = __setup_additional_pages(VDSO_ABI_AA32, mm, bprm,
+					       uses_interp);
+		if (ret)
+			goto out;
+	}
 
+	ret = aarch32_sigreturn_setup(mm);
 out:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	return ret;
 }
 #endif /* CONFIG_COMPAT */
 
-static int vdso_mremap(const struct vm_special_mapping *sm,
-		struct vm_area_struct *new_vma)
-{
-	return __vdso_remap(ARM64_VDSO, sm, new_vma);
-}
+enum aarch64_map {
+	AA64_MAP_VVAR,
+	AA64_MAP_VDSO,
+};
 
-/*
- * aarch64_vdso_pages:
- * 0 - vvar
- * 1 - vdso
- */
-#define A_VVAR		0
-#define A_VDSO		1
-#define A_PAGES		(A_VDSO + 1)
-static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
-	{
+static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
+	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
+		.fault = vvar_fault,
 	},
-	{
+	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",
 		.mremap = vdso_mremap,
 	},
@@ -405,28 +426,23 @@ static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
 
 static int __init vdso_init(void)
 {
-	vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
-	vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
+	vdso_info[VDSO_ABI_AA64].dm = &aarch64_vdso_maps[AA64_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA64].cm = &aarch64_vdso_maps[AA64_MAP_VDSO];
 
-	return __vdso_init(ARM64_VDSO);
+	return __vdso_init(VDSO_ABI_AA64);
 }
 arch_initcall(vdso_init);
 
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-				int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	int ret;
 
-	if (down_write_killable(&mm->mmap_sem))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	ret = __setup_additional_pages(ARM64_VDSO,
-				       mm,
-				       bprm,
-				       uses_interp);
-
-	up_write(&mm->mmap_sem);
+	ret = __setup_additional_pages(VDSO_ABI_AA64, mm, bprm, uses_interp);
+	mmap_write_unlock(mm);
 
 	return ret;
 }