1 files changed, 151 insertions, 46 deletions

diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 4e016574bd91..d4202a32abc9 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>
@@ -40,6 +41,12 @@ enum vdso_abi {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
@@ -107,25 +114,122 @@ static int __vdso_init(enum vdso_abi abi)
 			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_info[abi].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 + 1] = pfn_to_page(pfn + i);
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
+
+	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;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT_VDSO
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#endif
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
 
-	vdso_info[abi].dm->pages = &vdso_pagelist[0];
-	vdso_info[abi].cm->pages = &vdso_pagelist[1];
+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;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static int vvar_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;
+
+	if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
+		return -EINVAL;
 
 	return 0;
 }
@@ -139,9 +243,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
+	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)) {
@@ -149,8 +255,8 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
+	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;
@@ -158,7 +264,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += PAGE_SIZE;
+	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|gp_flags|
@@ -191,15 +297,12 @@ enum aarch32_map {
 #ifdef CONFIG_COMPAT_VDSO
 	AA32_MAP_VVAR,
 	AA32_MAP_VDSO,
-#else
-	AA32_MAP_SIGPAGE
 #endif
+	AA32_MAP_SIGPAGE
 };
 
 static struct page *aarch32_vectors_page __ro_after_init;
-#ifndef CONFIG_COMPAT_VDSO
 static struct page *aarch32_sig_page __ro_after_init;
-#endif
 
 static struct vm_special_mapping aarch32_vdso_maps[] = {
 	[AA32_MAP_VECTORS] = {
@@ -209,17 +312,18 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
 #ifdef CONFIG_COMPAT_VDSO
 	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
-#else
+#endif /* CONFIG_COMPAT_VDSO */
 	[AA32_MAP_SIGPAGE] = {
 		.name	= "[sigpage]", /* ABI */
 		.pages	= &aarch32_sig_page,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -242,27 +346,11 @@ static int aarch32_alloc_kuser_vdso_page(void)
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
-	int ret;
-
-	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
-	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
-
-	ret = __vdso_init(VDSO_ABI_AA32);
-	if (ret)
-		return ret;
-
-	return aarch32_alloc_kuser_vdso_page();
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+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;
 
 	sigpage = get_zeroed_page(GFP_ATOMIC);
 	if (!sigpage)
@@ -271,18 +359,34 @@ static int __aarch32_alloc_vdso_pages(void)
 	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
 	aarch32_sig_page = virt_to_page(sigpage);
 	flush_dcache_page(aarch32_sig_page);
+	return 0;
+}
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret)
-		free_page(sigpage);
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	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 ret;
+	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;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __aarch32_alloc_vdso_pages();
+	if (ret)
+		return ret;
+#endif
+
+	ret = aarch32_alloc_sigpage();
+	if (ret)
+		return ret;
+
+	return aarch32_alloc_kuser_vdso_page();
 }
 arch_initcall(aarch32_alloc_vdso_pages);
 
@@ -305,7 +409,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	return PTR_ERR_OR_ZERO(ret);
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 static int aarch32_sigreturn_setup(struct mm_struct *mm)
 {
 	unsigned long addr;
@@ -328,12 +431,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	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)
 {
@@ -352,10 +454,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 				       mm,
 				       bprm,
 				       uses_interp);
-#else
-	ret = aarch32_sigreturn_setup(mm);
+	if (ret)
+		goto out;
 #endif /* CONFIG_COMPAT_VDSO */
 
+	ret = aarch32_sigreturn_setup(mm);
 out:
 	mmap_write_unlock(mm);
 	return ret;
@@ -376,6 +479,8 @@ enum aarch64_map {
 static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
 	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
+		.fault = vvar_fault,
+		.mremap = vvar_mremap,
 	},
 	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",