1 files changed, 165 insertions, 125 deletions

diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 8bc269c55fd3..8c4e07d533c8 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -6,186 +6,226 @@
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
-#include <linux/init.h>
+#include <linux/binfmts.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
 #include <linux/slab.h>
-#include <linux/user.h>
-#include <linux/elf.h>
-#include <linux/security.h>
-#include <linux/memblock.h>
-#include <linux/compat.h>
-#include <linux/binfmts.h>
+#include <linux/smp.h>
+#include <linux/time_namespace.h>
 #include <vdso/datapage.h>
-#include <asm/asm-offsets.h>
-#include <asm/processor.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/sections.h>
 #include <asm/vdso.h>
-#include <asm/facility.h>
-#include <asm/timex.h>
 
-extern char vdso64_start, vdso64_end;
-static void *vdso64_kbase = &vdso64_start;
-static unsigned int vdso64_pages;
-static struct page **vdso64_pagelist;
+extern char vdso64_start[], vdso64_end[];
+static unsigned int vdso_pages;
+
+static struct vm_special_mapping vvar_mapping;
+
+static union {
+	struct vdso_data	data[CS_BASES];
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+
+struct vdso_data *vdso_data = vdso_data_store.data;
+
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
 
-/*
- * Should the kernel map a VDSO page into processes and pass its
- * address down to glibc upon exec()?
- */
 unsigned int __read_mostly vdso_enabled = 1;
 
-static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
-		      struct vm_area_struct *vma, struct vm_fault *vmf)
+static int __init vdso_setup(char *str)
+{
+	bool enabled;
+
+	if (!kstrtobool(str, &enabled))
+		vdso_enabled = enabled;
+	return 1;
+}
+__setup("vdso=", vdso_setup);
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 {
-	struct page **vdso_pagelist;
-	unsigned long vdso_pages;
+	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;
+}
 
-	vdso_pagelist = vdso64_pagelist;
-	vdso_pages = vdso64_pages;
+/*
+ * The VVAR page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will be re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_data() for details.
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
 
-	if (vmf->pgoff >= vdso_pages)
-		return VM_FAULT_SIGBUS;
+	mmap_read_lock(mm);
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
 
-	vmf->page = vdso_pagelist[vmf->pgoff];
-	get_page(vmf->page);
+		if (!vma_is_special_mapping(vma, &vvar_mapping))
+			continue;
+		zap_page_range(vma, vma->vm_start, size);
+		break;
+	}
+	mmap_read_unlock(mm);
 	return 0;
 }
+#else
+static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#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 addr, pfn;
+	vm_fault_t err;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		pfn = virt_to_pfn(vdso_data);
+		if (timens_page) {
+			/*
+			 * Fault in VVAR page too, since it will be accessed
+			 * to get clock data anyway.
+			 */
+			addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
+			err = vmf_insert_pfn(vma, addr, pfn);
+			if (unlikely(err & VM_FAULT_ERROR))
+				return err;
+			pfn = page_to_pfn(timens_page);
+		}
+		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 = virt_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		       struct vm_area_struct *vma)
 {
 	current->mm->context.vdso_base = vma->vm_start;
-
 	return 0;
 }
 
-static const struct vm_special_mapping vdso_mapping = {
+static struct vm_special_mapping vvar_mapping = {
+	.name = "[vvar]",
+	.fault = vvar_fault,
+};
+
+static struct vm_special_mapping vdso_mapping = {
 	.name = "[vdso]",
-	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
 
-static int __init vdso_setup(char *str)
-{
-	bool enabled;
-
-	if (!kstrtobool(str, &enabled))
-		vdso_enabled = enabled;
-	return 1;
-}
-__setup("vdso=", vdso_setup);
-
-/*
- * The vdso data page
- */
-static union {
-	struct vdso_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = (struct vdso_data *)&vdso_data_store.data;
-
-void vdso_getcpu_init(void)
+int vdso_getcpu_init(void)
 {
 	set_tod_programmable_field(smp_processor_id());
+	return 0;
 }
+early_initcall(vdso_getcpu_init); /* Must be called before SMP init */
 
-/*
- * This is called from binfmt_elf, we create the special vma for the
- * vDSO and insert it into the mm struct tree
- */
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
+	unsigned long vdso_text_len, vdso_mapping_len;
+	unsigned long vvar_start, vdso_text_start;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long vdso_pages;
-	unsigned long vdso_base;
 	int rc;
 
-	if (!vdso_enabled)
-		return 0;
-
-	if (is_compat_task())
-		return 0;
-
-	vdso_pages = vdso64_pages;
-	/*
-	 * vDSO has a problem and was disabled, just don't "enable" it for
-	 * the process
-	 */
-	if (vdso_pages == 0)
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	if (!vdso_enabled || is_compat_task())
 		return 0;
-
-	/*
-	 * pick a base address for the vDSO in process space. We try to put
-	 * it at vdso_base which is the "natural" base for it, but we might
-	 * fail and end up putting it elsewhere.
-	 */
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
-	vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
-	if (IS_ERR_VALUE(vdso_base)) {
-		rc = vdso_base;
-		goto out_up;
-	}
-
-	/*
-	 * our vma flags don't have VM_WRITE so by default, the process
-	 * isn't allowed to write those pages.
-	 * gdb can break that with ptrace interface, and thus trigger COW
-	 * on those pages but it's then your responsibility to never do that
-	 * on the "data" page of the vDSO or you'll stop getting kernel
-	 * updates and your nice userland gettimeofday will be totally dead.
-	 * It's fine to use that for setting breakpoints in the vDSO code
-	 * pages though.
-	 */
-	vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+	vdso_text_len = vdso_pages << PAGE_SHIFT;
+	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
+	vvar_start = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
+	rc = vvar_start;
+	if (IS_ERR_VALUE(vvar_start))
+		goto out;
+	vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP,
+				       &vvar_mapping);
+	rc = PTR_ERR(vma);
+	if (IS_ERR(vma))
+		goto out;
+	vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE;
+	/* VM_MAYWRITE for COW so gdb can set breakpoints */
+	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				       &vdso_mapping);
 	if (IS_ERR(vma)) {
+		do_munmap(mm, vvar_start, PAGE_SIZE, NULL);
 		rc = PTR_ERR(vma);
-		goto out_up;
+	} else {
+		current->mm->context.vdso_base = vdso_text_start;
+		rc = 0;
 	}
-
-	current->mm->context.vdso_base = vdso_base;
-	rc = 0;
-
-out_up:
+out:
 	mmap_write_unlock(mm);
 	return rc;
 }
 
 static int __init vdso_init(void)
 {
+	struct page **pages;
 	int i;
 
-	vdso_getcpu_init();
-	/* Calculate the size of the 64 bit vDSO */
-	vdso64_pages = ((&vdso64_end - &vdso64_start
-			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
-
-	/* Make sure pages are in the correct state */
-	vdso64_pagelist = kcalloc(vdso64_pages + 1, sizeof(struct page *),
-				  GFP_KERNEL);
-	BUG_ON(vdso64_pagelist == NULL);
-	for (i = 0; i < vdso64_pages - 1; i++) {
-		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
-		get_page(pg);
-		vdso64_pagelist[i] = pg;
+	vdso_pages = (vdso64_end - vdso64_start) >> PAGE_SHIFT;
+	pages = kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+	if (!pages) {
+		vdso_enabled = 0;
+		return -ENOMEM;
 	}
-	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
-	vdso64_pagelist[vdso64_pages] = NULL;
-
-	get_page(virt_to_page(vdso_data));
-
+	for (i = 0; i < vdso_pages; i++)
+		pages[i] = virt_to_page(vdso64_start + i * PAGE_SIZE);
+	pages[vdso_pages] = NULL;
+	vdso_mapping.pages = pages;
 	return 0;
 }
-early_initcall(vdso_init);
+arch_initcall(vdso_init);