x86, mm: Improve _install_special_mapping and fix x86 vdso naming

Using arch_vma_name to give special mappings a name is awkward.  x86
currently implements it by comparing the start address of the vma to
the expected address of the vdso.  This requires tracking the start
address of special mappings and is probably buggy if a special vma
is split or moved.

Improve _install_special_mapping to just name the vma directly.  Use
it to give the x86 vvar area a name, which should make CRIU's life
easier.

As a side effect, the vvar area will show up in core dumps.  This
could be considered weird and is fixable.

[hpa: I say we accept this as-is but be prepared to deal with knocking
 out the vvars from core dumps if this becomes a problem.]

Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/276b39b6b645fb11e345457b503f17b83c2c6fd0.1400538962.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

arch/x86/include/asm/vdso.h

@@ -7,10 +7,14 @@
 
 #ifndef __ASSEMBLER__
 
+#include <linux/mm_types.h>
+
 struct vdso_image {
 	void *data;
 	unsigned long size;   /* Always a multiple of PAGE_SIZE */
-	struct page **pages;  /* Big enough for data/size page pointers */
+
+	/* text_mapping.pages is big enough for data/size page pointers */
+	struct vm_special_mapping text_mapping;
 
 	unsigned long alt, alt_len;
 

arch/x86/mm/init_64.c

@@ -1223,9 +1223,6 @@ int in_gate_area_no_mm(unsigned long addr)
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	if (vma->vm_mm && vma->vm_start ==
-	    (long __force)vma->vm_mm->context.vdso)
-		return "[vdso]";
 	if (vma == &gate_vma)
 		return "[vsyscall]";
 	return NULL;

arch/x86/vdso/vdso2c.h

@@ -136,7 +136,10 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", data_size);
-	fprintf(outfile, "\t.pages = pages,\n");
+	fprintf(outfile, "\t.text_mapping = {\n");
+	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
+	fprintf(outfile, "\t\t.pages = pages,\n");
+	fprintf(outfile, "\t},\n");
 	if (alt_sec) {
 		fprintf(outfile, "\t.alt = %lu,\n",
 			(unsigned long)alt_sec->sh_offset);

arch/x86/vdso/vdso32-setup.c

@@ -119,13 +119,6 @@ __initcall(ia32_binfmt_init);
 
 #else  /* CONFIG_X86_32 */
 
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
-	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
-		return "[vdso]";
-	return NULL;
-}
-
 struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;

arch/x86/vdso/vma.c

@@ -30,7 +30,8 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 	BUG_ON(image->size % PAGE_SIZE != 0);
 	for (i = 0; i < npages; i++)
-		image->pages[i] = virt_to_page(image->data + i*PAGE_SIZE);
+		image->text_mapping.pages[i] =
+			virt_to_page(image->data + i*PAGE_SIZE);
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
@@ -91,6 +92,10 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	unsigned long addr;
 	int ret = 0;
 	static struct page *no_pages[] = {NULL};
+	static struct vm_special_mapping vvar_mapping = {
+		.name = "[vvar]",
+		.pages = no_pages,
+	};
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -112,21 +117,23 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
 	 */
-	ret = install_special_mapping(mm,
+	vma = _install_special_mapping(mm,
 				       addr,
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				      image->pages);
+				       &image->text_mapping);
 
-	if (ret)
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto up_fail;
+	}
 
 	vma = _install_special_mapping(mm,
 				       addr + image->size,
 				       image->sym_end_mapping - image->size,
 				       VM_READ,
-				       no_pages);
+				       &vvar_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);

include/linux/mm.h

@@ -1782,7 +1782,9 @@ extern struct file *get_mm_exe_file(struct mm_struct *mm);
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
 extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
-				   unsigned long flags, struct page **pages);
+				   unsigned long flags,
+				   const struct vm_special_mapping *spec);
+/* This is an obsolete alternative to _install_special_mapping. */
 extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags, struct page **pages);

include/linux/mm_types.h

@@ -510,4 +510,10 @@ static inline void clear_tlb_flush_pending(struct mm_struct *mm)
 }
 #endif
 
+struct vm_special_mapping
+{
+	const char *name;
+	struct page **pages;
+};
+
 #endif /* _LINUX_MM_TYPES_H */

mm/mmap.c

@@ -2872,6 +2872,31 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages)
 	return 1;
 }
 
+static int special_mapping_fault(struct vm_area_struct *vma,
+				 struct vm_fault *vmf);
+
+/*
+ * Having a close hook prevents vma merging regardless of flags.
+ */
+static void special_mapping_close(struct vm_area_struct *vma)
+{
+}
+
+static const char *special_mapping_name(struct vm_area_struct *vma)
+{
+	return ((struct vm_special_mapping *)vma->vm_private_data)->name;
+}
+
+static const struct vm_operations_struct special_mapping_vmops = {
+	.close = special_mapping_close,
+	.fault = special_mapping_fault,
+	.name = special_mapping_name,
+};
+
+static const struct vm_operations_struct legacy_special_mapping_vmops = {
+	.close = special_mapping_close,
+	.fault = special_mapping_fault,
+};
 
 static int special_mapping_fault(struct vm_area_struct *vma,
 				struct vm_fault *vmf)
@@ -2887,7 +2912,13 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	 */
 	pgoff = vmf->pgoff - vma->vm_pgoff;
 
-	for (pages = vma->vm_private_data; pgoff && *pages; ++pages)
+	if (vma->vm_ops == &legacy_special_mapping_vmops)
+		pages = vma->vm_private_data;
+	else
+		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
+			pages;
+
+	for (; pgoff && *pages; ++pages)
 		pgoff--;
 
 	if (*pages) {
@@ -2900,30 +2931,11 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	return VM_FAULT_SIGBUS;
 }
 
-/*
- * Having a close hook prevents vma merging regardless of flags.
- */
-static void special_mapping_close(struct vm_area_struct *vma)
-{
-}
-
-static const struct vm_operations_struct special_mapping_vmops = {
-	.close = special_mapping_close,
-	.fault = special_mapping_fault,
-};
-
-/*
- * Called with mm->mmap_sem held for writing.
- * Insert a new vma covering the given region, with the given flags.
- * Its pages are supplied by the given array of struct page *.
- * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
- * The region past the last page supplied will always produce SIGBUS.
- * The array pointer and the pages it points to are assumed to stay alive
- * for as long as this mapping might exist.
- */
-struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
+static struct vm_area_struct *__install_special_mapping(
+	struct mm_struct *mm,
 	unsigned long addr, unsigned long len,
-			    unsigned long vm_flags, struct page **pages)
+	unsigned long vm_flags, const struct vm_operations_struct *ops,
+	void *priv)
 {
 	int ret;
 	struct vm_area_struct *vma;
@@ -2940,8 +2952,8 @@ struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
-	vma->vm_ops = &special_mapping_vmops;
-	vma->vm_private_data = pages;
+	vma->vm_ops = ops;
+	vma->vm_private_data = priv;
 
 	ret = insert_vm_struct(mm, vma);
 	if (ret)
@@ -2958,12 +2970,31 @@ out:
 	return ERR_PTR(ret);
 }
 
+/*
+ * Called with mm->mmap_sem held for writing.
+ * Insert a new vma covering the given region, with the given flags.
+ * Its pages are supplied by the given array of struct page *.
+ * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
+ * The region past the last page supplied will always produce SIGBUS.
+ * The array pointer and the pages it points to are assumed to stay alive
+ * for as long as this mapping might exist.
+ */
+struct vm_area_struct *_install_special_mapping(
+	struct mm_struct *mm,
+	unsigned long addr, unsigned long len,
+	unsigned long vm_flags, const struct vm_special_mapping *spec)
+{
+	return __install_special_mapping(mm, addr, len, vm_flags,
+					 &special_mapping_vmops, (void *)spec);
+}
+
 int install_special_mapping(struct mm_struct *mm,
 			    unsigned long addr, unsigned long len,
 			    unsigned long vm_flags, struct page **pages)
 {
-	struct vm_area_struct *vma = _install_special_mapping(mm,
-			    addr, len, vm_flags, pages);
+	struct vm_area_struct *vma = __install_special_mapping(
+		mm, addr, len, vm_flags, &legacy_special_mapping_vmops,
+		(void *)pages);
 
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);