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>

diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index d0a2c909c72d6af36859cf520ba1cb7d27722b42..30be253dd283b29c0d84922a6588f0459d2b49c4 100644 (file)
--- a/arch/x86/include/asm/vdso.h
+++ b/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;
 

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6f881842116c19acae7242c9e51312aa2c175f91..9deb59b0baea230a0430f0bbbe206a8d88533a4a 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/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;

diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index ed2e894e89abb0785a38b06b6df7b67d8779fd3b..3dcc61e796e9f85d3fb6c1fb1adfb5ee75e1fc94 100644 (file)
--- a/arch/x86/vdso/vdso2c.h
+++ b/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);

diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index c3ed708e50f4114ee7ae339f4cdb751efb6a0c12..e4f7781ee16280a1606349262dcb14b055f5599b 100644 (file)
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/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;

diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 8ad0081df7a83c489db4be0e528d440e55fae544..e1513c47872a9a040b9bb3956b54d3f94c5a303d 100644 (file)
--- a/arch/x86/vdso/vma.c
+++ b/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,
-                                     addr,
-                                     image->size,
-                                     VM_READ|VM_EXEC|
-                                     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-                                     image->pages);
+       vma = _install_special_mapping(mm,
+                                      addr,
+                                      image->size,
+                                      VM_READ|VM_EXEC|
+                                      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+                                      &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);

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 63f8d4efe303091ada6e96cb3adbe9841751bfbb..05aab09803e6a9ee223c07fb6836ca37e23a4851 100644 (file)
--- a/include/linux/mm.h
+++ b/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);

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8967e20cbe57aceb991acac4218eb5d638e867f5..22c6f4e16d106456fd5926c0495a6455e60bc41e 100644 (file)
--- a/include/linux/mm_types.h
+++ b/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 */

diff --git a/mm/mmap.c b/mm/mmap.c
index b1202cf81f4bddf1dcc8393f1231ed85b1e64e6e..52bbc9514d9d005c470bc5292fc0946fc74f7794 100644 (file)
--- a/mm/mmap.c
+++ b/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,
-                           unsigned long addr, unsigned long len,
-                           unsigned long vm_flags, struct page **pages)
+static struct vm_area_struct *__install_special_mapping(
+       struct mm_struct *mm,
+       unsigned long addr, unsigned long len,
+       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);