vmcore: support mmap() on /proc/vmcore

This patch introduces mmap_vmcore().

Don't permit writable nor executable mapping even with mprotect()
because this mmap() is aimed at reading crash dump memory.  Non-writable
mapping is also requirement of remap_pfn_range() when mapping linear
pages on non-consecutive physical pages; see is_cow_mapping().

Set VM_MIXEDMAP flag to remap memory by remap_pfn_range and by
remap_vmalloc_range_pertial at the same time for a single vma.
do_munmap() can correctly clean partially remapped vma with two
functions in abnormal case.  See zap_pte_range(), vm_normal_page() and
their comments for details.

On x86-32 PAE kernels, mmap() supports at most 16TB memory only.  This
limitation comes from the fact that the third argument of
remap_pfn_range(), pfn, is of 32-bit length on x86-32: unsigned long.

[akpm@linux-foundation.org: use min(), switch to conventional error-unwinding approach]
Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Atsushi Kumagai <kumagai-atsushi@mxc.nes.nec.co.jp>
Cc: Lisa Mitchell <lisa.mitchell@hp.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Tested-by: Maxim Uvarov <muvarov@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 8ec6483689857377ab1ae4f12df72c87a869b5ba..28503172f2e4a2d16a87a87098ad5db615317565 100644 (file)
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/crash_dump.h>
 #include <linux/list.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include "internal.h"
@@ -194,9 +195,122 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
        return acc;
 }
 
+/**
+ * alloc_elfnotes_buf - allocate buffer for ELF note segment in
+ *                      vmalloc memory
+ *
+ * @notes_sz: size of buffer
+ *
+ * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
+ * the buffer to user-space by means of remap_vmalloc_range().
+ *
+ * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
+ * disabled and there's no need to allow users to mmap the buffer.
+ */
+static inline char *alloc_elfnotes_buf(size_t notes_sz)
+{
+#ifdef CONFIG_MMU
+       return vmalloc_user(notes_sz);
+#else
+       return vzalloc(notes_sz);
+#endif
+}
+
+/*
+ * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is
+ * essential for mmap_vmcore() in order to map physically
+ * non-contiguous objects (ELF header, ELF note segment and memory
+ * regions in the 1st kernel pointed to by PT_LOAD entries) into
+ * virtually contiguous user-space in ELF layout.
+ */
+#ifdef CONFIG_MMU
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+       size_t size = vma->vm_end - vma->vm_start;
+       u64 start, end, len, tsz;
+       struct vmcore *m;
+
+       start = (u64)vma->vm_pgoff << PAGE_SHIFT;
+       end = start + size;
+
+       if (size > vmcore_size || end > vmcore_size)
+               return -EINVAL;
+
+       if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+               return -EPERM;
+
+       vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
+       vma->vm_flags |= VM_MIXEDMAP;
+
+       len = 0;
+
+       if (start < elfcorebuf_sz) {
+               u64 pfn;
+
+               tsz = min(elfcorebuf_sz - (size_t)start, size);
+               pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
+               if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
+                                   vma->vm_page_prot))
+                       return -EAGAIN;
+               size -= tsz;
+               start += tsz;
+               len += tsz;
+
+               if (size == 0)
+                       return 0;
+       }
+
+       if (start < elfcorebuf_sz + elfnotes_sz) {
+               void *kaddr;
+
+               tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
+               kaddr = elfnotes_buf + start - elfcorebuf_sz;
+               if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
+                                               kaddr, tsz))
+                       goto fail;
+               size -= tsz;
+               start += tsz;
+               len += tsz;
+
+               if (size == 0)
+                       return 0;
+       }
+
+       list_for_each_entry(m, &vmcore_list, list) {
+               if (start < m->offset + m->size) {
+                       u64 paddr = 0;
+
+                       tsz = min_t(size_t, m->offset + m->size - start, size);
+                       paddr = m->paddr + start - m->offset;
+                       if (remap_pfn_range(vma, vma->vm_start + len,
+                                           paddr >> PAGE_SHIFT, tsz,
+                                           vma->vm_page_prot))
+                               goto fail;
+                       size -= tsz;
+                       start += tsz;
+                       len += tsz;
+
+                       if (size == 0)
+                               return 0;
+               }
+       }
+
+       return 0;
+fail:
+       do_munmap(vma->vm_mm, vma->vm_start, len);
+       return -EAGAIN;
+}
+#else
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+       return -ENOSYS;
+}
+#endif
+
 static const struct file_operations proc_vmcore_operations = {
        .read           = read_vmcore,
        .llseek         = default_llseek,
+       .mmap           = mmap_vmcore,
 };
 
 static struct vmcore* __init get_new_element(void)
@@ -348,7 +462,6 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
        Elf64_Ehdr *ehdr_ptr;
        Elf64_Phdr phdr;
        u64 phdr_sz = 0, note_off;
-       struct vm_struct *vm;
 
        ehdr_ptr = (Elf64_Ehdr *)elfptr;
 
@@ -361,18 +474,10 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
                return rc;
 
        *notes_sz = roundup(phdr_sz, PAGE_SIZE);
-       *notes_buf = vzalloc(*notes_sz);
+       *notes_buf = alloc_elfnotes_buf(*notes_sz);
        if (!*notes_buf)
                return -ENOMEM;
 
-       /*
-        * Allow users to remap ELF note segment buffer on vmalloc memory using
-        * remap_vmalloc_range.()
-        */
-       vm = find_vm_area(*notes_buf);
-       BUG_ON(!vm);
-       vm->flags |= VM_USERMAP;
-
        rc = copy_notes_elf64(ehdr_ptr, *notes_buf);
        if (rc < 0)
                return rc;
@@ -536,7 +641,6 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
        Elf32_Ehdr *ehdr_ptr;
        Elf32_Phdr phdr;
        u64 phdr_sz = 0, note_off;
-       struct vm_struct *vm;
 
        ehdr_ptr = (Elf32_Ehdr *)elfptr;
 
@@ -549,18 +653,10 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
                return rc;
 
        *notes_sz = roundup(phdr_sz, PAGE_SIZE);
-       *notes_buf = vzalloc(*notes_sz);
+       *notes_buf = alloc_elfnotes_buf(*notes_sz);
        if (!*notes_buf)
                return -ENOMEM;
 
-       /*
-        * Allow users to remap ELF note segment buffer on vmalloc memory using
-        * remap_vmalloc_range()
-        */
-       vm = find_vm_area(*notes_buf);
-       BUG_ON(!vm);
-       vm->flags |= VM_USERMAP;
-
        rc = copy_notes_elf32(ehdr_ptr, *notes_buf);
        if (rc < 0)
                return rc;