coredump_filter: add hugepage dumping

Presently hugepage's vma has a VM_RESERVED flag in order not to be
swapped.  But a VM_RESERVED vma isn't core dumped because this flag is
often used for some kernel vmas (e.g.  vmalloc, sound related).

Thus hugepages are never dumped and it can't be debugged easily.  Many
developers want hugepages to be included into core-dump.

However, We can't read generic VM_RESERVED area because this area is often
IO mapping area.  then these area reading may change device state.  it is
definitly undesiable side-effect.

So adding a hugepage specific bit to the coredump filter is better.  It
will be able to hugepage core dumping and doesn't cause any side-effect to
any i/o devices.

In additional, libhugetlb use hugetlb private mapping pages as anonymous
page.  Then, hugepage private mapping pages should be core dumped by
default.

Then, /proc/[pid]/core_dump_filter has two new bits.

 - bit 5 mean hugetlb private mapping pages are dumped or not. (default: yes)
 - bit 6 mean hugetlb shared mapping pages are dumped or not.  (default: no)

I tested by following method.

% ulimit -c unlimited
% ./crash_hugepage  50
% ./crash_hugepage  50  -p
% ls -lh
% gdb ./crash_hugepage core
%
% echo 0x43 > /proc/self/coredump_filter
% ./crash_hugepage  50
% ./crash_hugepage  50  -p
% ls -lh
% gdb ./crash_hugepage core

#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>
#include <string.h>

#include "hugetlbfs.h"

int main(int argc, char** argv){
	char* p;
	int ch;
	int mmap_flags = MAP_SHARED;
	int fd;
	int nr_pages;

	while((ch = getopt(argc, argv, "p")) != -1) {
		switch (ch) {
		case 'p':
			mmap_flags &= ~MAP_SHARED;
			mmap_flags |= MAP_PRIVATE;
			break;
		default:
			/* nothing*/
			break;
		}
	}
	argc -= optind;
	argv += optind;

	if (argc == 0){
		printf("need # of pages\n");
		exit(1);
	}

	nr_pages = atoi(argv[0]);
	if (nr_pages < 2) {
		printf("nr_pages must >2\n");
		exit(1);
	}

	fd = hugetlbfs_unlinked_fd();
	p = mmap(NULL, nr_pages * gethugepagesize(),
		 PROT_READ|PROT_WRITE, mmap_flags, fd, 0);

	sleep(2);

	*(p + gethugepagesize()) = 1; /* COW */
	sleep(2);

	/* crash! */
	*(int*)0 = 1;

	return 0;
}

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Kawai Hidehiro <hidehiro.kawai.ez@hitachi.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: William Irwin <wli@holomorphy.com>
Cc: Adam Litke <agl@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 10 insertions, 2 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c76afa26edf7..e2159063198a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1156,16 +1156,24 @@ static int dump_seek(struct file *file, loff_t off)
 static unsigned long vma_dump_size(struct vm_area_struct *vma,
                                    unsigned long mm_flags)
 {
+#define FILTER(type)    (mm_flags & (1UL << MMF_DUMP_##type))
+
         /* The vma can be set up to tell us the answer directly.  */
         if (vma->vm_flags & VM_ALWAYSDUMP)
                 goto whole;
 
+        /* Hugetlb memory check */
+        if (vma->vm_flags & VM_HUGETLB) {
+                if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+                        goto whole;
+                if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+                        goto whole;
+        }
+
         /* Do not dump I/O mapped devices or special mappings */
         if (vma->vm_flags & (VM_IO | VM_RESERVED))
                 return 0;
 
-#define FILTER(type)    (mm_flags & (1UL << MMF_DUMP_##type))
-
         /* By default, dump shared memory if mapped from an anonymous file. */
         if (vma->vm_flags & VM_SHARED) {
                 if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0 ?