summaryrefslogtreecommitdiffstats
path: root/fs/binfmt_elf.c
diff options
context:
space:
mode:
authorJason Baron <jbaron@redhat.com>2012-03-23 15:02:51 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-23 16:58:42 -0700
commit909af768e88867016f427264ae39d27a57b6a8ed (patch)
tree5068b4d98e4bedecde89d9113dc7ef8c69633f45 /fs/binfmt_elf.c
parent1cc684ab75123efe7ff446eb821d44375ba8fa30 (diff)
downloadlinux-stable-909af768e88867016f427264ae39d27a57b6a8ed.tar.gz
linux-stable-909af768e88867016f427264ae39d27a57b6a8ed.tar.bz2
linux-stable-909af768e88867016f427264ae39d27a57b6a8ed.zip
coredump: remove VM_ALWAYSDUMP flag
The motivation for this patchset was that I was looking at a way for a qemu-kvm process, to exclude the guest memory from its core dump, which can be quite large. There are already a number of filter flags in /proc/<pid>/coredump_filter, however, these allow one to specify 'types' of kernel memory, not specific address ranges (which is needed in this case). Since there are no more vma flags available, the first patch eliminates the need for the 'VM_ALWAYSDUMP' flag. The flag is used internally by the kernel to mark vdso and vsyscall pages. However, it is simple enough to check if a vma covers a vdso or vsyscall page without the need for this flag. The second patch then replaces the 'VM_ALWAYSDUMP' flag with a new 'VM_NODUMP' flag, which can be set by userspace using new madvise flags: 'MADV_DONTDUMP', and unset via 'MADV_DODUMP'. The core dump filters continue to work the same as before unless 'MADV_DONTDUMP' is set on the region. The qemu code which implements this features is at: http://people.redhat.com/~jbaron/qemu-dump/qemu-dump.patch In my testing the qemu core dump shrunk from 383MB -> 13MB with this patch. I also believe that the 'MADV_DONTDUMP' flag might be useful for security sensitive apps, which might want to select which areas are dumped. This patch: The VM_ALWAYSDUMP flag is currently used by the coredump code to indicate that a vma is part of a vsyscall or vdso section. However, we can determine if a vma is in one these sections by checking it against the gate_vma and checking for a non-NULL return value from arch_vma_name(). Thus, freeing a valuable vma bit. Signed-off-by: Jason Baron <jbaron@redhat.com> Acked-by: Roland McGrath <roland@hack.frob.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/binfmt_elf.c')
-rw-r--r--fs/binfmt_elf.c27
1 files changed, 25 insertions, 2 deletions
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 81878b78c9d4..b64be5b5ac21 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1093,6 +1093,29 @@ out:
*/
/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+ /* Any vsyscall mappings? */
+ if (vma == get_gate_vma(vma->vm_mm))
+ return true;
+ /*
+ * arch_vma_name() returns non-NULL for special architecture mappings,
+ * such as vDSO sections.
+ */
+ if (arch_vma_name(vma))
+ return true;
+
+ return false;
+}
+
+/*
* Decide what to dump of a segment, part, all or none.
*/
static unsigned long vma_dump_size(struct vm_area_struct *vma,
@@ -1100,8 +1123,8 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
{
#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)
+ /* always dump the vdso and vsyscall sections */
+ if (always_dump_vma(vma))
goto whole;
/* Hugetlb memory check */