binfmt_elf: Dump smaller VMAs first in ELF cores

Large cores may be truncated in some scenarios, such as with daemons
with stop timeouts that are not large enough or lack of disk space. This
impacts debuggability with large core dumps since critical information
necessary to form a usable backtrace, such as stacks and shared library
information, are omitted.

We attempted to figure out which VMAs are needed to create a useful
backtrace, and it turned out to be a non-trivial problem. Instead, we
try simply sorting the VMAs by size, which has the intended effect.

By sorting VMAs by dump size and dumping in that order, we have a
simple, yet effective heuristic.

Signed-off-by: Brian Mak <makb@juniper.net>
Link: https://lore.kernel.org/r/036CD6AE-C560-4FC7-9B02-ADD08E380DC9@juniper.net


Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Kees Cook <kees@kernel.org>

fs/coredump.c

@@ -18,6 +18,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/coredump.h>
+#include <linux/sort.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task_stack.h>
@@ -1249,6 +1250,18 @@ static void free_vma_snapshot(struct coredump_params *cprm)
 	}
 }
 
+static int cmp_vma_size(const void *vma_meta_lhs_ptr, const void *vma_meta_rhs_ptr)
+{
+	const struct core_vma_metadata *vma_meta_lhs = vma_meta_lhs_ptr;
+	const struct core_vma_metadata *vma_meta_rhs = vma_meta_rhs_ptr;
+
+	if (vma_meta_lhs->dump_size < vma_meta_rhs->dump_size)
+		return -1;
+	if (vma_meta_lhs->dump_size > vma_meta_rhs->dump_size)
+		return 1;
+	return 0;
+}
+
 /*
  * Under the mmap_lock, take a snapshot of relevant information about the task's
  * VMAs.
@@ -1311,5 +1324,8 @@ static bool dump_vma_snapshot(struct coredump_params *cprm)
 		cprm->vma_data_size += m->dump_size;
 	}
 
+	sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta),
+		cmp_vma_size, NULL);
+
 	return true;
 }