From 3e8da9bb1ae70b554374888ec2e9ba3aab390102 Mon Sep 17 00:00:00 2001
From: Gleb Smirnoff <glebius@FreeBSD.org>
Date: Fri, 12 Jan 2018 22:40:15 -0800
Subject: [PATCH] Return back checking file for sparseness. Use
 lseek(SEEK_HOLE) if supported by the system, otherwise fallback to block
 check. This allows to workaround bugs with SMB client and not introduce new
 bugs for filesystems with compression and deduplication.

This has theoretical bug if our collection spans different
filesystems and some filesystems support holes, and some not.
If this ever encountered we should use pathconf(2) and cache
its result for directories.
---
 configure.ac |  1 +
 monitor.c    | 34 +++++++++++++++++++++++++++-------
 2 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/configure.ac b/configure.ac
index 8eb55c9..1410a94 100644
--- a/configure.ac
+++ b/configure.ac
@@ -68,6 +68,7 @@ AC_C_BIGENDIAN
 AC_FUNC_FORK
 AC_FUNC_LSTAT_FOLLOWS_SLASHED_SYMLINK
 AC_CHECK_FUNCS([gethostname getifaddrs gettimeofday inet_ntoa memmove memset mkdir realpath select sendfile setlocale socket strcasecmp strchr strdup strerror strncasecmp strpbrk strrchr strstr strtol strtoul])
+AC_CHECK_DECLS([SEEK_HOLE])
 
 #
 # Check for struct ip_mreqn
diff --git a/monitor.c b/monitor.c
index d93b871..dcda631 100644
--- a/monitor.c
+++ b/monitor.c
@@ -19,6 +19,7 @@
 
 #include <stdio.h>
 #include <string.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <errno.h>
 #include <unistd.h>
@@ -471,6 +472,30 @@ monitor_insert_file(const char *name, const char *path)
 	return depth;
 }
 
+static bool
+check_notsparse(const char *path)
+#if HAVE_DECL_SEEK_HOLE
+{
+	int fd;
+	bool rv;
+
+	if ((fd = open(path, O_RDONLY)) == -1)
+		return (false);
+	if (lseek(fd, 0, SEEK_HOLE) == lseek(fd, 0, SEEK_END))
+		rv = true;
+	else
+		rv = false;
+	close(fd);
+	return (rv);
+}
+#else
+{
+	struct stat st;
+
+	return (stat(path, &st) == 0 && (st.st_blocks << 9 >= st.st_size));
+}
+#endif
+
 int
 monitor_insert_directory(int fd, char *name, const char * path)
 {
@@ -480,7 +505,6 @@ monitor_insert_directory(int fd, char *name, const char * path)
 	char path_buf[PATH_MAX];
 	enum file_types type = TYPE_UNKNOWN;
 	media_types dir_types;
-	struct stat st;
 
 	if( access(path, R_OK|X_OK) != 0 )
 	{
@@ -538,12 +562,8 @@ monitor_insert_directory(int fd, char *name, const char * path)
 		{
 			monitor_insert_directory(fd, esc_name, path_buf);
 		}
-		else if( type == TYPE_FILE )
-		{
-			if( (stat(path_buf, &st) == 0) )
-			{
-				monitor_insert_file(esc_name, path_buf);
-			}
+		else if( type == TYPE_FILE && check_notsparse(path_buf)) {
+			monitor_insert_file(esc_name, path_buf);
 		}
 		free(esc_name);
 	}