loopdev: sync capacity after setting it

I recently tried to mount an hfsplus file system from an image file with
a partition table by using the loop offset and sizelimit options to specify
the location of the file system.

hfsplus stores some metadata at a set offset from the end of the partition,
so it's sensitive to the device size reported by the kernel.

It worked with this:

But failed with this:

/dev/loop0: [0089]:2 (<imagefile>), offset 32768, sizelimit 102400000
/dev/loop1: [0089]:2 (<imagefile>), offset 32768, sizelimit 102400000

/proc/partitions shows the correct number of blocks to match the sizelimit.

But if I set a breakpoint in mount before the mount syscall, I could see:
102400000
102432768

The kernel loop driver will set the gendisk capacity of the device at
LOOP_SET_STATUS64 but won't sync it to the block device until one of two
conditions are met: All open file descriptors referring to the device are
closed (and it will sync when re-opened) or if the LOOP_SET_CAPACITY ioctl
is called to sync it. Since mount opens the device and passes it directly
to the mount syscall after LOOP_SET_STATUS64 without closing and reopening
it, the sizelimit argument is effectively ignroed. The capacity needs to
be synced immediately for it to work as expected.

This patch adds the LOOP_SET_CAPACITY call to loopctx_setup_device since
the device isn't yet released to the user, so it's safe to sync the capacity
immediately.

[kzak@redhat.com: - port to the current git HEAD,
                  - use uint64_t]

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Karel Zak <kzak@redhat.com>

3 files changed, 85 insertions, 6 deletions

diff --git a/lib/Makemodule.am b/lib/Makemodule.am
index a118958c5..afc2156c7 100644
--- a/lib/Makemodule.am
+++ b/lib/Makemodule.am
@@ -70,7 +70,7 @@ test_ttyutils_CFLAGS = -DTEST_PROGRAM
 test_ttyutils_LDADD = libcommon.la
 
 test_blkdev_SOURCES = lib/blkdev.c
-test_blkdev_CFLAGS = -DTEST_PROGRAM
+test_blkdev_CFLAGS = -DTEST_PROGRAM_BLKDEV
 test_blkdev_LDADD = libcommon.la
 
 test_ismounted_SOURCES = lib/ismounted.c
diff --git a/lib/blkdev.c b/lib/blkdev.c
index 09c1a2ff3..f8182c0b3 100644
--- a/lib/blkdev.c
+++ b/lib/blkdev.c
@@ -28,7 +28,6 @@
 #include "blkdev.h"
 #include "c.h"
 #include "linux_version.h"
-#include "xalloc.h"
 
 static long
 blkdev_valid_offset (int fd, off_t offset) {
@@ -336,7 +335,7 @@ const char *blkdev_scsi_type_to_name(int type)
 	return NULL;
 }
 
-#ifdef TEST_PROGRAM
+#ifdef TEST_PROGRAM_BLKDEV
 #include <stdio.h>
 #include <stdlib.h>
 #include <fcntl.h>
diff --git a/lib/loopdev.c b/lib/loopdev.c
index 2a696ab4d..c35e306f9 100644
--- a/lib/loopdev.c
+++ b/lib/loopdev.c
@@ -41,6 +41,7 @@
 #include "loopdev.h"
 #include "canonicalize.h"
 #include "at.h"
+#include "blkdev.h"
 
 #define CONFIG_LOOPDEV_DEBUG
 
@@ -1072,6 +1073,64 @@ int loopcxt_set_backing_file(struct loopdev_cxt *lc, const char *filename)
 }
 
 /*
+ * In kernels prior to v3.9, if the offset or sizelimit options
+ * are used, the block device's size won't be synced automatically.
+ * blockdev --getsize64 and filesystems will use the backing
+ * file size until the block device has been re-opened or the
+ * LOOP_SET_CAPACITY ioctl is called to sync the sizes.
+ *
+ * Since mount -oloop uses the LO_FLAGS_AUTOCLEAR option and passes
+ * the open file descriptor to the mount system call, we need to use
+ * the ioctl. Calling losetup directly doesn't have this problem since
+ * it closes the device when it exits and whatever consumes the device
+ * next will re-open it, causing the resync.
+ */
+static int loopcxt_check_size(struct loopdev_cxt *lc, int file_fd)
+{
+	uint64_t size, expected_size;
+	int dev_fd;
+	struct stat st;
+
+	if (!lc->info.lo_offset && !lc->info.lo_sizelimit)
+		return 0;
+
+	if (fstat(file_fd, &st))
+		return -errno;
+
+	expected_size = st.st_size;
+
+	if (lc->info.lo_offset > 0)
+		expected_size -= lc->info.lo_offset;
+
+	if (lc->info.lo_sizelimit > 0 && lc->info.lo_sizelimit < expected_size)
+		expected_size = lc->info.lo_sizelimit;
+
+	dev_fd = loopcxt_get_fd(lc);
+	if (dev_fd < 0)
+		return -errno;
+
+	if (blkdev_get_size(dev_fd, (unsigned long long *) &size))
+		return -errno;
+
+	if (expected_size != size) {
+		if (loopcxt_set_capacity(lc)) {
+			/* ioctl not available */
+			if (errno == ENOTTY || errno == EINVAL)
+				errno = ERANGE;
+			return -errno;
+		}
+
+		if (blkdev_get_size(dev_fd, (unsigned long long *) &size))
+			return -errno;
+
+		if (expected_size != size)
+			return -ERANGE;
+	}
+
+	return 0;
+}
+
+/*
  * @cl: context
  *
  * Associate the current device (see loopcxt_{set,get}_device()) with
@@ -1150,9 +1209,6 @@ int loopcxt_setup_device(struct loopdev_cxt *lc)
 
 	DBG(lc, loopdev_debug("setup: LOOP_SET_FD: OK"));
 
-	close(file_fd);
-	file_fd = -1;
-
 	if (ioctl(dev_fd, LOOP_SET_STATUS64, &lc->info)) {
 		DBG(lc, loopdev_debug("LOOP_SET_STATUS64 failed: %m"));
 		goto err;
@@ -1160,6 +1216,12 @@ int loopcxt_setup_device(struct loopdev_cxt *lc)
 
 	DBG(lc, loopdev_debug("setup: LOOP_SET_STATUS64: OK"));
 
+	if ((rc = loopcxt_check_size(lc, file_fd)))
+		goto err;
+
+	close(file_fd);
+	file_fd = -1;
+
 	memset(&lc->info, 0, sizeof(lc->info));
 	lc->has_info = 0;
 	lc->info_failed = 0;
@@ -1176,6 +1238,24 @@ err:
 	return rc;
 }
 
+int loopcxt_set_capacity(struct loopdev_cxt *lc)
+{
+	int fd = loopcxt_get_fd(lc);
+
+	if (fd < 0)
+		return -EINVAL;
+
+	/* Kernels prior to v2.6.30 don't support this ioctl */
+	if (ioctl(fd, LOOP_SET_CAPACITY, 0) < 0) {
+		int rc = -errno;
+		DBG(lc, loopdev_debug("LOOP_SET_CAPACITY failed: %m"));
+		return rc;
+	}
+
+	DBG(lc, loopdev_debug("capacity set"));
+	return 0;
+}
+
 int loopcxt_delete_device(struct loopdev_cxt *lc)
 {
 	int fd = loopcxt_get_fd(lc);