While checkpointing each file-descriptor, find all the locks on the
file and save information about the lock in the checkpoint-image.
A follow-on patch will use this informaiton to restore the file-locks.
Changelog[v2]:
[Matt Helsley]: Use fixed sizes (__s64) instead of 'loff_t' in
'struct ckpt_hdr_file_lock'.
[Matt Helsley, Serge Hallyn]: Highlight new use of BKL (using
lock_flocks() macros as suggested by Serge).
[Matt Helsley]: Reorg code a bit to simplify error handling.
[Matt Helsley]: Reorg code to initialize marker-lock (Pass a
NULL lock to checkpoint_one_lock() to indicate marker).
Signed-off-by: Sukadev Bhattiprolu <sukadev@xxxxxxxxxxxxxxxxxx>
---
fs/checkpoint.c | 101 ++++++++++++++++++++++++++++++++++-----
include/linux/checkpoint_hdr.h | 10 ++++
2 files changed, 98 insertions(+), 13 deletions(-)
diff --git a/fs/checkpoint.c b/fs/checkpoint.c
index e82f4f1..7773488 100644
--- a/fs/checkpoint.c
+++ b/fs/checkpoint.c
@@ -26,8 +26,19 @@
#include <linux/checkpoint.h>
#include <linux/eventpoll.h>
#include <linux/eventfd.h>
+#include <linux/smp_lock.h>
#include <net/sock.h>
+/*
+ * TODO: This code uses the BKL for consistency with other uses of
+ * 'for_each_lock()'. But since the BKL may be replaced with another
+ * lock in the future, use lock_flocks() macros instead. lock_flocks()
+ * are currently used in BKL-fix sand boxes and when those changes
+ * are merged, the following macros can be removed
+ */
+#define lock_flocks() lock_kernel()
+#define unlock_flocks() unlock_kernel()
+
/**************************************************************************
* Checkpoint
*/
@@ -256,8 +267,79 @@ static int checkpoint_file(struct ckpt_ctx *ctx, void *ptr)
return ret;
}
+static int checkpoint_one_file_lock(struct ckpt_ctx *ctx, struct file *file,
+ struct file_lock *lock)
+{
+ int rc;
+ struct ckpt_hdr_file_lock *h;
+
+ h = ckpt_hdr_get_type(ctx, sizeof(*h), CKPT_HDR_FILE_LOCK);
+ if (!h)
+ return -ENOMEM;
+
+ if (lock) {
+ h->fl_start = lock->fl_start;
+ h->fl_end = lock->fl_end;
+ h->fl_type = lock->fl_type;
+ h->fl_flags = lock->fl_flags;
+ } else {
+ /* Checkpoint a dummy lock as a marker */
+ h->fl_start = -1;
+ h->fl_flags = FL_POSIX;
+ }
+
+ rc = ckpt_write_obj(ctx, &h->h);
+
+ ckpt_hdr_put(ctx, h);
+
+ return rc;
+}
+
+int
+checkpoint_file_locks(struct ckpt_ctx *ctx, struct files_struct *files,
+ struct file *file)
+{
+ int rc;
+ struct inode *inode;
+ struct file_lock **lockpp;
+ struct file_lock *lockp;
+
+ lock_flocks();
+ inode = file->f_path.dentry->d_inode;
+ for_each_lock(inode, lockpp) {
+ lockp = *lockpp;
+ ckpt_debug("Lock [%lld, %lld, %d, 0x%x]\n", lockp->fl_start,
+ lockp->fl_end, lockp->fl_type, lockp->fl_flags);
+
+ if (lockp->fl_owner != files)
+ continue;
+
+ rc = -EBADF;
+ if (IS_POSIX(lockp))
+ rc = checkpoint_one_file_lock(ctx, file, lockp);
+
+ if (rc < 0) {
+ ckpt_err(ctx, rc, "%(T), checkpoint of lock "
+ "[%lld, %lld, %d, 0x%x] failed\n",
+ lockp->fl_start, lockp->fl_end,
+ lockp->fl_type, lockp->fl_flags);
+ goto out;
+ }
+ }
+
+ /*
+ * At the end of file-locks for this file, checkpoint a marker.
+ */
+ rc = checkpoint_one_file_lock(ctx, file, NULL);
+ if (rc < 0)
+ ckpt_err(ctx, rc, "%(T), checkpoint marker-lock failed\n");
+out:
+ unlock_flocks();
+ return rc;
+}
+
/**
- * ckpt_write_file_desc - dump the state of a given file descriptor
+ * checkpoint_file_desc - dump the state of a given file descriptor
* @ctx: checkpoint context
* @files: files_struct pointer
* @fd: file descriptor
@@ -288,18 +370,6 @@ static int checkpoint_file_desc(struct ckpt_ctx *ctx,
}
rcu_read_unlock();
- ret = find_locks_with_owner(file, files);
- /*
- * find_locks_with_owner() returns an error when there
- * are no locks found, so we *want* it to return an error
- * code. Its success means we have to fail the checkpoint.
- */
- if (!ret) {
- ret = -EBADF;
- ckpt_err(ctx, ret, "%(T)fd %d has file lock or lease\n", fd);
- goto out;
- }
-
/* sanity check (although this shouldn't happen) */
ret = -EBADF;
if (!file) {
@@ -323,6 +393,11 @@ static int checkpoint_file_desc(struct ckpt_ctx *ctx,
h->fd_close_on_exec = coe;
ret = ckpt_write_obj(ctx, &h->h);
+ if (ret < 0)
+ goto out;
+
+ ret = checkpoint_file_locks(ctx, files, file);
+
out:
ckpt_hdr_put(ctx, h);
if (file)
diff --git a/include/linux/checkpoint_hdr.h b/include/linux/checkpoint_hdr.h
index 44e2a0d..4509016 100644
--- a/include/linux/checkpoint_hdr.h
+++ b/include/linux/checkpoint_hdr.h
@@ -144,6 +144,8 @@ enum {
#define CKPT_HDR_TTY_LDISC CKPT_HDR_TTY_LDISC
CKPT_HDR_EPOLL_ITEMS, /* must be after file-table */
#define CKPT_HDR_EPOLL_ITEMS CKPT_HDR_EPOLL_ITEMS
+ CKPT_HDR_FILE_LOCK,
+#define CKPT_HDR_FILE_LOCK CKPT_HDR_FILE_LOCK
CKPT_HDR_MM = 401,
#define CKPT_HDR_MM CKPT_HDR_MM
@@ -581,6 +583,14 @@ struct ckpt_hdr_file_generic {
struct ckpt_hdr_file common;
} __attribute__((aligned(8)));
+struct ckpt_hdr_file_lock {
+ struct ckpt_hdr h;
+ __s64 fl_start;
+ __s64 fl_end;
+ __u8 fl_type;
+ __u8 fl_flags;
+};
+
struct ckpt_hdr_file_pipe {
struct ckpt_hdr_file common;
__s32 pipe_objref;
--
1.6.0.4
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
