Re: [PATCH] lockd: unlock lockd locks held for a certain filesystem

[Wendy Cheng <s.wendy.cheng@gmail.com>]

#if defined(BRUCE_CHECK_THIS_OUT)
error = nlmsvc_failover_path(nd.path.mnt->mnt_sb);
#else
error = nlmsvc_failover_path(nd.mnt->mnt_sb);
#endif

-- Wendy

---------- based on the following email ----------------------------

J. Bruce Fields wrote:
> On Wed, Apr 23, 2008 at 09:44:22AM +0200, Christoph Hellwig wrote:
>   
>> Please don't pass down the nameidata, but just the super_block.  That's
>> all we need in the lower layer functions.
>>     
>
> Yep, I agree that's nicer; here's the result.
>
> --b.
>
> commit 26a816586b71877d8a84fbb436373099384e328b
> Author: Wendy Cheng <wcheng@redhat.com>
> Date:   Thu Jan 17 11:10:12 2008 -0500
>
>     lockd: unlock lockd locks held for a certain filesystem
>     
>     Add /proc/fs/nfsd/unlock_filesystem, which allows e.g.:
>     
>     shell> echo /mnt/sfs1 > /proc/fs/nfsd/unlock_filesystem
>     
>     so that a filesystem can be unmounted before allowing a peer nfsd to
>     take over nfs service for the filesystem.
>     
>     Signed-off-by: S. Wendy Cheng <wcheng@redhat.com>
>     Cc: Lon Hohberger  <lhh@redhat.com>
>     Cc: Christoph Hellwig <hch@lst.de>
>     Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
>     
>      fs/lockd/svcsubs.c          |   66 +++++++++++++++++++++++++++++++++++++++-----
>      fs/nfsd/nfsctl.c            |   65 +++++++++++++++++++++++++++++++++++++++++++
>      include/linux/lockd/lockd.h |    7 ++++
>      3 files changed, 131 insertions(+), 7 deletions(-)
>
> diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
> index e12daba..dcdcff6 100644
> --- a/fs/lockd/svcsubs.c
> +++ b/fs/lockd/svcsubs.c
> @@ -196,6 +196,12 @@ again:
>  	return 0;
>  }
>  
> +static int
> +nlmsvc_always_match(void *dummy1, struct nlm_host *dummy2)
> +{
> +	return 1;
> +}
> +
>  /*
>   * Inspect a single file
>   */
> @@ -232,7 +238,8 @@ nlm_file_inuse(struct nlm_file *file)
>   * Loop over all files in the file table.
>   */
>  static int
> -nlm_traverse_files(void *data, nlm_host_match_fn_t match)
> +nlm_traverse_files(void *data, nlm_host_match_fn_t match,
> +		int (*is_failover_file)(void *data, struct nlm_file *file))
>  {
>  	struct hlist_node *pos, *next;
>  	struct nlm_file	*file;
> @@ -241,6 +248,8 @@ nlm_traverse_files(void *data, nlm_host_match_fn_t match)
>  	mutex_lock(&nlm_file_mutex);
>  	for (i = 0; i < FILE_NRHASH; i++) {
>  		hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) {
> +			if (is_failover_file && !is_failover_file(data, file))
> +				continue;
>  			file->f_count++;
>  			mutex_unlock(&nlm_file_mutex);
>  
> @@ -345,7 +354,7 @@ void
>  nlmsvc_mark_resources(void)
>  {
>  	dprintk("lockd: nlmsvc_mark_resources\n");
> -	nlm_traverse_files(NULL, nlmsvc_mark_host);
> +	nlm_traverse_files(NULL, nlmsvc_mark_host, NULL);
>  }
>  
>  /*
> @@ -356,7 +365,7 @@ nlmsvc_free_host_resources(struct nlm_host *host)
>  {
>  	dprintk("lockd: nlmsvc_free_host_resources\n");
>  
> -	if (nlm_traverse_files(host, nlmsvc_same_host)) {
> +	if (nlm_traverse_files(host, nlmsvc_same_host, NULL)) {
>  		printk(KERN_WARNING
>  			"lockd: couldn't remove all locks held by %s\n",
>  			host->h_name);
> @@ -376,8 +385,27 @@ nlmsvc_invalidate_all(void)
>  	 * turn, which is about as inefficient as it gets.
>  	 * Now we just do it once in nlm_traverse_files.
>  	 */
> -	nlm_traverse_files(NULL, nlmsvc_is_client);
> +	nlm_traverse_files(NULL, nlmsvc_is_client, NULL);
> +}
> +
> +static int
> +nlmsvc_failover_file_ok_path(void *datap, struct nlm_file *file)
> +{
> +	struct super_block *sb = datap;
> +
> +	return sb == file->f_file->f_path.mnt->mnt_sb;
> +}
> +
> +int
> +nlmsvc_failover_path(struct super_block *sb)
> +{
> +	int ret;
> +
> +	ret = nlm_traverse_files(sb, nlmsvc_always_match,
> +				 nlmsvc_failover_file_ok_path);
> +	return ret ? -EIO : 0;
>  }
> +EXPORT_SYMBOL_GPL(nlmsvc_failover_path);
>  
>  static int
>  nlmsvc_failover_file_ok_ip(void *datap, struct nlm_host *host)
> @@ -391,7 +419,8 @@ int
>  nlmsvc_failover_ip(__be32 server_addr)
>  {
>  	int ret;
> -	ret = nlm_traverse_files(&server_addr, nlmsvc_failover_file_ok_ip);
> +	ret = nlm_traverse_files(&server_addr, nlmsvc_failover_file_ok_ip,
> +						NULL);
>  	return ret ? -EIO : 0;
>  
>  }
> diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
> index 02c3949..b4ca5c9 100644
> --- a/fs/nfsd/nfsctl.c
> +++ b/fs/nfsd/nfsctl.c
> @@ -55,6 +55,7 @@ enum {
>  	NFSD_List,
>  	NFSD_Fh,
>  	NFSD_FO_UnlockIP,
> +	NFSD_FO_UnlockFS,
>  	NFSD_Threads,
>  	NFSD_Pool_Threads,
>  	NFSD_Versions,
> @@ -92,6 +93,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
>  #endif
>  
>  static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size);
> +static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size);
>  
>  static ssize_t (*write_op[])(struct file *, char *, size_t) = {
>  	[NFSD_Svc] = write_svc,
> @@ -103,6 +105,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
>  	[NFSD_Getfs] = write_getfs,
>  	[NFSD_Fh] = write_filehandle,
>  	[NFSD_FO_UnlockIP] = failover_unlock_ip,
> +	[NFSD_FO_UnlockFS] = failover_unlock_fs,
>  	[NFSD_Threads] = write_threads,
>  	[NFSD_Pool_Threads] = write_pool_threads,
>  	[NFSD_Versions] = write_versions,
> @@ -319,6 +322,33 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
>  	return nlmsvc_failover_ip(server_ip);
>  }
>  
> +static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size)
> +{
> +	struct nameidata nd;
> +	char *fo_path;
> +	int error;
> +
> +	/* sanity check */
> +	if (size == 0)
> +		return -EINVAL;
> +
> +	if (buf[size-1] != '\n')
> +		return -EINVAL;
> +
> +	fo_path = buf;
> +	if (qword_get(&buf, fo_path, size) < 0)
> +		return -EINVAL;
> +
> +	error = path_lookup(fo_path, 0, &nd);
> +	if (error)
> +		return error;
> +
> +	error = nlmsvc_failover_path(nd.path.mnt->mnt_sb);
> +
> +	path_put(&nd.path);
> +	return error;
> +}
> +
>  static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
>  {
>  	/* request is:
> @@ -729,6 +759,8 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
>  		[NFSD_List] = {"exports", &exports_operations, S_IRUGO},
>  		[NFSD_FO_UnlockIP] = {"unlock_ip",
>  					&transaction_ops, S_IWUSR|S_IRUSR},
> +		[NFSD_FO_UnlockFS] = {"unlock_filesystem",
> +					&transaction_ops, S_IWUSR|S_IRUSR},
>  		[NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR},
>  		[NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
>  		[NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
> diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
> index f06d2db..7cd9c8e 100644
> --- a/include/linux/lockd/lockd.h
> +++ b/include/linux/lockd/lockd.h
> @@ -220,6 +220,7 @@ void		  nlmsvc_invalidate_all(void);
>  /*
>   * Cluster failover support
>   */
> +int           nlmsvc_failover_path(struct super_block *sb);
>  int           nlmsvc_failover_ip(__be32 server_addr);
>  
>  static __inline__ struct inode *
>