From 4373ea84c84d8a96e99d3da99e813d3e36d1bd11 Mon Sep 17 00:00:00 2001 From: Wendy Cheng Date: Thu, 17 Jan 2008 11:10:12 -0500 Subject: lockd: unlock lockd locks associated with a given server ip For high-availability NFS service, we generally need to be able to drop file locks held on the exported filesystem before moving clients to a new server. Currently the only way to do that is by shutting down lockd entirely, which is often undesireable (for example, if you want to continue exporting other filesystems). This patch allows the administrator to release all locks held by clients accessing the client through a given server ip address, by echoing that address to a new file, /proc/fs/nfsd/unlock_ip, as in: shell> echo 10.1.1.2 > /proc/fs/nfsd/unlock_ip The expected sequence of events can be: 1. Tear down the IP address 2. Unexport the path 3. Write IP to /proc/fs/nfsd/unlock_ip to unlock files 4. Signal peer to begin take-over. For now we only support IPv4 addresses and NFSv2/v3 (NFSv4 locks are not affected). Also, if unmounting the filesystem is required, we assume at step 3 that clients using the given server ip are the only clients holding locks on the given filesystem; otherwise, an additional patch is required to allow revoking all locks held by lockd on a given filesystem. Signed-off-by: S. Wendy Cheng Cc: Lon Hohberger Cc: Christoph Hellwig Signed-off-by: J. Bruce Fields fs/lockd/svcsubs.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/nfsd/nfsctl.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockd/lockd.h | 7 ++++ 3 files changed, 131 insertions(+), 7 deletions(-) --- fs/nfsd/nfsctl.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'fs/nfsd') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 613bcb8171a..7706f6c9ab8 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -35,6 +36,7 @@ #include #include #include +#include #include #include @@ -53,6 +55,7 @@ enum { NFSD_Getfs, NFSD_List, NFSD_Fh, + NFSD_FO_UnlockIP, NFSD_Threads, NFSD_Pool_Threads, NFSD_Versions, @@ -89,6 +92,8 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size); 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 (*write_op[])(struct file *, char *, size_t) = { [NFSD_Svc] = write_svc, [NFSD_Add] = write_add, @@ -98,6 +103,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = { [NFSD_Getfd] = write_getfd, [NFSD_Getfs] = write_getfs, [NFSD_Fh] = write_filehandle, + [NFSD_FO_UnlockIP] = failover_unlock_ip, [NFSD_Threads] = write_threads, [NFSD_Pool_Threads] = write_pool_threads, [NFSD_Versions] = write_versions, @@ -298,6 +304,31 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) return err; } +static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size) +{ + __be32 server_ip; + char *fo_path, c; + int b1, b2, b3, b4; + + /* 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; + + /* get ipv4 address */ + if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4) + return -EINVAL; + server_ip = htonl((((((b1<<8)|b2)<<8)|b3)<<8)|b4); + + return nlmsvc_unlock_all_by_ip(server_ip); +} + static ssize_t write_filehandle(struct file *file, char *buf, size_t size) { /* request is: @@ -700,6 +731,8 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_List] = {"exports", &exports_operations, S_IRUGO}, + [NFSD_FO_UnlockIP] = {"unlock_ip", + &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}, -- cgit v1.2.3 From 17efa372cfe4d189705edf6cd4fbe283827a5dc7 Mon Sep 17 00:00:00 2001 From: Wendy Cheng Date: Thu, 17 Jan 2008 11:10:12 -0500 Subject: 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 Cc: Lon Hohberger Cc: Christoph Hellwig Signed-off-by: J. Bruce Fields fs/lockd/svcsubs.c | 66 +++++++++++++++++++++++++++++++++++++++----- fs/nfsd/nfsctl.c | 65 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockd/lockd.h | 7 ++++ 3 files changed, 131 insertions(+), 7 deletions(-) --- fs/nfsd/nfsctl.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'fs/nfsd') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7706f6c9ab8..42f3820ee8f 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -56,6 +56,7 @@ enum { NFSD_List, NFSD_Fh, NFSD_FO_UnlockIP, + NFSD_FO_UnlockFS, NFSD_Threads, NFSD_Pool_Threads, NFSD_Versions, @@ -93,6 +94,7 @@ 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, @@ -104,6 +106,7 @@ 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, @@ -329,6 +332,33 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size) return nlmsvc_unlock_all_by_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_unlock_all_by_sb(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: @@ -733,6 +763,8 @@ 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}, -- cgit v1.2.3 From 1a747ee0cc11a198f9e2435add821bd0dfedb7c1 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 24 Apr 2008 10:08:22 -0400 Subject: locks: don't call ->copy_lock methods on return of conflicting locks The file_lock structure is used both as a heavy-weight representation of an active lock, with pointers to reference-counted structures, etc., and as a simple container for parameters that describe a file lock. The conflicting lock returned from __posix_lock_file is an example of the latter; so don't call the filesystem or lock manager callbacks when copying to it. This also saves the need for an unnecessary locks_init_lock in the nfsv4 server. Thanks to Trond for pointing out the error. Signed-off-by: J. Bruce Fields Cc: Trond Myklebust --- fs/nfsd/nfs4state.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/nfsd') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 55dfdd71f1b..8799b870818 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2712,9 +2712,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * Note: locks.c uses the BKL to protect the inode's lock list. */ - /* XXX?: Just to divert the locks_release_private at the start of - * locks_copy_lock: */ - locks_init_lock(&conflock); err = vfs_lock_file(filp, cmd, &file_lock, &conflock); switch (-err) { case 0: /* success! */ -- cgit v1.2.3 From e36cd4a2873c398ba188f16e4087cce7f00a1506 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 24 Apr 2008 16:59:30 -0400 Subject: nfsd: don't allow setting ctime over v4 Presumably this is left over from earlier drafts of v4, which listed TIME_METADATA as writeable. It's read-only in rfc 3530, and shouldn't be modifiable anyway. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'fs/nfsd') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1ba7ad98193..c513bbdf2d3 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -376,20 +376,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia goto xdr_error; } } - if (bmval[1] & FATTR4_WORD1_TIME_METADATA) { - /* We require the high 32 bits of 'seconds' to be 0, and we ignore - all 32 bits of 'nseconds'. */ - READ_BUF(12); - len += 12; - READ32(dummy32); - if (dummy32) - return nfserr_inval; - READ32(iattr->ia_ctime.tv_sec); - READ32(iattr->ia_ctime.tv_nsec); - if (iattr->ia_ctime.tv_nsec >= (u32)1000000000) - return nfserr_inval; - iattr->ia_valid |= ATTR_CTIME; - } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { READ_BUF(4); len += 4; -- cgit v1.2.3