From dd8ac1da4190139de70da18823ff8f5992a649ae Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 01/87] nfs: Keep index within mnt_errtbl[] Ensure that index i remains within array mnt_errtbl[] and mnt3_errtbl[]. Signed-off-by: Roel Kluin Signed-off-by: Trond Myklebust --- fs/nfs/mount_clnt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 38ef9eaec407..8b9affc8bab2 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -258,7 +258,7 @@ static int decode_status(struct xdr_stream *xdr, struct mountres *res) return -EIO; status = ntohl(*p); - for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) { + for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) { if (mnt_errtbl[i].status == status) { res->errno = mnt_errtbl[i].errno; return 0; @@ -309,7 +309,7 @@ static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res) return -EIO; status = ntohl(*p); - for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) { + for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) { if (mnt3_errtbl[i].status == status) { res->errno = mnt3_errtbl[i].errno; return 0; From a78cb57a106fceeba26da2907db9d8886700e1dc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 02/87] NFSv4: Don't loop forever on state recovery failure... If the server is broken, then retrying forever won't fix it. We should just give up after a while, and return an error to the user. We set the number of retries to 10 for now... Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6917311f201c..d95f7f9e60c4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -61,6 +61,8 @@ #define NFS4_POLL_RETRY_MIN (HZ/10) #define NFS4_POLL_RETRY_MAX (15*HZ) +#define NFS4_MAX_LOOP_ON_RECOVER (10) + struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); @@ -426,17 +428,19 @@ out: static int nfs4_recover_session(struct nfs4_session *session) { struct nfs_client *clp = session->clp; + unsigned int loop; int ret; - for (;;) { + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { ret = nfs4_wait_clnt_recover(clp); if (ret != 0) - return ret; + break; if (!test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) break; nfs4_schedule_state_manager(clp); + ret = -EIO; } - return 0; + return ret; } static int nfs41_setup_sequence(struct nfs4_session *session, @@ -1444,18 +1448,20 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) static int nfs4_recover_expired_lease(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; + unsigned int loop; int ret; - for (;;) { + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { ret = nfs4_wait_clnt_recover(clp); if (ret != 0) - return ret; + break; if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) && !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state)) break; nfs4_schedule_state_recovery(clp); + ret = -EIO; } - return 0; + return ret; } /* From 62ab460cf5e450e1d207a98a9c6cf2e4a6a78fd1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 03/87] NFSv4: Add 'server capability' flags for NFSv4 recommended attributes If the NFSv4 server doesn't support a POSIX attribute, the generic NFS code needs to know that, so that it don't keep trying to poll for it. However, by the same count, if the NFSv4 server does support that attribute, then we should ensure that the inode metadata is appropriately labelled as being untrusted. For instance, if we don't know the correct value of the file's uid, we should certainly not be caching ACLs or ACCESS results. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 7 ++- fs/nfs/inode.c | 92 +++++++++++++++++++++++++++++++++------ fs/nfs/nfs4proc.c | 22 ++++++++++ include/linux/nfs_fs_sb.h | 9 ++++ 4 files changed, 114 insertions(+), 16 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8d25ccb2d51d..8f34fd8028fc 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -809,6 +809,9 @@ static int nfs_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; server->options = data->options; + server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); @@ -1274,7 +1277,7 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; - server->caps |= NFS_CAP_ATOMIC_OPEN; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; server->options = data->options; /* Get a client record */ @@ -1400,7 +1403,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, /* Initialise the client representation from the parent server */ nfs_server_copy_userdata(server, parent_server); - server->caps |= NFS_CAP_ATOMIC_OPEN; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; /* Get a client representation. * Note: NFSv4 always uses TCP, */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bd7938eda6a8..fe5a8b45d867 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -286,6 +286,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; + if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 + && nfs_server_capable(inode, NFS_CAP_MODE)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ @@ -330,20 +335,46 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; + else if (nfs_server_capable(inode, NFS_CAP_ATIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; + else if (nfs_server_capable(inode, NFS_CAP_MTIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; + else if (nfs_server_capable(inode, NFS_CAP_CTIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_CHANGE) nfsi->change_attr = fattr->change_attr; + else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA; if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); + else + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_REVAL_PAGECACHE; if (fattr->valid & NFS_ATTR_FATTR_NLINK) inode->i_nlink = fattr->nlink; + else if (nfs_server_capable(inode, NFS_CAP_NLINK)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { @@ -1145,6 +1176,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) loff_t cur_isize, new_isize; unsigned long invalid = 0; unsigned long now = jiffies; + unsigned long save_cache_validity; dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1171,10 +1203,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) */ nfsi->read_cache_jiffies = fattr->time_start; - if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME))) - nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ATIME - | NFS_INO_REVAL_PAGECACHE); + save_cache_validity = nfsi->cache_validity; + nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED + | NFS_INO_REVAL_PAGECACHE); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -1189,7 +1222,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); nfsi->change_attr = fattr->change_attr; } - } + } else if (server->caps & NFS_CAP_CHANGE_ATTR) + invalid |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { /* NFSv2/v3: Check if the mtime agrees */ @@ -1201,7 +1235,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } - } + } else if (server->caps & NFS_CAP_MTIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_CTIME) { /* If ctime has changed we should definitely clear access+acl caches */ if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) { @@ -1215,7 +1254,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); } - } + } else if (server->caps & NFS_CAP_CTIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1231,30 +1274,50 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) dprintk("NFS: isize change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } - } + } else + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); + else if (server->caps & NFS_CAP_ATIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_mode = fattr->mode; } - } + } else if (server->caps & NFS_CAP_MODE) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (inode->i_uid != fattr->uid) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } + } else if (server->caps & NFS_CAP_OWNER) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (inode->i_gid != fattr->gid) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } + } else if (server->caps & NFS_CAP_OWNER_GROUP) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1263,7 +1326,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; inode->i_nlink = fattr->nlink; } - } + } else if (server->caps & NFS_CAP_NLINK) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* @@ -1293,9 +1358,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; if (!nfs_have_delegation(inode, FMODE_READ) || - (nfsi->cache_validity & NFS_INO_REVAL_FORCED)) + (save_cache_validity & NFS_INO_REVAL_FORCED)) nfsi->cache_validity |= invalid; - nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED; return 0; out_changed: diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d95f7f9e60c4..be6544aef41f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2003,12 +2003,34 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f status = nfs4_call_sync(server, &msg, &args, &res, 0); if (status == 0) { memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); + server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS| + NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER| + NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME| + NFS_CAP_CTIME|NFS_CAP_MTIME); if (res.attr_bitmask[0] & FATTR4_WORD0_ACL) server->caps |= NFS_CAP_ACLS; if (res.has_links != 0) server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID) + server->caps |= NFS_CAP_FILEID; + if (res.attr_bitmask[1] & FATTR4_WORD1_MODE) + server->caps |= NFS_CAP_MODE; + if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS) + server->caps |= NFS_CAP_NLINK; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER) + server->caps |= NFS_CAP_OWNER; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP) + server->caps |= NFS_CAP_OWNER_GROUP; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS) + server->caps |= NFS_CAP_ATIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA) + server->caps |= NFS_CAP_CTIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY) + server->caps |= NFS_CAP_MTIME; + memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 19fe15d12042..320569eabe3b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -167,6 +167,15 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) +#define NFS_CAP_CHANGE_ATTR (1U << 5) +#define NFS_CAP_FILEID (1U << 6) +#define NFS_CAP_MODE (1U << 7) +#define NFS_CAP_NLINK (1U << 8) +#define NFS_CAP_OWNER (1U << 9) +#define NFS_CAP_OWNER_GROUP (1U << 10) +#define NFS_CAP_ATIME (1U << 11) +#define NFS_CAP_CTIME (1U << 12) +#define NFS_CAP_MTIME (1U << 13) /* maximum number of slots to use */ From 80e52aced138bb41b045a8595a87510f27d8d8c5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 04/87] NFSv4: Don't do idmapper upcalls for asynchronous RPC calls We don't want to cause rpciod to hang... Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 86 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 58 insertions(+), 28 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 617273e7d47f..e65cc2e650c8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3075,7 +3075,8 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t return ret; } -static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid) +static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_client *clp, uint32_t *uid, int may_sleep) { uint32_t len; __be32 *p; @@ -3088,7 +3089,9 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf READ_BUF(4); READ32(len); READ_BUF(len); - if (len < XDR_MAX_NETOBJ) { + if (!may_sleep) { + /* do nothing */ + } else if (len < XDR_MAX_NETOBJ) { if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0) ret = NFS_ATTR_FATTR_OWNER; else @@ -3103,7 +3106,8 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf return ret; } -static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid) +static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_client *clp, uint32_t *gid, int may_sleep) { uint32_t len; __be32 *p; @@ -3116,7 +3120,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf READ_BUF(4); READ32(len); READ_BUF(len); - if (len < XDR_MAX_NETOBJ) { + if (!may_sleep) { + /* do nothing */ + } else if (len < XDR_MAX_NETOBJ) { if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0) ret = NFS_ATTR_FATTR_GROUP; else @@ -3466,7 +3472,8 @@ xdr_error: return status; } -static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, const struct nfs_server *server) +static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + const struct nfs_server *server, int may_sleep) { __be32 *savep; uint32_t attrlen, @@ -3538,12 +3545,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons goto xdr_error; fattr->valid |= status; - status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid); + status = decode_attr_owner(xdr, bitmap, server->nfs_client, + &fattr->uid, may_sleep); if (status < 0) goto xdr_error; fattr->valid |= status; - status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid); + status = decode_attr_group(xdr, bitmap, server->nfs_client, + &fattr->gid, may_sleep); if (status < 0) goto xdr_error; fattr->valid |= status; @@ -4370,7 +4379,8 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, __be32 *p, struct status = decode_open_downgrade(&xdr, res); if (status != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4397,7 +4407,8 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_ac status = decode_access(&xdr, res); if (status != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4424,7 +4435,8 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_lo goto out; if ((status = decode_getfh(&xdr, res->fh)) != 0) goto out; - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server + ,!RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4448,7 +4460,8 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, __be32 *p, struct nf if ((status = decode_putrootfh(&xdr)) != 0) goto out; if ((status = decode_getfh(&xdr, res->fh)) == 0) - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4473,7 +4486,8 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, __be32 *p, struct nfs_rem goto out; if ((status = decode_remove(&xdr, &res->cinfo)) != 0) goto out; - decode_getfattr(&xdr, &res->dir_attr, res->server); + decode_getfattr(&xdr, &res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4503,11 +4517,13 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_re if ((status = decode_rename(&xdr, &res->old_cinfo, &res->new_cinfo)) != 0) goto out; /* Current FH is target directory */ - if (decode_getfattr(&xdr, res->new_fattr, res->server) != 0) + if (decode_getfattr(&xdr, res->new_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->old_fattr, res->server); + decode_getfattr(&xdr, res->old_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4540,11 +4556,13 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_link * Note order: OP_LINK leaves the directory as the current * filehandle. */ - if (decode_getfattr(&xdr, res->dir_attr, res->server) != 0) + if (decode_getfattr(&xdr, res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4573,11 +4591,13 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_cr goto out; if ((status = decode_getfh(&xdr, res->fh)) != 0) goto out; - if (decode_getfattr(&xdr, res->fattr, res->server) != 0) + if (decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->dir_fattr, res->server); + decode_getfattr(&xdr, res->dir_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4609,7 +4629,8 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_g status = decode_putfh(&xdr); if (status) goto out; - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4716,7 +4737,8 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, __be32 *p, struct nfs_clos * an ESTALE error. Shouldn't be a problem, * though, since fattr->valid will remain unset. */ - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4748,11 +4770,13 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, __be32 *p, struct nfs_openr goto out; if (decode_getfh(&xdr, &res->fh) != 0) goto out; - if (decode_getfattr(&xdr, res->f_attr, res->server) != 0) + if (decode_getfattr(&xdr, res->f_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if (decode_restorefh(&xdr) != 0) goto out; - decode_getfattr(&xdr, res->dir_attr, res->server); + decode_getfattr(&xdr, res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4800,7 +4824,8 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, __be32 *p, struct nf status = decode_open(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->f_attr, res->server); + decode_getfattr(&xdr, res->f_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4827,7 +4852,8 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_se status = decode_setattr(&xdr); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5001,7 +5027,8 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, __be32 *p, struct nfs_writ status = decode_write(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); if (!status) status = res->count; out: @@ -5030,7 +5057,8 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, __be32 *p, struct nfs_wri status = decode_commit(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5194,7 +5222,8 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, __be32 *p, struct nf if (status != 0) goto out; status = decode_delegreturn(&xdr); - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5222,7 +5251,8 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p, goto out; xdr_enter_page(&xdr, PAGE_SIZE); status = decode_getfattr(&xdr, &res->fs_locations->fattr, - res->fs_locations->server); + res->fs_locations->server, + !RPC_IS_ASYNC(req->rq_task)); out: return status; } From cbf1107126af2950623fafdaa5c9df43ab00f046 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 05/87] SUNRPC: convert some sysctls into module parameters Parameters like the minimum reserved port, and the number of slot entries should really be module parameters rather than sysctls. Signed-off-by: Trond Myklebust --- Documentation/kernel-parameters.txt | 21 ++++++++++++ net/sunrpc/xprtsock.c | 52 +++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index dd1a6d4bb747..2f1820683b69 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2391,6 +2391,18 @@ and is between 256 and 4096 characters. It is defined in the file stifb= [HW] Format: bpp:[:[:...]] + sunrpc.min_resvport= + sunrpc.max_resvport= + [NFS,SUNRPC] + SunRPC servers often require that client requests + originate from a privileged port (i.e. a port in the + range 0 < portnr < 1024). + An administrator who wishes to reserve some of these + ports for other uses may adjust the range that the + kernel's sunrpc client considers to be privileged + using these two parameters to set the minimum and + maximum port values. + sunrpc.pool_mode= [NFS] Control how the NFS server code allocates CPUs to @@ -2407,6 +2419,15 @@ and is between 256 and 4096 characters. It is defined in the file pernode one pool for each NUMA node (equivalent to global on non-NUMA machines) + sunrpc.tcp_slot_table_entries= + sunrpc.udp_slot_table_entries= + [NFS,SUNRPC] + Sets the upper limit on the number of simultaneous + RPC calls that can be sent from the client to a + server. Increasing these values may allow you to + improve throughput, but will also increase the + amount of memory reserved for use by the client. + swiotlb= [IA-64] Number of I/O TLB slabs switches= [HW,M68k] diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 83c73c4d017a..585a864c1c4c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2412,3 +2412,55 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); } + +static int param_set_uint_minmax(const char *val, struct kernel_param *kp, + unsigned int min, unsigned int max) +{ + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num < min || num > max) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} + +static int param_set_portnr(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_RESVPORT, + RPC_MAX_RESVPORT); +} + +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(min_resvport, xprt_min_resvport, portnr, 0644); +module_param_named(max_resvport, xprt_max_resvport, portnr, 0644); + +static int param_set_slot_table_size(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE); +} + +static int param_get_slot_table_size(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, + slot_table_size, 0644); +module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, + slot_table_size, 0644); + From c140aa91357c415c91269884518fa1d6fdebc20d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:06:19 -0400 Subject: [PATCH 06/87] NFSv4: Clean up the nfs.callback_tcpport option Tighten up the validity checking in param_set_port: check for NULL pointers. Ensure that the option shows up on 'modinfo' output. Signed-off-by: Trond Myklebust --- fs/nfs/callback.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 7f604c7941fb..293fa0528a6e 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -43,21 +43,29 @@ static struct svc_program nfs4_callback_program; unsigned int nfs_callback_set_tcpport; unsigned short nfs_callback_tcpport; unsigned short nfs_callback_tcpport6; -static const int nfs_set_port_min = 0; -static const int nfs_set_port_max = 65535; +#define NFS_CALLBACK_MAXPORTNR (65535U) -static int param_set_port(const char *val, struct kernel_param *kp) +static int param_set_portnr(const char *val, struct kernel_param *kp) { - char *endp; - int num = simple_strtol(val, &endp, 0); - if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max) + unsigned long num; + int ret; + + if (!val) return -EINVAL; - *((int *)kp->arg) = num; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR) + return -EINVAL; + *((unsigned int *)kp->arg) = num; return 0; } -module_param_call(callback_tcpport, param_set_port, param_get_int, - &nfs_callback_set_tcpport, 0644); +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) __param_check(name, p, unsigned int); + +module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); /* * This is the NFSv4 callback kernel thread. From f3f4f4ed26b116f621596f74d42d2b736171e968 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:29 -0400 Subject: [PATCH 07/87] NFS: Fix up new minorversion= option The new minorversion= mount option (commit 3fd5be9e) was merged at the same time as the recent sloppy parser fixes (commit a5a16bae), so minorversion= still uses the old value parsing logic. If the minorversion= option specifies a bogus value, it should fail with "bad value" not "bad option." Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0b4cbdc60abd..83a31070bc1a 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -158,7 +158,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_mountvers, "mountvers=%s" }, { Opt_nfsvers, "nfsvers=%s" }, { Opt_nfsvers, "vers=%s" }, - { Opt_minorversion, "minorversion=%u" }, + { Opt_minorversion, "minorversion=%s" }, { Opt_sec, "sec=%s" }, { Opt_proto, "proto=%s" }, @@ -1001,7 +1001,6 @@ static int nfs_parse_mount_options(char *raw, while ((p = strsep(&raw, ",")) != NULL) { substring_t args[MAX_OPT_ARGS]; unsigned long option; - int int_option; int token; if (!*p) @@ -1273,11 +1272,16 @@ static int nfs_parse_mount_options(char *raw, } break; case Opt_minorversion: - if (match_int(args, &int_option)) - return 0; - if (int_option < 0 || int_option > NFS4_MAX_MINOR_VERSION) - return 0; - mnt->minorversion = int_option; + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = strict_strtoul(string, 10, &option); + kfree(string); + if (rc != 0) + goto out_invalid_value; + if (option > NFS4_MAX_MINOR_VERSION) + goto out_invalid_value; + mnt->minorversion = option; break; /* From 0b524123c93893391ec9e6c9b04998a45235f9c8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:30 -0400 Subject: [PATCH 08/87] NFS: Add ability to send MOUNTPROC_UMNT to the kernel's mountd client After certain failure modes of an NFS mount, an NFS client should send a MOUNTPROC_UMNT request to remove the just-added mount entry from the server's mount table. While no-one should rely on the accuracy of the server's mount table, sending a UMNT is simply being a good internet neighbor. Since NFS mount processing is handled in the kernel now, we will need a function in the kernel's mountd client that can post a MOUNTRPC_UMNT request, in order to handle these failure modes. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 1 + fs/nfs/mount_clnt.c | 79 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7dd90a6769d0..8d2b71d57d29 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -102,6 +102,7 @@ struct nfs_mount_request { }; extern int nfs_mount(struct nfs_mount_request *info); +extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern struct rpc_program nfs_program; diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 38ef9eaec407..72dd8b6ccafa 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -209,6 +209,71 @@ out_mnt_err: goto out; } +/** + * nfs_umount - Notify a server that we have unmounted this export + * @info: pointer to umount request arguments + * + * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always + * use UDP. + */ +void nfs_umount(const struct nfs_mount_request *info) +{ + static const struct rpc_timeout nfs_umnt_timeout = { + .to_initval = 1 * HZ, + .to_maxval = 3 * HZ, + .to_retries = 2, + }; + struct rpc_create_args args = { + .protocol = IPPROTO_UDP, + .address = info->sap, + .addrsize = info->salen, + .timeout = &nfs_umnt_timeout, + .servername = info->hostname, + .program = &mnt_program, + .version = info->version, + .authflavor = RPC_AUTH_UNIX, + .flags = RPC_CLNT_CREATE_NOPING, + }; + struct mountres result; + struct rpc_message msg = { + .rpc_argp = info->dirpath, + .rpc_resp = &result, + }; + struct rpc_clnt *clnt; + int status; + + if (info->noresvport) + args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + + clnt = rpc_create(&args); + if (unlikely(IS_ERR(clnt))) + goto out_clnt_err; + + dprintk("NFS: sending UMNT request for %s:%s\n", + (info->hostname ? info->hostname : "server"), info->dirpath); + + if (info->version == NFS_MNT3_VERSION) + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT]; + else + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT]; + + status = rpc_call_sync(clnt, &msg, 0); + rpc_shutdown_client(clnt); + + if (unlikely(status < 0)) + goto out_call_err; + + return; + +out_clnt_err: + dprintk("NFS: failed to create UMNT RPC client, status=%ld\n", + PTR_ERR(clnt)); + return; + +out_call_err: + dprintk("NFS: UMNT request failed, status=%d\n", status); +} + /* * XDR encode/decode functions for MOUNT */ @@ -407,6 +472,13 @@ static struct rpc_procinfo mnt_procedures[] = { .p_statidx = MOUNTPROC_MNT, .p_name = "MOUNT", }, + [MOUNTPROC_UMNT] = { + .p_proc = MOUNTPROC_UMNT, + .p_encode = (kxdrproc_t)mnt_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC_UMNT, + .p_name = "UMOUNT", + }, }; static struct rpc_procinfo mnt3_procedures[] = { @@ -419,6 +491,13 @@ static struct rpc_procinfo mnt3_procedures[] = { .p_statidx = MOUNTPROC3_MNT, .p_name = "MOUNT", }, + [MOUNTPROC3_UMNT] = { + .p_proc = MOUNTPROC3_UMNT, + .p_encode = (kxdrproc_t)mnt_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC3_UMNT, + .p_name = "UMOUNT", + }, }; From 059f90b323c0f5d34656ab7e0548d7d033c2a51a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:31 -0400 Subject: [PATCH 09/87] NFS: Fix auth flavor len accounting Previous logic in the NFS mount parsing code path assumed auth_flavor_len was set to zero for simple authentication flavors (like AUTH_UNIX), and 1 for compound flavors (like AUTH_GSS). At some earlier point (maybe even before the option parsers were merged?) specific checks for auth_flavor_len being zero were removed from the functions that validate the mount option that sets the mount point's authentication flavor. Since we are populating an array for authentication flavors, the auth_flavor_len should always be set to the number of flavors. Let's eliminate some cleverness here, and prepare for new logic that needs to know the number of flavors in the auth_flavors[] array. (auth_flavors[] is an array because at some point we want to allow a list of acceptable authentication flavors to be specified via the sec= mount option. For now it remains a single element array). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 83a31070bc1a..a33e608713e9 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -904,8 +904,6 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) /* * Parse the value of the 'sec=' option. - * - * The flavor_len setting is for v4 mounts. */ static int nfs_parse_security_flavors(char *value, struct nfs_parsed_mount_data *mnt) @@ -916,53 +914,43 @@ static int nfs_parse_security_flavors(char *value, switch (match_token(value, nfs_secflavor_tokens, args)) { case Opt_sec_none: - mnt->auth_flavor_len = 0; mnt->auth_flavors[0] = RPC_AUTH_NULL; break; case Opt_sec_sys: - mnt->auth_flavor_len = 0; mnt->auth_flavors[0] = RPC_AUTH_UNIX; break; case Opt_sec_krb5: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5; break; case Opt_sec_krb5i: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I; break; case Opt_sec_krb5p: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P; break; case Opt_sec_lkey: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY; break; case Opt_sec_lkeyi: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI; break; case Opt_sec_lkeyp: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP; break; case Opt_sec_spkm: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM; break; case Opt_sec_spkmi: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI; break; case Opt_sec_spkmp: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP; break; default: return 0; } + mnt->auth_flavor_len = 1; return 1; } @@ -1680,6 +1668,7 @@ static int nfs_validate_mount_data(void *options, args->nfs_server.port = 0; /* autobind unless user sets port */ args->nfs_server.protocol = XPRT_TRANSPORT_TCP; args->auth_flavors[0] = RPC_AUTH_UNIX; + args->auth_flavor_len = 1; switch (data->version) { case 1: @@ -2343,7 +2332,7 @@ static int nfs4_validate_mount_data(void *options, args->acdirmax = NFS_DEF_ACDIRMAX; args->nfs_server.port = NFS_PORT; /* 2049 unless user set port= */ args->auth_flavors[0] = RPC_AUTH_UNIX; - args->auth_flavor_len = 0; + args->auth_flavor_len = 1; args->minorversion = 0; switch (data->version) { From ec88f28d1eb77346f19ca324ceec76e645cdd9da Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:32 -0400 Subject: [PATCH 10/87] NFS: Use the authentication flavor list returned by mountd Commit a14017db added support in the kernel's NFS mount client to decode the authentication flavor list returned by mountd. The NFS client can now use this list to determine whether the authentication flavor requested by the user is actually supported by the server. Note we don't actually negotiate the security flavor if none was specified by the user. Instead, we try to use AUTH_SYS, and fail if the server does not support it. This prevents us from negotiating an inappropriate security flavor (some servers list AUTH_NULL first). If the server does not support AUTH_SYS, the user must provide an appropriate security flavor by specifying the "sec=" mount option. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 58 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 51 insertions(+), 7 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a33e608713e9..8526008eba72 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1436,6 +1436,42 @@ out_security_failure: return 0; } +/* + * Match the requested auth flavors with the list returned by + * the server. Returns zero and sets the mount's authentication + * flavor on success; returns -EACCES if server does not support + * the requested flavor. + */ +static int nfs_walk_authlist(struct nfs_parsed_mount_data *args, + struct nfs_mount_request *request) +{ + unsigned int i, j, server_authlist_len = *(request->auth_flav_len); + + /* + * We avoid sophisticated negotiating here, as there are + * plenty of cases where we can get it wrong, providing + * either too little or too much security. + * + * RFC 2623, section 2.7 suggests we SHOULD prefer the + * flavor listed first. However, some servers list + * AUTH_NULL first. Our caller plants AUTH_SYS, the + * preferred default, in args->auth_flavors[0] if user + * didn't specify sec= mount option. + */ + for (i = 0; i < args->auth_flavor_len; i++) + for (j = 0; j < server_authlist_len; j++) + if (args->auth_flavors[i] == request->auth_flavs[j]) { + dfprintk(MOUNT, "NFS: using auth flavor %d\n", + request->auth_flavs[j]); + args->auth_flavors[0] = request->auth_flavs[j]; + return 0; + } + + dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n"); + nfs_umount(request); + return -EACCES; +} + /* * Use the remote server's MOUNT service to request the NFS file handle * corresponding to the provided path. @@ -1443,7 +1479,8 @@ out_security_failure: static int nfs_try_mount(struct nfs_parsed_mount_data *args, struct nfs_fh *root_fh) { - unsigned int auth_flavor_len = 0; + rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS]; + unsigned int server_authlist_len = ARRAY_SIZE(server_authlist); struct nfs_mount_request request = { .sap = (struct sockaddr *) &args->mount_server.address, @@ -1451,7 +1488,8 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, .protocol = args->mount_server.protocol, .fh = root_fh, .noresvport = args->flags & NFS_MOUNT_NORESVPORT, - .auth_flav_len = &auth_flavor_len, + .auth_flav_len = &server_authlist_len, + .auth_flavs = server_authlist, }; int status; @@ -1488,12 +1526,18 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, * to a file handle. */ status = nfs_mount(&request); - if (status == 0) - return 0; + if (status != 0) { + dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", + request.hostname, status); + return status; + } - dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", - request.hostname, status); - return status; + /* + * MNTv1 (NFSv2) does not support auth flavor negotiation. + */ + if (args->mount_server.version != NFS_MNT3_VERSION) + return 0; + return nfs_walk_authlist(args, &request); } static int nfs_parse_simple_hostname(const char *dev_name, From 169026a61e6f436dfc12c9d10d95455c4e9f945b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:32 -0400 Subject: [PATCH 11/87] SUNRPC: Clean up RPCBIND_MAXUADDRLEN definitions Clean up: Replace the single-integer definition of RPCBIND_MAXUADDRLEN with a definition that is based on previously defined address string sizes, and document the way this maximum is calculated. Also provide a separate macro for the size of the port number extension. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/msg_prot.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 70df4f1d8847..77e624883393 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -189,7 +189,22 @@ typedef __be32 rpc_fraghdr; * Additionally, the two alternative forms specified in Section 2.2 of * [RFC2373] are also acceptable. */ -#define RPCBIND_MAXUADDRLEN (56u) + +#include + +/* Maximum size of the port number part of a universal address */ +#define RPCBIND_MAXUADDRPLEN sizeof(".255.255") + +/* Maximum size of an IPv4 universal address */ +#define RPCBIND_MAXUADDR4LEN \ + (INET_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN) + +/* Maximum size of an IPv6 universal address */ +#define RPCBIND_MAXUADDR6LEN \ + (INET6_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN) + +/* Assume INET6_ADDRSTRLEN will always be larger than INET_ADDRSTRLEN... */ +#define RPCBIND_MAXUADDRLEN RPCBIND_MAXUADDR6LEN #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ From 0b10bf5e14d856d1d27a2117d07af2bebee81b75 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:33 -0400 Subject: [PATCH 12/87] SUNRPC: Move XDR data type size macros Clean up: To make subsequent patches cleaner, move the XDR data type size macros to the top of the file (similar to nfs4xdr.c) first. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 56 +++++++++++++++++++++++------------------- 1 file changed, 31 insertions(+), 25 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index beee6da33035..ad1d7315c498 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -75,6 +75,37 @@ enum { #define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) +/* + * XDR data type sizes + */ +#define RPCB_program_sz (1) +#define RPCB_version_sz (1) +#define RPCB_protocol_sz (1) +#define RPCB_port_sz (1) +#define RPCB_boolean_sz (1) + +#define RPCB_netid_sz (1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) +#define RPCB_addr_sz (1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) +#define RPCB_ownerstring_sz (1 + XDR_QUADLEN(RPCB_MAXOWNERLEN)) + +/* + * XDR argument and result sizes + */ +#define RPCB_mappingargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_protocol_sz + RPCB_port_sz) +#define RPCB_getaddrargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_netid_sz + RPCB_addr_sz + \ + RPCB_ownerstring_sz) + +#define RPCB_getportres_sz RPCB_port_sz +#define RPCB_setres_sz RPCB_boolean_sz + +/* + * Note that RFC 1833 does not put any size restrictions on the + * address string returned by the remote rpcbind database. + */ +#define RPCB_getaddrres_sz RPCB_addr_sz + static void rpcb_getport_done(struct rpc_task *, void *); static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; @@ -768,31 +799,6 @@ out_err: return -EIO; } -#define RPCB_program_sz (1u) -#define RPCB_version_sz (1u) -#define RPCB_protocol_sz (1u) -#define RPCB_port_sz (1u) -#define RPCB_boolean_sz (1u) - -#define RPCB_netid_sz (1+XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) -#define RPCB_addr_sz (1+XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) -#define RPCB_ownerstring_sz (1+XDR_QUADLEN(RPCB_MAXOWNERLEN)) - -#define RPCB_mappingargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_protocol_sz+RPCB_port_sz -#define RPCB_getaddrargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_netid_sz+RPCB_addr_sz+ \ - RPCB_ownerstring_sz - -#define RPCB_setres_sz RPCB_boolean_sz -#define RPCB_getportres_sz RPCB_port_sz - -/* - * Note that RFC 1833 does not put any size restrictions on the - * address string returned by the remote rpcbind database. - */ -#define RPCB_getaddrres_sz RPCB_addr_sz - #define PROC(proc, argtype, restype) \ [RPCBPROC_##proc] = { \ .p_proc = RPCBPROC_##proc, \ From a02d692611348f11ee1bc37431a883c3ff2de23e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:34 -0400 Subject: [PATCH 13/87] SUNRPC: Provide functions for managing universal addresses Introduce a set of functions in the kernel's RPC implementation for converting between a socket address and either a standard presentation address string or an RPC universal address. The universal address functions will be used to encode and decode RPCB_FOO and NFSv4 SETCLIENTID arguments. The other functions are part of a previous promise to deliver shared functions that can be used by upper-layer protocols to display and manipulate IP addresses. The kernel's current address printf formatters were designed specifically for kernel to user-space APIs that require a particular string format for socket addresses, thus are somewhat limited for the purposes of sunrpc.ko. The formatter for IPv6 addresses, %pI6, does not support short-handing or scope IDs. Also, these printf formatters are unique per address family, so a separate formatter string is required for printing AF_INET and AF_INET6 addresses. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 2 - include/linux/sunrpc/clnt.h | 38 ++++ net/sunrpc/Makefile | 2 +- net/sunrpc/addr.c | 364 ++++++++++++++++++++++++++++++++++++ 4 files changed, 403 insertions(+), 3 deletions(-) create mode 100644 net/sunrpc/addr.c diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 8d2b71d57d29..ff68397f9b19 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -370,8 +370,6 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) PAGE_SIZE - 1) >> PAGE_SHIFT; } -#define IPV6_SCOPE_DELIMITER '%' - /* * Set the port number in an address. Be agnostic about the address * family. diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 37881f1a0bd7..2636e8ad551c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -9,6 +9,10 @@ #ifndef _LINUX_SUNRPC_CLNT_H #define _LINUX_SUNRPC_CLNT_H +#include +#include +#include + #include #include #include @@ -151,5 +155,39 @@ void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); +size_t rpc_ntop(const struct sockaddr *, char *, const size_t); +size_t rpc_pton(const char *, const size_t, + struct sockaddr *, const size_t); +char * rpc_sockaddr2uaddr(const struct sockaddr *); +size_t rpc_uaddr2sockaddr(const char *, const size_t, + struct sockaddr *, const size_t); + +static inline unsigned short rpc_get_port(const struct sockaddr *sap) +{ + switch (sap->sa_family) { + case AF_INET: + return ntohs(((struct sockaddr_in *)sap)->sin_port); + case AF_INET6: + return ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + } + return 0; +} + +static inline void rpc_set_port(struct sockaddr *sap, + const unsigned short port) +{ + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + break; + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + break; + } +} + +#define IPV6_SCOPE_DELIMITER '%' +#define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index db73fd2a3f0e..9d2fca5ad14a 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ - rpcb_clnt.o timer.o xdr.o \ + addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c new file mode 100644 index 000000000000..22e8fd89477f --- /dev/null +++ b/net/sunrpc/addr.c @@ -0,0 +1,364 @@ +/* + * Copyright 2009, Oracle. All rights reserved. + * + * Convert socket addresses to presentation addresses and universal + * addresses, and vice versa. + * + * Universal addresses are introduced by RFC 1833 and further refined by + * recent RFCs describing NFSv4. The universal address format is part + * of the external (network) interface provided by rpcbind version 3 + * and 4, and by NFSv4. Such an address is a string containing a + * presentation format IP address followed by a port number in + * "hibyte.lobyte" format. + * + * IPv6 addresses can also include a scope ID, typically denoted by + * a '%' followed by a device name or a non-negative integer. Refer to + * RFC 4291, Section 2.2 for details on IPv6 presentation formats. + */ + +#include +#include + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + const struct in6_addr *addr = &sin6->sin6_addr; + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded ANY address + */ + if (ipv6_addr_any(addr)) + return snprintf(buf, buflen, "::"); + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded loopback address + */ + if (ipv6_addr_loopback(addr)) + return snprintf(buf, buflen, "::1"); + + /* + * RFC 4291, Section 2.2.3 + * + * Special presentation address format for mapped v4 + * addresses. + */ + if (ipv6_addr_v4mapped(addr)) + return snprintf(buf, buflen, "::ffff:%pI4", + &addr->s6_addr32[3]); + + /* + * RFC 4291, Section 2.2.1 + * + * To keep the result as short as possible, especially + * since we don't shorthand, we don't want leading zeros + * in each halfword, so avoid %pI6. + */ + return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x", + ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]), + ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]), + ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]), + ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7])); +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char scopebuf[IPV6_SCOPE_ID_LEN]; + size_t len; + int rc; + + len = rpc_ntop6_noscopeid(sap, buf, buflen); + if (unlikely(len == 0)) + return len; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return len; + + rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", + IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); + if (unlikely((size_t)rc > sizeof(scopebuf))) + return 0; + + len += rc; + if (unlikely(len > buflen)) + return 0; + + strcat(buf, scopebuf); + return len; +} + +#else /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + return 0; +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + return 0; +} + +#endif /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static int rpc_ntop4(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in *sin = (struct sockaddr_in *)sap; + + return snprintf(buf, buflen, "%pI4", &sin->sin_addr); +} + +/** + * rpc_ntop - construct a presentation address in @buf + * @sap: socket address + * @buf: construction area + * @buflen: size of @buf, in bytes + * + * Plants a %NUL-terminated string in @buf and returns the length + * of the string, excluding the %NUL. Otherwise zero is returned. + */ +size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen) +{ + switch (sap->sa_family) { + case AF_INET: + return rpc_ntop4(sap, buf, buflen); + case AF_INET6: + return rpc_ntop6(sap, buf, buflen); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_ntop); + +static size_t rpc_pton4(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + u8 *addr = (u8 *)&sin->sin_addr.s_addr; + + if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in)); + + if (in4_pton(buf, buflen, addr, '\0', NULL) == 0) + return 0; + + sin->sin_family = AF_INET; + return sizeof(struct sockaddr_in);; +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static int rpc_parse_scope_id(const char *buf, const size_t buflen, + const char *delim, struct sockaddr_in6 *sin6) +{ + char *p; + size_t len; + + if ((buf + buflen) == delim) + return 1; + + if (*delim != IPV6_SCOPE_DELIMITER) + return 0; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return 0; + + len = (buf + buflen) - delim - 1; + p = kstrndup(delim + 1, len, GFP_KERNEL); + if (p) { + unsigned long scope_id = 0; + struct net_device *dev; + + dev = dev_get_by_name(&init_net, p); + if (dev != NULL) { + scope_id = dev->ifindex; + dev_put(dev); + } else { + if (strict_strtoul(p, 10, &scope_id) == 0) { + kfree(p); + return 0; + } + } + + kfree(p); + + sin6->sin6_scope_id = scope_id; + return 1; + } + + return 0; +} + +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; + const char *delim; + + if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) || + salen < sizeof(struct sockaddr_in6)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in6)); + + if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0) + return 0; + + if (!rpc_parse_scope_id(buf, buflen, delim, sin6)) + return 0; + + sin6->sin6_family = AF_INET6; + return sizeof(struct sockaddr_in6); +} +#else +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + return 0; +} +#endif + +/** + * rpc_pton - Construct a sockaddr in @sap + * @buf: C string containing presentation format IP address + * @buflen: length of presentation address in bytes + * @sap: buffer into which to plant socket address + * @salen: size of buffer in bytes + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + * + * Plants a socket address in @sap and returns the size of the + * socket address, if successful. Returns zero if an error + * occurred. + */ +size_t rpc_pton(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + unsigned int i; + + for (i = 0; i < buflen; i++) + if (buf[i] == ':') + return rpc_pton6(buf, buflen, sap, salen); + return rpc_pton4(buf, buflen, sap, salen); +} +EXPORT_SYMBOL_GPL(rpc_pton); + +/** + * rpc_sockaddr2uaddr - Construct a universal address string from @sap. + * @sap: socket address + * + * Returns a %NUL-terminated string in dynamically allocated memory; + * otherwise NULL is returned if an error occurred. Caller must + * free the returned string. + */ +char *rpc_sockaddr2uaddr(const struct sockaddr *sap) +{ + char portbuf[RPCBIND_MAXUADDRPLEN]; + char addrbuf[RPCBIND_MAXUADDRLEN]; + unsigned short port; + + switch (sap->sa_family) { + case AF_INET: + if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in *)sap)->sin_port); + break; + case AF_INET6: + if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + break; + default: + return NULL; + } + + if (snprintf(portbuf, sizeof(portbuf), + ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + return NULL; + + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + return NULL; + + return kstrdup(addrbuf, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); + +/** + * rpc_uaddr2sockaddr - convert a universal address to a socket address. + * @uaddr: C string containing universal address to convert + * @uaddr_len: length of universal address string + * @sap: buffer into which to plant socket address + * @salen: size of buffer + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + */ +size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, + struct sockaddr *sap, const size_t salen) +{ + char *c, buf[RPCBIND_MAXUADDRLEN]; + unsigned long portlo, porthi; + unsigned short port; + + if (uaddr_len > sizeof(buf)) + return 0; + + memcpy(buf, uaddr, uaddr_len); + + buf[uaddr_len] = '\n'; + buf[uaddr_len + 1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0)) + return 0; + if (unlikely(portlo > 255)) + return 0; + + c[0] = '\n'; + c[1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0)) + return 0; + if (unlikely(porthi > 255)) + return 0; + + port = (unsigned short)((porthi << 8) | portlo); + + c[0] = '\0'; + + if (rpc_pton(buf, strlen(buf), sap, salen) == 0) + return 0; + + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + return sizeof(struct sockaddr_in); + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + return sizeof(struct sockaddr_in6); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr); From ba809130bc260fce04141aca01ef9e068d32af2a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:35 -0400 Subject: [PATCH 14/87] SUNRPC: Remove duplicate universal address generation RPC universal address generation is currently done in several places: rpcb_clnt.c, nfs4proc.c xprtsock.c, and xprtrdma.c. Remove the redundant cases that convert a socket address to a universal address. The nfs4proc.c case takes a pre-formatted presentation address string, not a socket address, so we'll leave that one. Because the new uaddr constructor uses the recently introduced rpc_ntop(), it now supports proper "::" shorthanding for IPv6 addresses. This allows the kernel to register properly formed universal addresses with the local rpcbind service, in _all_ cases. The kernel can now also send properly formed universal addresses in RPCB_GETADDR requests, and support link-local properly when encoding and decoding IPv6 addresses. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/rpcb_clnt.c | 48 ++++++++++++++++++++------------- net/sunrpc/xprtrdma/transport.c | 8 ------ net/sunrpc/xprtsock.c | 18 ------------- 4 files changed, 29 insertions(+), 46 deletions(-) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 1175d58efc2e..65fad9534d93 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -41,7 +41,6 @@ enum rpc_display_format_t { RPC_DISPLAY_ALL, RPC_DISPLAY_HEX_ADDR, RPC_DISPLAY_HEX_PORT, - RPC_DISPLAY_UNIVERSAL_ADDR, RPC_DISPLAY_NETID, RPC_DISPLAY_MAX, }; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index ad1d7315c498..1fb1c070c19d 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -153,6 +153,7 @@ static void rpcb_map_release(void *data) rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status); xprt_put(map->r_xprt); + kfree(map->r_addr); kfree(map); } @@ -299,12 +300,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); - char buf[32]; + int result; - /* Construct AF_INET universal address */ - snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &sin->sin_addr.s_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -315,7 +313,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } /* @@ -327,16 +327,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); - char buf[64]; + int result; - /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&sin6->sin6_addr)) - snprintf(buf, sizeof(buf), "::.%u.%u", - port >> 8, port & 0xff); - else - snprintf(buf, sizeof(buf), "%pI6.%u.%u", - &sin6->sin6_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -347,7 +340,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) @@ -570,6 +565,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } + /* Parent transport's destination address */ salen = rpc_peeraddr(clnt, sap, sizeof(addr)); /* Don't ever use rpcbind v2 for AF_INET6 requests */ @@ -620,11 +616,22 @@ void rpcb_getport_async(struct rpc_task *task) map->r_prot = xprt->prot; map->r_port = 0; map->r_xprt = xprt_get(xprt); - map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); - map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); - map->r_owner = ""; map->r_status = -EIO; + switch (bind_version) { + case RPCBVERS_4: + case RPCBVERS_3: + map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); + map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_owner = ""; + break; + case RPCBVERS_2: + map->r_addr = NULL; + break; + default: + BUG(); + } + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { @@ -722,6 +729,9 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, struct rpcbind_args *rpcb) { + if (rpcb->r_addr == NULL) + return -EIO; + dprintk("RPC: encoding rpcb request (%u, %u, %s)\n", rpcb->r_prog, rpcb->r_vers, rpcb->r_addr); *p++ = htonl(rpcb->r_prog); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 1dd6123070e9..537c210a8b92 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -202,14 +202,6 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt) snprintf(buf, 8, "%4hx", ntohs(addr->sin_port)); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - buf = kzalloc(30, GFP_KERNEL); - if (buf) - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - /* netid */ xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 83c73c4d017a..a42c2adda59f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -341,15 +341,6 @@ static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, } xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - buf = kzalloc(30, GFP_KERNEL); - if (buf) { - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); - } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - xprt->address_strings[RPC_DISPLAY_NETID] = netid; } @@ -397,15 +388,6 @@ static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, } xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - buf = kzalloc(50, GFP_KERNEL); - if (buf) { - snprintf(buf, 50, "%pI6.%u.%u", - &addr->sin6_addr, - ntohs(addr->sin6_port) >> 8, - ntohs(addr->sin6_port) & 0xff); - } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - xprt->address_strings[RPC_DISPLAY_NETID] = netid; } From c877b849d302d1275452af80b7221a2555dc02e1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:36 -0400 Subject: [PATCH 15/87] SUNRPC: Use rpc_ntop() for constructing transport address strings Clean up: In addition to using the new generic rpc_ntop() and rpc_get_port() functions, have the RPC client compute the presentation address buffer sizes dynamically using kstrdup(). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/xprtrdma/transport.c | 41 +++++------- net/sunrpc/xprtsock.c | 113 ++++++++++---------------------- 2 files changed, 52 insertions(+), 102 deletions(-) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 537c210a8b92..5f9b8676b6bd 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -168,39 +168,30 @@ static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = (struct sockaddr_in *) + struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - char *buf; + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[64]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%u", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - buf = kzalloc(48, GFP_KERNEL); - if (buf) - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), "rdma"); - xprt->address_strings[RPC_DISPLAY_ALL] = buf; + (void)snprintf(buf, sizeof(buf), "addr=%s port=%s proto=rdma", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); + xprt->address_strings[RPC_DISPLAY_ALL] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(10, GFP_KERNEL); - if (buf) - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%4hx", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); /* netid */ xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index a42c2adda59f..302a40904923 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -296,99 +296,58 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt) return (struct sockaddr_in6 *) &xprt->addr; } +static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) +{ + struct sockaddr *sap = xs_addr(xprt); + char buf[128]; + + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "addr=%s port=%s proto=%s", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + xprt->address_strings[RPC_DISPLAY_ALL] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); +} + static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, const char *protocol, const char *netid) { - struct sockaddr_in *addr = xs_addr_in(xprt); - char *buf; - - buf = kzalloc(20, GFP_KERNEL); - if (buf) { - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + struct sockaddr_in *sin = xs_addr_in(xprt); + char buf[16]; xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - - buf = kzalloc(48, GFP_KERNEL); - if (buf) { - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) { - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - } - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xs_format_common_peer_addresses(xprt); } static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, const char *protocol, const char *netid) { - struct sockaddr_in6 *addr = xs_addr_in6(xprt); - char *buf; - - buf = kzalloc(40, GFP_KERNEL); - if (buf) { - snprintf(buf, 40, "%pI6",&addr->sin6_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + struct sockaddr_in6 *sin6 = xs_addr_in6(xprt); + char buf[48]; xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - - buf = kzalloc(64, GFP_KERNEL); - if (buf) { - snprintf(buf, 64, "addr=%pI6 port=%u proto=%s", - &addr->sin6_addr, - ntohs(addr->sin6_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(36, GFP_KERNEL); - if (buf) - snprintf(buf, 36, "%pi6", &addr->sin6_addr); - - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + + (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xs_format_common_peer_addresses(xprt); } static void xs_free_peer_addresses(struct rpc_xprt *xprt) From 53a0b9c4c99ab0085a06421f71592722e5b3fd5f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:36 -0400 Subject: [PATCH 16/87] NFS: Replace nfs_parse_ip_address() with rpc_pton() Clean up: Use the common routine now provided in sunrpc.ko for parsing mount addresses. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 1 - fs/nfs/nfs4namespace.c | 6 +- fs/nfs/super.c | 148 ++++++----------------------------------- 3 files changed, 22 insertions(+), 133 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ff68397f9b19..cf1da3e22004 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -214,7 +214,6 @@ void nfs_zap_acl_cache(struct inode *inode); extern int nfs_wait_bit_killable(void *word); /* super.c */ -void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *); extern struct file_system_type nfs_xdev_fs_type; #ifdef CONFIG_NFS_V4 extern struct file_system_type nfs4_xdev_fs_type; diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 2a2a0a7143ad..43c86b7556e1 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -121,9 +121,9 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len)) continue; - nfs_parse_ip_address(buf->data, buf->len, - mountdata->addr, &mountdata->addrlen); - if (mountdata->addr->sa_family == AF_UNSPEC) + mountdata->addrlen = rpc_pton(buf->data, buf->len, + mountdata->addr, mountdata->addrlen); + if (mountdata->addrlen == 0) continue; nfs_set_port(mountdata->addr, NFS_PORT); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 8526008eba72..1eeba8e53802 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -742,129 +742,10 @@ static int nfs_verify_server_address(struct sockaddr *addr) } } + dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); return 0; } -static void nfs_parse_ipv4_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - struct sockaddr_in *sin = (struct sockaddr_in *)sap; - u8 *addr = (u8 *)&sin->sin_addr.s_addr; - - if (str_len <= INET_ADDRSTRLEN) { - dfprintk(MOUNT, "NFS: parsing IPv4 address %*s\n", - (int)str_len, string); - - sin->sin_family = AF_INET; - *addr_len = sizeof(*sin); - if (in4_pton(string, str_len, addr, '\0', NULL)) - return; - } - - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len, - const char *delim, - struct sockaddr_in6 *sin6) -{ - char *p; - size_t len; - - if ((string + str_len) == delim) - return 1; - - if (*delim != IPV6_SCOPE_DELIMITER) - return 0; - - if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) - return 0; - - len = (string + str_len) - delim - 1; - p = kstrndup(delim + 1, len, GFP_KERNEL); - if (p) { - unsigned long scope_id = 0; - struct net_device *dev; - - dev = dev_get_by_name(&init_net, p); - if (dev != NULL) { - scope_id = dev->ifindex; - dev_put(dev); - } else { - if (strict_strtoul(p, 10, &scope_id) == 0) { - kfree(p); - return 0; - } - } - - kfree(p); - - sin6->sin6_scope_id = scope_id; - dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id); - return 1; - } - - return 0; -} - -static void nfs_parse_ipv6_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; - u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; - const char *delim; - - if (str_len <= INET6_ADDRSTRLEN) { - dfprintk(MOUNT, "NFS: parsing IPv6 address %*s\n", - (int)str_len, string); - - sin6->sin6_family = AF_INET6; - *addr_len = sizeof(*sin6); - if (in6_pton(string, str_len, addr, - IPV6_SCOPE_DELIMITER, &delim) != 0) { - if (nfs_parse_ipv6_scope_id(string, str_len, - delim, sin6) != 0) - return; - } - } - - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} -#else -static void nfs_parse_ipv6_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} -#endif - -/* - * Construct a sockaddr based on the contents of a string that contains - * an IP address in presentation format. - * - * If there is a problem constructing the new sockaddr, set the address - * family to AF_UNSPEC. - */ -void nfs_parse_ip_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - unsigned int i, colons; - - colons = 0; - for (i = 0; i < str_len; i++) - if (string[i] == ':') - colons++; - - if (colons >= 2) - nfs_parse_ipv6_address(string, str_len, sap, addr_len); - else - nfs_parse_ipv4_address(string, str_len, sap, addr_len); -} - /* * Sanity check the NFS transport protocol. * @@ -1344,11 +1225,14 @@ static int nfs_parse_mount_options(char *raw, string = match_strdup(args); if (string == NULL) goto out_nomem; - nfs_parse_ip_address(string, strlen(string), - (struct sockaddr *) - &mnt->nfs_server.address, - &mnt->nfs_server.addrlen); + mnt->nfs_server.addrlen = + rpc_pton(string, strlen(string), + (struct sockaddr *) + &mnt->nfs_server.address, + sizeof(mnt->nfs_server.address)); kfree(string); + if (mnt->nfs_server.addrlen == 0) + goto out_invalid_address; break; case Opt_clientaddr: string = match_strdup(args); @@ -1368,11 +1252,14 @@ static int nfs_parse_mount_options(char *raw, string = match_strdup(args); if (string == NULL) goto out_nomem; - nfs_parse_ip_address(string, strlen(string), - (struct sockaddr *) - &mnt->mount_server.address, - &mnt->mount_server.addrlen); + mnt->mount_server.addrlen = + rpc_pton(string, strlen(string), + (struct sockaddr *) + &mnt->mount_server.address, + sizeof(mnt->mount_server.address)); kfree(string); + if (mnt->mount_server.addrlen == 0) + goto out_invalid_address; break; case Opt_lookupcache: string = match_strdup(args); @@ -1424,8 +1311,11 @@ static int nfs_parse_mount_options(char *raw, return 1; +out_invalid_address: + printk(KERN_INFO "NFS: bad IP address specified: %s\n", p); + return 0; out_invalid_value: - printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p); + printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p); return 0; out_nomem: printk(KERN_INFO "NFS: not enough memory to parse option\n"); From ec6ee61250acfccbc5578dd4014735fb2cbe53b5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:37 -0400 Subject: [PATCH 17/87] NFS: Replace nfs_set_port() with rpc_set_port() Clean up. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 19 ------------------- fs/nfs/nfs4namespace.c | 2 +- fs/nfs/super.c | 6 +++--- 3 files changed, 4 insertions(+), 23 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index cf1da3e22004..c2f171a3d70e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -368,22 +368,3 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } - -/* - * Set the port number in an address. Be agnostic about the address - * family. - */ -static inline void nfs_set_port(struct sockaddr *sap, unsigned short port) -{ - struct sockaddr_in *ap = (struct sockaddr_in *)sap; - struct sockaddr_in6 *ap6 = (struct sockaddr_in6 *)sap; - - switch (sap->sa_family) { - case AF_INET: - ap->sin_port = htons(port); - break; - case AF_INET6: - ap6->sin6_port = htons(port); - break; - } -} diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 43c86b7556e1..ef22ee89aa77 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -125,7 +125,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, mountdata->addr, mountdata->addrlen); if (mountdata->addrlen == 0) continue; - nfs_set_port(mountdata->addr, NFS_PORT); + rpc_set_port(mountdata->addr, NFS_PORT); memcpy(page2, buf->data, buf->len); page2[buf->len] = '\0'; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 1eeba8e53802..9c85cdb353aa 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1409,7 +1409,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, /* * autobind will be used if mount_server.port == 0 */ - nfs_set_port(request.sap, args->mount_server.port); + rpc_set_port(request.sap, args->mount_server.port); /* * Now ask the mount server to map our export path @@ -1703,7 +1703,7 @@ static int nfs_validate_mount_data(void *options, &args->nfs_server.address)) goto out_no_address; - nfs_set_port((struct sockaddr *)&args->nfs_server.address, + rpc_set_port((struct sockaddr *)&args->nfs_server.address, args->nfs_server.port); nfs_set_mount_transport_protocol(args); @@ -2336,7 +2336,7 @@ static int nfs4_validate_mount_data(void *options, &args->nfs_server.address)) return -EINVAL; - nfs_set_port((struct sockaddr *)&args->nfs_server.address, + rpc_set_port((struct sockaddr *)&args->nfs_server.address, args->nfs_server.port); nfs_validate_transport_protocol(args); From b97a56747ea3f6c1a27dd0719bf1424959f1ebae Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:38 -0400 Subject: [PATCH 18/87] lockd: Replace nlm_clear_port() Clean up: Use shared rpc_set_port() function instead of nlm_clear_port(). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/lockd/host.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 99d737bd4325..7cb076ac6b45 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -87,18 +87,6 @@ static unsigned int nlm_hash_address(const struct sockaddr *sap) return hash & (NLM_HOST_NRHASH - 1); } -static void nlm_clear_port(struct sockaddr *sap) -{ - switch (sap->sa_family) { - case AF_INET: - ((struct sockaddr_in *)sap)->sin_port = 0; - break; - case AF_INET6: - ((struct sockaddr_in6 *)sap)->sin6_port = 0; - break; - } -} - /* * Common host lookup routine for server & client */ @@ -177,7 +165,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni) host->h_addrbuf = nsm->sm_addrbuf; memcpy(nlm_addr(host), ni->sap, ni->salen); host->h_addrlen = ni->salen; - nlm_clear_port(nlm_addr(host)); + rpc_set_port(nlm_addr(host), 0); memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len); host->h_version = ni->version; host->h_proto = ni->protocol; From c15128c5e428af1e8ada1476484a74c970665edd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:39 -0400 Subject: [PATCH 19/87] lockd: Replace nsm_display_address() with rpc_ntop() Clean up. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/lockd/mon.c | 44 +++++--------------------------------------- 1 file changed, 5 insertions(+), 39 deletions(-) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 7fce1b525849..30c933188dd7 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -61,43 +61,6 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm) return (struct sockaddr *)&nsm->sm_addr; } -static void nsm_display_ipv4_address(const struct sockaddr *sap, char *buf, - const size_t len) -{ - const struct sockaddr_in *sin = (struct sockaddr_in *)sap; - snprintf(buf, len, "%pI4", &sin->sin_addr.s_addr); -} - -static void nsm_display_ipv6_address(const struct sockaddr *sap, char *buf, - const size_t len) -{ - const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; - - if (ipv6_addr_v4mapped(&sin6->sin6_addr)) - snprintf(buf, len, "%pI4", &sin6->sin6_addr.s6_addr32[3]); - else if (sin6->sin6_scope_id != 0) - snprintf(buf, len, "%pI6%%%u", &sin6->sin6_addr, - sin6->sin6_scope_id); - else - snprintf(buf, len, "%pI6", &sin6->sin6_addr); -} - -static void nsm_display_address(const struct sockaddr *sap, - char *buf, const size_t len) -{ - switch (sap->sa_family) { - case AF_INET: - nsm_display_ipv4_address(sap, buf, len); - break; - case AF_INET6: - nsm_display_ipv6_address(sap, buf, len); - break; - default: - snprintf(buf, len, "unsupported address family"); - break; - } -} - static struct rpc_clnt *nsm_create(void) { struct sockaddr_in sin = { @@ -307,8 +270,11 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, memcpy(nsm_addr(new), sap, salen); new->sm_addrlen = salen; nsm_init_private(new); - nsm_display_address((const struct sockaddr *)&new->sm_addr, - new->sm_addrbuf, sizeof(new->sm_addrbuf)); + + if (rpc_ntop(nsm_addr(new), new->sm_addrbuf, + sizeof(new->sm_addrbuf)) == 0) + (void)snprintf(new->sm_addrbuf, sizeof(new->sm_addrbuf), + "unsupported address family"); memcpy(new->sm_name, hostname, hostname_len); new->sm_name[hostname_len] = '\0'; From 4116092b92f859e5e9a90c99d740933e651ee8c0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:40 -0400 Subject: [PATCH 20/87] NFSD: Support IPv6 addresses in write_failover_ip() In write_failover_ip(), replace the sscanf() with a call to the common sunrpc.ko presentation address parser. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfsd/nfsctl.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6d0847562d87..7e906c5b7671 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -490,22 +491,18 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) * * Input: * buf: '\n'-terminated C string containing a - * presentation format IPv4 address + * presentation format IP address * size: length of C string in @buf * Output: * On success: returns zero if all specified locks were released; * returns one if one or more locks were not released * On error: return code is negative errno value - * - * Note: Only AF_INET client addresses are passed in */ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) { - struct sockaddr_in sin = { - .sin_family = AF_INET, - }; - int b1, b2, b3, b4; - char c; + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + size_t salen = sizeof(address); char *fo_path; /* sanity check */ @@ -519,14 +516,10 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) 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) + if (rpc_pton(fo_path, size, sap, salen) == 0) return -EINVAL; - if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255) - return -EINVAL; - sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4); - return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin); + return nlmsvc_unlock_all_by_ip(sap); } /** From 6f2c2db7a46243bd86e3d7ff5f9ff982f26a9fe8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:40 -0400 Subject: [PATCH 21/87] SUNRPC: Introduce new xdr_stream-based encoders to rpcb_clnt.c Replace the open-coded encode logic for rpcbind arguments with an xdr_stream-based implementation, similar to what NFSv4 uses, to better protect against buffer overflows. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 76 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 75 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 1fb1c070c19d..823d20dbad09 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -708,6 +708,30 @@ static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, return 0; } +static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) +{ + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + + p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); + if (unlikely(p == NULL)) + return -EIO; + + *p++ = htonl(rpcb->r_prog); + *p++ = htonl(rpcb->r_vers); + *p++ = htonl(rpcb->r_prot); + *p = htonl(rpcb->r_port); + + return 0; +} + static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, unsigned short *portp) { @@ -746,6 +770,56 @@ static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, return 0; } +static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) +{ + u32 len; + __be32 *p; + + if (unlikely(string == NULL)) + return -EIO; + len = strlen(string); + if (unlikely(len > maxstrlen)) + return -EIO; + + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (unlikely(p == NULL)) + return -EIO; + xdr_encode_opaque(p, string, len); + + return 0; +} + +static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) +{ + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + rpcb->r_prog, rpcb->r_vers, + rpcb->r_netid, rpcb->r_addr); + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + + p = xdr_reserve_space(&xdr, + sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); + *p = htonl(rpcb->r_vers); + + if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) + return -EIO; + + return 0; +} + static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, unsigned short *portp) { @@ -812,7 +886,7 @@ out_err: #define PROC(proc, argtype, restype) \ [RPCBPROC_##proc] = { \ .p_proc = RPCBPROC_##proc, \ - .p_encode = (kxdrproc_t) rpcb_encode_##argtype, \ + .p_encode = (kxdrproc_t) rpcb_enc_##argtype, \ .p_decode = (kxdrproc_t) rpcb_decode_##restype, \ .p_arglen = RPCB_##argtype##args_sz, \ .p_replen = RPCB_##restype##res_sz, \ From 0d36c4f7574d5a33bedd8f0e3c793490d45d83c6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:41 -0400 Subject: [PATCH 22/87] SUNRPC: Clean up: Remove unused XDR encoder functions from rpcb_clnt.c Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 823d20dbad09..e0d7b31e54a7 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -694,20 +694,6 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) -{ - dprintk("RPC: encoding rpcb request (%u, %u, %d, %u)\n", - rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); - *p++ = htonl(rpcb->r_prot); - *p++ = htonl(rpcb->r_port); - - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); - return 0; -} - static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, const struct rpcbind_args *rpcb) { @@ -750,26 +736,6 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) -{ - if (rpcb->r_addr == NULL) - return -EIO; - - dprintk("RPC: encoding rpcb request (%u, %u, %s)\n", - rpcb->r_prog, rpcb->r_vers, rpcb->r_addr); - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); - - p = xdr_encode_string(p, rpcb->r_netid); - p = xdr_encode_string(p, rpcb->r_addr); - p = xdr_encode_string(p, rpcb->r_owner); - - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); - - return 0; -} - static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, const u32 maxstrlen) { From 7ed0ff983c8ad30bf4e2b9fdbb299a3e3ec08d08 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:42 -0400 Subject: [PATCH 23/87] SUNRPC: Introduce xdr_stream-based decoders for RPCB_UNSET Replace the open-coded decode logic for rpcbind UNSET results with an xdr_stream-based implementation, similar to what NFSv4 uses, to protect against buffer overflows. The new function is unused for the moment. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index e0d7b31e54a7..fe183af5cc72 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -736,6 +736,28 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, return 0; } +static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, + unsigned int *boolp) +{ + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + *boolp = 0; + if (*p) + *boolp = 1; + + dprintk("RPC: %5u RPCB_%s call %s\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + (*boolp ? "succeeded" : "failed")); + return 0; +} + static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, const u32 maxstrlen) { From c0c077df009f2f329875051ac5283df235288689 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:43 -0400 Subject: [PATCH 24/87] SUNRPC: Introduce new xdr_stream-based decoders to rpcb_clnt.c Replace the open-coded decode logic for PMAP_GETPORT/RPCB_GETADDR with an xdr_stream-based implementation, similar to what NFSv4 uses, to protect against buffer overflows. The new implementation also checks that the incoming port number is reasonable. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 80 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index fe183af5cc72..88de754e3b02 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -454,7 +454,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) struct rpc_message msg = { .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT], .rpc_argp = &map, - .rpc_resp = &map.r_port, + .rpc_resp = &map, }; struct rpc_clnt *rpcb_clnt; int status; @@ -484,7 +484,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi struct rpc_message msg = { .rpc_proc = proc, .rpc_argp = map, - .rpc_resp = &map->r_port, + .rpc_resp = map, }; struct rpc_task_setup task_setup_data = { .rpc_client = rpcb_clnt, @@ -727,6 +727,31 @@ static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, return 0; } +static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) +{ + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + unsigned long port; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + rpcb->r_port = 0; + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + port = ntohl(*p); + dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, port); + if (unlikely(port > USHORT_MAX)) + return -EIO; + + rpcb->r_port = port; + return 0; +} + static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, unsigned int *boolp) { @@ -871,11 +896,60 @@ out_err: return -EIO; } +static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) +{ + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + u32 len; + + rpcb->r_port = 0; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + goto out_fail; + len = ntohl(*p); + + /* + * If the returned universal address is a null string, + * the requested RPC service was not registered. + */ + if (len == 0) { + dprintk("RPC: %5u RPCB reply: program not registered\n", + task->tk_pid); + return 0; + } + + if (unlikely(len > RPCBIND_MAXUADDRLEN)) + goto out_fail; + + p = xdr_inline_decode(&xdr, len); + if (unlikely(p == NULL)) + goto out_fail; + dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, (char *)p); + + if (rpc_uaddr2sockaddr((char *)p, len, sap, sizeof(address)) == 0) + goto out_fail; + rpcb->r_port = rpc_get_port(sap); + + return 0; + +out_fail: + dprintk("RPC: %5u malformed RPCB_%s reply\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name); + return -EIO; +} + #define PROC(proc, argtype, restype) \ [RPCBPROC_##proc] = { \ .p_proc = RPCBPROC_##proc, \ .p_encode = (kxdrproc_t) rpcb_enc_##argtype, \ - .p_decode = (kxdrproc_t) rpcb_decode_##restype, \ + .p_decode = (kxdrproc_t) rpcb_dec_##restype, \ .p_arglen = RPCB_##argtype##args_sz, \ .p_replen = RPCB_##restype##res_sz, \ .p_statidx = RPCBPROC_##proc, \ From 0e47f0d665efcf1b45f293422d21d8383f07d122 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:43 -0400 Subject: [PATCH 25/87] SUNRPC: Clean up: Remove unused XDR decoder functions from rpcb_clnt.c Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 81 ------------------------------------------ 1 file changed, 81 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 88de754e3b02..c4b716cacf21 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -718,15 +718,6 @@ static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) -{ - *portp = (unsigned short) ntohl(*p++); - dprintk("RPC: rpcb getport result: %u\n", - *portp); - return 0; -} - static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, struct rpcbind_args *rpcb) { @@ -752,15 +743,6 @@ static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, - unsigned int *boolp) -{ - *boolp = (unsigned int) ntohl(*p++); - dprintk("RPC: rpcb set/unset call %s\n", - (*boolp ? "succeeded" : "failed")); - return 0; -} - static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, unsigned int *boolp) { @@ -833,69 +815,6 @@ static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) -{ - char *addr; - u32 addr_len; - int c, i, f, first, val; - - *portp = 0; - addr_len = ntohl(*p++); - - if (addr_len == 0) { - dprintk("RPC: rpcb_decode_getaddr: " - "service is not registered\n"); - return 0; - } - - /* - * Simple sanity check. - */ - if (addr_len > RPCBIND_MAXUADDRLEN) - goto out_err; - - /* - * Start at the end and walk backwards until the first dot - * is encountered. When the second dot is found, we have - * both parts of the port number. - */ - addr = (char *)p; - val = 0; - first = 1; - f = 1; - for (i = addr_len - 1; i > 0; i--) { - c = addr[i]; - if (c >= '0' && c <= '9') { - val += (c - '0') * f; - f *= 10; - } else if (c == '.') { - if (first) { - *portp = val; - val = first = 0; - f = 1; - } else { - *portp |= (val << 8); - break; - } - } - } - - /* - * Simple sanity check. If we never saw a dot in the reply, - * then this was probably just garbage. - */ - if (first) - goto out_err; - - dprintk("RPC: rpcb_decode_getaddr port=%u\n", *portp); - return 0; - -out_err: - dprintk("RPC: rpcbind server returned malformed reply\n"); - return -EIO; -} - static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, struct rpcbind_args *rpcb) { From f8b761eff1e49fde43dd940ac32b38cf7cee2a95 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:44 -0400 Subject: [PATCH 26/87] SUNRPC: Eliminate PROC macro from rpcb_clnt Clean up: Replace PROC macro with open coded C99 structure initializers to improve readability. The rpcbind v4 GETVERSADDR procedure is never sent by the current implementation, so it is not copied to the new structures. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 113 +++++++++++++++++++++++++++++++++-------- 1 file changed, 91 insertions(+), 22 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c4b716cacf21..830faf4d9997 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -864,39 +864,108 @@ out_fail: return -EIO; } -#define PROC(proc, argtype, restype) \ - [RPCBPROC_##proc] = { \ - .p_proc = RPCBPROC_##proc, \ - .p_encode = (kxdrproc_t) rpcb_enc_##argtype, \ - .p_decode = (kxdrproc_t) rpcb_dec_##restype, \ - .p_arglen = RPCB_##argtype##args_sz, \ - .p_replen = RPCB_##restype##res_sz, \ - .p_statidx = RPCBPROC_##proc, \ - .p_timer = 0, \ - .p_name = #proc, \ - } - /* * Not all rpcbind procedures described in RFC 1833 are implemented * since the Linux kernel RPC code requires only these. */ + static struct rpc_procinfo rpcb_procedures2[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), - PROC(GETPORT, mapping, getport), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETPORT] = { + .p_proc = RPCBPROC_GETPORT, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_getportres_sz, + .p_statidx = RPCBPROC_GETPORT, + .p_timer = 0, + .p_name = "GETPORT", + }, }; static struct rpc_procinfo rpcb_procedures3[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpc_procinfo rpcb_procedures4[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), - PROC(GETVERSADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpcb_info rpcb_next_version[] = { From fbfffbd5e74c5fa8c9165e110cb5899ec21e6364 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:46 -0400 Subject: [PATCH 27/87] SUNRPC: Rename sock_xprt.addr as sock_xprt.srcaddr Clean up: Give the "addr" and "port" field less ambiguous names. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 302a40904923..7bc3c178ccb3 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -248,8 +248,8 @@ struct sock_xprt { * Connection of transports */ struct delayed_work connect_worker; - struct sockaddr_storage addr; - unsigned short port; + struct sockaddr_storage srcaddr; + unsigned short srcport; /* * UDP socket buffer size parameters @@ -1546,7 +1546,7 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock) { - unsigned short port = transport->port; + unsigned short port = transport->srcport; if (port == 0 && transport->xprt.resvport) port = xs_get_random_port(); @@ -1555,8 +1555,8 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port) { - if (transport->port != 0) - transport->port = 0; + if (transport->srcport != 0) + transport->srcport = 0; if (!transport->xprt.resvport) return 0; if (port <= xprt_min_resvport || port > xprt_max_resvport) @@ -1574,7 +1574,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in *)&transport->addr; + sa = (struct sockaddr_in *)&transport->srcaddr; myaddr.sin_addr = sa->sin_addr; do { myaddr.sin_port = htons(port); @@ -1583,7 +1583,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1607,7 +1607,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in6 *)&transport->addr; + sa = (struct sockaddr_in6 *)&transport->srcaddr; myaddr.sin6_addr = sa->sin6_addr; do { myaddr.sin6_port = htons(port); @@ -1616,7 +1616,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -2061,7 +2061,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.sends, xprt->stat.recvs, @@ -2085,7 +2085,7 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) idle_time = (long)(jiffies - xprt->last_used) / HZ; seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.connect_count, xprt->stat.connect_time, @@ -2164,7 +2164,7 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, memcpy(&xprt->addr, args->dstaddr, args->addrlen); xprt->addrlen = args->addrlen; if (args->srcaddr) - memcpy(&new->addr, args->srcaddr, args->addrlen); + memcpy(&new->srcaddr, args->srcaddr, args->addrlen); return xprt; } From c740eff84bcfd63c0497ef880e80171931cb8222 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:46 -0400 Subject: [PATCH 28/87] SUNRPC: Kill RPC_DISPLAY_ALL At some point, I recall that rpc_pipe_fs used RPC_DISPLAY_ALL. Currently there are no uses of RPC_DISPLAY_ALL outside the transport modules themselves, so we can safely get rid of it. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprtrdma/transport.c | 5 ---- net/sunrpc/xprtsock.c | 50 ++++++++++++++++++++++----------- 3 files changed, 34 insertions(+), 22 deletions(-) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 65fad9534d93..c090df442572 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -38,7 +38,6 @@ enum rpc_display_format_t { RPC_DISPLAY_ADDR = 0, RPC_DISPLAY_PORT, RPC_DISPLAY_PROTO, - RPC_DISPLAY_ALL, RPC_DISPLAY_HEX_ADDR, RPC_DISPLAY_HEX_PORT, RPC_DISPLAY_NETID, diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 5f9b8676b6bd..9a63f669ece4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -181,11 +181,6 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt) xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - (void)snprintf(buf, sizeof(buf), "addr=%s port=%s proto=rdma", - xprt->address_strings[RPC_DISPLAY_ADDR], - xprt->address_strings[RPC_DISPLAY_PORT]); - xprt->address_strings[RPC_DISPLAY_ALL] = kstrdup(buf, GFP_KERNEL); - (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", NIPQUAD(sin->sin_addr.s_addr)); xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 7bc3c178ccb3..eee5ac96e177 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -307,12 +307,6 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - (void)snprintf(buf, sizeof(buf), "addr=%s port=%s proto=%s", - xprt->address_strings[RPC_DISPLAY_ADDR], - xprt->address_strings[RPC_DISPLAY_PORT], - xprt->address_strings[RPC_DISPLAY_PROTO]); - xprt->address_strings[RPC_DISPLAY_ALL] = kstrdup(buf, GFP_KERNEL); - (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); } @@ -1721,8 +1715,11 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1763,8 +1760,11 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1889,8 +1889,11 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt, goto out_eagain; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); dprintk("RPC: %p connect status %d connected %d sock state %d\n", @@ -2228,8 +2231,15 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); if (try_module_get(THIS_MODULE)) return xprt; @@ -2293,8 +2303,16 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + if (try_module_get(THIS_MODULE)) return xprt; From 9dc3b095b78347bfb02c324b5ee2e558f7267396 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:46 -0400 Subject: [PATCH 29/87] SUNRPC: Update xprt address strings after an rpcbind completes After a bind completes, update the transport instance's address strings so debugging messages display the current port the transport is connected to. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 82 +++++++++++++++++++++---------------------- 1 file changed, 41 insertions(+), 41 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index eee5ac96e177..8aaf9003fe6e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -299,11 +299,34 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt) static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) { struct sockaddr *sap = xs_addr(xprt); + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; char buf[128]; (void)rpc_ntop(sap, buf, sizeof(buf)); xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); + switch (sap->sa_family) { + case AF_INET: + sin = xs_addr_in(xprt); + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + break; + case AF_INET6: + sin6 = xs_addr_in6(xprt); + (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + break; + default: + BUG(); + } + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); +} + +static void xs_format_common_peer_ports(struct rpc_xprt *xprt) +{ + struct sockaddr *sap = xs_addr(xprt); + char buf[128]; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); @@ -311,37 +334,22 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); } -static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_peer_addresses(struct rpc_xprt *xprt, + const char *protocol, + const char *netid) { - struct sockaddr_in *sin = xs_addr_in(xprt); - char buf[16]; - xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; xprt->address_strings[RPC_DISPLAY_NETID] = netid; - - (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", - NIPQUAD(sin->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); - xs_format_common_peer_addresses(xprt); + xs_format_common_peer_ports(xprt); } -static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_update_peer_port(struct rpc_xprt *xprt) { - struct sockaddr_in6 *sin6 = xs_addr_in6(xprt); - char buf[48]; + kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); + kfree(xprt->address_strings[RPC_DISPLAY_PORT]); - xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - xprt->address_strings[RPC_DISPLAY_NETID] = netid; - - (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); - - xs_format_common_peer_addresses(xprt); + xs_format_common_peer_ports(xprt); } static void xs_free_peer_addresses(struct rpc_xprt *xprt) @@ -1522,20 +1530,10 @@ static unsigned short xs_get_random_port(void) */ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) { - struct sockaddr *addr = xs_addr(xprt); - dprintk("RPC: setting port for xprt %p to %u\n", xprt, port); - switch (addr->sa_family) { - case AF_INET: - ((struct sockaddr_in *)addr)->sin_port = htons(port); - break; - case AF_INET6: - ((struct sockaddr_in6 *)addr)->sin6_port = htons(port); - break; - default: - BUG(); - } + rpc_set_port(xs_addr(xprt), port); + xs_update_peer_port(xprt); } static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock) @@ -2216,7 +2214,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) @@ -2224,7 +2222,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); break; default: kfree(xprt); @@ -2288,15 +2286,17 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) if (((struct sockaddr_in *)addr)->sin_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker4); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker6); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); break; default: kfree(xprt); From c05988cdb06237738d361ef82fbf4df1020aa3db Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 9 Aug 2009 15:09:47 -0400 Subject: [PATCH 30/87] SUNRPC: Add documenting comments in net/sunrpc/timer.c Clean up: provide documenting comments for the functions in net/sunrpc/timer.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/timer.c | 45 +++++++++++++++++++++++++++++---------------- 1 file changed, 29 insertions(+), 16 deletions(-) diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c index 31becbf09263..dd824341c349 100644 --- a/net/sunrpc/timer.c +++ b/net/sunrpc/timer.c @@ -25,8 +25,13 @@ #define RPC_RTO_INIT (HZ/5) #define RPC_RTO_MIN (HZ/10) -void -rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) +/** + * rpc_init_rtt - Initialize an RPC RTT estimator context + * @rt: context to initialize + * @timeo: initial timeout value, in jiffies + * + */ +void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) { unsigned long init = 0; unsigned i; @@ -43,12 +48,16 @@ rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) } EXPORT_SYMBOL_GPL(rpc_init_rtt); -/* +/** + * rpc_update_rtt - Update an RPC RTT estimator context + * @rt: context to update + * @timer: timer array index (request type) + * @m: recent actual RTT, in jiffies + * * NB: When computing the smoothed RTT and standard deviation, * be careful not to produce negative intermediate results. */ -void -rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) +void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) { long *srtt, *sdrtt; @@ -79,21 +88,25 @@ rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) } EXPORT_SYMBOL_GPL(rpc_update_rtt); -/* - * Estimate rto for an nfs rpc sent via. an unreliable datagram. - * Use the mean and mean deviation of rtt for the appropriate type of rpc - * for the frequent rpcs and a default for the others. - * The justification for doing "other" this way is that these rpcs - * happen so infrequently that timer est. would probably be stale. - * Also, since many of these rpcs are - * non-idempotent, a conservative timeout is desired. +/** + * rpc_calc_rto - Provide an estimated timeout value + * @rt: context to use for calculation + * @timer: timer array index (request type) + * + * Estimate RTO for an NFS RPC sent via an unreliable datagram. Use + * the mean and mean deviation of RTT for the appropriate type of RPC + * for frequently issued RPCs, and a fixed default for the others. + * + * The justification for doing "other" this way is that these RPCs + * happen so infrequently that timer estimation would probably be + * stale. Also, since many of these RPCs are non-idempotent, a + * conservative timeout is desired. + * * getattr, lookup, * read, write, commit - A+4D * other - timeo */ - -unsigned long -rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) { unsigned long res; From b693ba4a338da15db1db4b5ebaa36e4ab9781c82 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:15 -0400 Subject: [PATCH 31/87] SUNRPC: Constify rpc_pipe_ops... Signed-off-by: Trond Myklebust --- fs/nfs/idmap.c | 2 +- include/linux/sunrpc/rpc_pipe_fs.h | 5 +++-- net/sunrpc/auth_gss/auth_gss.c | 8 ++++---- net/sunrpc/rpc_pipe.c | 7 ++++--- 4 files changed, 12 insertions(+), 10 deletions(-) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 86147b0ab2cf..fae0d3e52b44 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -101,7 +101,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static unsigned int fnvhash32(const void *, size_t); -static struct rpc_pipe_ops idmap_upcall_ops = { +static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = idmap_pipe_upcall, .downcall = idmap_pipe_downcall, .destroy_msg = idmap_pipe_destroy_msg, diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index cea764c2359f..91f5b13389c5 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -32,8 +32,8 @@ struct rpc_inode { wait_queue_head_t waitq; #define RPC_PIPE_WAIT_FOR_OPEN 1 int flags; - struct rpc_pipe_ops *ops; struct delayed_work queue_timeout; + const struct rpc_pipe_ops *ops; }; static inline struct rpc_inode * @@ -46,7 +46,8 @@ extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); extern int rpc_rmdir(struct dentry *); -extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, struct rpc_pipe_ops *, int flags); +extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, + const struct rpc_pipe_ops *, int flags); extern int rpc_unlink(struct dentry *); extern struct vfsmount *rpc_get_mount(void); extern void rpc_put_mount(void); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 66d458fc6920..23eb3864ffc0 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); static void gss_free_ctx(struct gss_cl_ctx *); -static struct rpc_pipe_ops gss_upcall_ops_v0; -static struct rpc_pipe_ops gss_upcall_ops_v1; +static const struct rpc_pipe_ops gss_upcall_ops_v0; +static const struct rpc_pipe_ops gss_upcall_ops_v1; static inline struct gss_cl_ctx * gss_get_ctx(struct gss_cl_ctx *ctx) @@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = { .crunwrap_resp = gss_unwrap_resp, }; -static struct rpc_pipe_ops gss_upcall_ops_v0 = { +static const struct rpc_pipe_ops gss_upcall_ops_v0 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, @@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = { .release_pipe = gss_pipe_release, }; -static struct rpc_pipe_ops gss_upcall_ops_v1 = { +static const struct rpc_pipe_ops gss_upcall_ops_v1 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9ced0628d69c..f6f60f625e3f 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -125,7 +125,7 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); - struct rpc_pipe_ops *ops; + const struct rpc_pipe_ops *ops; int need_release; mutex_lock(&inode->i_mutex); @@ -776,8 +776,9 @@ rpc_rmdir(struct dentry *dentry) * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private. */ -struct dentry * -rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags) +struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, + void *private, const struct rpc_pipe_ops *ops, + int flags) { struct dentry *dentry; struct inode *dir, *inode; From 7364af6a2d5e708b5c6fee3cce08d1bd7b27c9f1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:16 -0400 Subject: [PATCH 32/87] SUNRPC: Allow rpc_pipefs_ops to have null values for upcall and downcall Also ensure that we use the umode_t type when appropriate... Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index f6f60f625e3f..8fa718201e3f 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -417,7 +417,7 @@ enum { struct rpc_filelist { char *name; const struct file_operations *i_fop; - int mode; + umode_t mode; }; static struct rpc_filelist files[] = { @@ -516,7 +516,7 @@ rpc_release_path(struct nameidata *nd) } static struct inode * -rpc_get_inode(struct super_block *sb, int mode) +rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) @@ -589,7 +589,8 @@ rpc_populate(struct dentry *parent, struct inode *inode, *dir = parent->d_inode; void *private = RPC_I(dir)->private; struct dentry *dentry; - int mode, i; + umode_t mode; + int i; mutex_lock(&dir->i_mutex); for (i = start; i < eof; i++) { @@ -783,6 +784,12 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, struct dentry *dentry; struct inode *dir, *inode; struct rpc_inode *rpci; + umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + + if (ops->upcall == NULL) + umode &= ~S_IRUGO; + if (ops->downcall == NULL) + umode &= ~S_IWUGO; dentry = rpc_lookup_create(parent, name, strlen(name), 0); if (IS_ERR(dentry)) @@ -799,7 +806,7 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, rpci->nkern_readwriters++; goto out; } - inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR); + inode = rpc_get_inode(dir->i_sb, umode); if (!inode) goto err_dput; inode->i_ino = iunique(dir->i_sb, 100); From b5bb61da2efe7519eedd6a8f3830ab33ab774b83 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:17 -0400 Subject: [PATCH 33/87] SUNRPC: Clean up rpc_pipefs lookup code... Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 8fa718201e3f..2940b926648c 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -484,12 +484,12 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -static int -rpc_lookup_parent(char *path, struct nameidata *nd) +static int __rpc_lookup_path(const char *pathname, unsigned flags, + struct nameidata *nd) { struct vfsmount *mnt; - if (path[0] == '\0') + if (pathname[0] == '\0') return -ENOENT; mnt = rpc_get_mount(); @@ -499,15 +499,20 @@ rpc_lookup_parent(char *path, struct nameidata *nd) return PTR_ERR(mnt); } - if (vfs_path_lookup(mnt->mnt_root, mnt, path, LOOKUP_PARENT, nd)) { + if (vfs_path_lookup(mnt->mnt_root, mnt, pathname, flags, nd)) { printk(KERN_WARNING "%s: %s failed to find path %s\n", - __FILE__, __func__, path); + __FILE__, __func__, pathname); rpc_put_mount(); return -ENOENT; } return 0; } +static int rpc_lookup_parent(const char *pathname, struct nameidata *nd) +{ + return __rpc_lookup_path(pathname, LOOKUP_PARENT, nd); +} + static void rpc_release_path(struct nameidata *nd) { From 7589806e961a16449003b636b369edec537c2726 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:17 -0400 Subject: [PATCH 34/87] SUNRPC: Clean up file creation code in rpc_pipefs Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 120 +++++++++++++++++++++++++++--------------- 1 file changed, 77 insertions(+), 43 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 2940b926648c..d8c78150e9ca 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -539,6 +539,68 @@ rpc_get_inode(struct super_block *sb, umode_t mode) return inode; } +static int __rpc_create_common(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) +{ + struct inode *inode; + + BUG_ON(!d_unhashed(dentry)); + inode = rpc_get_inode(dir->i_sb, mode); + if (!inode) + goto out_err; + inode->i_ino = iunique(dir->i_sb, 100); + if (i_fop) + inode->i_fop = i_fop; + if (private) + rpc_inode_setowner(inode, private); + d_add(dentry, inode); + return 0; +out_err: + printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", + __FILE__, __func__, dentry->d_name.name); + dput(dentry); + return -ENOMEM; +} + +static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) +{ + int err; + + err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private); + if (err) + return err; + inc_nlink(dir); + fsnotify_mkdir(dir, dentry); + return 0; +} + +static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private, + const struct rpc_pipe_ops *ops, + int flags) +{ + struct rpc_inode *rpci; + int err; + + err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); + if (err) + return err; + rpci = RPC_I(dentry->d_inode); + rpci->nkern_readwriters = 1; + rpci->private = private; + rpci->flags = flags; + rpci->ops = ops; + fsnotify_create(dir, dentry); + return 0; +} + /* * FIXME: This probably has races. */ @@ -628,25 +690,6 @@ out_bad: return -ENOMEM; } -static int -__rpc_mkdir(struct inode *dir, struct dentry *dentry) -{ - struct inode *inode; - - inode = rpc_get_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO); - if (!inode) - goto out_err; - inode->i_ino = iunique(dir->i_sb, 100); - d_instantiate(dentry, inode); - inc_nlink(dir); - fsnotify_mkdir(dir, dentry); - return 0; -out_err: - printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", - __FILE__, __func__, dentry->d_name.name); - return -ENOMEM; -} - static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) { @@ -717,9 +760,9 @@ rpc_mkdir(char *path, struct rpc_clnt *rpc_client) if (IS_ERR(dentry)) return dentry; dir = nd.path.dentry->d_inode; - if ((error = __rpc_mkdir(dir, dentry)) != 0) - goto err_dput; - RPC_I(dentry->d_inode)->private = rpc_client; + error = __rpc_mkdir(dir, dentry, S_IRUGO | S_IXUGO, NULL, rpc_client); + if (error != 0) + goto out_err; error = rpc_populate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); if (error) @@ -732,8 +775,7 @@ out: err_depopulate: rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); __rpc_rmdir(dir, dentry); -err_dput: - dput(dentry); +out_err: printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", __FILE__, __func__, path, error); dentry = ERR_PTR(error); @@ -787,9 +829,9 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, int flags) { struct dentry *dentry; - struct inode *dir, *inode; - struct rpc_inode *rpci; + struct inode *dir = parent->d_inode; umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + int err; if (ops->upcall == NULL) umode &= ~S_IRUGO; @@ -801,7 +843,7 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, return dentry; dir = parent->d_inode; if (dentry->d_inode) { - rpci = RPC_I(dentry->d_inode); + struct rpc_inode *rpci = RPC_I(dentry->d_inode); if (rpci->private != private || rpci->ops != ops || rpci->flags != flags) { @@ -811,28 +853,20 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, rpci->nkern_readwriters++; goto out; } - inode = rpc_get_inode(dir->i_sb, umode); - if (!inode) - goto err_dput; - inode->i_ino = iunique(dir->i_sb, 100); - inode->i_fop = &rpc_pipe_fops; - d_instantiate(dentry, inode); - rpci = RPC_I(inode); - rpci->private = private; - rpci->flags = flags; - rpci->ops = ops; - rpci->nkern_readwriters = 1; - fsnotify_create(dir, dentry); + + err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops, + private, ops, flags); + if (err) + goto out_err; dget(dentry); out: mutex_unlock(&dir->i_mutex); return dentry; -err_dput: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); +out_err: + dentry = ERR_PTR(err); printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n", __FILE__, __func__, parent->d_name.name, name, - -ENOMEM); + err); goto out; } EXPORT_SYMBOL_GPL(rpc_mkpipe); From 810d90bc2a76ff54295cfb3aa9b165160faa47ef Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:18 -0400 Subject: [PATCH 35/87] SUNRPC: Clean up rpc_unlink() Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index d8c78150e9ca..cf30bf58bfcf 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -601,6 +601,29 @@ static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, return 0; } +static int __rpc_unlink(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_unlink(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct rpc_inode *rpci = RPC_I(inode); + + rpci->nkern_readwriters--; + if (rpci->nkern_readwriters != 0) + return 0; + rpc_close_pipes(inode); + return __rpc_unlink(dir, dentry); +} + /* * FIXME: This probably has races. */ @@ -848,14 +871,15 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, rpci->ops != ops || rpci->flags != flags) { dput (dentry); - dentry = ERR_PTR(-EBUSY); + err = -EBUSY; + goto out_err; } rpci->nkern_readwriters++; goto out; } err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops, - private, ops, flags); + private, ops, flags); if (err) goto out_err; dget(dentry); @@ -889,12 +913,7 @@ rpc_unlink(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (--RPC_I(dentry->d_inode)->nkern_readwriters == 0) { - rpc_close_pipes(dentry->d_inode); - error = simple_unlink(dir, dentry); - if (!error) - d_delete(dentry); - } + error = __rpc_rmpipe(dir, dentry); dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); From cfeaa4a3caaf590c1fdb7a83fcd5326e7cdc70c3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:20 -0400 Subject: [PATCH 36/87] SUNRPC: Clean up rpc_lookup_create Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 100 +++++++++++++++++++++++++----------------- 1 file changed, 59 insertions(+), 41 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index cf30bf58bfcf..36338515f342 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -624,6 +624,57 @@ static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) return __rpc_unlink(dir, dentry); } +static struct dentry *__rpc_lookup_create(struct dentry *parent, + struct qstr *name) +{ + struct dentry *dentry; + + dentry = d_lookup(parent, name); + if (!dentry) { + dentry = d_alloc(parent, name); + if (!dentry) { + dentry = ERR_PTR(-ENOMEM); + goto out_err; + } + } + if (!dentry->d_inode) + dentry->d_op = &rpc_dentry_operations; +out_err: + return dentry; +} + +static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, + struct qstr *name) +{ + struct dentry *dentry; + + dentry = __rpc_lookup_create(parent, name); + if (dentry->d_inode == NULL) + return dentry; + dput(dentry); + return ERR_PTR(-EEXIST); +} + +static struct dentry *rpc_lookup_negative(const char *path, + struct nameidata *nd) +{ + struct inode *dir; + struct dentry *dentry; + int error; + + error = rpc_lookup_parent(path, nd); + if (error != 0) + return ERR_PTR(error); + dir = nd->path.dentry->d_inode; + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create_exclusive(nd->path.dentry, &nd->last); + if (IS_ERR(dentry)) { + mutex_unlock(&dir->i_mutex); + rpc_release_path(nd); + } + return dentry; +} + /* * FIXME: This probably has races. */ @@ -723,44 +774,6 @@ __rpc_rmdir(struct inode *dir, struct dentry *dentry) return error; } -static struct dentry * -rpc_lookup_create(struct dentry *parent, const char *name, int len, int exclusive) -{ - struct inode *dir = parent->d_inode; - struct dentry *dentry; - - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, parent, len); - if (IS_ERR(dentry)) - goto out_err; - if (!dentry->d_inode) - dentry->d_op = &rpc_dentry_operations; - else if (exclusive) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - goto out_err; - } - return dentry; -out_err: - mutex_unlock(&dir->i_mutex); - return dentry; -} - -static struct dentry * -rpc_lookup_negative(char *path, struct nameidata *nd) -{ - struct dentry *dentry; - int error; - - if ((error = rpc_lookup_parent(path, nd)) != 0) - return ERR_PTR(error); - dentry = rpc_lookup_create(nd->path.dentry, nd->last.name, nd->last.len, - 1); - if (IS_ERR(dentry)) - rpc_release_path(nd); - return dentry; -} - /** * rpc_mkdir - Create a new directory in rpc_pipefs * @path: path from the rpc_pipefs root to the new directory @@ -854,6 +867,7 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, struct dentry *dentry; struct inode *dir = parent->d_inode; umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + struct qstr q; int err; if (ops->upcall == NULL) @@ -861,10 +875,14 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, if (ops->downcall == NULL) umode &= ~S_IWUGO; - dentry = rpc_lookup_create(parent, name, strlen(name), 0); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len), + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create(parent, &q); if (IS_ERR(dentry)) - return dentry; - dir = parent->d_inode; + goto out; if (dentry->d_inode) { struct rpc_inode *rpci = RPC_I(dentry->d_inode); if (rpci->private != private || From ac6fecee3121a6825a01c8fda2f5cbf1ad6a3ebd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:20 -0400 Subject: [PATCH 37/87] SUNRPC: Clean up rpc_populate/depopulate Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 191 +++++++++++++++++++++++------------------- 1 file changed, 103 insertions(+), 88 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 36338515f342..e5f37ded1565 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -401,7 +401,6 @@ static const struct file_operations rpc_info_operations = { * We have a single directory with 1 node in it. */ enum { - RPCAUTH_Root = 1, RPCAUTH_lockd, RPCAUTH_mount, RPCAUTH_nfs, @@ -415,12 +414,12 @@ enum { * Description of fs contents. */ struct rpc_filelist { - char *name; + const char *name; const struct file_operations *i_fop; umode_t mode; }; -static struct rpc_filelist files[] = { +static const struct rpc_filelist files[] = { [RPCAUTH_lockd] = { .name = "lockd", .mode = S_IFDIR | S_IRUGO | S_IXUGO, @@ -448,11 +447,11 @@ static struct rpc_filelist files[] = { }; enum { - RPCAUTH_info = 2, + RPCAUTH_info, RPCAUTH_EOF }; -static struct rpc_filelist authfiles[] = { +static const struct rpc_filelist authfiles[] = { [RPCAUTH_info] = { .name = "info", .i_fop = &rpc_info_operations, @@ -564,6 +563,20 @@ out_err: return -ENOMEM; } +static int __rpc_create(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) +{ + int err; + + err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private); + if (err) + return err; + fsnotify_create(dir, dentry); + return 0; +} + static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, const struct file_operations *i_fop, @@ -601,6 +614,17 @@ static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, return 0; } +static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_rmdir(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + static int __rpc_unlink(struct inode *dir, struct dentry *dentry) { int ret; @@ -678,100 +702,96 @@ static struct dentry *rpc_lookup_negative(const char *path, /* * FIXME: This probably has races. */ -static void rpc_depopulate(struct dentry *parent, - unsigned long start, unsigned long eof) +static void __rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + struct qstr name; + int i; + + for (i = start; i < eof; i++) { + name.name = files[i].name; + name.len = strlen(files[i].name); + name.hash = full_name_hash(name.name, name.len); + dentry = d_lookup(parent, &name); + + if (dentry == NULL) + continue; + if (dentry->d_inode == NULL) + goto next; + switch (dentry->d_inode->i_mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + __rpc_unlink(dir, dentry); + break; + case S_IFDIR: + __rpc_rmdir(dir, dentry); + } +next: + dput(dentry); + } +} + +static void rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) { struct inode *dir = parent->d_inode; - struct list_head *pos, *next; - struct dentry *dentry, *dvec[10]; - int n = 0; mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); -repeat: - spin_lock(&dcache_lock); - list_for_each_safe(pos, next, &parent->d_subdirs) { - dentry = list_entry(pos, struct dentry, d_u.d_child); - if (!dentry->d_inode || - dentry->d_inode->i_ino < start || - dentry->d_inode->i_ino >= eof) - continue; - spin_lock(&dentry->d_lock); - if (!d_unhashed(dentry)) { - dget_locked(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - dvec[n++] = dentry; - if (n == ARRAY_SIZE(dvec)) - break; - } else - spin_unlock(&dentry->d_lock); - } - spin_unlock(&dcache_lock); - if (n) { - do { - dentry = dvec[--n]; - if (S_ISREG(dentry->d_inode->i_mode)) - simple_unlink(dir, dentry); - else if (S_ISDIR(dentry->d_inode->i_mode)) - simple_rmdir(dir, dentry); - d_delete(dentry); - dput(dentry); - } while (n); - goto repeat; - } + __rpc_depopulate(parent, files, start, eof); mutex_unlock(&dir->i_mutex); } -static int -rpc_populate(struct dentry *parent, - struct rpc_filelist *files, - int start, int eof) +static int rpc_populate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof, + void *private) { - struct inode *inode, *dir = parent->d_inode; - void *private = RPC_I(dir)->private; + struct inode *dir = parent->d_inode; struct dentry *dentry; - umode_t mode; - int i; + int i, err; mutex_lock(&dir->i_mutex); for (i = start; i < eof; i++) { - dentry = d_alloc_name(parent, files[i].name); - if (!dentry) - goto out_bad; - dentry->d_op = &rpc_dentry_operations; - mode = files[i].mode; - inode = rpc_get_inode(dir->i_sb, mode); - if (!inode) { - dput(dentry); + struct qstr q; + + q.name = files[i].name; + q.len = strlen(files[i].name); + q.hash = full_name_hash(q.name, q.len); + dentry = __rpc_lookup_create_exclusive(parent, &q); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) goto out_bad; + switch (files[i].mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + err = __rpc_create(dir, dentry, + files[i].mode, + files[i].i_fop, + private); + break; + case S_IFDIR: + err = __rpc_mkdir(dir, dentry, + files[i].mode, + NULL, + private); } - inode->i_ino = i; - if (files[i].i_fop) - inode->i_fop = files[i].i_fop; - if (private) - rpc_inode_setowner(inode, private); - if (S_ISDIR(mode)) - inc_nlink(dir); - d_add(dentry, inode); - fsnotify_create(dir, dentry); + if (err != 0) + goto out_bad; } mutex_unlock(&dir->i_mutex); return 0; out_bad: + __rpc_depopulate(parent, files, start, eof); mutex_unlock(&dir->i_mutex); printk(KERN_WARNING "%s: %s failed to populate directory %s\n", __FILE__, __func__, parent->d_name.name); - return -ENOMEM; -} - -static int -__rpc_rmdir(struct inode *dir, struct dentry *dentry) -{ - int error; - error = simple_rmdir(dir, dentry); - if (!error) - d_delete(dentry); - return error; + return err; } /** @@ -800,16 +820,14 @@ rpc_mkdir(char *path, struct rpc_clnt *rpc_client) if (error != 0) goto out_err; error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF); + RPCAUTH_info, RPCAUTH_EOF, rpc_client); if (error) - goto err_depopulate; - dget(dentry); + goto err_rmdir; out: mutex_unlock(&dir->i_mutex); rpc_release_path(&nd); return dentry; -err_depopulate: - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); +err_rmdir: __rpc_rmdir(dir, dentry); out_err: printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", @@ -832,9 +850,8 @@ rpc_rmdir(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); + rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); error = __rpc_rmdir(dir, dentry); - dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; @@ -900,7 +917,6 @@ struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, private, ops, flags); if (err) goto out_err; - dget(dentry); out: mutex_unlock(&dir->i_mutex); return dentry; @@ -932,7 +948,6 @@ rpc_unlink(struct dentry *dentry) dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); error = __rpc_rmpipe(dir, dentry); - dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; @@ -970,7 +985,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) iput(inode); return -ENOMEM; } - if (rpc_populate(root, files, RPCAUTH_Root + 1, RPCAUTH_RootEOF)) + if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) goto out; sb->s_root = root; return 0; From bb1567491e43df4113ec8b088ff0ebc22f568bc5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:21 -0400 Subject: [PATCH 38/87] SUNRPC: rpc_pipefs cleanup Move the files[] array closer to rpc_fill_super() Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 80 +++++++++++++++++++++---------------------- 1 file changed, 40 insertions(+), 40 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index e5f37ded1565..2a4e6eb0a3e9 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -397,19 +397,6 @@ static const struct file_operations rpc_info_operations = { }; -/* - * We have a single directory with 1 node in it. - */ -enum { - RPCAUTH_lockd, - RPCAUTH_mount, - RPCAUTH_nfs, - RPCAUTH_portmap, - RPCAUTH_statd, - RPCAUTH_nfsd4_cb, - RPCAUTH_RootEOF -}; - /* * Description of fs contents. */ @@ -419,33 +406,6 @@ struct rpc_filelist { umode_t mode; }; -static const struct rpc_filelist files[] = { - [RPCAUTH_lockd] = { - .name = "lockd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_mount] = { - .name = "mount", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfs] = { - .name = "nfs", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_portmap] = { - .name = "portmap", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_statd] = { - .name = "statd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfsd4_cb] = { - .name = "nfsd4_cb", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, -}; - enum { RPCAUTH_info, RPCAUTH_EOF @@ -965,6 +925,46 @@ static struct super_operations s_ops = { #define RPCAUTH_GSSMAGIC 0x67596969 +/* + * We have a single directory with 1 node in it. + */ +enum { + RPCAUTH_lockd, + RPCAUTH_mount, + RPCAUTH_nfs, + RPCAUTH_portmap, + RPCAUTH_statd, + RPCAUTH_nfsd4_cb, + RPCAUTH_RootEOF +}; + +static const struct rpc_filelist files[] = { + [RPCAUTH_lockd] = { + .name = "lockd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_mount] = { + .name = "mount", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfs] = { + .name = "nfs", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_portmap] = { + .name = "portmap", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_statd] = { + .name = "statd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfsd4_cb] = { + .name = "nfsd4_cb", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { From 458adb8ba9b26bfc66593866013adbb62a1a3d2e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:22 -0400 Subject: [PATCH 39/87] SUNRPC: Rename rpc_mkdir to rpc_create_client_dir() This reflects the fact that rpc_mkdir() as it stands today, can only create a RPC client type directory. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 5 +++-- net/sunrpc/clnt.c | 6 +++--- net/sunrpc/rpc_pipe.c | 11 +++++------ 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 91f5b13389c5..8de0ac276499 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -44,8 +44,9 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); -extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); -extern int rpc_rmdir(struct dentry *); +struct rpc_clnt; +extern struct dentry *rpc_create_client_dir(const char *, struct rpc_clnt *); +extern int rpc_remove_client_dir(struct dentry *); extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, const struct rpc_pipe_ops *, int flags); extern int rpc_unlink(struct dentry *); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index ebfcf9b89909..6ec37701a165 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -113,7 +113,7 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) "%s/clnt%x", dir_name, (unsigned int)clntid++); clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_dentry = rpc_mkdir(clnt->cl_pathname, clnt); + clnt->cl_dentry = rpc_create_client_dir(clnt->cl_pathname, clnt); if (!IS_ERR(clnt->cl_dentry)) return 0; error = PTR_ERR(clnt->cl_dentry); @@ -232,7 +232,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru out_no_auth: if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + rpc_remove_client_dir(clnt->cl_dentry); rpc_put_mount(); } out_no_path: @@ -424,7 +424,7 @@ rpc_free_client(struct kref *kref) dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + rpc_remove_client_dir(clnt->cl_dentry); rpc_put_mount(); } if (clnt->cl_parent != clnt) { diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 2a4e6eb0a3e9..08580bedc25f 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -755,7 +755,7 @@ out_bad: } /** - * rpc_mkdir - Create a new directory in rpc_pipefs + * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs * @path: path from the rpc_pipefs root to the new directory * @rpc_client: rpc client to associate with this directory * @@ -764,8 +764,8 @@ out_bad: * information about the client, together with any "pipes" that may * later be created using rpc_mkpipe(). */ -struct dentry * -rpc_mkdir(char *path, struct rpc_clnt *rpc_client) +struct dentry *rpc_create_client_dir(const char *path, + struct rpc_clnt *rpc_client) { struct nameidata nd; struct dentry *dentry; @@ -797,11 +797,10 @@ out_err: } /** - * rpc_rmdir - Remove a directory created with rpc_mkdir() + * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() * @dentry: directory to remove */ -int -rpc_rmdir(struct dentry *dentry) +int rpc_remove_client_dir(struct dentry *dentry) { struct dentry *parent; struct inode *dir; From 7d59d1e86531a53d7648726ab8a6a670ecbd8f06 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:23 -0400 Subject: [PATCH 40/87] SUNRPC: Clean up rpc_create_client_dir() Factor out the code that does lookups from the code that actually creates the directory. Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 83 +++++++++++++++++++++---------------------- 1 file changed, 41 insertions(+), 42 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 08580bedc25f..6d152f69587e 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -639,26 +639,6 @@ static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, return ERR_PTR(-EEXIST); } -static struct dentry *rpc_lookup_negative(const char *path, - struct nameidata *nd) -{ - struct inode *dir; - struct dentry *dentry; - int error; - - error = rpc_lookup_parent(path, nd); - if (error != 0) - return ERR_PTR(error); - dir = nd->path.dentry->d_inode; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = __rpc_lookup_create_exclusive(nd->path.dentry, &nd->last); - if (IS_ERR(dentry)) { - mutex_unlock(&dir->i_mutex); - rpc_release_path(nd); - } - return dentry; -} - /* * FIXME: This probably has races. */ @@ -754,44 +734,30 @@ out_bad: return err; } -/** - * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs - * @path: path from the rpc_pipefs root to the new directory - * @rpc_client: rpc client to associate with this directory - * - * This creates a directory at the given @path associated with - * @rpc_clnt, which will contain a file named "info" with some basic - * information about the client, together with any "pipes" that may - * later be created using rpc_mkpipe(). - */ -struct dentry *rpc_create_client_dir(const char *path, - struct rpc_clnt *rpc_client) +struct dentry *rpc_mkdir_populate(struct dentry *parent, + struct qstr *name, umode_t mode, void *private) { - struct nameidata nd; struct dentry *dentry; - struct inode *dir; + struct inode *dir = parent->d_inode; int error; - dentry = rpc_lookup_negative(path, &nd); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) - return dentry; - dir = nd.path.dentry->d_inode; - error = __rpc_mkdir(dir, dentry, S_IRUGO | S_IXUGO, NULL, rpc_client); + goto out; + error = __rpc_mkdir(dir, dentry, mode, NULL, private); if (error != 0) goto out_err; error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF, rpc_client); + RPCAUTH_info, RPCAUTH_EOF, private); if (error) goto err_rmdir; out: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); return dentry; err_rmdir: __rpc_rmdir(dir, dentry); out_err: - printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", - __FILE__, __func__, path, error); dentry = ERR_PTR(error); goto out; } @@ -913,6 +879,39 @@ rpc_unlink(struct dentry *dentry) } EXPORT_SYMBOL_GPL(rpc_unlink); +/** + * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs + * @path: path from the rpc_pipefs root to the new directory + * @rpc_client: rpc client to associate with this directory + * + * This creates a directory at the given @path associated with + * @rpc_clnt, which will contain a file named "info" with some basic + * information about the client, together with any "pipes" that may + * later be created using rpc_mkpipe(). + */ +struct dentry *rpc_create_client_dir(const char *path, + struct rpc_clnt *rpc_client) +{ + struct nameidata nd; + struct dentry *ret; + struct inode *dir; + + ret = ERR_PTR(rpc_lookup_parent(path, &nd)); + if (IS_ERR(ret)) + goto out_err; + dir = nd.path.dentry->d_inode; + + ret = rpc_mkdir_populate(nd.path.dentry, &nd.last, + S_IRUGO | S_IXUGO, rpc_client); + rpc_release_path(&nd); + if (!IS_ERR(ret)) + return ret; +out_err: + printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %ld)\n", + __FILE__, __func__, path, PTR_ERR(ret)); + return ret; +} + /* * populate the filesystem */ From 7d217caca5d704e48aa5e59aba0b3ad4c7af4fd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:24 -0400 Subject: [PATCH 41/87] SUNRPC: Replace rpc_client->cl_dentry and cl_mnt, with a cl_path Signed-off-by: Trond Myklebust --- fs/nfs/idmap.c | 4 ++-- include/linux/sunrpc/clnt.h | 4 ++-- net/sunrpc/auth_gss/auth_gss.c | 4 ++-- net/sunrpc/clnt.c | 24 ++++++++++++------------ 4 files changed, 18 insertions(+), 18 deletions(-) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index fae0d3e52b44..21a84d45916f 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -119,8 +119,8 @@ nfs_idmap_new(struct nfs_client *clp) if (idmap == NULL) return -ENOMEM; - idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap", - idmap, &idmap_upcall_ops, 0); + idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry, + "idmap", idmap, &idmap_upcall_ops, 0); if (IS_ERR(idmap->idmap_dentry)) { error = PTR_ERR(idmap->idmap_dentry); kfree(idmap); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 37881f1a0bd7..38ad162330a2 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -17,6 +17,7 @@ #include #include #include +#include struct rpc_inode; @@ -51,8 +52,7 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; char cl_pathname[30];/* Path in rpc_pipe_fs */ - struct vfsmount * cl_vfsmnt; - struct dentry * cl_dentry; /* inode */ + struct path cl_path; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23eb3864ffc0..fc6a43ccd950 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) * that we supported only the old pipe. So we instead create * the new pipe first. */ - gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry, "gssd", clnt, &gss_upcall_ops_v1, RPC_PIPE_WAIT_FOR_OPEN); @@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) goto err_put_mech; } - gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry, gss_auth->mech->gm_name, clnt, &gss_upcall_ops_v0, RPC_PIPE_WAIT_FOR_OPEN); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 6ec37701a165..b3f863346300 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -99,24 +99,24 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) static uint32_t clntid; int error; - clnt->cl_vfsmnt = ERR_PTR(-ENOENT); - clnt->cl_dentry = ERR_PTR(-ENOENT); + clnt->cl_path.mnt = ERR_PTR(-ENOENT); + clnt->cl_path.dentry = ERR_PTR(-ENOENT); if (dir_name == NULL) return 0; - clnt->cl_vfsmnt = rpc_get_mount(); - if (IS_ERR(clnt->cl_vfsmnt)) - return PTR_ERR(clnt->cl_vfsmnt); + clnt->cl_path.mnt = rpc_get_mount(); + if (IS_ERR(clnt->cl_path.mnt)) + return PTR_ERR(clnt->cl_path.mnt); for (;;) { snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname), "%s/clnt%x", dir_name, (unsigned int)clntid++); clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_dentry = rpc_create_client_dir(clnt->cl_pathname, clnt); - if (!IS_ERR(clnt->cl_dentry)) + clnt->cl_path.dentry = rpc_create_client_dir(clnt->cl_pathname, clnt); + if (!IS_ERR(clnt->cl_path.dentry)) return 0; - error = PTR_ERR(clnt->cl_dentry); + error = PTR_ERR(clnt->cl_path.dentry); if (error != -EEXIST) { printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n", clnt->cl_pathname, error); @@ -231,8 +231,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru return clnt; out_no_auth: - if (!IS_ERR(clnt->cl_dentry)) { - rpc_remove_client_dir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } out_no_path: @@ -423,8 +423,8 @@ rpc_free_client(struct kref *kref) dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); - if (!IS_ERR(clnt->cl_dentry)) { - rpc_remove_client_dir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } if (clnt->cl_parent != clnt) { From 23ac6581702ac6d029643328a7e6ea3baf834c5e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:25 -0400 Subject: [PATCH 42/87] SUNRPC: clean up rpc_setup_pipedir() There is still a little wart or two there: Since we've already got a vfsmount, we might as well pass that in to rpc_create_client_dir. Another point is that if we open code __rpc_lookup_path() here, then we can avoid looking up the entire parent directory path over and over again: it doesn't change. Also get rid of rpc_clnt->cl_pathname, since it has no users... Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - include/linux/sunrpc/rpc_pipe_fs.h | 2 +- net/sunrpc/clnt.c | 48 +++++++++++++++++-------- net/sunrpc/rpc_pipe.c | 58 ++---------------------------- 4 files changed, 37 insertions(+), 72 deletions(-) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 38ad162330a2..1848d44922ef 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -51,7 +51,6 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; - char cl_pathname[30];/* Path in rpc_pipe_fs */ struct path cl_path; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 8de0ac276499..88332ef1e959 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -45,7 +45,7 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); struct rpc_clnt; -extern struct dentry *rpc_create_client_dir(const char *, struct rpc_clnt *); +extern struct dentry *rpc_create_client_dir(struct dentry *, struct qstr *, struct rpc_clnt *); extern int rpc_remove_client_dir(struct dentry *); extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, const struct rpc_pipe_ops *, int flags); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b3f863346300..c1e467e1b07d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -27,6 +27,8 @@ #include #include #include +#include +#include #include #include #include @@ -97,6 +99,12 @@ static int rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) { static uint32_t clntid; + struct nameidata nd; + struct path path; + char name[15]; + struct qstr q = { + .name = name, + }; int error; clnt->cl_path.mnt = ERR_PTR(-ENOENT); @@ -104,26 +112,36 @@ rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) if (dir_name == NULL) return 0; - clnt->cl_path.mnt = rpc_get_mount(); - if (IS_ERR(clnt->cl_path.mnt)) - return PTR_ERR(clnt->cl_path.mnt); + path.mnt = rpc_get_mount(); + if (IS_ERR(path.mnt)) + return PTR_ERR(path.mnt); + error = vfs_path_lookup(path.mnt->mnt_root, path.mnt, dir_name, 0, &nd); + if (error) + goto err; for (;;) { - snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname), - "%s/clnt%x", dir_name, - (unsigned int)clntid++); - clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_path.dentry = rpc_create_client_dir(clnt->cl_pathname, clnt); - if (!IS_ERR(clnt->cl_path.dentry)) - return 0; - error = PTR_ERR(clnt->cl_path.dentry); + q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); + name[sizeof(name) - 1] = '\0'; + q.hash = full_name_hash(q.name, q.len); + path.dentry = rpc_create_client_dir(nd.path.dentry, &q, clnt); + if (!IS_ERR(path.dentry)) + break; + error = PTR_ERR(path.dentry); if (error != -EEXIST) { - printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n", - clnt->cl_pathname, error); - rpc_put_mount(); - return error; + printk(KERN_INFO "RPC: Couldn't create pipefs entry" + " %s/%s, error %d\n", + dir_name, name, error); + goto err_path_put; } } + path_put(&nd.path); + clnt->cl_path = path; + return 0; +err_path_put: + path_put(&nd.path); +err: + rpc_put_mount(); + return error; } static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 6d152f69587e..1613d858ba38 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -443,42 +443,6 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -static int __rpc_lookup_path(const char *pathname, unsigned flags, - struct nameidata *nd) -{ - struct vfsmount *mnt; - - if (pathname[0] == '\0') - return -ENOENT; - - mnt = rpc_get_mount(); - if (IS_ERR(mnt)) { - printk(KERN_WARNING "%s: %s failed to mount " - "pseudofilesystem \n", __FILE__, __func__); - return PTR_ERR(mnt); - } - - if (vfs_path_lookup(mnt->mnt_root, mnt, pathname, flags, nd)) { - printk(KERN_WARNING "%s: %s failed to find path %s\n", - __FILE__, __func__, pathname); - rpc_put_mount(); - return -ENOENT; - } - return 0; -} - -static int rpc_lookup_parent(const char *pathname, struct nameidata *nd) -{ - return __rpc_lookup_path(pathname, LOOKUP_PARENT, nd); -} - -static void -rpc_release_path(struct nameidata *nd) -{ - path_put(&nd->path); - rpc_put_mount(); -} - static struct inode * rpc_get_inode(struct super_block *sb, umode_t mode) { @@ -889,27 +853,11 @@ EXPORT_SYMBOL_GPL(rpc_unlink); * information about the client, together with any "pipes" that may * later be created using rpc_mkpipe(). */ -struct dentry *rpc_create_client_dir(const char *path, +struct dentry *rpc_create_client_dir(struct dentry *dentry, + struct qstr *name, struct rpc_clnt *rpc_client) { - struct nameidata nd; - struct dentry *ret; - struct inode *dir; - - ret = ERR_PTR(rpc_lookup_parent(path, &nd)); - if (IS_ERR(ret)) - goto out_err; - dir = nd.path.dentry->d_inode; - - ret = rpc_mkdir_populate(nd.path.dentry, &nd.last, - S_IRUGO | S_IXUGO, rpc_client); - rpc_release_path(&nd); - if (!IS_ERR(ret)) - return ret; -out_err: - printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %ld)\n", - __FILE__, __func__, path, PTR_ERR(ret)); - return ret; + return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, rpc_client); } /* From e57aed77ad48d28ac617ba157ad2f665f5301b30 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:26 -0400 Subject: [PATCH 43/87] SUNRPC: One more clean up for rpc_create_client_dir() In order to allow rpc_pipefs to create directories with different types of subtrees, it is useful to allow the caller to customise the subtree filling process. In order to do so, we separate out the parts which are specific to making an RPC client directory, and put them in a separate helper, then we convert the process of filling the directory contents into a callback. Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 78 +++++++++++++++++++++++++++---------------- 1 file changed, 50 insertions(+), 28 deletions(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 1613d858ba38..57e9cd3c49b6 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -406,19 +406,6 @@ struct rpc_filelist { umode_t mode; }; -enum { - RPCAUTH_info, - RPCAUTH_EOF -}; - -static const struct rpc_filelist authfiles[] = { - [RPCAUTH_info] = { - .name = "info", - .i_fop = &rpc_info_operations, - .mode = S_IFREG | S_IRUSR, - }, -}; - struct vfsmount *rpc_get_mount(void) { int err; @@ -698,8 +685,9 @@ out_bad: return err; } -struct dentry *rpc_mkdir_populate(struct dentry *parent, - struct qstr *name, umode_t mode, void *private) +static struct dentry *rpc_mkdir_populate(struct dentry *parent, + struct qstr *name, umode_t mode, void *private, + int (*populate)(struct dentry *, void *), void *args_populate) { struct dentry *dentry; struct inode *dir = parent->d_inode; @@ -712,10 +700,11 @@ struct dentry *rpc_mkdir_populate(struct dentry *parent, error = __rpc_mkdir(dir, dentry, mode, NULL, private); if (error != 0) goto out_err; - error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF, private); - if (error) - goto err_rmdir; + if (populate != NULL) { + error = populate(dentry, args_populate); + if (error) + goto err_rmdir; + } out: mutex_unlock(&dir->i_mutex); return dentry; @@ -726,11 +715,8 @@ out_err: goto out; } -/** - * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() - * @dentry: directory to remove - */ -int rpc_remove_client_dir(struct dentry *dentry) +static int rpc_rmdir_depopulate(struct dentry *dentry, + void (*depopulate)(struct dentry *)) { struct dentry *parent; struct inode *dir; @@ -739,7 +725,8 @@ int rpc_remove_client_dir(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); + if (depopulate != NULL) + depopulate(dentry); error = __rpc_rmdir(dir, dentry); mutex_unlock(&dir->i_mutex); dput(parent); @@ -843,6 +830,31 @@ rpc_unlink(struct dentry *dentry) } EXPORT_SYMBOL_GPL(rpc_unlink); +enum { + RPCAUTH_info, + RPCAUTH_EOF +}; + +static const struct rpc_filelist authfiles[] = { + [RPCAUTH_info] = { + .name = "info", + .i_fop = &rpc_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +static int rpc_clntdir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + authfiles, RPCAUTH_info, RPCAUTH_EOF, + private); +} + +static void rpc_clntdir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); +} + /** * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs * @path: path from the rpc_pipefs root to the new directory @@ -854,10 +866,20 @@ EXPORT_SYMBOL_GPL(rpc_unlink); * later be created using rpc_mkpipe(). */ struct dentry *rpc_create_client_dir(struct dentry *dentry, - struct qstr *name, - struct rpc_clnt *rpc_client) + struct qstr *name, + struct rpc_clnt *rpc_client) { - return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, rpc_client); + return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, + rpc_clntdir_populate, rpc_client); +} + +/** + * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() + * @dentry: directory to remove + */ +int rpc_remove_client_dir(struct dentry *dentry) +{ + return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); } /* From 2da8ca26c6bfad685bfddf39728eac1c83906aa9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:26 -0400 Subject: [PATCH 44/87] NFSD: Clean up the idmapper warning... What part of 'internal use' is so hard to understand? Signed-off-by: Trond Myklebust --- fs/nfsd/nfs4idmap.c | 4 ++-- include/linux/sunrpc/cache.h | 3 ++- net/sunrpc/cache.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 5b398421b051..e9012ad36ac0 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -175,10 +175,10 @@ idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) } static void -warn_no_idmapd(struct cache_detail *detail) +warn_no_idmapd(struct cache_detail *detail, int has_died) { printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n", - detail->last_close? "died" : "not been started"); + has_died ? "died" : "not been started"); } diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 2d8b211b9324..3d1fad22185a 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -79,6 +79,8 @@ struct cache_detail { int (*cache_show)(struct seq_file *m, struct cache_detail *cd, struct cache_head *h); + void (*warn_no_listener)(struct cache_detail *cd, + int has_died); struct cache_head * (*alloc)(void); int (*match)(struct cache_head *orig, struct cache_head *new); @@ -102,7 +104,6 @@ struct cache_detail { atomic_t readers; /* how many time is /chennel open */ time_t last_close; /* if no readers, when did last close */ time_t last_warn; /* when we last warned about no readers */ - void (*warn_no_listener)(struct cache_detail *cd); }; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ff0c23053d2f..8ede4a6f384b 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1020,7 +1020,7 @@ static void warn_no_listener(struct cache_detail *detail) if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) - detail->warn_no_listener(detail); + detail->warn_no_listener(detail, detail->last_close != 0); } } From 5b7a1b9f9214cb89dd164b43ca3fab7af4058e06 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:27 -0400 Subject: [PATCH 45/87] SUNRPC: Ensure we initialise the cache_detail before creating procfs files Also ensure that we destroy those files before we destroy the cache_detail. Otherwise, user processes might attempt to write into uninitialised caches. Signed-off-by: Trond Myklebust --- net/sunrpc/cache.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 8ede4a6f384b..062d4f4307eb 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -347,13 +347,8 @@ static int create_cache_proc_entries(struct cache_detail *cd) } #endif -int cache_register(struct cache_detail *cd) +static void sunrpc_init_cache_detail(struct cache_detail *cd) { - int ret; - - ret = create_cache_proc_entries(cd); - if (ret) - return ret; rwlock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); @@ -367,11 +362,9 @@ int cache_register(struct cache_detail *cd) /* start the cleaning process */ schedule_delayed_work(&cache_cleaner, 0); - return 0; } -EXPORT_SYMBOL_GPL(cache_register); -void cache_unregister(struct cache_detail *cd) +static void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); @@ -386,7 +379,6 @@ void cache_unregister(struct cache_detail *cd) list_del_init(&cd->others); write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); - remove_cache_proc_entries(cd); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); @@ -395,6 +387,24 @@ void cache_unregister(struct cache_detail *cd) out: printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); } + +int cache_register(struct cache_detail *cd) +{ + int ret; + + sunrpc_init_cache_detail(cd); + ret = create_cache_proc_entries(cd); + if (ret) + sunrpc_destroy_cache_detail(cd); + return ret; +} +EXPORT_SYMBOL_GPL(cache_register); + +void cache_unregister(struct cache_detail *cd) +{ + remove_cache_proc_entries(cd); + sunrpc_destroy_cache_detail(cd); +} EXPORT_SYMBOL_GPL(cache_unregister); /* clean cache tries to find something to clean From da77005f0d64486cd760f43d9b7cc2379262a363 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:28 -0400 Subject: [PATCH 46/87] SUNRPC: Remove the global temporary write buffer in net/sunrpc/cache.c While we do want to protect against multiple concurrent readers and writers on each upcall/downcall pipe, we don't want to limit concurrent reading and writing to separate caches. This patch therefore replaces the static buffer 'write_buf', which can only be used by one writer at a time, with use of the page cache as the temporary buffer for downcalls. We still fall back to using the the old global buffer if the downcall is larger than PAGE_CACHE_SIZE, since this is apparently needed by the SPKM security context initialisation. It then replaces the use of the global 'queue_io_mutex' with the inode->i_mutex in cache_read() and cache_write(). Signed-off-by: Trond Myklebust --- net/sunrpc/cache.c | 95 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 70 insertions(+), 25 deletions(-) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 062d4f4307eb..c8e7d2d07260 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -702,13 +703,14 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct inode *inode = filp->f_path.dentry->d_inode; + struct cache_detail *cd = PDE(inode)->data; int err; if (count == 0) return 0; - mutex_lock(&queue_io_mutex); /* protect against multiple concurrent + mutex_lock(&inode->i_mutex); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); @@ -721,7 +723,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); BUG_ON(rp->offset); return 0; } @@ -768,38 +770,81 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (err == -EAGAIN) goto again; - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); return err ? err : count; } -static char write_buf[8192]; /* protected by queue_io_mutex */ +static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, + size_t count, struct cache_detail *cd) +{ + ssize_t ret; + + if (copy_from_user(kaddr, buf, count)) + return -EFAULT; + kaddr[count] = '\0'; + ret = cd->cache_parse(cd, kaddr, count); + if (!ret) + ret = count; + return ret; +} + +static ssize_t cache_slow_downcall(const char __user *buf, + size_t count, struct cache_detail *cd) +{ + static char write_buf[8192]; /* protected by queue_io_mutex */ + ssize_t ret = -EINVAL; + + if (count >= sizeof(write_buf)) + goto out; + mutex_lock(&queue_io_mutex); + ret = cache_do_downcall(write_buf, buf, count, cd); + mutex_unlock(&queue_io_mutex); +out: + return ret; +} + +static ssize_t cache_downcall(struct address_space *mapping, + const char __user *buf, + size_t count, struct cache_detail *cd) +{ + struct page *page; + char *kaddr; + ssize_t ret = -ENOMEM; + + if (count >= PAGE_CACHE_SIZE) + goto out_slow; + + page = find_or_create_page(mapping, 0, GFP_KERNEL); + if (!page) + goto out_slow; + + kaddr = kmap(page); + ret = cache_do_downcall(kaddr, buf, count, cd); + kunmap(page); + unlock_page(page); + page_cache_release(page); + return ret; +out_slow: + return cache_slow_downcall(buf, count, cd); +} static ssize_t cache_write(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - int err; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct address_space *mapping = filp->f_mapping; + struct inode *inode = filp->f_path.dentry->d_inode; + struct cache_detail *cd = PDE(inode)->data; + ssize_t ret = -EINVAL; - if (count == 0) - return 0; - if (count >= sizeof(write_buf)) - return -EINVAL; + if (!cd->cache_parse) + goto out; - mutex_lock(&queue_io_mutex); - - if (copy_from_user(write_buf, buf, count)) { - mutex_unlock(&queue_io_mutex); - return -EFAULT; - } - write_buf[count] = '\0'; - if (cd->cache_parse) - err = cd->cache_parse(cd, write_buf, count); - else - err = -EINVAL; - - mutex_unlock(&queue_io_mutex); - return err ? err : count; + mutex_lock(&inode->i_mutex); + ret = cache_downcall(mapping, buf, count, cd); + mutex_unlock(&inode->i_mutex); +out: + return ret; } static DECLARE_WAIT_QUEUE_HEAD(queue_wait); From bc74b4f5e63a09fb78e245794a0de1e5a2716bbe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:29 -0400 Subject: [PATCH 47/87] SUNRPC: Allow the cache_detail to specify alternative upcall mechanisms For events that are rare, such as referral DNS lookups, it makes limited sense to have a daemon constantly listening for upcalls on a channel. An alternative in those cases might simply be to run the app that fills the cache using call_usermodehelper_exec() and friends. The following patch allows the cache_detail to specify alternative upcall mechanisms for these particular cases. Signed-off-by: Trond Myklebust --- fs/nfsd/export.c | 14 ++++++++++++-- fs/nfsd/nfs4idmap.c | 16 ++++++++++++++-- include/linux/sunrpc/cache.h | 13 ++++++++++--- net/sunrpc/auth_gss/svcauth_gss.c | 7 ++++++- net/sunrpc/cache.c | 26 ++++++++++++++++++-------- net/sunrpc/svcauth_unix.c | 14 ++++++++++++-- 6 files changed, 72 insertions(+), 18 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index b92a27629fb7..d9462643155c 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -85,6 +85,11 @@ static void expkey_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, expkey_request); +} + static struct svc_expkey *svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old); static struct svc_expkey *svc_expkey_lookup(struct svc_expkey *); static struct cache_detail svc_expkey_cache; @@ -259,7 +264,7 @@ static struct cache_detail svc_expkey_cache = { .hash_table = expkey_table, .name = "nfsd.fh", .cache_put = expkey_put, - .cache_request = expkey_request, + .cache_upcall = expkey_upcall, .cache_parse = expkey_parse, .cache_show = expkey_show, .match = expkey_match, @@ -355,6 +360,11 @@ static void svc_export_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, svc_export_request); +} + static struct svc_export *svc_export_update(struct svc_export *new, struct svc_export *old); static struct svc_export *svc_export_lookup(struct svc_export *); @@ -724,7 +734,7 @@ struct cache_detail svc_export_cache = { .hash_table = export_table, .name = "nfsd.export", .cache_put = svc_export_put, - .cache_request = svc_export_request, + .cache_upcall = svc_export_upcall, .cache_parse = svc_export_parse, .cache_show = svc_export_show, .match = svc_export_match, diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index e9012ad36ac0..cdfa86fa1471 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -145,6 +145,12 @@ idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, (*bpp)[-1] = '\n'; } +static int +idtoname_upcall(struct cache_detail *cd, struct cache_head *ch) +{ + return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request); +} + static int idtoname_match(struct cache_head *ca, struct cache_head *cb) { @@ -192,7 +198,7 @@ static struct cache_detail idtoname_cache = { .hash_table = idtoname_table, .name = "nfs4.idtoname", .cache_put = ent_put, - .cache_request = idtoname_request, + .cache_upcall = idtoname_upcall, .cache_parse = idtoname_parse, .cache_show = idtoname_show, .warn_no_listener = warn_no_idmapd, @@ -324,6 +330,12 @@ nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, (*bpp)[-1] = '\n'; } +static int +nametoid_upcall(struct cache_detail *cd, struct cache_head *ch) +{ + return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request); +} + static int nametoid_match(struct cache_head *ca, struct cache_head *cb) { @@ -363,7 +375,7 @@ static struct cache_detail nametoid_cache = { .hash_table = nametoid_table, .name = "nfs4.nametoid", .cache_put = ent_put, - .cache_request = nametoid_request, + .cache_upcall = nametoid_upcall, .cache_parse = nametoid_parse, .cache_show = nametoid_show, .warn_no_listener = warn_no_idmapd, diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 3d1fad22185a..23ee25981a0c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -70,9 +70,9 @@ struct cache_detail { char *name; void (*cache_put)(struct kref *); - void (*cache_request)(struct cache_detail *cd, - struct cache_head *h, - char **bpp, int *blen); + int (*cache_upcall)(struct cache_detail *, + struct cache_head *); + int (*cache_parse)(struct cache_detail *, char *buf, int len); @@ -135,6 +135,13 @@ extern struct cache_head * sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); +extern int +sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)); + extern void cache_clean_deferred(void *owner); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 2278a50c6444..2e6a148d277c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, rsi_request); +} + static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) @@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = { .hash_table = rsi_table, .name = "auth.rpcsec.init", .cache_put = rsi_put, - .cache_request = rsi_request, + .cache_upcall = rsi_upcall, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index c8e7d2d07260..e438352bed7b 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -176,7 +176,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, } EXPORT_SYMBOL_GPL(sunrpc_cache_update); -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h); +static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h) +{ + if (!cd->cache_upcall) + return -EINVAL; + return cd->cache_upcall(cd, h); +} + /* * This is the generic cache management routine for all * the authentication caches. @@ -322,7 +328,7 @@ static int create_cache_proc_entries(struct cache_detail *cd) if (p == NULL) goto out_nomem; - if (cd->cache_request || cd->cache_parse) { + if (cd->cache_upcall || cd->cache_parse) { p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, cd->proc_ent, &cache_file_operations, cd); cd->channel_ent = p; @@ -1080,10 +1086,16 @@ static void warn_no_listener(struct cache_detail *detail) } /* - * register an upcall request to user-space. + * register an upcall request to user-space and queue it up for read() by the + * upcall daemon. + * * Each request is at most one page long. */ -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) +int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)) { char *buf; @@ -1091,9 +1103,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) char *bp; int len; - if (detail->cache_request == NULL) - return -EINVAL; - if (atomic_read(&detail->readers) == 0 && detail->last_close < get_seconds() - 30) { warn_no_listener(detail); @@ -1112,7 +1121,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) bp = buf; len = PAGE_SIZE; - detail->cache_request(detail, h, &bp, &len); + cache_request(detail, h, &bp, &len); if (len < 0) { kfree(buf); @@ -1130,6 +1139,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) wake_up(&queue_wait); return 0; } +EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); /* * parse a message from user-space and pass it diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 5c865e2d299e..6caffa34ac01 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -171,6 +171,11 @@ static void ip_map_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, ip_map_request); +} + static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr); static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry); @@ -289,7 +294,7 @@ struct cache_detail ip_map_cache = { .hash_table = ip_table, .name = "auth.unix.ip", .cache_put = ip_map_put, - .cache_request = ip_map_request, + .cache_upcall = ip_map_upcall, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, @@ -523,6 +528,11 @@ static void unix_gid_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request); +} + static struct unix_gid *unix_gid_lookup(uid_t uid); extern struct cache_detail unix_gid_cache; @@ -622,7 +632,7 @@ struct cache_detail unix_gid_cache = { .hash_table = gid_table, .name = "auth.unix.gid", .cache_put = unix_gid_put, - .cache_request = unix_gid_request, + .cache_upcall = unix_gid_upcall, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, From 173912a6add00f4715774dcecf9ee53274c5924c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:29 -0400 Subject: [PATCH 48/87] SUNRPC: Move procfs-specific stuff out of the generic sunrpc cache code Signed-off-by: Trond Myklebust --- include/linux/sunrpc/cache.h | 11 +- net/sunrpc/cache.c | 321 +++++++++++++++++++++-------------- 2 files changed, 200 insertions(+), 132 deletions(-) diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 23ee25981a0c..8e5bf3036652 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -59,6 +59,11 @@ struct cache_head { #define CACHE_NEW_EXPIRY 120 /* keep new things pending confirmation for 120 seconds */ +struct cache_detail_procfs { + struct proc_dir_entry *proc_ent; + struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; +}; + struct cache_detail { struct module * owner; int hash_size; @@ -98,12 +103,14 @@ struct cache_detail { /* fields for communication over channel */ struct list_head queue; - struct proc_dir_entry *proc_ent; - struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; atomic_t readers; /* how many time is /chennel open */ time_t last_close; /* if no readers, when did last close */ time_t last_warn; /* when we last warned about no readers */ + + union { + struct cache_detail_procfs procfs; + } u; }; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index e438352bed7b..1cd82eda56d0 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -291,69 +291,9 @@ static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; -static const struct file_operations cache_file_operations; -static const struct file_operations content_file_operations; -static const struct file_operations cache_flush_operations; - static void do_cache_clean(struct work_struct *work); static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean); -static void remove_cache_proc_entries(struct cache_detail *cd) -{ - if (cd->proc_ent == NULL) - return; - if (cd->flush_ent) - remove_proc_entry("flush", cd->proc_ent); - if (cd->channel_ent) - remove_proc_entry("channel", cd->proc_ent); - if (cd->content_ent) - remove_proc_entry("content", cd->proc_ent); - cd->proc_ent = NULL; - remove_proc_entry(cd->name, proc_net_rpc); -} - -#ifdef CONFIG_PROC_FS -static int create_cache_proc_entries(struct cache_detail *cd) -{ - struct proc_dir_entry *p; - - cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc); - if (cd->proc_ent == NULL) - goto out_nomem; - cd->channel_ent = cd->content_ent = NULL; - - p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_flush_operations, cd); - cd->flush_ent = p; - if (p == NULL) - goto out_nomem; - - if (cd->cache_upcall || cd->cache_parse) { - p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_file_operations, cd); - cd->channel_ent = p; - if (p == NULL) - goto out_nomem; - } - if (cd->cache_show) { - p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &content_file_operations, cd); - cd->content_ent = p; - if (p == NULL) - goto out_nomem; - } - return 0; -out_nomem: - remove_cache_proc_entries(cd); - return -ENOMEM; -} -#else /* CONFIG_PROC_FS */ -static int create_cache_proc_entries(struct cache_detail *cd) -{ - return 0; -} -#endif - static void sunrpc_init_cache_detail(struct cache_detail *cd) { rwlock_init(&cd->hash_lock); @@ -395,25 +335,6 @@ out: printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); } -int cache_register(struct cache_detail *cd) -{ - int ret; - - sunrpc_init_cache_detail(cd); - ret = create_cache_proc_entries(cd); - if (ret) - sunrpc_destroy_cache_detail(cd); - return ret; -} -EXPORT_SYMBOL_GPL(cache_register); - -void cache_unregister(struct cache_detail *cd) -{ - remove_cache_proc_entries(cd); - sunrpc_destroy_cache_detail(cd); -} -EXPORT_SYMBOL_GPL(cache_unregister); - /* clean cache tries to find something to clean * and cleans it. * It returns 1 if it cleaned something, @@ -704,13 +625,12 @@ struct cache_reader { int offset; /* if non-0, we have a refcnt on next request */ }; -static ssize_t -cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, + loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; struct inode *inode = filp->f_path.dentry->d_inode; - struct cache_detail *cd = PDE(inode)->data; int err; if (count == 0) @@ -834,13 +754,12 @@ out_slow: return cache_slow_downcall(buf, count, cd); } -static ssize_t -cache_write(struct file *filp, const char __user *buf, size_t count, - loff_t *ppos) +static ssize_t cache_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) { struct address_space *mapping = filp->f_mapping; struct inode *inode = filp->f_path.dentry->d_inode; - struct cache_detail *cd = PDE(inode)->data; ssize_t ret = -EINVAL; if (!cd->cache_parse) @@ -855,13 +774,12 @@ out: static DECLARE_WAIT_QUEUE_HEAD(queue_wait); -static unsigned int -cache_poll(struct file *filp, poll_table *wait) +static unsigned int cache_poll(struct file *filp, poll_table *wait, + struct cache_detail *cd) { unsigned int mask; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; poll_wait(filp, &queue_wait, wait); @@ -883,14 +801,13 @@ cache_poll(struct file *filp, poll_table *wait) return mask; } -static int -cache_ioctl(struct inode *ino, struct file *filp, - unsigned int cmd, unsigned long arg) +static int cache_ioctl(struct inode *ino, struct file *filp, + unsigned int cmd, unsigned long arg, + struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(ino)->data; if (cmd != FIONREAD || !rp) return -EINVAL; @@ -913,15 +830,13 @@ cache_ioctl(struct inode *ino, struct file *filp, return put_user(len, (int __user *)arg); } -static int -cache_open(struct inode *inode, struct file *filp) +static int cache_open(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = NULL; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { - struct cache_detail *cd = PDE(inode)->data; - rp = kmalloc(sizeof(*rp), GFP_KERNEL); if (!rp) return -ENOMEM; @@ -936,11 +851,10 @@ cache_open(struct inode *inode, struct file *filp) return 0; } -static int -cache_release(struct inode *inode, struct file *filp) +static int cache_release(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; - struct cache_detail *cd = PDE(inode)->data; if (rp) { spin_lock(&queue_lock); @@ -969,18 +883,6 @@ cache_release(struct inode *inode, struct file *filp) -static const struct file_operations cache_file_operations = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = cache_read, - .write = cache_write, - .poll = cache_poll, - .ioctl = cache_ioctl, /* for FIONREAD */ - .open = cache_open, - .release = cache_release, -}; - - static void queue_loose(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq; @@ -1307,10 +1209,10 @@ static const struct seq_operations cache_content_op = { .show = c_show, }; -static int content_open(struct inode *inode, struct file *file) +static int content_open(struct inode *inode, struct file *file, + struct cache_detail *cd) { struct handle *han; - struct cache_detail *cd = PDE(inode)->data; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); if (han == NULL) @@ -1320,17 +1222,10 @@ static int content_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations content_file_operations = { - .open = content_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; - static ssize_t read_flush(struct file *file, char __user *buf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; unsigned long p = *ppos; size_t len; @@ -1348,10 +1243,10 @@ static ssize_t read_flush(struct file *file, char __user *buf, return len; } -static ssize_t write_flush(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t write_flush(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; char *ep; long flushtime; @@ -1372,8 +1267,174 @@ static ssize_t write_flush(struct file * file, const char __user * buf, return count; } -static const struct file_operations cache_flush_operations = { - .open = nonseekable_open, - .read = read_flush, - .write = write_flush, +static ssize_t cache_read_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_procfs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_open(inode, filp, cd); +} + +static int cache_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_release(inode, filp, cd); +} + +static const struct file_operations cache_file_operations_procfs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_procfs, + .write = cache_write_procfs, + .poll = cache_poll_procfs, + .ioctl = cache_ioctl_procfs, /* for FIONREAD */ + .open = cache_open_procfs, + .release = cache_release_procfs, }; + +static int content_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_open(inode, filp, cd); +} + +static const struct file_operations content_file_operations_procfs = { + .open = content_open_procfs, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static ssize_t read_flush_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_procfs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return write_flush(filp, buf, count, ppos, cd); +} + +static const struct file_operations cache_flush_operations_procfs = { + .open = nonseekable_open, + .read = read_flush_procfs, + .write = write_flush_procfs, +}; + +static void remove_cache_proc_entries(struct cache_detail *cd) +{ + if (cd->u.procfs.proc_ent == NULL) + return; + if (cd->u.procfs.flush_ent) + remove_proc_entry("flush", cd->u.procfs.proc_ent); + if (cd->u.procfs.channel_ent) + remove_proc_entry("channel", cd->u.procfs.proc_ent); + if (cd->u.procfs.content_ent) + remove_proc_entry("content", cd->u.procfs.proc_ent); + cd->u.procfs.proc_ent = NULL; + remove_proc_entry(cd->name, proc_net_rpc); +} + +#ifdef CONFIG_PROC_FS +static int create_cache_proc_entries(struct cache_detail *cd) +{ + struct proc_dir_entry *p; + + cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc); + if (cd->u.procfs.proc_ent == NULL) + goto out_nomem; + cd->u.procfs.channel_ent = NULL; + cd->u.procfs.content_ent = NULL; + + p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_flush_operations_procfs, cd); + cd->u.procfs.flush_ent = p; + if (p == NULL) + goto out_nomem; + + if (cd->cache_upcall || cd->cache_parse) { + p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_file_operations_procfs, cd); + cd->u.procfs.channel_ent = p; + if (p == NULL) + goto out_nomem; + } + if (cd->cache_show) { + p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &content_file_operations_procfs, cd); + cd->u.procfs.content_ent = p; + if (p == NULL) + goto out_nomem; + } + return 0; +out_nomem: + remove_cache_proc_entries(cd); + return -ENOMEM; +} +#else /* CONFIG_PROC_FS */ +static int create_cache_proc_entries(struct cache_detail *cd) +{ + return 0; +} +#endif + +int cache_register(struct cache_detail *cd) +{ + int ret; + + sunrpc_init_cache_detail(cd); + ret = create_cache_proc_entries(cd); + if (ret) + sunrpc_destroy_cache_detail(cd); + return ret; +} +EXPORT_SYMBOL_GPL(cache_register); + +void cache_unregister(struct cache_detail *cd) +{ + remove_cache_proc_entries(cd); + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(cache_unregister); From 8854e82d9accc80f43c0bc3ff06b5979ac858185 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Aug 2009 15:14:30 -0400 Subject: [PATCH 49/87] SUNRPC: Add an rpc_pipefs front end for the sunrpc cache code Signed-off-by: Trond Myklebust --- include/linux/sunrpc/cache.h | 13 +++ include/linux/sunrpc/rpc_pipe_fs.h | 8 ++ net/sunrpc/cache.c | 126 +++++++++++++++++++++++++++++ net/sunrpc/rpc_pipe.c | 43 ++++++++++ 4 files changed, 190 insertions(+) diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 8e5bf3036652..6f52b4d7c447 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -64,6 +64,10 @@ struct cache_detail_procfs { struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; }; +struct cache_detail_pipefs { + struct dentry *dir; +}; + struct cache_detail { struct module * owner; int hash_size; @@ -110,6 +114,7 @@ struct cache_detail { union { struct cache_detail_procfs procfs; + struct cache_detail_pipefs pipefs; } u; }; @@ -135,6 +140,10 @@ struct cache_deferred_req { }; +extern const struct file_operations cache_file_operations_pipefs; +extern const struct file_operations content_file_operations_pipefs; +extern const struct file_operations cache_flush_operations_pipefs; + extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash); @@ -186,6 +195,10 @@ extern void cache_purge(struct cache_detail *detail); extern int cache_register(struct cache_detail *cd); extern void cache_unregister(struct cache_detail *cd); +extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *, + mode_t, struct cache_detail *); +extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); + extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); extern int qword_get(char **bpp, char *dest, int bufsize); diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 88332ef1e959..a92571a34556 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -47,6 +47,14 @@ extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); struct rpc_clnt; extern struct dentry *rpc_create_client_dir(struct dentry *, struct qstr *, struct rpc_clnt *); extern int rpc_remove_client_dir(struct dentry *); + +struct cache_detail; +extern struct dentry *rpc_create_cache_dir(struct dentry *, + struct qstr *, + mode_t umode, + struct cache_detail *); +extern void rpc_remove_cache_dir(struct dentry *); + extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, const struct rpc_pipe_ops *, int flags); extern int rpc_unlink(struct dentry *); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 1cd82eda56d0..db7720e453c3 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -32,6 +32,7 @@ #include #include #include +#include #define RPCDBG_FACILITY RPCDBG_CACHE @@ -1438,3 +1439,128 @@ void cache_unregister(struct cache_detail *cd) sunrpc_destroy_cache_detail(cd); } EXPORT_SYMBOL_GPL(cache_unregister); + +static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_pipefs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_open(inode, filp, cd); +} + +static int cache_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_release(inode, filp, cd); +} + +const struct file_operations cache_file_operations_pipefs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_pipefs, + .write = cache_write_pipefs, + .poll = cache_poll_pipefs, + .ioctl = cache_ioctl_pipefs, /* for FIONREAD */ + .open = cache_open_pipefs, + .release = cache_release_pipefs, +}; + +static int content_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_open(inode, filp, cd); +} + +const struct file_operations content_file_operations_pipefs = { + .open = content_open_pipefs, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_pipefs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return write_flush(filp, buf, count, ppos, cd); +} + +const struct file_operations cache_flush_operations_pipefs = { + .open = nonseekable_open, + .read = read_flush_pipefs, + .write = write_flush_pipefs, +}; + +int sunrpc_cache_register_pipefs(struct dentry *parent, + const char *name, mode_t umode, + struct cache_detail *cd) +{ + struct qstr q; + struct dentry *dir; + int ret = 0; + + sunrpc_init_cache_detail(cd); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len); + dir = rpc_create_cache_dir(parent, &q, umode, cd); + if (!IS_ERR(dir)) + cd->u.pipefs.dir = dir; + else { + sunrpc_destroy_cache_detail(cd); + ret = PTR_ERR(dir); + } + return ret; +} +EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); + +void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) +{ + rpc_remove_cache_dir(cd->u.pipefs.dir); + cd->u.pipefs.dir = NULL; + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); + diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 57e9cd3c49b6..8dd81535e08f 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -26,6 +26,7 @@ #include #include #include +#include static struct vfsmount *rpc_mount __read_mostly; static int rpc_mount_count; @@ -882,6 +883,48 @@ int rpc_remove_client_dir(struct dentry *dentry) return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); } +static const struct rpc_filelist cache_pipefs_files[3] = { + [0] = { + .name = "channel", + .i_fop = &cache_file_operations_pipefs, + .mode = S_IFIFO|S_IRUSR|S_IWUSR, + }, + [1] = { + .name = "content", + .i_fop = &content_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR, + }, + [2] = { + .name = "flush", + .i_fop = &cache_flush_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, +}; + +static int rpc_cachedir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + cache_pipefs_files, 0, 3, + private); +} + +static void rpc_cachedir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, cache_pipefs_files, 0, 3); +} + +struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name, + mode_t umode, struct cache_detail *cd) +{ + return rpc_mkdir_populate(parent, name, umode, NULL, + rpc_cachedir_populate, cd); +} + +void rpc_remove_cache_dir(struct dentry *dentry) +{ + rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate); +} + /* * populate the filesystem */ From 074cc1deec5dee63fcd5d966b36fa4f3765b50fc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 10 Aug 2009 08:54:13 -0400 Subject: [PATCH 50/87] NFS: Add a ->migratepage() aop for NFS Make NFS a bit more friendly to NUMA and memory hot removal... Signed-off-by: Trond Myklebust --- fs/nfs/file.c | 1 + fs/nfs/internal.h | 6 ++++ fs/nfs/write.c | 91 +++++++++++++++++++++++++++++++++++------------ 3 files changed, 76 insertions(+), 22 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 05062329b678..dfc89671dc94 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -479,6 +479,7 @@ const struct address_space_operations nfs_file_aops = { .invalidatepage = nfs_invalidate_page, .releasepage = nfs_release_page, .direct_IO = nfs_direct_IO, + .migratepage = nfs_migrate_page, .launder_page = nfs_launder_page, }; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7dd90a6769d0..e2ccb4a4398a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -248,6 +248,12 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); /* write.c */ extern void nfs_write_prepare(struct rpc_task *task, void *calldata); +#ifdef CONFIG_MIGRATION +extern int nfs_migrate_page(struct address_space *, + struct page *, struct page *); +#else +#define nfs_migrate_page NULL +#endif /* nfs4proc.c */ extern int _nfs4_call_sync(struct nfs_server *server, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 0a0a2ff767c3..6240e644f249 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -26,6 +27,7 @@ #include "internal.h" #include "iostat.h" #include "nfs4_fs.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -220,24 +222,17 @@ static void nfs_end_page_writeback(struct page *page) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } -/* - * Find an associated nfs write request, and prepare to flush it out - * May return an error if the user signalled nfs_wait_on_request(). - */ -static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page) +static struct nfs_page *nfs_find_and_lock_request(struct page *page) { struct inode *inode = page->mapping->host; struct nfs_page *req; int ret; spin_lock(&inode->i_lock); - for(;;) { + for (;;) { req = nfs_page_find_request_locked(page); - if (req == NULL) { - spin_unlock(&inode->i_lock); - return 0; - } + if (req == NULL) + break; if (nfs_set_page_tag_locked(req)) break; /* Note: If we hold the page lock, as is the case in nfs_writepage, @@ -249,23 +244,40 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, ret = nfs_wait_on_request(req); nfs_release_request(req); if (ret != 0) - return ret; + return ERR_PTR(ret); spin_lock(&inode->i_lock); } - if (test_bit(PG_CLEAN, &req->wb_flags)) { - spin_unlock(&inode->i_lock); - BUG(); - } - if (nfs_set_page_writeback(page) != 0) { - spin_unlock(&inode->i_lock); - BUG(); - } spin_unlock(&inode->i_lock); + return req; +} + +/* + * Find an associated nfs write request, and prepare to flush it out + * May return an error if the user signalled nfs_wait_on_request(). + */ +static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, + struct page *page) +{ + struct nfs_page *req; + int ret = 0; + + req = nfs_find_and_lock_request(page); + if (!req) + goto out; + ret = PTR_ERR(req); + if (IS_ERR(req)) + goto out; + + ret = nfs_set_page_writeback(page); + BUG_ON(ret != 0); + BUG_ON(test_bit(PG_CLEAN, &req->wb_flags)); + if (!nfs_pageio_add_request(pgio, req)) { nfs_redirty_request(req); - return pgio->pg_error; + ret = pgio->pg_error; } - return 0; +out: + return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) @@ -1582,6 +1594,41 @@ int nfs_wb_page(struct inode *inode, struct page* page) return nfs_wb_page_priority(inode, page, FLUSH_STABLE); } +#ifdef CONFIG_MIGRATION +int nfs_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page) +{ + struct nfs_page *req; + int ret; + + if (PageFsCache(page)) + nfs_fscache_release_page(page, GFP_KERNEL); + + req = nfs_find_and_lock_request(page); + ret = PTR_ERR(req); + if (IS_ERR(req)) + goto out; + + ret = migrate_page(mapping, newpage, page); + if (!req) + goto out; + if (ret) + goto out_unlock; + page_cache_get(newpage); + req->wb_page = newpage; + SetPagePrivate(newpage); + set_page_private(newpage, page_private(page)); + ClearPagePrivate(page); + set_page_private(page, 0); + page_cache_release(page); +out_unlock: + nfs_clear_page_tag_locked(req); + nfs_release_request(req); +out: + return ret; +} +#endif + int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", From 38c73044f5f4da2ef4339319b170e5e19f8dec87 Mon Sep 17 00:00:00 2001 From: Peter Staubach Date: Mon, 10 Aug 2009 08:54:16 -0400 Subject: [PATCH 51/87] NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach Signed-off-by: Trond Myklebust --- fs/nfs/file.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index dfc89671dc94..5021b75d2d1e 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -327,6 +327,42 @@ nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync) return nfs_do_fsync(ctx, inode); } +/* + * Decide whether a read/modify/write cycle may be more efficient + * then a modify/write/read cycle when writing to a page in the + * page cache. + * + * The modify/write/read cycle may occur if a page is read before + * being completely filled by the writer. In this situation, the + * page must be completely written to stable storage on the server + * before it can be refilled by reading in the page from the server. + * This can lead to expensive, small, FILE_SYNC mode writes being + * done. + * + * It may be more efficient to read the page first if the file is + * open for reading in addition to writing, the page is not marked + * as Uptodate, it is not dirty or waiting to be committed, + * indicating that it was previously allocated and then modified, + * that there were valid bytes of data in that range of the file, + * and that the new data won't completely replace the old data in + * that range of the file. + */ +static int nfs_want_read_modify_write(struct file *file, struct page *page, + loff_t pos, unsigned len) +{ + unsigned int pglen = nfs_page_length(page); + unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned int end = offset + len; + + if ((file->f_mode & FMODE_READ) && /* open for read? */ + !PageUptodate(page) && /* Uptodate? */ + !PagePrivate(page) && /* i/o request already? */ + pglen && /* valid bytes of file? */ + (end < pglen || offset)) /* replace all valid bytes? */ + return 1; + return 0; +} + /* * This does the "real" work of the write. We must allocate and lock the * page to be sent back to the generic routine, which then copies the @@ -340,15 +376,16 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { int ret; - pgoff_t index; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; struct page *page; - index = pos >> PAGE_CACHE_SHIFT; + int once_thru = 0; dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, mapping->host->i_ino, len, (long long) pos); +start: /* * Prevent starvation issues if someone is doing a consistency * sync-to-disk @@ -367,6 +404,13 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, if (ret) { unlock_page(page); page_cache_release(page); + } else if (!once_thru && + nfs_want_read_modify_write(file, page, pos, len)) { + once_thru = 1; + ret = nfs_readpage(file, page); + page_cache_release(page); + if (!ret) + goto start; } return ret; } From e576e05a73bc1a00cdf56630942dbada1bf280a1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Mon, 10 Aug 2009 08:54:16 -0400 Subject: [PATCH 52/87] nfs: remove superfluous BUG_ON()s Subject: [PATCH] nfs: remove superfluous BUG_ON()s Remove duplicated BUG_ON()s from nfs[4]_create_server() (we make the same checks earlier in both functions). This takes care of the following entries from Dan's list: fs/nfs/client.c +1078 nfs_create_server(47) warning: variable derefenced before check 'server->nfs_client' fs/nfs/client.c +1079 nfs_create_server(48) warning: variable derefenced before check 'server->nfs_client->rpc_ops' fs/nfs/client.c +1363 nfs4_create_server(43) warning: variable derefenced before check 'server->nfs_client' fs/nfs/client.c +1364 nfs4_create_server(44) warning: variable derefenced before check 'server->nfs_ Reported-by: Dan Carpenter Cc: corbet@lwn.net Cc: eteo@redhat.com Cc: Julia Lawall Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8f34fd8028fc..d36925f9b952 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1077,10 +1077,6 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, (unsigned long long) server->fsid.major, (unsigned long long) server->fsid.minor); - BUG_ON(!server->nfs_client); - BUG_ON(!server->nfs_client->rpc_ops); - BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); - spin_lock(&nfs_client_lock); list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks); list_add_tail(&server->master_link, &nfs_volume_list); @@ -1362,10 +1358,6 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) server->namelen = NFS4_MAXNAMLEN; - BUG_ON(!server->nfs_client); - BUG_ON(!server->nfs_client->rpc_ops); - BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); - spin_lock(&nfs_client_lock); list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks); list_add_tail(&server->master_link, &nfs_volume_list); From 9f162d2a810b4db48f7b8d7e734d0932c81ec2a1 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:18:44 +0300 Subject: [PATCH 53/87] sunrpc: hton -> cpu_to_be* htonl is already defined as cpu_to_be32. cpu_to_be64 has architecture specific optimized implementations. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 5 ++--- net/sunrpc/xdr.c | 6 +++--- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index b99c625fddfe..f94bbdc75c4b 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -117,9 +117,8 @@ static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int le static inline __be32 * xdr_encode_hyper(__be32 *p, __u64 val) { - *p++ = htonl(val >> 32); - *p++ = htonl(val & 0xFFFFFFFF); - return p; + *(__be64 *)p = cpu_to_be64(val); + return p + 2; } static inline __be32 * diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 406e26de584e..0d05d2554b42 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -24,7 +24,7 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) unsigned int quadlen = XDR_QUADLEN(obj->len); p[quadlen] = 0; /* zero trailing bytes */ - *p++ = htonl(obj->len); + *p++ = cpu_to_be32(obj->len); memcpy(p, obj->data, obj->len); return p + XDR_QUADLEN(obj->len); } @@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed); */ __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes) { - *p++ = htonl(nbytes); + *p++ = cpu_to_be32(nbytes); return xdr_encode_opaque_fixed(p, ptr, nbytes); } EXPORT_SYMBOL_GPL(xdr_encode_opaque); @@ -779,7 +779,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_word); int xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) { - __be32 raw = htonl(obj); + __be32 raw = cpu_to_be32(obj); return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj)); } From 98866b5abe1513cdacc011874ca045d40002eccd Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:18:49 +0300 Subject: [PATCH 54/87] sunrpc: ntoh -> be*_to_cpu ntohl is already defined as be32_to_cpu. be64_to_cpu has architecture specific optimized implementations. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 5 ++--- net/sunrpc/xdr.c | 6 +++--- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f94bbdc75c4b..7da466ba4b0d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -124,9 +124,8 @@ xdr_encode_hyper(__be32 *p, __u64 val) static inline __be32 * xdr_decode_hyper(__be32 *p, __u64 *valp) { - *valp = ((__u64) ntohl(*p++)) << 32; - *valp |= ntohl(*p++); - return p; + *valp = be64_to_cpup((__be64 *)p); + return p + 2; } /* diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 0d05d2554b42..8bd690c48b69 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -35,7 +35,7 @@ xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) { unsigned int len; - if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ) + if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ) return NULL; obj->len = len; obj->data = (u8 *) p; @@ -101,7 +101,7 @@ xdr_decode_string_inplace(__be32 *p, char **sp, { u32 len; - len = ntohl(*p++); + len = be32_to_cpu(*p++); if (len > maxlen) return NULL; *lenp = len; @@ -771,7 +771,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj) status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); if (status) return status; - *obj = ntohl(raw); + *obj = be32_to_cpu(raw); return 0; } EXPORT_SYMBOL_GPL(xdr_decode_word); From e75bc1c89e0c7dda0b140408ddee2ffaef7ba6d4 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:18:54 +0300 Subject: [PATCH 55/87] nfs: nfs4xdr: get rid of WRITE32 s/WRITE32/*p++ = cpu_to_be32/ Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 291 +++++++++++++++++++++++------------------------ 1 file changed, 145 insertions(+), 146 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 617273e7d47f..9a03b24ead5f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -712,7 +712,6 @@ struct compound_hdr { * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define WRITE32(n) *p++ = htonl(n) #define WRITE64(n) do { \ *p++ = htonl((uint32_t)((n) >> 32)); \ *p++ = htonl((uint32_t)(n)); \ @@ -750,11 +749,11 @@ static void encode_compound_hdr(struct xdr_stream *xdr, dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag); BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); RESERVE_SPACE(12+(XDR_QUADLEN(hdr->taglen)<<2)); - WRITE32(hdr->taglen); + *p++ = cpu_to_be32(hdr->taglen); WRITEMEM(hdr->tag, hdr->taglen); - WRITE32(hdr->minorversion); + *p++ = cpu_to_be32(hdr->minorversion); hdr->nops_p = p; - WRITE32(hdr->nops); + *p++ = cpu_to_be32(hdr->nops); } static void encode_nops(struct compound_hdr *hdr) @@ -835,7 +834,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const * We write the bitmap length now, but leave the bitmap and the attribute * buffer length to be backfilled at the end of this routine. */ - WRITE32(2); + *p++ = cpu_to_be32(2); q = p; p += 3; @@ -845,39 +844,39 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const } if (iap->ia_valid & ATTR_MODE) { bmval1 |= FATTR4_WORD1_MODE; - WRITE32(iap->ia_mode & S_IALLUGO); + *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO); } if (iap->ia_valid & ATTR_UID) { bmval1 |= FATTR4_WORD1_OWNER; - WRITE32(owner_namelen); + *p++ = cpu_to_be32(owner_namelen); WRITEMEM(owner_name, owner_namelen); } if (iap->ia_valid & ATTR_GID) { bmval1 |= FATTR4_WORD1_OWNER_GROUP; - WRITE32(owner_grouplen); + *p++ = cpu_to_be32(owner_grouplen); WRITEMEM(owner_group, owner_grouplen); } if (iap->ia_valid & ATTR_ATIME_SET) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - WRITE32(NFS4_SET_TO_CLIENT_TIME); - WRITE32(0); - WRITE32(iap->ia_mtime.tv_sec); - WRITE32(iap->ia_mtime.tv_nsec); + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); } else if (iap->ia_valid & ATTR_ATIME) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - WRITE32(NFS4_SET_TO_SERVER_TIME); + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } if (iap->ia_valid & ATTR_MTIME_SET) { bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - WRITE32(NFS4_SET_TO_CLIENT_TIME); - WRITE32(0); - WRITE32(iap->ia_mtime.tv_sec); - WRITE32(iap->ia_mtime.tv_nsec); + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); } else if (iap->ia_valid & ATTR_MTIME) { bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - WRITE32(NFS4_SET_TO_SERVER_TIME); + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } /* @@ -901,8 +900,8 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd __be32 *p; RESERVE_SPACE(8); - WRITE32(OP_ACCESS); - WRITE32(access); + *p++ = cpu_to_be32(OP_ACCESS); + *p++ = cpu_to_be32(access); hdr->nops++; hdr->replen += decode_access_maxsz; } @@ -912,8 +911,8 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg __be32 *p; RESERVE_SPACE(8+NFS4_STATEID_SIZE); - WRITE32(OP_CLOSE); - WRITE32(arg->seqid->sequence->counter); + *p++ = cpu_to_be32(OP_CLOSE); + *p++ = cpu_to_be32(arg->seqid->sequence->counter); WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_close_maxsz; @@ -924,9 +923,9 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar __be32 *p; RESERVE_SPACE(16); - WRITE32(OP_COMMIT); + *p++ = cpu_to_be32(OP_COMMIT); WRITE64(args->offset); - WRITE32(args->count); + *p++ = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_commit_maxsz; } @@ -936,20 +935,20 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * __be32 *p; RESERVE_SPACE(8); - WRITE32(OP_CREATE); - WRITE32(create->ftype); + *p++ = cpu_to_be32(OP_CREATE); + *p++ = cpu_to_be32(create->ftype); switch (create->ftype) { case NF4LNK: RESERVE_SPACE(4); - WRITE32(create->u.symlink.len); + *p++ = cpu_to_be32(create->u.symlink.len); xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len); break; case NF4BLK: case NF4CHR: RESERVE_SPACE(8); - WRITE32(create->u.device.specdata1); - WRITE32(create->u.device.specdata2); + *p++ = cpu_to_be32(create->u.device.specdata1); + *p++ = cpu_to_be32(create->u.device.specdata2); break; default: @@ -957,7 +956,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * } RESERVE_SPACE(4 + create->name->len); - WRITE32(create->name->len); + *p++ = cpu_to_be32(create->name->len); WRITEMEM(create->name->name, create->name->len); hdr->nops++; hdr->replen += decode_create_maxsz; @@ -970,9 +969,9 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c __be32 *p; RESERVE_SPACE(12); - WRITE32(OP_GETATTR); - WRITE32(1); - WRITE32(bitmap); + *p++ = cpu_to_be32(OP_GETATTR); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(bitmap); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -982,10 +981,10 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm __be32 *p; RESERVE_SPACE(16); - WRITE32(OP_GETATTR); - WRITE32(2); - WRITE32(bm0); - WRITE32(bm1); + *p++ = cpu_to_be32(OP_GETATTR); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p++ = cpu_to_be32(bm1); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -1013,7 +1012,7 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_GETFH); + *p++ = cpu_to_be32(OP_GETFH); hdr->nops++; hdr->replen += decode_getfh_maxsz; } @@ -1023,8 +1022,8 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct __be32 *p; RESERVE_SPACE(8 + name->len); - WRITE32(OP_LINK); - WRITE32(name->len); + *p++ = cpu_to_be32(OP_LINK); + *p++ = cpu_to_be32(name->len); WRITEMEM(name->name, name->len); hdr->nops++; hdr->replen += decode_link_maxsz; @@ -1053,26 +1052,26 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args __be32 *p; RESERVE_SPACE(32); - WRITE32(OP_LOCK); - WRITE32(nfs4_lock_type(args->fl, args->block)); - WRITE32(args->reclaim); + *p++ = cpu_to_be32(OP_LOCK); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block)); + *p++ = cpu_to_be32(args->reclaim); WRITE64(args->fl->fl_start); WRITE64(nfs4_lock_length(args->fl)); - WRITE32(args->new_lock_owner); + *p++ = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ RESERVE_SPACE(4+NFS4_STATEID_SIZE+32); - WRITE32(args->open_seqid->sequence->counter); + *p++ = cpu_to_be32(args->open_seqid->sequence->counter); WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE); - WRITE32(args->lock_seqid->sequence->counter); + *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); WRITE64(args->lock_owner.clientid); - WRITE32(16); + *p++ = cpu_to_be32(16); WRITEMEM("lock id:", 8); WRITE64(args->lock_owner.id); } else { RESERVE_SPACE(NFS4_STATEID_SIZE+4); WRITEMEM(args->lock_stateid->data, NFS4_STATEID_SIZE); - WRITE32(args->lock_seqid->sequence->counter); + *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); } hdr->nops++; hdr->replen += decode_lock_maxsz; @@ -1083,12 +1082,12 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar __be32 *p; RESERVE_SPACE(52); - WRITE32(OP_LOCKT); - WRITE32(nfs4_lock_type(args->fl, 0)); + *p++ = cpu_to_be32(OP_LOCKT); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); WRITE64(args->fl->fl_start); WRITE64(nfs4_lock_length(args->fl)); WRITE64(args->lock_owner.clientid); - WRITE32(16); + *p++ = cpu_to_be32(16); WRITEMEM("lock id:", 8); WRITE64(args->lock_owner.id); hdr->nops++; @@ -1100,9 +1099,9 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar __be32 *p; RESERVE_SPACE(12+NFS4_STATEID_SIZE+16); - WRITE32(OP_LOCKU); - WRITE32(nfs4_lock_type(args->fl, 0)); - WRITE32(args->seqid->sequence->counter); + *p++ = cpu_to_be32(OP_LOCKU); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); + *p++ = cpu_to_be32(args->seqid->sequence->counter); WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE); WRITE64(args->fl->fl_start); WRITE64(nfs4_lock_length(args->fl)); @@ -1116,8 +1115,8 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc __be32 *p; RESERVE_SPACE(8 + len); - WRITE32(OP_LOOKUP); - WRITE32(len); + *p++ = cpu_to_be32(OP_LOOKUP); + *p++ = cpu_to_be32(len); WRITEMEM(name->name, len); hdr->nops++; hdr->replen += decode_lookup_maxsz; @@ -1130,18 +1129,18 @@ static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) RESERVE_SPACE(8); switch (fmode & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ: - WRITE32(NFS4_SHARE_ACCESS_READ); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ); break; case FMODE_WRITE: - WRITE32(NFS4_SHARE_ACCESS_WRITE); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE); break; case FMODE_READ|FMODE_WRITE: - WRITE32(NFS4_SHARE_ACCESS_BOTH); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH); break; default: - WRITE32(0); + *p++ = cpu_to_be32(0); } - WRITE32(0); /* for linux, share_deny = 0 always */ + *p++ = cpu_to_be32(0); /* for linux, share_deny = 0 always */ } static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1152,12 +1151,12 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena * owner 4 = 32 */ RESERVE_SPACE(8); - WRITE32(OP_OPEN); - WRITE32(arg->seqid->sequence->counter); + *p++ = cpu_to_be32(OP_OPEN); + *p++ = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); RESERVE_SPACE(28); WRITE64(arg->clientid); - WRITE32(16); + *p++ = cpu_to_be32(16); WRITEMEM("open id:", 8); WRITE64(arg->id); } @@ -1169,11 +1168,11 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op RESERVE_SPACE(4); switch(arg->open_flags & O_EXCL) { case 0: - WRITE32(NFS4_CREATE_UNCHECKED); + *p++ = cpu_to_be32(NFS4_CREATE_UNCHECKED); encode_attrs(xdr, arg->u.attrs, arg->server); break; default: - WRITE32(NFS4_CREATE_EXCLUSIVE); + *p++ = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); encode_nfs4_verifier(xdr, &arg->u.verifier); } } @@ -1185,11 +1184,11 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a RESERVE_SPACE(4); switch (arg->open_flags & O_CREAT) { case 0: - WRITE32(NFS4_OPEN_NOCREATE); + *p++ = cpu_to_be32(NFS4_OPEN_NOCREATE); break; default: BUG_ON(arg->claim != NFS4_OPEN_CLAIM_NULL); - WRITE32(NFS4_OPEN_CREATE); + *p++ = cpu_to_be32(NFS4_OPEN_CREATE); encode_createmode(xdr, arg); } } @@ -1201,13 +1200,13 @@ static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delega RESERVE_SPACE(4); switch (delegation_type) { case 0: - WRITE32(NFS4_OPEN_DELEGATE_NONE); + *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); break; case FMODE_READ: - WRITE32(NFS4_OPEN_DELEGATE_READ); + *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_READ); break; case FMODE_WRITE|FMODE_READ: - WRITE32(NFS4_OPEN_DELEGATE_WRITE); + *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE); break; default: BUG(); @@ -1219,7 +1218,7 @@ static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr * __be32 *p; RESERVE_SPACE(4); - WRITE32(NFS4_OPEN_CLAIM_NULL); + *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); encode_string(xdr, name->len, name->name); } @@ -1228,7 +1227,7 @@ static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type) __be32 *p; RESERVE_SPACE(4); - WRITE32(NFS4_OPEN_CLAIM_PREVIOUS); + *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); encode_delegation_type(xdr, type); } @@ -1237,7 +1236,7 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc __be32 *p; RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(NFS4_OPEN_CLAIM_DELEGATE_CUR); + *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); WRITEMEM(stateid->data, NFS4_STATEID_SIZE); encode_string(xdr, name->len, name->name); } @@ -1268,9 +1267,9 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co __be32 *p; RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); - WRITE32(OP_OPEN_CONFIRM); + *p++ = cpu_to_be32(OP_OPEN_CONFIRM); WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); - WRITE32(arg->seqid->sequence->counter); + *p++ = cpu_to_be32(arg->seqid->sequence->counter); hdr->nops++; hdr->replen += decode_open_confirm_maxsz; } @@ -1280,9 +1279,9 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close __be32 *p; RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); - WRITE32(OP_OPEN_DOWNGRADE); + *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE); WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); - WRITE32(arg->seqid->sequence->counter); + *p++ = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); hdr->nops++; hdr->replen += decode_open_downgrade_maxsz; @@ -1295,8 +1294,8 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd __be32 *p; RESERVE_SPACE(8 + len); - WRITE32(OP_PUTFH); - WRITE32(len); + *p++ = cpu_to_be32(OP_PUTFH); + *p++ = cpu_to_be32(len); WRITEMEM(fh->data, len); hdr->nops++; hdr->replen += decode_putfh_maxsz; @@ -1307,7 +1306,7 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_PUTROOTFH); + *p++ = cpu_to_be32(OP_PUTROOTFH); hdr->nops++; hdr->replen += decode_putrootfh_maxsz; } @@ -1330,13 +1329,13 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_READ); + *p++ = cpu_to_be32(OP_READ); encode_stateid(xdr, args->context); RESERVE_SPACE(12); WRITE64(args->offset); - WRITE32(args->count); + *p++ = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_read_maxsz; } @@ -1350,19 +1349,19 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg __be32 *p; RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20); - WRITE32(OP_READDIR); + *p++ = cpu_to_be32(OP_READDIR); WRITE64(readdir->cookie); WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE); - WRITE32(readdir->count >> 1); /* We're not doing readdirplus */ - WRITE32(readdir->count); - WRITE32(2); + *p++ = cpu_to_be32(readdir->count >> 1); /* We're not doing readdirplus */ + *p++ = cpu_to_be32(readdir->count); + *p++ = cpu_to_be32(2); /* Switch to mounted_on_fileid if the server supports it */ if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) attrs[0] &= ~FATTR4_WORD0_FILEID; else attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; - WRITE32(attrs[0] & readdir->bitmask[0]); - WRITE32(attrs[1] & readdir->bitmask[1]); + *p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]); + *p++ = cpu_to_be32(attrs[1] & readdir->bitmask[1]); hdr->nops++; hdr->replen += decode_readdir_maxsz; dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n", @@ -1379,7 +1378,7 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink * __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_READLINK); + *p++ = cpu_to_be32(OP_READLINK); hdr->nops++; hdr->replen += decode_readlink_maxsz; } @@ -1389,8 +1388,8 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc __be32 *p; RESERVE_SPACE(8 + name->len); - WRITE32(OP_REMOVE); - WRITE32(name->len); + *p++ = cpu_to_be32(OP_REMOVE); + *p++ = cpu_to_be32(name->len); WRITEMEM(name->name, name->len); hdr->nops++; hdr->replen += decode_remove_maxsz; @@ -1401,12 +1400,12 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co __be32 *p; RESERVE_SPACE(8 + oldname->len); - WRITE32(OP_RENAME); - WRITE32(oldname->len); + *p++ = cpu_to_be32(OP_RENAME); + *p++ = cpu_to_be32(oldname->len); WRITEMEM(oldname->name, oldname->len); RESERVE_SPACE(4 + newname->len); - WRITE32(newname->len); + *p++ = cpu_to_be32(newname->len); WRITEMEM(newname->name, newname->len); hdr->nops++; hdr->replen += decode_rename_maxsz; @@ -1417,7 +1416,7 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client __be32 *p; RESERVE_SPACE(12); - WRITE32(OP_RENEW); + *p++ = cpu_to_be32(OP_RENEW); WRITE64(client_stateid->cl_clientid); hdr->nops++; hdr->replen += decode_renew_maxsz; @@ -1429,7 +1428,7 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_RESTOREFH); + *p++ = cpu_to_be32(OP_RESTOREFH); hdr->nops++; hdr->replen += decode_restorefh_maxsz; } @@ -1440,15 +1439,15 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun __be32 *p; RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(OP_SETATTR); + *p++ = cpu_to_be32(OP_SETATTR); WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE); RESERVE_SPACE(2*4); - WRITE32(1); - WRITE32(FATTR4_WORD0_ACL); + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(FATTR4_WORD0_ACL); if (arg->acl_len % 4) return -EINVAL; RESERVE_SPACE(4); - WRITE32(arg->acl_len); + *p++ = cpu_to_be32(arg->acl_len); xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); hdr->nops++; hdr->replen += decode_setacl_maxsz; @@ -1461,7 +1460,7 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_SAVEFH); + *p++ = cpu_to_be32(OP_SAVEFH); hdr->nops++; hdr->replen += decode_savefh_maxsz; } @@ -1471,7 +1470,7 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs __be32 *p; RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(OP_SETATTR); + *p++ = cpu_to_be32(OP_SETATTR); WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_setattr_maxsz; @@ -1483,16 +1482,16 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie __be32 *p; RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE); - WRITE32(OP_SETCLIENTID); + *p++ = cpu_to_be32(OP_SETCLIENTID); WRITEMEM(setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); RESERVE_SPACE(4); - WRITE32(setclientid->sc_prog); + *p++ = cpu_to_be32(setclientid->sc_prog); encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid); encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr); RESERVE_SPACE(4); - WRITE32(setclientid->sc_cb_ident); + *p++ = cpu_to_be32(setclientid->sc_cb_ident); hdr->nops++; hdr->replen += decode_setclientid_maxsz; } @@ -1502,7 +1501,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ __be32 *p; RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE); - WRITE32(OP_SETCLIENTID_CONFIRM); + *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); WRITE64(client_state->cl_clientid); WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); hdr->nops++; @@ -1514,14 +1513,14 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg __be32 *p; RESERVE_SPACE(4); - WRITE32(OP_WRITE); + *p++ = cpu_to_be32(OP_WRITE); encode_stateid(xdr, args->context); RESERVE_SPACE(16); WRITE64(args->offset); - WRITE32(args->stable); - WRITE32(args->count); + *p++ = cpu_to_be32(args->stable); + *p++ = cpu_to_be32(args->count); xdr_write_pages(xdr, args->pages, args->pgbase, args->count); hdr->nops++; @@ -1534,7 +1533,7 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(OP_DELEGRETURN); + *p++ = cpu_to_be32(OP_DELEGRETURN); WRITEMEM(stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_delegreturn_maxsz; @@ -1549,15 +1548,15 @@ static void encode_exchange_id(struct xdr_stream *xdr, __be32 *p; RESERVE_SPACE(4 + sizeof(args->verifier->data)); - WRITE32(OP_EXCHANGE_ID); + *p++ = cpu_to_be32(OP_EXCHANGE_ID); WRITEMEM(args->verifier->data, sizeof(args->verifier->data)); encode_string(xdr, args->id_len, args->id); RESERVE_SPACE(12); - WRITE32(args->flags); - WRITE32(0); /* zero length state_protect4_a */ - WRITE32(0); /* zero length implementation id array */ + *p++ = cpu_to_be32(args->flags); + *p++ = cpu_to_be32(0); /* zero length state_protect4_a */ + *p++ = cpu_to_be32(0); /* zero length implementation id array */ hdr->nops++; hdr->replen += decode_exchange_id_maxsz; } @@ -1572,54 +1571,54 @@ static void encode_create_session(struct xdr_stream *xdr, struct nfs_client *clp = args->client; RESERVE_SPACE(4); - WRITE32(OP_CREATE_SESSION); + *p++ = cpu_to_be32(OP_CREATE_SESSION); RESERVE_SPACE(8); WRITE64(clp->cl_ex_clid); RESERVE_SPACE(8); - WRITE32(clp->cl_seqid); /*Sequence id */ - WRITE32(args->flags); /*flags */ + *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ + *p++ = cpu_to_be32(args->flags); /*flags */ RESERVE_SPACE(2*28); /* 2 channel_attrs */ /* Fore Channel */ - WRITE32(args->fc_attrs.headerpadsz); /* header padding size */ - WRITE32(args->fc_attrs.max_rqst_sz); /* max req size */ - WRITE32(args->fc_attrs.max_resp_sz); /* max resp size */ - WRITE32(args->fc_attrs.max_resp_sz_cached); /* Max resp sz cached */ - WRITE32(args->fc_attrs.max_ops); /* max operations */ - WRITE32(args->fc_attrs.max_reqs); /* max requests */ - WRITE32(0); /* rdmachannel_attrs */ + *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->fc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->fc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ /* Back Channel */ - WRITE32(args->fc_attrs.headerpadsz); /* header padding size */ - WRITE32(args->bc_attrs.max_rqst_sz); /* max req size */ - WRITE32(args->bc_attrs.max_resp_sz); /* max resp size */ - WRITE32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ - WRITE32(args->bc_attrs.max_ops); /* max operations */ - WRITE32(args->bc_attrs.max_reqs); /* max requests */ - WRITE32(0); /* rdmachannel_attrs */ + *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->bc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->bc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ RESERVE_SPACE(4); - WRITE32(args->cb_program); /* cb_program */ + *p++ = cpu_to_be32(args->cb_program); /* cb_program */ RESERVE_SPACE(4); /* # of security flavors */ - WRITE32(1); + *p++ = cpu_to_be32(1); RESERVE_SPACE(4); - WRITE32(RPC_AUTH_UNIX); /* auth_sys */ + *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ RESERVE_SPACE(4); - WRITE32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ + *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ len = scnprintf(machine_name, sizeof(machine_name), "%s", clp->cl_ipaddr); RESERVE_SPACE(16 + len); - WRITE32(len); + *p++ = cpu_to_be32(len); WRITEMEM(machine_name, len); - WRITE32(0); /* UID */ - WRITE32(0); /* GID */ - WRITE32(0); /* No more gids */ + *p++ = cpu_to_be32(0); /* UID */ + *p++ = cpu_to_be32(0); /* GID */ + *p++ = cpu_to_be32(0); /* No more gids */ hdr->nops++; hdr->replen += decode_create_session_maxsz; } @@ -1630,7 +1629,7 @@ static void encode_destroy_session(struct xdr_stream *xdr, { __be32 *p; RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN); - WRITE32(OP_DESTROY_SESSION); + *p++ = cpu_to_be32(OP_DESTROY_SESSION); WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); hdr->nops++; hdr->replen += decode_destroy_session_maxsz; @@ -1656,7 +1655,7 @@ static void encode_sequence(struct xdr_stream *xdr, slot = tp->slots + args->sa_slotid; RESERVE_SPACE(4); - WRITE32(OP_SEQUENCE); + *p++ = cpu_to_be32(OP_SEQUENCE); /* * Sessionid + seqid + slotid + max slotid + cache_this @@ -1672,10 +1671,10 @@ static void encode_sequence(struct xdr_stream *xdr, tp->highest_used_slotid, args->sa_cache_this); RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 16); WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(slot->seq_nr); - WRITE32(args->sa_slotid); - WRITE32(tp->highest_used_slotid); - WRITE32(args->sa_cache_this); + *p++ = cpu_to_be32(slot->seq_nr); + *p++ = cpu_to_be32(args->sa_slotid); + *p++ = cpu_to_be32(tp->highest_used_slotid); + *p++ = cpu_to_be32(args->sa_cache_this); hdr->nops++; hdr->replen += decode_sequence_maxsz; #endif /* CONFIG_NFS_V4_1 */ From b95be5a976848febff82edb21d5b4351b3997bf6 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:01 +0300 Subject: [PATCH 56/87] nfs: nfs4xdr: get rid of WRITE64 s/WRITE64/p = xdr_encode_hyper(p, / Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 44 ++++++++++++++++++++------------------------ 1 file changed, 20 insertions(+), 24 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 9a03b24ead5f..5d80766fc672 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -712,10 +712,6 @@ struct compound_hdr { * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define WRITE64(n) do { \ - *p++ = htonl((uint32_t)((n) >> 32)); \ - *p++ = htonl((uint32_t)(n)); \ -} while (0) #define WRITEMEM(ptr,nbytes) do { \ p = xdr_encode_opaque_fixed(p, ptr, nbytes); \ } while (0) @@ -840,7 +836,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const if (iap->ia_valid & ATTR_SIZE) { bmval0 |= FATTR4_WORD0_SIZE; - WRITE64(iap->ia_size); + p = xdr_encode_hyper(p, iap->ia_size); } if (iap->ia_valid & ATTR_MODE) { bmval1 |= FATTR4_WORD1_MODE; @@ -924,7 +920,7 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar RESERVE_SPACE(16); *p++ = cpu_to_be32(OP_COMMIT); - WRITE64(args->offset); + p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_commit_maxsz; @@ -1055,18 +1051,18 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args *p++ = cpu_to_be32(OP_LOCK); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block)); *p++ = cpu_to_be32(args->reclaim); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); *p++ = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ RESERVE_SPACE(4+NFS4_STATEID_SIZE+32); *p++ = cpu_to_be32(args->open_seqid->sequence->counter); WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); - WRITE64(args->lock_owner.clientid); + p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); WRITEMEM("lock id:", 8); - WRITE64(args->lock_owner.id); + p = xdr_encode_hyper(p, args->lock_owner.id); } else { RESERVE_SPACE(NFS4_STATEID_SIZE+4); @@ -1084,12 +1080,12 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar RESERVE_SPACE(52); *p++ = cpu_to_be32(OP_LOCKT); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); - WRITE64(args->lock_owner.clientid); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); WRITEMEM("lock id:", 8); - WRITE64(args->lock_owner.id); + p = xdr_encode_hyper(p, args->lock_owner.id); hdr->nops++; hdr->replen += decode_lockt_maxsz; } @@ -1103,8 +1099,8 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); *p++ = cpu_to_be32(args->seqid->sequence->counter); WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); hdr->nops++; hdr->replen += decode_locku_maxsz; } @@ -1155,10 +1151,10 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena *p++ = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); RESERVE_SPACE(28); - WRITE64(arg->clientid); + p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(16); WRITEMEM("open id:", 8); - WRITE64(arg->id); + p = xdr_encode_hyper(p, arg->id); } static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1334,7 +1330,7 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, encode_stateid(xdr, args->context); RESERVE_SPACE(12); - WRITE64(args->offset); + p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_read_maxsz; @@ -1350,7 +1346,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20); *p++ = cpu_to_be32(OP_READDIR); - WRITE64(readdir->cookie); + p = xdr_encode_hyper(p, readdir->cookie); WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(readdir->count >> 1); /* We're not doing readdirplus */ *p++ = cpu_to_be32(readdir->count); @@ -1417,7 +1413,7 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client RESERVE_SPACE(12); *p++ = cpu_to_be32(OP_RENEW); - WRITE64(client_stateid->cl_clientid); + p = xdr_encode_hyper(p, client_stateid->cl_clientid); hdr->nops++; hdr->replen += decode_renew_maxsz; } @@ -1502,7 +1498,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); - WRITE64(client_state->cl_clientid); + p = xdr_encode_hyper(p, client_state->cl_clientid); WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); hdr->nops++; hdr->replen += decode_setclientid_confirm_maxsz; @@ -1518,7 +1514,7 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg encode_stateid(xdr, args->context); RESERVE_SPACE(16); - WRITE64(args->offset); + p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->stable); *p++ = cpu_to_be32(args->count); @@ -1574,7 +1570,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(OP_CREATE_SESSION); RESERVE_SPACE(8); - WRITE64(clp->cl_ex_clid); + p = xdr_encode_hyper(p, clp->cl_ex_clid); RESERVE_SPACE(8); *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ From 93f0cf25944695e1229fe90a2897af0211fbd425 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:06 +0300 Subject: [PATCH 57/87] nfs: nfs4xdr: get rid of WRITEMEM s/WRITEMEM(/p = xdr_encode_opaque_fixed(p, / Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 68 +++++++++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 36 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5d80766fc672..17915c8ea7fa 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -712,10 +712,6 @@ struct compound_hdr { * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define WRITEMEM(ptr,nbytes) do { \ - p = xdr_encode_opaque_fixed(p, ptr, nbytes); \ -} while (0) - #define RESERVE_SPACE(nbytes) do { \ p = xdr_reserve_space(xdr, nbytes); \ BUG_ON(!p); \ @@ -746,7 +742,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr, BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); RESERVE_SPACE(12+(XDR_QUADLEN(hdr->taglen)<<2)); *p++ = cpu_to_be32(hdr->taglen); - WRITEMEM(hdr->tag, hdr->taglen); + p = xdr_encode_opaque_fixed(p, hdr->tag, hdr->taglen); *p++ = cpu_to_be32(hdr->minorversion); hdr->nops_p = p; *p++ = cpu_to_be32(hdr->nops); @@ -845,12 +841,12 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const if (iap->ia_valid & ATTR_UID) { bmval1 |= FATTR4_WORD1_OWNER; *p++ = cpu_to_be32(owner_namelen); - WRITEMEM(owner_name, owner_namelen); + p = xdr_encode_opaque_fixed(p, owner_name, owner_namelen); } if (iap->ia_valid & ATTR_GID) { bmval1 |= FATTR4_WORD1_OWNER_GROUP; *p++ = cpu_to_be32(owner_grouplen); - WRITEMEM(owner_group, owner_grouplen); + p = xdr_encode_opaque_fixed(p, owner_group, owner_grouplen); } if (iap->ia_valid & ATTR_ATIME_SET) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; @@ -909,7 +905,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg RESERVE_SPACE(8+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_CLOSE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_close_maxsz; } @@ -953,7 +949,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * RESERVE_SPACE(4 + create->name->len); *p++ = cpu_to_be32(create->name->len); - WRITEMEM(create->name->name, create->name->len); + p = xdr_encode_opaque_fixed(p, create->name->name, create->name->len); hdr->nops++; hdr->replen += decode_create_maxsz; @@ -1020,7 +1016,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct RESERVE_SPACE(8 + name->len); *p++ = cpu_to_be32(OP_LINK); *p++ = cpu_to_be32(name->len); - WRITEMEM(name->name, name->len); + p = xdr_encode_opaque_fixed(p, name->name, name->len); hdr->nops++; hdr->replen += decode_link_maxsz; } @@ -1057,16 +1053,16 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args if (args->new_lock_owner){ RESERVE_SPACE(4+NFS4_STATEID_SIZE+32); *p++ = cpu_to_be32(args->open_seqid->sequence->counter); - WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); - WRITEMEM("lock id:", 8); + p = xdr_encode_opaque_fixed(p, "lock id:", 8); p = xdr_encode_hyper(p, args->lock_owner.id); } else { RESERVE_SPACE(NFS4_STATEID_SIZE+4); - WRITEMEM(args->lock_stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); } hdr->nops++; @@ -1084,7 +1080,7 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); - WRITEMEM("lock id:", 8); + p = xdr_encode_opaque_fixed(p, "lock id:", 8); p = xdr_encode_hyper(p, args->lock_owner.id); hdr->nops++; hdr->replen += decode_lockt_maxsz; @@ -1098,7 +1094,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar *p++ = cpu_to_be32(OP_LOCKU); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); *p++ = cpu_to_be32(args->seqid->sequence->counter); - WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE); p = xdr_encode_hyper(p, args->fl->fl_start); p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); hdr->nops++; @@ -1113,7 +1109,7 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc RESERVE_SPACE(8 + len); *p++ = cpu_to_be32(OP_LOOKUP); *p++ = cpu_to_be32(len); - WRITEMEM(name->name, len); + p = xdr_encode_opaque_fixed(p, name->name, len); hdr->nops++; hdr->replen += decode_lookup_maxsz; } @@ -1153,7 +1149,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena RESERVE_SPACE(28); p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(16); - WRITEMEM("open id:", 8); + p = xdr_encode_opaque_fixed(p, "open id:", 8); p = xdr_encode_hyper(p, arg->id); } @@ -1233,7 +1229,7 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc RESERVE_SPACE(4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); - WRITEMEM(stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); encode_string(xdr, name->len, name->name); } @@ -1264,7 +1260,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_CONFIRM); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); hdr->nops++; hdr->replen += decode_open_confirm_maxsz; @@ -1276,7 +1272,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); hdr->nops++; @@ -1292,7 +1288,7 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd RESERVE_SPACE(8 + len); *p++ = cpu_to_be32(OP_PUTFH); *p++ = cpu_to_be32(len); - WRITEMEM(fh->data, len); + p = xdr_encode_opaque_fixed(p, fh->data, len); hdr->nops++; hdr->replen += decode_putfh_maxsz; } @@ -1315,9 +1311,9 @@ static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context RESERVE_SPACE(NFS4_STATEID_SIZE); if (ctx->state != NULL) { nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner); - WRITEMEM(stateid.data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE); } else - WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); } static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr) @@ -1347,7 +1343,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20); *p++ = cpu_to_be32(OP_READDIR); p = xdr_encode_hyper(p, readdir->cookie); - WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE); + p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(readdir->count >> 1); /* We're not doing readdirplus */ *p++ = cpu_to_be32(readdir->count); *p++ = cpu_to_be32(2); @@ -1386,7 +1382,7 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc RESERVE_SPACE(8 + name->len); *p++ = cpu_to_be32(OP_REMOVE); *p++ = cpu_to_be32(name->len); - WRITEMEM(name->name, name->len); + p = xdr_encode_opaque_fixed(p, name->name, name->len); hdr->nops++; hdr->replen += decode_remove_maxsz; } @@ -1398,11 +1394,11 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co RESERVE_SPACE(8 + oldname->len); *p++ = cpu_to_be32(OP_RENAME); *p++ = cpu_to_be32(oldname->len); - WRITEMEM(oldname->name, oldname->len); + p = xdr_encode_opaque_fixed(p, oldname->name, oldname->len); RESERVE_SPACE(4 + newname->len); *p++ = cpu_to_be32(newname->len); - WRITEMEM(newname->name, newname->len); + p = xdr_encode_opaque_fixed(p, newname->name, newname->len); hdr->nops++; hdr->replen += decode_rename_maxsz; } @@ -1436,7 +1432,7 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun RESERVE_SPACE(4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); - WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); RESERVE_SPACE(2*4); *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(FATTR4_WORD0_ACL); @@ -1467,7 +1463,7 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs RESERVE_SPACE(4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); - WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_setattr_maxsz; encode_attrs(xdr, arg->iap, server); @@ -1479,7 +1475,7 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID); - WRITEMEM(setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); + p = xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); RESERVE_SPACE(4); @@ -1499,7 +1495,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); p = xdr_encode_hyper(p, client_state->cl_clientid); - WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); + p = xdr_encode_opaque_fixed(p, client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); hdr->nops++; hdr->replen += decode_setclientid_confirm_maxsz; } @@ -1530,7 +1526,7 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state RESERVE_SPACE(4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_DELEGRETURN); - WRITEMEM(stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_delegreturn_maxsz; } @@ -1545,7 +1541,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, RESERVE_SPACE(4 + sizeof(args->verifier->data)); *p++ = cpu_to_be32(OP_EXCHANGE_ID); - WRITEMEM(args->verifier->data, sizeof(args->verifier->data)); + p = xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data)); encode_string(xdr, args->id_len, args->id); @@ -1611,7 +1607,7 @@ static void encode_create_session(struct xdr_stream *xdr, clp->cl_ipaddr); RESERVE_SPACE(16 + len); *p++ = cpu_to_be32(len); - WRITEMEM(machine_name, len); + p = xdr_encode_opaque_fixed(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ *p++ = cpu_to_be32(0); /* No more gids */ @@ -1626,7 +1622,7 @@ static void encode_destroy_session(struct xdr_stream *xdr, __be32 *p; RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN); *p++ = cpu_to_be32(OP_DESTROY_SESSION); - WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); hdr->nops++; hdr->replen += decode_destroy_session_maxsz; } @@ -1666,7 +1662,7 @@ static void encode_sequence(struct xdr_stream *xdr, slot->seq_nr, args->sa_slotid, tp->highest_used_slotid, args->sa_cache_this); RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 16); - WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); *p++ = cpu_to_be32(slot->seq_nr); *p++ = cpu_to_be32(args->sa_slotid); *p++ = cpu_to_be32(tp->highest_used_slotid); From 42edd698125b76a38bd9999015202db036dfbc76 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:13 +0300 Subject: [PATCH 58/87] nfs: nfs4xdr: optimize RESERVE_SPACE in encode_create_session and encode_sequence Coalesce multilpe constant RESERVE_SPACEs into one Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 22 +++++----------------- 1 file changed, 5 insertions(+), 17 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 17915c8ea7fa..d460d81758ae 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1562,17 +1562,15 @@ static void encode_create_session(struct xdr_stream *xdr, uint32_t len; struct nfs_client *clp = args->client; - RESERVE_SPACE(4); + len = scnprintf(machine_name, sizeof(machine_name), "%s", + clp->cl_ipaddr); + + RESERVE_SPACE(20 + 2*28 + 20 + len + 12); *p++ = cpu_to_be32(OP_CREATE_SESSION); - - RESERVE_SPACE(8); p = xdr_encode_hyper(p, clp->cl_ex_clid); - - RESERVE_SPACE(8); *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ *p++ = cpu_to_be32(args->flags); /*flags */ - RESERVE_SPACE(2*28); /* 2 channel_attrs */ /* Fore Channel */ *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ @@ -1591,21 +1589,12 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(args->bc_attrs.max_reqs); /* max requests */ *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ - RESERVE_SPACE(4); *p++ = cpu_to_be32(args->cb_program); /* cb_program */ - - RESERVE_SPACE(4); /* # of security flavors */ *p++ = cpu_to_be32(1); - - RESERVE_SPACE(4); *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - RESERVE_SPACE(4); *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ - len = scnprintf(machine_name, sizeof(machine_name), "%s", - clp->cl_ipaddr); - RESERVE_SPACE(16 + len); *p++ = cpu_to_be32(len); p = xdr_encode_opaque_fixed(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ @@ -1646,7 +1635,7 @@ static void encode_sequence(struct xdr_stream *xdr, WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE); slot = tp->slots + args->sa_slotid; - RESERVE_SPACE(4); + RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN + 16); *p++ = cpu_to_be32(OP_SEQUENCE); /* @@ -1661,7 +1650,6 @@ static void encode_sequence(struct xdr_stream *xdr, ((u32 *)session->sess_id.data)[3], slot->seq_nr, args->sa_slotid, tp->highest_used_slotid, args->sa_cache_this); - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 16); p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); *p++ = cpu_to_be32(slot->seq_nr); *p++ = cpu_to_be32(args->sa_slotid); From 2220f13a8b90d2259f3094cb54cf4de67d8eee2d Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:18 +0300 Subject: [PATCH 59/87] nfs: nfs4xdr: encode_compound_hdr does not have to round up reserved bytes This is already done by xdr_reserve_space and since encode_compound_hdr is adding a byte count to "12" which is already word aligned, the xdr level rounding will work just as well. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d460d81758ae..7c2b162dd845 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -740,7 +740,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr, dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag); BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); - RESERVE_SPACE(12+(XDR_QUADLEN(hdr->taglen)<<2)); + RESERVE_SPACE(12 + hdr->taglen); *p++ = cpu_to_be32(hdr->taglen); p = xdr_encode_opaque_fixed(p, hdr->tag, hdr->taglen); *p++ = cpu_to_be32(hdr->minorversion); From 13c65ce90006badccd5663e558e3c85869ae5ce6 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:25 +0300 Subject: [PATCH 60/87] nfs: nfs4xdr: change RESERVE_SPACE macro into a static helper In order to open code and expose the result pointer assignment. Alternatively, we can open code the call to xdr_reserve_space and do the BUG_ON an the error case at the call site. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 138 ++++++++++++++++++++++------------------------- 1 file changed, 65 insertions(+), 73 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7c2b162dd845..3bcde49fbea8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -702,20 +702,12 @@ struct compound_hdr { u32 minorversion; }; -/* - * START OF "GENERIC" ENCODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ -#define RESERVE_SPACE(nbytes) do { \ - p = xdr_reserve_space(xdr, nbytes); \ - BUG_ON(!p); \ -} while (0) +static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p = xdr_reserve_space(xdr, nbytes); + BUG_ON(!p); + return p; +} static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) { @@ -740,7 +732,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr, dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag); BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); - RESERVE_SPACE(12 + hdr->taglen); + p = reserve_space(xdr, 12 + hdr->taglen); *p++ = cpu_to_be32(hdr->taglen); p = xdr_encode_opaque_fixed(p, hdr->tag, hdr->taglen); *p++ = cpu_to_be32(hdr->minorversion); @@ -820,7 +812,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const len += 16; else if (iap->ia_valid & ATTR_MTIME) len += 4; - RESERVE_SPACE(len); + p = reserve_space(xdr, len); /* * We write the bitmap length now, but leave the bitmap and the attribute @@ -891,7 +883,7 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd { __be32 *p; - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_ACCESS); *p++ = cpu_to_be32(access); hdr->nops++; @@ -902,7 +894,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg { __be32 *p; - RESERVE_SPACE(8+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 8+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_CLOSE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); @@ -914,7 +906,7 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar { __be32 *p; - RESERVE_SPACE(16); + p = reserve_space(xdr, 16); *p++ = cpu_to_be32(OP_COMMIT); p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->count); @@ -926,19 +918,19 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * { __be32 *p; - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_CREATE); *p++ = cpu_to_be32(create->ftype); switch (create->ftype) { case NF4LNK: - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(create->u.symlink.len); xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len); break; case NF4BLK: case NF4CHR: - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); *p++ = cpu_to_be32(create->u.device.specdata1); *p++ = cpu_to_be32(create->u.device.specdata2); break; @@ -947,7 +939,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * break; } - RESERVE_SPACE(4 + create->name->len); + p = reserve_space(xdr, 4 + create->name->len); *p++ = cpu_to_be32(create->name->len); p = xdr_encode_opaque_fixed(p, create->name->name, create->name->len); hdr->nops++; @@ -960,7 +952,7 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c { __be32 *p; - RESERVE_SPACE(12); + p = reserve_space(xdr, 12); *p++ = cpu_to_be32(OP_GETATTR); *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(bitmap); @@ -972,7 +964,7 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm { __be32 *p; - RESERVE_SPACE(16); + p = reserve_space(xdr, 16); *p++ = cpu_to_be32(OP_GETATTR); *p++ = cpu_to_be32(2); *p++ = cpu_to_be32(bm0); @@ -1003,7 +995,7 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_GETFH); hdr->nops++; hdr->replen += decode_getfh_maxsz; @@ -1013,7 +1005,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct { __be32 *p; - RESERVE_SPACE(8 + name->len); + p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_LINK); *p++ = cpu_to_be32(name->len); p = xdr_encode_opaque_fixed(p, name->name, name->len); @@ -1043,7 +1035,7 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args { __be32 *p; - RESERVE_SPACE(32); + p = reserve_space(xdr, 32); *p++ = cpu_to_be32(OP_LOCK); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block)); *p++ = cpu_to_be32(args->reclaim); @@ -1051,7 +1043,7 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); *p++ = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ - RESERVE_SPACE(4+NFS4_STATEID_SIZE+32); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+32); *p++ = cpu_to_be32(args->open_seqid->sequence->counter); p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); @@ -1061,7 +1053,7 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args p = xdr_encode_hyper(p, args->lock_owner.id); } else { - RESERVE_SPACE(NFS4_STATEID_SIZE+4); + p = reserve_space(xdr, NFS4_STATEID_SIZE+4); p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); } @@ -1073,7 +1065,7 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar { __be32 *p; - RESERVE_SPACE(52); + p = reserve_space(xdr, 52); *p++ = cpu_to_be32(OP_LOCKT); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); p = xdr_encode_hyper(p, args->fl->fl_start); @@ -1090,7 +1082,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar { __be32 *p; - RESERVE_SPACE(12+NFS4_STATEID_SIZE+16); + p = reserve_space(xdr, 12+NFS4_STATEID_SIZE+16); *p++ = cpu_to_be32(OP_LOCKU); *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); *p++ = cpu_to_be32(args->seqid->sequence->counter); @@ -1106,7 +1098,7 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc int len = name->len; __be32 *p; - RESERVE_SPACE(8 + len); + p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_LOOKUP); *p++ = cpu_to_be32(len); p = xdr_encode_opaque_fixed(p, name->name, len); @@ -1118,7 +1110,7 @@ static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) { __be32 *p; - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); switch (fmode & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ: *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ); @@ -1142,11 +1134,11 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4, * owner 4 = 32 */ - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_OPEN); *p++ = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); - RESERVE_SPACE(28); + p = reserve_space(xdr, 28); p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(16); p = xdr_encode_opaque_fixed(p, "open id:", 8); @@ -1157,7 +1149,7 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch(arg->open_flags & O_EXCL) { case 0: *p++ = cpu_to_be32(NFS4_CREATE_UNCHECKED); @@ -1173,7 +1165,7 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch (arg->open_flags & O_CREAT) { case 0: *p++ = cpu_to_be32(NFS4_OPEN_NOCREATE); @@ -1189,7 +1181,7 @@ static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delega { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch (delegation_type) { case 0: *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); @@ -1209,7 +1201,7 @@ static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr * { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); encode_string(xdr, name->len, name->name); } @@ -1218,7 +1210,7 @@ static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); encode_delegation_type(xdr, type); } @@ -1227,7 +1219,7 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); encode_string(xdr, name->len, name->name); @@ -1258,7 +1250,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_CONFIRM); p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); @@ -1270,7 +1262,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE); p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); @@ -1285,7 +1277,7 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd int len = fh->size; __be32 *p; - RESERVE_SPACE(8 + len); + p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_PUTFH); *p++ = cpu_to_be32(len); p = xdr_encode_opaque_fixed(p, fh->data, len); @@ -1297,7 +1289,7 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_PUTROOTFH); hdr->nops++; hdr->replen += decode_putrootfh_maxsz; @@ -1308,7 +1300,7 @@ static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context nfs4_stateid stateid; __be32 *p; - RESERVE_SPACE(NFS4_STATEID_SIZE); + p = reserve_space(xdr, NFS4_STATEID_SIZE); if (ctx->state != NULL) { nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner); p = xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE); @@ -1320,12 +1312,12 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_READ); encode_stateid(xdr, args->context); - RESERVE_SPACE(12); + p = reserve_space(xdr, 12); p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->count); hdr->nops++; @@ -1340,7 +1332,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg }; __be32 *p; - RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20); + p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20); *p++ = cpu_to_be32(OP_READDIR); p = xdr_encode_hyper(p, readdir->cookie); p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE); @@ -1369,7 +1361,7 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink * { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_READLINK); hdr->nops++; hdr->replen += decode_readlink_maxsz; @@ -1379,7 +1371,7 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc { __be32 *p; - RESERVE_SPACE(8 + name->len); + p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_REMOVE); *p++ = cpu_to_be32(name->len); p = xdr_encode_opaque_fixed(p, name->name, name->len); @@ -1391,12 +1383,12 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co { __be32 *p; - RESERVE_SPACE(8 + oldname->len); + p = reserve_space(xdr, 8 + oldname->len); *p++ = cpu_to_be32(OP_RENAME); *p++ = cpu_to_be32(oldname->len); p = xdr_encode_opaque_fixed(p, oldname->name, oldname->len); - RESERVE_SPACE(4 + newname->len); + p = reserve_space(xdr, 4 + newname->len); *p++ = cpu_to_be32(newname->len); p = xdr_encode_opaque_fixed(p, newname->name, newname->len); hdr->nops++; @@ -1407,7 +1399,7 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client { __be32 *p; - RESERVE_SPACE(12); + p = reserve_space(xdr, 12); *p++ = cpu_to_be32(OP_RENEW); p = xdr_encode_hyper(p, client_stateid->cl_clientid); hdr->nops++; @@ -1419,7 +1411,7 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_RESTOREFH); hdr->nops++; hdr->replen += decode_restorefh_maxsz; @@ -1430,15 +1422,15 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); p = xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); - RESERVE_SPACE(2*4); + p = reserve_space(xdr, 2*4); *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(FATTR4_WORD0_ACL); if (arg->acl_len % 4) return -EINVAL; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(arg->acl_len); xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); hdr->nops++; @@ -1451,7 +1443,7 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_SAVEFH); hdr->nops++; hdr->replen += decode_savefh_maxsz; @@ -1461,7 +1453,7 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); p = xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE); hdr->nops++; @@ -1473,16 +1465,16 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie { __be32 *p; - RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE); + p = reserve_space(xdr, 4 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID); p = xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(setclientid->sc_prog); encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid); encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr); - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(setclientid->sc_cb_ident); hdr->nops++; hdr->replen += decode_setclientid_maxsz; @@ -1492,7 +1484,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ { __be32 *p; - RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE); + p = reserve_space(xdr, 12 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); p = xdr_encode_hyper(p, client_state->cl_clientid); p = xdr_encode_opaque_fixed(p, client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); @@ -1504,12 +1496,12 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); *p++ = cpu_to_be32(OP_WRITE); encode_stateid(xdr, args->context); - RESERVE_SPACE(16); + p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->stable); *p++ = cpu_to_be32(args->count); @@ -1523,7 +1515,7 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_DELEGRETURN); p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); @@ -1539,13 +1531,13 @@ static void encode_exchange_id(struct xdr_stream *xdr, { __be32 *p; - RESERVE_SPACE(4 + sizeof(args->verifier->data)); + p = reserve_space(xdr, 4 + sizeof(args->verifier->data)); *p++ = cpu_to_be32(OP_EXCHANGE_ID); p = xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data)); encode_string(xdr, args->id_len, args->id); - RESERVE_SPACE(12); + p = reserve_space(xdr, 12); *p++ = cpu_to_be32(args->flags); *p++ = cpu_to_be32(0); /* zero length state_protect4_a */ *p++ = cpu_to_be32(0); /* zero length implementation id array */ @@ -1565,7 +1557,7 @@ static void encode_create_session(struct xdr_stream *xdr, len = scnprintf(machine_name, sizeof(machine_name), "%s", clp->cl_ipaddr); - RESERVE_SPACE(20 + 2*28 + 20 + len + 12); + p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12); *p++ = cpu_to_be32(OP_CREATE_SESSION); p = xdr_encode_hyper(p, clp->cl_ex_clid); *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ @@ -1609,7 +1601,7 @@ static void encode_destroy_session(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN); + p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN); *p++ = cpu_to_be32(OP_DESTROY_SESSION); p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); hdr->nops++; @@ -1635,7 +1627,7 @@ static void encode_sequence(struct xdr_stream *xdr, WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE); slot = tp->slots + args->sa_slotid; - RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN + 16); + p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN + 16); *p++ = cpu_to_be32(OP_SEQUENCE); /* From 345585132a204859fbb7d8b662e9b6e5b563c6dc Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:30 +0300 Subject: [PATCH 61/87] nfs: nfs4xdr: optimize low level encoding do not increment encoding ptr if not needed. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 128 +++++++++++++++++++++++------------------------ 1 file changed, 64 insertions(+), 64 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3bcde49fbea8..d75f821cad01 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -737,7 +737,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr, p = xdr_encode_opaque_fixed(p, hdr->tag, hdr->taglen); *p++ = cpu_to_be32(hdr->minorversion); hdr->nops_p = p; - *p++ = cpu_to_be32(hdr->nops); + *p = cpu_to_be32(hdr->nops); } static void encode_nops(struct compound_hdr *hdr) @@ -874,7 +874,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const len = (char *)p - (char *)q - 12; *q++ = htonl(bmval0); *q++ = htonl(bmval1); - *q++ = htonl(len); + *q = htonl(len); /* out: */ } @@ -885,7 +885,7 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_ACCESS); - *p++ = cpu_to_be32(access); + *p = cpu_to_be32(access); hdr->nops++; hdr->replen += decode_access_maxsz; } @@ -897,7 +897,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg p = reserve_space(xdr, 8+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_CLOSE); *p++ = cpu_to_be32(arg->seqid->sequence->counter); - p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_close_maxsz; } @@ -909,7 +909,7 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar p = reserve_space(xdr, 16); *p++ = cpu_to_be32(OP_COMMIT); p = xdr_encode_hyper(p, args->offset); - *p++ = cpu_to_be32(args->count); + *p = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_commit_maxsz; } @@ -920,19 +920,19 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_CREATE); - *p++ = cpu_to_be32(create->ftype); + *p = cpu_to_be32(create->ftype); switch (create->ftype) { case NF4LNK: p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(create->u.symlink.len); + *p = cpu_to_be32(create->u.symlink.len); xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len); break; case NF4BLK: case NF4CHR: p = reserve_space(xdr, 8); *p++ = cpu_to_be32(create->u.device.specdata1); - *p++ = cpu_to_be32(create->u.device.specdata2); + *p = cpu_to_be32(create->u.device.specdata2); break; default: @@ -941,7 +941,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * p = reserve_space(xdr, 4 + create->name->len); *p++ = cpu_to_be32(create->name->len); - p = xdr_encode_opaque_fixed(p, create->name->name, create->name->len); + xdr_encode_opaque_fixed(p, create->name->name, create->name->len); hdr->nops++; hdr->replen += decode_create_maxsz; @@ -955,7 +955,7 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c p = reserve_space(xdr, 12); *p++ = cpu_to_be32(OP_GETATTR); *p++ = cpu_to_be32(1); - *p++ = cpu_to_be32(bitmap); + *p = cpu_to_be32(bitmap); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -968,7 +968,7 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm *p++ = cpu_to_be32(OP_GETATTR); *p++ = cpu_to_be32(2); *p++ = cpu_to_be32(bm0); - *p++ = cpu_to_be32(bm1); + *p = cpu_to_be32(bm1); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -996,7 +996,7 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_GETFH); + *p = cpu_to_be32(OP_GETFH); hdr->nops++; hdr->replen += decode_getfh_maxsz; } @@ -1008,7 +1008,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_LINK); *p++ = cpu_to_be32(name->len); - p = xdr_encode_opaque_fixed(p, name->name, name->len); + xdr_encode_opaque_fixed(p, name->name, name->len); hdr->nops++; hdr->replen += decode_link_maxsz; } @@ -1041,7 +1041,7 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args *p++ = cpu_to_be32(args->reclaim); p = xdr_encode_hyper(p, args->fl->fl_start); p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); - *p++ = cpu_to_be32(args->new_lock_owner); + *p = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+32); *p++ = cpu_to_be32(args->open_seqid->sequence->counter); @@ -1050,12 +1050,12 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); p = xdr_encode_opaque_fixed(p, "lock id:", 8); - p = xdr_encode_hyper(p, args->lock_owner.id); + xdr_encode_hyper(p, args->lock_owner.id); } else { p = reserve_space(xdr, NFS4_STATEID_SIZE+4); p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE); - *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); + *p = cpu_to_be32(args->lock_seqid->sequence->counter); } hdr->nops++; hdr->replen += decode_lock_maxsz; @@ -1073,7 +1073,7 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar p = xdr_encode_hyper(p, args->lock_owner.clientid); *p++ = cpu_to_be32(16); p = xdr_encode_opaque_fixed(p, "lock id:", 8); - p = xdr_encode_hyper(p, args->lock_owner.id); + xdr_encode_hyper(p, args->lock_owner.id); hdr->nops++; hdr->replen += decode_lockt_maxsz; } @@ -1088,7 +1088,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar *p++ = cpu_to_be32(args->seqid->sequence->counter); p = xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE); p = xdr_encode_hyper(p, args->fl->fl_start); - p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + xdr_encode_hyper(p, nfs4_lock_length(args->fl)); hdr->nops++; hdr->replen += decode_locku_maxsz; } @@ -1101,7 +1101,7 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_LOOKUP); *p++ = cpu_to_be32(len); - p = xdr_encode_opaque_fixed(p, name->name, len); + xdr_encode_opaque_fixed(p, name->name, len); hdr->nops++; hdr->replen += decode_lookup_maxsz; } @@ -1124,7 +1124,7 @@ static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) default: *p++ = cpu_to_be32(0); } - *p++ = cpu_to_be32(0); /* for linux, share_deny = 0 always */ + *p = cpu_to_be32(0); /* for linux, share_deny = 0 always */ } static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1136,13 +1136,13 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ p = reserve_space(xdr, 8); *p++ = cpu_to_be32(OP_OPEN); - *p++ = cpu_to_be32(arg->seqid->sequence->counter); + *p = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); p = reserve_space(xdr, 28); p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(16); p = xdr_encode_opaque_fixed(p, "open id:", 8); - p = xdr_encode_hyper(p, arg->id); + xdr_encode_hyper(p, arg->id); } static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1152,11 +1152,11 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op p = reserve_space(xdr, 4); switch(arg->open_flags & O_EXCL) { case 0: - *p++ = cpu_to_be32(NFS4_CREATE_UNCHECKED); + *p = cpu_to_be32(NFS4_CREATE_UNCHECKED); encode_attrs(xdr, arg->u.attrs, arg->server); break; default: - *p++ = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); encode_nfs4_verifier(xdr, &arg->u.verifier); } } @@ -1168,11 +1168,11 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a p = reserve_space(xdr, 4); switch (arg->open_flags & O_CREAT) { case 0: - *p++ = cpu_to_be32(NFS4_OPEN_NOCREATE); + *p = cpu_to_be32(NFS4_OPEN_NOCREATE); break; default: BUG_ON(arg->claim != NFS4_OPEN_CLAIM_NULL); - *p++ = cpu_to_be32(NFS4_OPEN_CREATE); + *p = cpu_to_be32(NFS4_OPEN_CREATE); encode_createmode(xdr, arg); } } @@ -1184,13 +1184,13 @@ static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delega p = reserve_space(xdr, 4); switch (delegation_type) { case 0: - *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); break; case FMODE_READ: - *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_READ); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_READ); break; case FMODE_WRITE|FMODE_READ: - *p++ = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE); break; default: BUG(); @@ -1202,7 +1202,7 @@ static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr * __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); encode_string(xdr, name->len, name->name); } @@ -1211,7 +1211,7 @@ static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type) __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); encode_delegation_type(xdr, type); } @@ -1221,7 +1221,7 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); - p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); encode_string(xdr, name->len, name->name); } @@ -1253,7 +1253,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_CONFIRM); p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); - *p++ = cpu_to_be32(arg->seqid->sequence->counter); + *p = cpu_to_be32(arg->seqid->sequence->counter); hdr->nops++; hdr->replen += decode_open_confirm_maxsz; } @@ -1265,7 +1265,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE); p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); - *p++ = cpu_to_be32(arg->seqid->sequence->counter); + *p = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); hdr->nops++; hdr->replen += decode_open_downgrade_maxsz; @@ -1280,7 +1280,7 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_PUTFH); *p++ = cpu_to_be32(len); - p = xdr_encode_opaque_fixed(p, fh->data, len); + xdr_encode_opaque_fixed(p, fh->data, len); hdr->nops++; hdr->replen += decode_putfh_maxsz; } @@ -1290,7 +1290,7 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_PUTROOTFH); + *p = cpu_to_be32(OP_PUTROOTFH); hdr->nops++; hdr->replen += decode_putrootfh_maxsz; } @@ -1303,9 +1303,9 @@ static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context p = reserve_space(xdr, NFS4_STATEID_SIZE); if (ctx->state != NULL) { nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner); - p = xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE); } else - p = xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); } static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr) @@ -1313,13 +1313,13 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_READ); + *p = cpu_to_be32(OP_READ); encode_stateid(xdr, args->context); p = reserve_space(xdr, 12); p = xdr_encode_hyper(p, args->offset); - *p++ = cpu_to_be32(args->count); + *p = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_read_maxsz; } @@ -1345,7 +1345,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg else attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; *p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]); - *p++ = cpu_to_be32(attrs[1] & readdir->bitmask[1]); + *p = cpu_to_be32(attrs[1] & readdir->bitmask[1]); hdr->nops++; hdr->replen += decode_readdir_maxsz; dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n", @@ -1362,7 +1362,7 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink * __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_READLINK); + *p = cpu_to_be32(OP_READLINK); hdr->nops++; hdr->replen += decode_readlink_maxsz; } @@ -1374,7 +1374,7 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_REMOVE); *p++ = cpu_to_be32(name->len); - p = xdr_encode_opaque_fixed(p, name->name, name->len); + xdr_encode_opaque_fixed(p, name->name, name->len); hdr->nops++; hdr->replen += decode_remove_maxsz; } @@ -1386,11 +1386,11 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co p = reserve_space(xdr, 8 + oldname->len); *p++ = cpu_to_be32(OP_RENAME); *p++ = cpu_to_be32(oldname->len); - p = xdr_encode_opaque_fixed(p, oldname->name, oldname->len); + xdr_encode_opaque_fixed(p, oldname->name, oldname->len); p = reserve_space(xdr, 4 + newname->len); *p++ = cpu_to_be32(newname->len); - p = xdr_encode_opaque_fixed(p, newname->name, newname->len); + xdr_encode_opaque_fixed(p, newname->name, newname->len); hdr->nops++; hdr->replen += decode_rename_maxsz; } @@ -1401,7 +1401,7 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client p = reserve_space(xdr, 12); *p++ = cpu_to_be32(OP_RENEW); - p = xdr_encode_hyper(p, client_stateid->cl_clientid); + xdr_encode_hyper(p, client_stateid->cl_clientid); hdr->nops++; hdr->replen += decode_renew_maxsz; } @@ -1412,7 +1412,7 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_RESTOREFH); + *p = cpu_to_be32(OP_RESTOREFH); hdr->nops++; hdr->replen += decode_restorefh_maxsz; } @@ -1424,14 +1424,14 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); - p = xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); p = reserve_space(xdr, 2*4); *p++ = cpu_to_be32(1); - *p++ = cpu_to_be32(FATTR4_WORD0_ACL); + *p = cpu_to_be32(FATTR4_WORD0_ACL); if (arg->acl_len % 4) return -EINVAL; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(arg->acl_len); + *p = cpu_to_be32(arg->acl_len); xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); hdr->nops++; hdr->replen += decode_setacl_maxsz; @@ -1444,7 +1444,7 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_SAVEFH); + *p = cpu_to_be32(OP_SAVEFH); hdr->nops++; hdr->replen += decode_savefh_maxsz; } @@ -1455,7 +1455,7 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_SETATTR); - p = xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_setattr_maxsz; encode_attrs(xdr, arg->iap, server); @@ -1467,15 +1467,15 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie p = reserve_space(xdr, 4 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID); - p = xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); + xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(setclientid->sc_prog); + *p = cpu_to_be32(setclientid->sc_prog); encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid); encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr); p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(setclientid->sc_cb_ident); + *p = cpu_to_be32(setclientid->sc_cb_ident); hdr->nops++; hdr->replen += decode_setclientid_maxsz; } @@ -1487,7 +1487,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ p = reserve_space(xdr, 12 + NFS4_VERIFIER_SIZE); *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); p = xdr_encode_hyper(p, client_state->cl_clientid); - p = xdr_encode_opaque_fixed(p, client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); + xdr_encode_opaque_fixed(p, client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); hdr->nops++; hdr->replen += decode_setclientid_confirm_maxsz; } @@ -1497,14 +1497,14 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg __be32 *p; p = reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_WRITE); + *p = cpu_to_be32(OP_WRITE); encode_stateid(xdr, args->context); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, args->offset); *p++ = cpu_to_be32(args->stable); - *p++ = cpu_to_be32(args->count); + *p = cpu_to_be32(args->count); xdr_write_pages(xdr, args->pages, args->pgbase, args->count); hdr->nops++; @@ -1518,7 +1518,7 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); *p++ = cpu_to_be32(OP_DELEGRETURN); - p = xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_delegreturn_maxsz; } @@ -1533,14 +1533,14 @@ static void encode_exchange_id(struct xdr_stream *xdr, p = reserve_space(xdr, 4 + sizeof(args->verifier->data)); *p++ = cpu_to_be32(OP_EXCHANGE_ID); - p = xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data)); + xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data)); encode_string(xdr, args->id_len, args->id); p = reserve_space(xdr, 12); *p++ = cpu_to_be32(args->flags); *p++ = cpu_to_be32(0); /* zero length state_protect4_a */ - *p++ = cpu_to_be32(0); /* zero length implementation id array */ + *p = cpu_to_be32(0); /* zero length implementation id array */ hdr->nops++; hdr->replen += decode_exchange_id_maxsz; } @@ -1591,7 +1591,7 @@ static void encode_create_session(struct xdr_stream *xdr, p = xdr_encode_opaque_fixed(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ - *p++ = cpu_to_be32(0); /* No more gids */ + *p = cpu_to_be32(0); /* No more gids */ hdr->nops++; hdr->replen += decode_create_session_maxsz; } @@ -1603,7 +1603,7 @@ static void encode_destroy_session(struct xdr_stream *xdr, __be32 *p; p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN); *p++ = cpu_to_be32(OP_DESTROY_SESSION); - p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); hdr->nops++; hdr->replen += decode_destroy_session_maxsz; } @@ -1646,7 +1646,7 @@ static void encode_sequence(struct xdr_stream *xdr, *p++ = cpu_to_be32(slot->seq_nr); *p++ = cpu_to_be32(args->sa_slotid); *p++ = cpu_to_be32(tp->highest_used_slotid); - *p++ = cpu_to_be32(args->sa_cache_this); + *p = cpu_to_be32(args->sa_cache_this); hdr->nops++; hdr->replen += decode_sequence_maxsz; #endif /* CONFIG_NFS_V4_1 */ From 811652bd6edd66dd35bf9caacdfe96d19f75a47e Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:34 +0300 Subject: [PATCH 62/87] nfs: nfs4xdr: merge xdr_encode_int+xdr_encode_opaque_fixed into xdr_encode_opaque use encode_string where appropriate. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 42 ++++++++++++++---------------------------- 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d75f821cad01..efa78ad98228 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -732,9 +732,8 @@ static void encode_compound_hdr(struct xdr_stream *xdr, dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag); BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); - p = reserve_space(xdr, 12 + hdr->taglen); - *p++ = cpu_to_be32(hdr->taglen); - p = xdr_encode_opaque_fixed(p, hdr->tag, hdr->taglen); + p = reserve_space(xdr, 4 + hdr->taglen + 8); + p = xdr_encode_opaque(p, hdr->tag, hdr->taglen); *p++ = cpu_to_be32(hdr->minorversion); hdr->nops_p = p; *p = cpu_to_be32(hdr->nops); @@ -832,13 +831,11 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const } if (iap->ia_valid & ATTR_UID) { bmval1 |= FATTR4_WORD1_OWNER; - *p++ = cpu_to_be32(owner_namelen); - p = xdr_encode_opaque_fixed(p, owner_name, owner_namelen); + p = xdr_encode_opaque(p, owner_name, owner_namelen); } if (iap->ia_valid & ATTR_GID) { bmval1 |= FATTR4_WORD1_OWNER_GROUP; - *p++ = cpu_to_be32(owner_grouplen); - p = xdr_encode_opaque_fixed(p, owner_group, owner_grouplen); + p = xdr_encode_opaque(p, owner_group, owner_grouplen); } if (iap->ia_valid & ATTR_ATIME_SET) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; @@ -939,9 +936,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * break; } - p = reserve_space(xdr, 4 + create->name->len); - *p++ = cpu_to_be32(create->name->len); - xdr_encode_opaque_fixed(p, create->name->name, create->name->len); + encode_string(xdr, create->name->len, create->name->name); hdr->nops++; hdr->replen += decode_create_maxsz; @@ -1007,8 +1002,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_LINK); - *p++ = cpu_to_be32(name->len); - xdr_encode_opaque_fixed(p, name->name, name->len); + xdr_encode_opaque(p, name->name, name->len); hdr->nops++; hdr->replen += decode_link_maxsz; } @@ -1100,8 +1094,7 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_LOOKUP); - *p++ = cpu_to_be32(len); - xdr_encode_opaque_fixed(p, name->name, len); + xdr_encode_opaque(p, name->name, len); hdr->nops++; hdr->replen += decode_lookup_maxsz; } @@ -1279,8 +1272,7 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd p = reserve_space(xdr, 8 + len); *p++ = cpu_to_be32(OP_PUTFH); - *p++ = cpu_to_be32(len); - xdr_encode_opaque_fixed(p, fh->data, len); + xdr_encode_opaque(p, fh->data, len); hdr->nops++; hdr->replen += decode_putfh_maxsz; } @@ -1373,8 +1365,7 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc p = reserve_space(xdr, 8 + name->len); *p++ = cpu_to_be32(OP_REMOVE); - *p++ = cpu_to_be32(name->len); - xdr_encode_opaque_fixed(p, name->name, name->len); + xdr_encode_opaque(p, name->name, name->len); hdr->nops++; hdr->replen += decode_remove_maxsz; } @@ -1383,14 +1374,10 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co { __be32 *p; - p = reserve_space(xdr, 8 + oldname->len); - *p++ = cpu_to_be32(OP_RENAME); - *p++ = cpu_to_be32(oldname->len); - xdr_encode_opaque_fixed(p, oldname->name, oldname->len); - - p = reserve_space(xdr, 4 + newname->len); - *p++ = cpu_to_be32(newname->len); - xdr_encode_opaque_fixed(p, newname->name, newname->len); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_RENAME); + encode_string(xdr, oldname->len, oldname->name); + encode_string(xdr, newname->len, newname->name); hdr->nops++; hdr->replen += decode_rename_maxsz; } @@ -1587,8 +1574,7 @@ static void encode_create_session(struct xdr_stream *xdr, /* authsys_parms rfc1831 */ *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ - *p++ = cpu_to_be32(len); - p = xdr_encode_opaque_fixed(p, machine_name, len); + p = xdr_encode_opaque(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ *p = cpu_to_be32(0); /* No more gids */ From 6f723f7710024bb151ca8c5277ce8c71beec4db8 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:37 +0300 Subject: [PATCH 63/87] nfs: nfs4xdr: get rid of READ32 s/READ32\((.*)\)/\1 = be32_to_cpup(p++)/ Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 145 +++++++++++++++++++++++------------------------ 1 file changed, 72 insertions(+), 73 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index efa78ad98228..5f6b46f17c5b 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2433,7 +2433,6 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define READ32(x) (x) = ntohl(*p++) #define READ64(x) do { \ (x) = (u64)ntohl(*p++) << 32; \ (x) |= ntohl(*p++); \ @@ -2464,7 +2463,7 @@ static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char __be32 *p; READ_BUF(4); - READ32(*len); + *len = be32_to_cpup(p++); READ_BUF(*len); *string = (char *)p; return 0; @@ -2475,13 +2474,13 @@ static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) __be32 *p; READ_BUF(8); - READ32(hdr->status); - READ32(hdr->taglen); + hdr->status = be32_to_cpup(p++); + hdr->taglen = be32_to_cpup(p++); READ_BUF(hdr->taglen + 4); hdr->tag = (char *)p; p += XDR_QUADLEN(hdr->taglen); - READ32(hdr->nops); + hdr->nops = be32_to_cpup(p++); if (unlikely(hdr->nops < 1)) return nfs4_stat_to_errno(hdr->status); return 0; @@ -2494,14 +2493,14 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) int32_t nfserr; READ_BUF(8); - READ32(opnum); + opnum = be32_to_cpup(p++); if (opnum != expected) { dprintk("nfs: Server returned operation" " %d but we issued a request for %d\n", opnum, expected); return -EIO; } - READ32(nfserr); + nfserr = be32_to_cpup(p++); if (nfserr != NFS_OK) return nfs4_stat_to_errno(nfserr); return 0; @@ -2524,14 +2523,14 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) __be32 *p; READ_BUF(4); - READ32(bmlen); + bmlen = be32_to_cpup(p++); bitmap[0] = bitmap[1] = 0; READ_BUF((bmlen << 2)); if (bmlen > 0) { - READ32(bitmap[0]); + bitmap[0] = be32_to_cpup(p++); if (bmlen > 1) - READ32(bitmap[1]); + bitmap[1] = be32_to_cpup(p++); } return 0; } @@ -2541,7 +2540,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 *p; READ_BUF(4); - READ32(*attrlen); + *attrlen = be32_to_cpup(p++); *savep = xdr->p; return 0; } @@ -2567,7 +2566,7 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) { READ_BUF(4); - READ32(*type); + *type = be32_to_cpup(p++); if (*type < NF4REG || *type > NF4NAMEDATTR) { dprintk("%s: bad type %d\n", __func__, *type); return -EIO; @@ -2625,7 +2624,7 @@ static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, ui return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) { READ_BUF(4); - READ32(*res); + *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT; } dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true"); @@ -2641,7 +2640,7 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) { READ_BUF(4); - READ32(*res); + *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT; } dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true"); @@ -2679,7 +2678,7 @@ static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) { READ_BUF(4); - READ32(*res); + *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME; } dprintk("%s: file size=%u\n", __func__, (unsigned int)*res); @@ -2695,7 +2694,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) { READ_BUF(4); - READ32(*res); + *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT; } dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res); @@ -2796,7 +2795,7 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) int status = 0; READ_BUF(4); - READ32(n); + n = be32_to_cpup(p++); if (n == 0) goto root_path; dprintk("path "); @@ -2848,7 +2847,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(status != 0)) goto out; READ_BUF(4); - READ32(n); + n = be32_to_cpup(p++); if (n <= 0) goto out_eio; res->nlocations = 0; @@ -2857,7 +2856,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st struct nfs4_fs_location *loc = &res->locations[res->nlocations]; READ_BUF(4); - READ32(m); + m = be32_to_cpup(p++); loc->nservers = 0; dprintk("%s: servers ", __func__); @@ -2928,7 +2927,7 @@ static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) { READ_BUF(4); - READ32(*maxlink); + *maxlink = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_MAXLINK; } dprintk("%s: maxlink=%u\n", __func__, *maxlink); @@ -2945,7 +2944,7 @@ static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) { READ_BUF(4); - READ32(*maxname); + *maxname = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_MAXNAME; } dprintk("%s: maxname=%u\n", __func__, *maxname); @@ -3005,7 +3004,7 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MODE)) { READ_BUF(4); - READ32(tmp); + tmp = be32_to_cpup(p++); *mode = tmp & ~S_IFMT; bitmap[1] &= ~FATTR4_WORD1_MODE; ret = NFS_ATTR_FATTR_MODE; @@ -3024,7 +3023,7 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) { READ_BUF(4); - READ32(*nlink); + *nlink = be32_to_cpup(p++); bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; ret = NFS_ATTR_FATTR_NLINK; } @@ -3043,7 +3042,7 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) { READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); READ_BUF(len); if (len < XDR_MAX_NETOBJ) { if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0) @@ -3071,7 +3070,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) { READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); READ_BUF(len); if (len < XDR_MAX_NETOBJ) { if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0) @@ -3101,8 +3100,8 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde dev_t tmp; READ_BUF(8); - READ32(major); - READ32(minor); + major = be32_to_cpup(p++); + minor = be32_to_cpup(p++); tmp = MKDEV(major, minor); if (MAJOR(tmp) == major && MINOR(tmp) == minor) *rdev = tmp; @@ -3191,7 +3190,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) READ_BUF(12); READ64(sec); - READ32(nsec); + nsec = be32_to_cpup(p++); time->tv_sec = (time_t)sec; time->tv_nsec = (long)nsec; return 0; @@ -3273,7 +3272,7 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c __be32 *p; READ_BUF(20); - READ32(cinfo->atomic); + cinfo->atomic = be32_to_cpup(p++); READ64(cinfo->before); READ64(cinfo->after); return 0; @@ -3289,8 +3288,8 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) if (status) return status; READ_BUF(8); - READ32(supp); - READ32(acc); + supp = be32_to_cpup(p++); + acc = be32_to_cpup(p++); access->supported = supp; access->access = acc; return 0; @@ -3336,7 +3335,7 @@ static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) if ((status = decode_change_info(xdr, cinfo))) return status; READ_BUF(4); - READ32(bmlen); + bmlen = be32_to_cpup(p++); READ_BUF(bmlen << 2); return 0; } @@ -3591,7 +3590,7 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) return status; READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); if (len > NFS4_FHSIZE) return -EIO; fh->size = len; @@ -3622,7 +3621,7 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) READ_BUF(32); READ64(offset); READ64(length); - READ32(type); + type = be32_to_cpup(p++); if (fl != NULL) { fl->fl_start = (loff_t)offset; fl->fl_end = fl->fl_start + (loff_t)length - 1; @@ -3634,7 +3633,7 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) fl->fl_pid = 0; } READ64(clientid); - READ32(namelen); + namelen = be32_to_cpup(p++); READ_BUF(namelen); return -NFS4ERR_DENIED; } @@ -3695,14 +3694,14 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) uint32_t limit_type, nblocks, blocksize; READ_BUF(12); - READ32(limit_type); + limit_type = be32_to_cpup(p++); switch (limit_type) { case 1: READ64(*maxsize); break; case 2: - READ32(nblocks); - READ32(blocksize); + nblocks = be32_to_cpup(p++); + blocksize = be32_to_cpup(p++); *maxsize = (uint64_t)nblocks * (uint64_t)blocksize; } return 0; @@ -3714,14 +3713,14 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) uint32_t delegation_type; READ_BUF(4); - READ32(delegation_type); + delegation_type = be32_to_cpup(p++); if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { res->delegation_type = 0; return 0; } READ_BUF(NFS4_STATEID_SIZE+4); COPYMEM(res->delegation.data, NFS4_STATEID_SIZE); - READ32(res->do_recall); + res->do_recall = be32_to_cpup(p++); switch (delegation_type) { case NFS4_OPEN_DELEGATE_READ: @@ -3752,15 +3751,15 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) decode_change_info(xdr, &res->cinfo); READ_BUF(8); - READ32(res->rflags); - READ32(bmlen); + res->rflags = be32_to_cpup(p++); + bmlen = be32_to_cpup(p++); if (bmlen > 10) goto xdr_error; READ_BUF(bmlen << 2); savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE); for (i = 0; i < savewords; ++i) - READ32(res->attrset[i]); + res->attrset[i] = be32_to_cpup(p++); for (; i < NFS4_BITMAP_SIZE; i++) res->attrset[i] = 0; @@ -3821,8 +3820,8 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ if (status) return status; READ_BUF(8); - READ32(eof); - READ32(count); + eof = be32_to_cpup(p++); + count = be32_to_cpup(p++); hdrlen = (u8 *) p - (u8 *) iov->iov_base; recvd = req->rq_rcv_buf.len - hdrlen; if (count > recvd) { @@ -3948,7 +3947,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) /* Convert length of symlink */ READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); if (len >= rcvbuf->page_len || len <= 0) { dprintk("nfs: server returned giant symlink!\n"); return -ENAMETOOLONG; @@ -4070,7 +4069,7 @@ static int decode_setattr(struct xdr_stream *xdr) if (status) return status; READ_BUF(4); - READ32(bmlen); + bmlen = be32_to_cpup(p++); READ_BUF(bmlen << 2); return 0; } @@ -4082,13 +4081,13 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) int32_t nfserr; READ_BUF(8); - READ32(opnum); + opnum = be32_to_cpup(p++); if (opnum != OP_SETCLIENTID) { dprintk("nfs: decode_setclientid: Server returned operation" " %d\n", opnum); return -EIO; } - READ32(nfserr); + nfserr = be32_to_cpup(p++); if (nfserr == NFS_OK) { READ_BUF(8 + NFS4_VERIFIER_SIZE); READ64(clp->cl_clientid); @@ -4098,12 +4097,12 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) /* skip netid string */ READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); READ_BUF(len); /* skip uaddr string */ READ_BUF(4); - READ32(len); + len = be32_to_cpup(p++); READ_BUF(len); return -NFSERR_CLID_INUSE; } else @@ -4127,8 +4126,8 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) return status; READ_BUF(16); - READ32(res->count); - READ32(res->verf->committed); + res->count = be32_to_cpup(p++); + res->verf->committed = be32_to_cpup(p++); COPYMEM(res->verf->verifier, 8); return 0; } @@ -4154,11 +4153,11 @@ static int decode_exchange_id(struct xdr_stream *xdr, READ_BUF(8); READ64(clp->cl_ex_clid); READ_BUF(12); - READ32(clp->cl_seqid); - READ32(clp->cl_exchange_flags); + clp->cl_seqid = be32_to_cpup(p++); + clp->cl_exchange_flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy != SP4_NONE) return -EIO; @@ -4167,17 +4166,17 @@ static int decode_exchange_id(struct xdr_stream *xdr, /* Throw away Major id */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); /* Throw away server_scope */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); /* Throw away Implementation id array */ READ_BUF(4); - READ32(dummy); + dummy = be32_to_cpup(p++); READ_BUF(dummy); return 0; @@ -4190,13 +4189,13 @@ static int decode_chan_attrs(struct xdr_stream *xdr, u32 nr_attrs; READ_BUF(28); - READ32(attrs->headerpadsz); - READ32(attrs->max_rqst_sz); - READ32(attrs->max_resp_sz); - READ32(attrs->max_resp_sz_cached); - READ32(attrs->max_ops); - READ32(attrs->max_reqs); - READ32(nr_attrs); + attrs->headerpadsz = be32_to_cpup(p++); + attrs->max_rqst_sz = be32_to_cpup(p++); + attrs->max_resp_sz = be32_to_cpup(p++); + attrs->max_resp_sz_cached = be32_to_cpup(p++); + attrs->max_ops = be32_to_cpup(p++); + attrs->max_reqs = be32_to_cpup(p++); + nr_attrs = be32_to_cpup(p++); if (unlikely(nr_attrs > 1)) { printk(KERN_WARNING "%s: Invalid rdma channel attrs count %u\n", __func__, nr_attrs); @@ -4226,8 +4225,8 @@ static int decode_create_session(struct xdr_stream *xdr, /* seqid, flags */ READ_BUF(8); - READ32(clp->cl_seqid); - READ32(session->flags); + clp->cl_seqid = be32_to_cpup(p++); + session->flags = be32_to_cpup(p++); /* Channel attributes */ status = decode_chan_attrs(xdr, &session->fc_attrs); @@ -4275,23 +4274,23 @@ static int decode_sequence(struct xdr_stream *xdr, goto out_err; } /* seqid */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy != slot->seq_nr) { dprintk("%s Invalid sequence number\n", __func__); goto out_err; } /* slot id */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy != res->sr_slotid) { dprintk("%s Invalid slot id\n", __func__); goto out_err; } /* highest slot id - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* target highest slot id - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* result flags - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p++); status = 0; out_err: res->sr_status = status; From 3ceb4dbb993fdab6a6fafc69db36686278871134 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:41 +0300 Subject: [PATCH 64/87] nfs: nfs4xdr: get rid of READ64 s/READ64\(\*(.*)\)/p = xdr_decode_hyper(p, \1)/ s/READ64\((.*)\)/p = xdr_decode_hyper(p, &\1)/ Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 54 ++++++++++++++++++++++-------------------------- 1 file changed, 25 insertions(+), 29 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5f6b46f17c5b..238189ceae3f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2433,10 +2433,6 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define READ64(x) do { \ - (x) = (u64)ntohl(*p++) << 32; \ - (x) |= ntohl(*p++); \ -} while (0) #define READTIME(x) do { \ p++; \ (x.tv_sec) = ntohl(*p++); \ @@ -2588,7 +2584,7 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) { READ_BUF(8); - READ64(*change); + p = xdr_decode_hyper(p, change); bitmap[0] &= ~FATTR4_WORD0_CHANGE; ret = NFS_ATTR_FATTR_CHANGE; } @@ -2607,7 +2603,7 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t * return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) { READ_BUF(8); - READ64(*size); + p = xdr_decode_hyper(p, size); bitmap[0] &= ~FATTR4_WORD0_SIZE; ret = NFS_ATTR_FATTR_SIZE; } @@ -2658,8 +2654,8 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FSID)) { READ_BUF(16); - READ64(fsid->major); - READ64(fsid->minor); + p = xdr_decode_hyper(p, &fsid->major); + p = xdr_decode_hyper(p, &fsid->minor); bitmap[0] &= ~FATTR4_WORD0_FSID; ret = NFS_ATTR_FATTR_FSID; } @@ -2711,7 +2707,7 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) { READ_BUF(8); - READ64(*fileid); + p = xdr_decode_hyper(p, fileid); bitmap[0] &= ~FATTR4_WORD0_FILEID; ret = NFS_ATTR_FATTR_FILEID; } @@ -2729,7 +2725,7 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) { READ_BUF(8); - READ64(*fileid); + p = xdr_decode_hyper(p, fileid); bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; ret = NFS_ATTR_FATTR_FILEID; } @@ -2747,7 +2743,7 @@ static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL; } dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res); @@ -2764,7 +2760,7 @@ static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_FREE; } dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res); @@ -2781,7 +2777,7 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL; } dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res); @@ -2910,7 +2906,7 @@ static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uin return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE; } dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res); @@ -2962,7 +2958,7 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ if (likely(bitmap[0] & FATTR4_WORD0_MAXREAD)) { uint64_t maxread; READ_BUF(8); - READ64(maxread); + p = xdr_decode_hyper(p, &maxread); if (maxread > 0x7FFFFFFF) maxread = 0x7FFFFFFF; *res = (uint32_t)maxread; @@ -2983,7 +2979,7 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 if (likely(bitmap[0] & FATTR4_WORD0_MAXWRITE)) { uint64_t maxwrite; READ_BUF(8); - READ64(maxwrite); + p = xdr_decode_hyper(p, &maxwrite); if (maxwrite > 0x7FFFFFFF) maxwrite = 0x7FFFFFFF; *res = (uint32_t)maxwrite; @@ -3122,7 +3118,7 @@ static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL; } dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res); @@ -3139,7 +3135,7 @@ static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE; } dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res); @@ -3156,7 +3152,7 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) { READ_BUF(8); - READ64(*res); + p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL; } dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res); @@ -3173,7 +3169,7 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) { READ_BUF(8); - READ64(*used); + p = xdr_decode_hyper(p, used); bitmap[1] &= ~FATTR4_WORD1_SPACE_USED; ret = NFS_ATTR_FATTR_SPACE_USED; } @@ -3189,7 +3185,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) uint32_t nsec; READ_BUF(12); - READ64(sec); + p = xdr_decode_hyper(p, &sec); nsec = be32_to_cpup(p++); time->tv_sec = (time_t)sec; time->tv_nsec = (long)nsec; @@ -3273,8 +3269,8 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c READ_BUF(20); cinfo->atomic = be32_to_cpup(p++); - READ64(cinfo->before); - READ64(cinfo->after); + p = xdr_decode_hyper(p, &cinfo->before); + p = xdr_decode_hyper(p, &cinfo->after); return 0; } @@ -3619,8 +3615,8 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) uint32_t namelen, type; READ_BUF(32); - READ64(offset); - READ64(length); + p = xdr_decode_hyper(p, &offset); + p = xdr_decode_hyper(p, &length); type = be32_to_cpup(p++); if (fl != NULL) { fl->fl_start = (loff_t)offset; @@ -3632,7 +3628,7 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) fl->fl_type = F_RDLCK; fl->fl_pid = 0; } - READ64(clientid); + p = xdr_decode_hyper(p, &clientid); namelen = be32_to_cpup(p++); READ_BUF(namelen); return -NFS4ERR_DENIED; @@ -3697,7 +3693,7 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) limit_type = be32_to_cpup(p++); switch (limit_type) { case 1: - READ64(*maxsize); + p = xdr_decode_hyper(p, maxsize); break; case 2: nblocks = be32_to_cpup(p++); @@ -4090,7 +4086,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) nfserr = be32_to_cpup(p++); if (nfserr == NFS_OK) { READ_BUF(8 + NFS4_VERIFIER_SIZE); - READ64(clp->cl_clientid); + p = xdr_decode_hyper(p, &clp->cl_clientid); COPYMEM(clp->cl_confirm.data, NFS4_VERIFIER_SIZE); } else if (nfserr == NFSERR_CLID_INUSE) { uint32_t len; @@ -4151,7 +4147,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, return status; READ_BUF(8); - READ64(clp->cl_ex_clid); + p = xdr_decode_hyper(p, &clp->cl_ex_clid); READ_BUF(12); clp->cl_seqid = be32_to_cpup(p++); clp->cl_exchange_flags = be32_to_cpup(p++); From c816fd3406462702dee2e3859e70132c3aab7c10 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:44 +0300 Subject: [PATCH 65/87] nfs: nfs4xdr: get rid of READTIME It has no users. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 238189ceae3f..0c26bb2d43d9 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2433,11 +2433,6 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define READTIME(x) do { \ - p++; \ - (x.tv_sec) = ntohl(*p++); \ - (x.tv_nsec) = ntohl(*p++); \ -} while (0) #define COPYMEM(x,nbytes) do { \ memcpy((x), p, nbytes); \ p += XDR_QUADLEN(nbytes); \ From 686841b3cc3a71918b45ed148be7a01a4f10e3f8 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:48 +0300 Subject: [PATCH 66/87] nfs: nfs4xdr: introduce print_overflow_msg Part fo the nfs4xdr cleanup. READ_BUF will go away. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0c26bb2d43d9..8255ec7079d4 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2441,14 +2441,18 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, #define READ_BUF(nbytes) do { \ p = xdr_inline_decode(xdr, nbytes); \ if (unlikely(!p)) { \ - dprintk("nfs: %s: prematurely hit end of receive" \ - " buffer\n", __func__); \ - dprintk("nfs: %s: xdr->p=%p, bytes=%u, xdr->end=%p\n", \ - __func__, xdr->p, nbytes, xdr->end); \ + print_overflow_msg(__func__, xdr); \ return -EIO; \ } \ } while (0) +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("nfs: %s: prematurely hit end of receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} + static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string) { __be32 *p; From 07d30434cfe2f1a1553143c6b20f1fe68d2ef80a Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:52 +0300 Subject: [PATCH 67/87] nfs: nfs4xdr: introduce decode_opaque_fixed and decode_stateid helpers Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 71 +++++++++++++++++++++++++++--------------------- 1 file changed, 40 insertions(+), 31 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 8255ec7079d4..86e6983ef4fa 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3290,19 +3290,34 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) return 0; } -static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) +static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) { __be32 *p; + + p = xdr_inline_decode(xdr, len); + if (likely(p)) { + memcpy(buf, p, len); + return 0; + } + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + return decode_opaque_fixed(xdr, stateid->data, NFS4_STATEID_SIZE); +} + +static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) +{ int status; status = decode_op_hdr(xdr, OP_CLOSE); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; } static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res) @@ -3635,15 +3650,15 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_LOCK); if (status == -EIO) goto out; if (status == 0) { - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) + goto out; } else if (status == -NFS4ERR_DENIED) status = decode_lock_denied(xdr, NULL); if (res->open_seqid != NULL) @@ -3664,16 +3679,13 @@ static int decode_lockt(struct xdr_stream *xdr, struct nfs_lockt_res *res) static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_LOCKU); if (status != -EIO) nfs_increment_lock_seqid(status, res->seqid); - if (status == 0) { - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - } + if (status == 0) + status = decode_stateid(xdr, &res->stateid); return status; } @@ -3706,6 +3718,7 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) { __be32 *p; uint32_t delegation_type; + int status; READ_BUF(4); delegation_type = be32_to_cpup(p++); @@ -3713,8 +3726,10 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) res->delegation_type = 0; return 0; } - READ_BUF(NFS4_STATEID_SIZE+4); - COPYMEM(res->delegation.data, NFS4_STATEID_SIZE); + status = decode_stateid(xdr, &res->delegation); + if (unlikely(status)) + return status; + READ_BUF(4); res->do_recall = be32_to_cpup(p++); switch (delegation_type) { @@ -3738,10 +3753,10 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) status = decode_op_hdr(xdr, OP_OPEN); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) + if (!status) + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); decode_change_info(xdr, &res->cinfo); @@ -3766,32 +3781,26 @@ xdr_error: static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_OPEN_CONFIRM); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; } static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_OPEN_DOWNGRADE); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; } static int decode_putfh(struct xdr_stream *xdr) From db942bbd09563e169cc5d9004c32c1de33220fd1 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:19:56 +0300 Subject: [PATCH 68/87] nfs: nfs4xdr: introduce decode_verifier helper Signed-off-by: Benny Halevy [Trond: Fixed up an 'uninitialised variable' issue in decode_readdir] Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 86e6983ef4fa..404f2e6373f2 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3320,17 +3320,19 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) return status; } +static int decode_verifier(struct xdr_stream *xdr, void *verifier) +{ + return decode_opaque_fixed(xdr, verifier, 8); +} + static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_COMMIT); - if (status) - return status; - READ_BUF(8); - COPYMEM(res->verf->verifier, 8); - return 0; + if (!status) + status = decode_verifier(xdr, res->verf->verifier); + return status; } static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -3852,17 +3854,17 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n int status; status = decode_op_hdr(xdr, OP_READDIR); - if (status) + if (!status) + status = decode_verifier(xdr, readdir->verifier.data); + if (unlikely(status)) return status; - READ_BUF(8); - COPYMEM(readdir->verifier.data, 8); dprintk("%s: verifier = %08x:%08x\n", __func__, ((u32 *)readdir->verifier.data)[0], ((u32 *)readdir->verifier.data)[1]); - hdrlen = (char *) p - (char *) iov->iov_base; + hdrlen = (char *) xdr->p - (char *) iov->iov_base; recvd = rcvbuf->len - hdrlen; if (pglen > recvd) pglen = recvd; From e78291e4e07520348b0634095cf19ed3bc868965 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:20:00 +0300 Subject: [PATCH 69/87] nfs: nfs4xdr: introduce decode_sessionid helper Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 404f2e6373f2..00630f42a2b4 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4212,6 +4212,11 @@ static int decode_chan_attrs(struct xdr_stream *xdr, return 0; } +static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) +{ + return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); +} + static int decode_create_session(struct xdr_stream *xdr, struct nfs41_create_session_res *res) { @@ -4221,14 +4226,11 @@ static int decode_create_session(struct xdr_stream *xdr, struct nfs4_session *session = clp->cl_session; status = decode_op_hdr(xdr, OP_CREATE_SESSION); - - if (status) + if (!status) + status = decode_sessionid(xdr, &session->sess_id); + if (unlikely(status)) return status; - /* sessionid */ - READ_BUF(NFS4_MAX_SESSIONID_LEN); - COPYMEM(&session->sess_id, NFS4_MAX_SESSIONID_LEN); - /* seqid, flags */ READ_BUF(8); clp->cl_seqid = be32_to_cpup(p++); @@ -4262,7 +4264,9 @@ static int decode_sequence(struct xdr_stream *xdr, return 0; status = decode_op_hdr(xdr, OP_SEQUENCE); - if (status) + if (!status) + status = decode_sessionid(xdr, &id); + if (unlikely(status)) goto out_err; /* @@ -4271,15 +4275,16 @@ static int decode_sequence(struct xdr_stream *xdr, */ status = -ESERVERFAULT; - slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; - READ_BUF(NFS4_MAX_SESSIONID_LEN + 20); - COPYMEM(id.data, NFS4_MAX_SESSIONID_LEN); if (memcmp(id.data, res->sr_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("%s Invalid session id\n", __func__); goto out_err; } + + READ_BUF(20); + /* seqid */ + slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; dummy = be32_to_cpup(p++); if (dummy != slot->seq_nr) { dprintk("%s Invalid sequence number\n", __func__); From 99398d0655ada44ae464a1c93d13cd438a306ecd Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:20:05 +0300 Subject: [PATCH 70/87] nfs: nfs4xdr: get rid of COPYMEM Just directly call memcpy. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 00630f42a2b4..f69aafc23d44 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2433,11 +2433,6 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, * task to translate them into Linux-specific versions which are more * consistent with the style used in NFSv2/v3... */ -#define COPYMEM(x,nbytes) do { \ - memcpy((x), p, nbytes); \ - p += XDR_QUADLEN(nbytes); \ -} while (0) - #define READ_BUF(nbytes) do { \ p = xdr_inline_decode(xdr, nbytes); \ if (unlikely(!p)) { \ @@ -3607,7 +3602,7 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) return -EIO; fh->size = len; READ_BUF(len); - COPYMEM(fh->data, len); + memcpy(fh->data, p, len); return 0; } @@ -4097,7 +4092,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) if (nfserr == NFS_OK) { READ_BUF(8 + NFS4_VERIFIER_SIZE); p = xdr_decode_hyper(p, &clp->cl_clientid); - COPYMEM(clp->cl_confirm.data, NFS4_VERIFIER_SIZE); + memcpy(clp->cl_confirm.data, p, NFS4_VERIFIER_SIZE); } else if (nfserr == NFSERR_CLID_INUSE) { uint32_t len; @@ -4134,7 +4129,7 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) READ_BUF(16); res->count = be32_to_cpup(p++); res->verf->committed = be32_to_cpup(p++); - COPYMEM(res->verf->verifier, 8); + memcpy(res->verf->verifier, p, 8); return 0; } From 2460ba57c49c36dfef0b62c929461de09240fe17 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:20:10 +0300 Subject: [PATCH 71/87] nfs: nfs4xdr: simplify decode_exchange_id by reusing decode_opaque_inline Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f69aafc23d44..3f49da0960e3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4144,6 +4144,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, { __be32 *p; uint32_t dummy; + char *dummy_str; int status; struct nfs_client *clp = res->client; @@ -4166,19 +4167,19 @@ static int decode_exchange_id(struct xdr_stream *xdr, READ_BUF(8); /* Throw away Major id */ - READ_BUF(4); - dummy = be32_to_cpup(p++); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; /* Throw away server_scope */ - READ_BUF(4); - dummy = be32_to_cpup(p++); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; /* Throw away Implementation id array */ - READ_BUF(4); - dummy = be32_to_cpup(p++); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; return 0; } From c0eae66ece40bdb8cd88c5106834b71a1c9f421c Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:20:14 +0300 Subject: [PATCH 72/87] nfs: nfs4xdr: get rid of READ_BUF Use xdr_inline_decode instead. Open code debug printout and error return. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 475 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 379 insertions(+), 96 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3f49da0960e3..b0d690c3a24c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2423,24 +2423,6 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, } #endif /* CONFIG_NFS_V4_1 */ -/* - * START OF "GENERIC" DECODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ -#define READ_BUF(nbytes) do { \ - p = xdr_inline_decode(xdr, nbytes); \ - if (unlikely(!p)) { \ - print_overflow_msg(__func__, xdr); \ - return -EIO; \ - } \ -} while (0) - static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) { dprintk("nfs: %s: prematurely hit end of receive buffer. " @@ -2452,28 +2434,42 @@ static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char { __be32 *p; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *len = be32_to_cpup(p++); - READ_BUF(*len); + p = xdr_inline_decode(xdr, *len); + if (unlikely(!p)) + goto out_overflow; *string = (char *)p; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; hdr->status = be32_to_cpup(p++); hdr->taglen = be32_to_cpup(p++); - READ_BUF(hdr->taglen + 4); + p = xdr_inline_decode(xdr, hdr->taglen + 4); + if (unlikely(!p)) + goto out_overflow; hdr->tag = (char *)p; p += XDR_QUADLEN(hdr->taglen); hdr->nops = be32_to_cpup(p++); if (unlikely(hdr->nops < 1)) return nfs4_stat_to_errno(hdr->status); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) @@ -2482,7 +2478,9 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) uint32_t opnum; int32_t nfserr; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; opnum = be32_to_cpup(p++); if (opnum != expected) { dprintk("nfs: Server returned operation" @@ -2494,6 +2492,9 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) if (nfserr != NFS_OK) return nfs4_stat_to_errno(nfserr); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } /* Dummy routine */ @@ -2503,8 +2504,11 @@ static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp) unsigned int strlen; char *str; - READ_BUF(12); - return decode_opaque_inline(xdr, &strlen, &str); + p = xdr_inline_decode(xdr, 12); + if (likely(p)) + return decode_opaque_inline(xdr, &strlen, &str); + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) @@ -2512,27 +2516,39 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) uint32_t bmlen; __be32 *p; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; bmlen = be32_to_cpup(p++); bitmap[0] = bitmap[1] = 0; - READ_BUF((bmlen << 2)); + p = xdr_inline_decode(xdr, (bmlen << 2)); + if (unlikely(!p)) + goto out_overflow; if (bmlen > 0) { bitmap[0] = be32_to_cpup(p++); if (bmlen > 1) bitmap[1] = be32_to_cpup(p++); } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep) { __be32 *p; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *attrlen = be32_to_cpup(p++); *savep = xdr->p; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask) @@ -2555,7 +2571,9 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *type = be32_to_cpup(p++); if (*type < NF4REG || *type > NF4NAMEDATTR) { dprintk("%s: bad type %d\n", __func__, *type); @@ -2566,6 +2584,9 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * } dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change) @@ -2577,7 +2598,9 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, change); bitmap[0] &= ~FATTR4_WORD0_CHANGE; ret = NFS_ATTR_FATTR_CHANGE; @@ -2585,6 +2608,9 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t dprintk("%s: change attribute=%Lu\n", __func__, (unsigned long long)*change); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size) @@ -2596,13 +2622,18 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t * if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, size); bitmap[0] &= ~FATTR4_WORD0_SIZE; ret = NFS_ATTR_FATTR_SIZE; } dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2613,12 +2644,17 @@ static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, ui if (unlikely(bitmap[0] & (FATTR4_WORD0_LINK_SUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT; } dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true"); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2629,12 +2665,17 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, if (unlikely(bitmap[0] & (FATTR4_WORD0_SYMLINK_SUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT; } dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true"); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid) @@ -2647,7 +2688,9 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs if (unlikely(bitmap[0] & (FATTR4_WORD0_FSID - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FSID)) { - READ_BUF(16); + p = xdr_inline_decode(xdr, 16); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &fsid->major); p = xdr_decode_hyper(p, &fsid->minor); bitmap[0] &= ~FATTR4_WORD0_FSID; @@ -2657,6 +2700,9 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs (unsigned long long)fsid->major, (unsigned long long)fsid->minor); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2667,12 +2713,17 @@ static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_LEASE_TIME - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME; } dprintk("%s: file size=%u\n", __func__, (unsigned int)*res); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2683,12 +2734,17 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *res = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT; } dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) @@ -2700,13 +2756,18 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, fileid); bitmap[0] &= ~FATTR4_WORD0_FILEID; ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) @@ -2718,13 +2779,18 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, fileid); bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2736,12 +2802,17 @@ static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_AVAIL - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL; } dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2753,12 +2824,17 @@ static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_FREE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_FREE; } dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2770,12 +2846,17 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_TOTAL - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL; } dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) @@ -2784,7 +2865,9 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) __be32 *p; int status = 0; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; n = be32_to_cpup(p++); if (n == 0) goto root_path; @@ -2819,6 +2902,9 @@ out_eio: dprintk(" status %d", status); status = -EIO; goto out; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res) @@ -2836,7 +2922,9 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st status = decode_pathname(xdr, &res->fs_path); if (unlikely(status != 0)) goto out; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; n = be32_to_cpup(p++); if (n <= 0) goto out_eio; @@ -2845,7 +2933,9 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st u32 m; struct nfs4_fs_location *loc = &res->locations[res->nlocations]; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; m = be32_to_cpup(p++); loc->nservers = 0; @@ -2885,6 +2975,8 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st out: dprintk("%s: fs_locations done, error = %d\n", __func__, status); return status; +out_overflow: + print_overflow_msg(__func__, xdr); out_eio: status = -EIO; goto out; @@ -2899,12 +2991,17 @@ static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXFILESIZE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE; } dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxlink) @@ -2916,12 +3013,17 @@ static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXLINK - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *maxlink = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_MAXLINK; } dprintk("%s: maxlink=%u\n", __func__, *maxlink); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxname) @@ -2933,12 +3035,17 @@ static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXNAME - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *maxname = be32_to_cpup(p++); bitmap[0] &= ~FATTR4_WORD0_MAXNAME; } dprintk("%s: maxname=%u\n", __func__, *maxname); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2951,7 +3058,9 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXREAD)) { uint64_t maxread; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &maxread); if (maxread > 0x7FFFFFFF) maxread = 0x7FFFFFFF; @@ -2960,6 +3069,9 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ } dprintk("%s: maxread=%lu\n", __func__, (unsigned long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2972,7 +3084,9 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXWRITE)) { uint64_t maxwrite; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &maxwrite); if (maxwrite > 0x7FFFFFFF) maxwrite = 0x7FFFFFFF; @@ -2981,6 +3095,9 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 } dprintk("%s: maxwrite=%lu\n", __func__, (unsigned long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode) @@ -2993,7 +3110,9 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MODE)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; tmp = be32_to_cpup(p++); *mode = tmp & ~S_IFMT; bitmap[1] &= ~FATTR4_WORD1_MODE; @@ -3001,6 +3120,9 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m } dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink) @@ -3012,13 +3134,18 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; *nlink = be32_to_cpup(p++); bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; ret = NFS_ATTR_FATTR_NLINK; } dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid) @@ -3031,9 +3158,13 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); - READ_BUF(len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; if (len < XDR_MAX_NETOBJ) { if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0) ret = NFS_ATTR_FATTR_OWNER; @@ -3047,6 +3178,9 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf } dprintk("%s: uid=%d\n", __func__, (int)*uid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid) @@ -3059,9 +3193,13 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) { - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); - READ_BUF(len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; if (len < XDR_MAX_NETOBJ) { if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0) ret = NFS_ATTR_FATTR_GROUP; @@ -3075,6 +3213,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf } dprintk("%s: gid=%d\n", __func__, (int)*gid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev) @@ -3089,7 +3230,9 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde if (likely(bitmap[1] & FATTR4_WORD1_RAWDEV)) { dev_t tmp; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; major = be32_to_cpup(p++); minor = be32_to_cpup(p++); tmp = MKDEV(major, minor); @@ -3100,6 +3243,9 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde } dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3111,12 +3257,17 @@ static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_AVAIL - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL; } dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3128,12 +3279,17 @@ static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_FREE - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE; } dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3145,12 +3301,17 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_TOTAL - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL; } dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used) @@ -3162,7 +3323,9 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) { - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, used); bitmap[1] &= ~FATTR4_WORD1_SPACE_USED; ret = NFS_ATTR_FATTR_SPACE_USED; @@ -3170,6 +3333,9 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint dprintk("%s: space used=%Lu\n", __func__, (unsigned long long)*used); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) @@ -3178,12 +3344,17 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) uint64_t sec; uint32_t nsec; - READ_BUF(12); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &sec); nsec = be32_to_cpup(p++); time->tv_sec = (time_t)sec; time->tv_nsec = (long)nsec; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) @@ -3261,11 +3432,16 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c { __be32 *p; - READ_BUF(20); + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; cinfo->atomic = be32_to_cpup(p++); p = xdr_decode_hyper(p, &cinfo->before); p = xdr_decode_hyper(p, &cinfo->after); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) @@ -3277,12 +3453,17 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) status = decode_op_hdr(xdr, OP_ACCESS); if (status) return status; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; supp = be32_to_cpup(p++); acc = be32_to_cpup(p++); access->supported = supp; access->access = acc; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) @@ -3341,10 +3522,16 @@ static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) return status; if ((status = decode_change_info(xdr, cinfo))) return status; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; bmlen = be32_to_cpup(p++); - READ_BUF(bmlen << 2); - return 0; + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) @@ -3596,14 +3783,21 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) if (status) return status; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); if (len > NFS4_FHSIZE) return -EIO; fh->size = len; - READ_BUF(len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; memcpy(fh->data, p, len); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -3625,7 +3819,9 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) __be32 *p; uint32_t namelen, type; - READ_BUF(32); + p = xdr_inline_decode(xdr, 32); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &offset); p = xdr_decode_hyper(p, &length); type = be32_to_cpup(p++); @@ -3641,8 +3837,12 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) } p = xdr_decode_hyper(p, &clientid); namelen = be32_to_cpup(p++); - READ_BUF(namelen); - return -NFS4ERR_DENIED; + p = xdr_inline_decode(xdr, namelen); + if (likely(p)) + return -NFS4ERR_DENIED; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res) @@ -3697,7 +3897,9 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) __be32 *p; uint32_t limit_type, nblocks, blocksize; - READ_BUF(12); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; limit_type = be32_to_cpup(p++); switch (limit_type) { case 1: @@ -3709,6 +3911,9 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) *maxsize = (uint64_t)nblocks * (uint64_t)blocksize; } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) @@ -3717,7 +3922,9 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) uint32_t delegation_type; int status; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; delegation_type = be32_to_cpup(p++); if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { res->delegation_type = 0; @@ -3726,7 +3933,9 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) status = decode_stateid(xdr, &res->delegation); if (unlikely(status)) return status; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; res->do_recall = be32_to_cpup(p++); switch (delegation_type) { @@ -3739,6 +3948,9 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) return -EIO; } return decode_ace(xdr, NULL, res->server->nfs_client); +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) @@ -3757,13 +3969,17 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) decode_change_info(xdr, &res->cinfo); - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; res->rflags = be32_to_cpup(p++); bmlen = be32_to_cpup(p++); if (bmlen > 10) goto xdr_error; - READ_BUF(bmlen << 2); + p = xdr_inline_decode(xdr, bmlen << 2); + if (unlikely(!p)) + goto out_overflow; savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE); for (i = 0; i < savewords; ++i) res->attrset[i] = be32_to_cpup(p++); @@ -3774,6 +3990,9 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) xdr_error: dprintk("%s: Bitmap too large! Length = %u\n", __func__, bmlen); return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res) @@ -3820,7 +4039,9 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ status = decode_op_hdr(xdr, OP_READ); if (status) return status; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; eof = be32_to_cpup(p++); count = be32_to_cpup(p++); hdrlen = (u8 *) p - (u8 *) iov->iov_base; @@ -3835,6 +4056,9 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ res->eof = eof; res->count = count; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir) @@ -3947,7 +4171,9 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) return status; /* Convert length of symlink */ - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); if (len >= rcvbuf->page_len || len <= 0) { dprintk("nfs: server returned giant symlink!\n"); @@ -3972,6 +4198,9 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) kaddr[len+rcvbuf->page_base] = '\0'; kunmap_atomic(kaddr, KM_USER0); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_remove(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -4069,10 +4298,16 @@ static int decode_setattr(struct xdr_stream *xdr) status = decode_op_hdr(xdr, OP_SETATTR); if (status) return status; - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; bmlen = be32_to_cpup(p++); - READ_BUF(bmlen << 2); - return 0; + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) @@ -4081,7 +4316,9 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) uint32_t opnum; int32_t nfserr; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; opnum = be32_to_cpup(p++); if (opnum != OP_SETCLIENTID) { dprintk("nfs: decode_setclientid: Server returned operation" @@ -4090,26 +4327,39 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) } nfserr = be32_to_cpup(p++); if (nfserr == NFS_OK) { - READ_BUF(8 + NFS4_VERIFIER_SIZE); + p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &clp->cl_clientid); memcpy(clp->cl_confirm.data, p, NFS4_VERIFIER_SIZE); } else if (nfserr == NFSERR_CLID_INUSE) { uint32_t len; /* skip netid string */ - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); - READ_BUF(len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; /* skip uaddr string */ - READ_BUF(4); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; len = be32_to_cpup(p++); - READ_BUF(len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; return -NFSERR_CLID_INUSE; } else return nfs4_stat_to_errno(nfserr); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_setclientid_confirm(struct xdr_stream *xdr) @@ -4126,11 +4376,16 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) if (status) return status; - READ_BUF(16); + p = xdr_inline_decode(xdr, 16); + if (unlikely(!p)) + goto out_overflow; res->count = be32_to_cpup(p++); res->verf->committed = be32_to_cpup(p++); memcpy(res->verf->verifier, p, 8); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_delegreturn(struct xdr_stream *xdr) @@ -4152,9 +4407,13 @@ static int decode_exchange_id(struct xdr_stream *xdr, if (status) return status; - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &clp->cl_ex_clid); - READ_BUF(12); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; clp->cl_seqid = be32_to_cpup(p++); clp->cl_exchange_flags = be32_to_cpup(p++); @@ -4164,7 +4423,9 @@ static int decode_exchange_id(struct xdr_stream *xdr, return -EIO; /* Throw away minor_id */ - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; /* Throw away Major id */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); @@ -4182,6 +4443,9 @@ static int decode_exchange_id(struct xdr_stream *xdr, return status; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_chan_attrs(struct xdr_stream *xdr, @@ -4190,7 +4454,9 @@ static int decode_chan_attrs(struct xdr_stream *xdr, __be32 *p; u32 nr_attrs; - READ_BUF(28); + p = xdr_inline_decode(xdr, 28); + if (unlikely(!p)) + goto out_overflow; attrs->headerpadsz = be32_to_cpup(p++); attrs->max_rqst_sz = be32_to_cpup(p++); attrs->max_resp_sz = be32_to_cpup(p++); @@ -4203,9 +4469,15 @@ static int decode_chan_attrs(struct xdr_stream *xdr, __func__, nr_attrs); return -EINVAL; } - if (nr_attrs == 1) - READ_BUF(4); /* skip rdma_attrs */ + if (nr_attrs == 1) { + p = xdr_inline_decode(xdr, 4); /* skip rdma_attrs */ + if (unlikely(!p)) + goto out_overflow; + } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) @@ -4228,7 +4500,9 @@ static int decode_create_session(struct xdr_stream *xdr, return status; /* seqid, flags */ - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; clp->cl_seqid = be32_to_cpup(p++); session->flags = be32_to_cpup(p++); @@ -4237,6 +4511,9 @@ static int decode_create_session(struct xdr_stream *xdr, if (!status) status = decode_chan_attrs(xdr, &session->bc_attrs); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) @@ -4277,7 +4554,9 @@ static int decode_sequence(struct xdr_stream *xdr, goto out_err; } - READ_BUF(20); + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; /* seqid */ slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; @@ -4302,6 +4581,10 @@ static int decode_sequence(struct xdr_stream *xdr, out_err: res->sr_status = status; return status; +out_overflow: + print_overflow_msg(__func__, xdr); + status = -EIO; + goto out_err; #else /* CONFIG_NFS_V4_1 */ return 0; #endif /* CONFIG_NFS_V4_1 */ From cccddf4f5580131c9b963900e1d3400655e633cc Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 14 Aug 2009 17:20:19 +0300 Subject: [PATCH 73/87] nfs: nfs4xdr: optimize low level decoding do not increment decoding ptr if not needed. Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 118 +++++++++++++++++++++++------------------------ 1 file changed, 59 insertions(+), 59 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b0d690c3a24c..14b6f513648f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2437,7 +2437,7 @@ static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *len = be32_to_cpup(p++); + *len = be32_to_cpup(p); p = xdr_inline_decode(xdr, *len); if (unlikely(!p)) goto out_overflow; @@ -2456,14 +2456,14 @@ static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) if (unlikely(!p)) goto out_overflow; hdr->status = be32_to_cpup(p++); - hdr->taglen = be32_to_cpup(p++); + hdr->taglen = be32_to_cpup(p); p = xdr_inline_decode(xdr, hdr->taglen + 4); if (unlikely(!p)) goto out_overflow; hdr->tag = (char *)p; p += XDR_QUADLEN(hdr->taglen); - hdr->nops = be32_to_cpup(p++); + hdr->nops = be32_to_cpup(p); if (unlikely(hdr->nops < 1)) return nfs4_stat_to_errno(hdr->status); return 0; @@ -2488,7 +2488,7 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) opnum, expected); return -EIO; } - nfserr = be32_to_cpup(p++); + nfserr = be32_to_cpup(p); if (nfserr != NFS_OK) return nfs4_stat_to_errno(nfserr); return 0; @@ -2519,7 +2519,7 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - bmlen = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); bitmap[0] = bitmap[1] = 0; p = xdr_inline_decode(xdr, (bmlen << 2)); @@ -2528,7 +2528,7 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) if (bmlen > 0) { bitmap[0] = be32_to_cpup(p++); if (bmlen > 1) - bitmap[1] = be32_to_cpup(p++); + bitmap[1] = be32_to_cpup(p); } return 0; out_overflow: @@ -2543,7 +2543,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *attrlen = be32_to_cpup(p++); + *attrlen = be32_to_cpup(p); *savep = xdr->p; return 0; out_overflow: @@ -2574,7 +2574,7 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *type = be32_to_cpup(p++); + *type = be32_to_cpup(p); if (*type < NF4REG || *type > NF4NAMEDATTR) { dprintk("%s: bad type %d\n", __func__, *type); return -EIO; @@ -2601,7 +2601,7 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, change); + xdr_decode_hyper(p, change); bitmap[0] &= ~FATTR4_WORD0_CHANGE; ret = NFS_ATTR_FATTR_CHANGE; } @@ -2625,7 +2625,7 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t * p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, size); + xdr_decode_hyper(p, size); bitmap[0] &= ~FATTR4_WORD0_SIZE; ret = NFS_ATTR_FATTR_SIZE; } @@ -2647,7 +2647,7 @@ static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, ui p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *res = be32_to_cpup(p++); + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT; } dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true"); @@ -2668,7 +2668,7 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *res = be32_to_cpup(p++); + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT; } dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true"); @@ -2692,7 +2692,7 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs if (unlikely(!p)) goto out_overflow; p = xdr_decode_hyper(p, &fsid->major); - p = xdr_decode_hyper(p, &fsid->minor); + xdr_decode_hyper(p, &fsid->minor); bitmap[0] &= ~FATTR4_WORD0_FSID; ret = NFS_ATTR_FATTR_FSID; } @@ -2716,7 +2716,7 @@ static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *res = be32_to_cpup(p++); + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME; } dprintk("%s: file size=%u\n", __func__, (unsigned int)*res); @@ -2737,7 +2737,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *res = be32_to_cpup(p++); + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT; } dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res); @@ -2759,7 +2759,7 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, fileid); + xdr_decode_hyper(p, fileid); bitmap[0] &= ~FATTR4_WORD0_FILEID; ret = NFS_ATTR_FATTR_FILEID; } @@ -2782,7 +2782,7 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, fileid); + xdr_decode_hyper(p, fileid); bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; ret = NFS_ATTR_FATTR_FILEID; } @@ -2805,7 +2805,7 @@ static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL; } dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res); @@ -2827,7 +2827,7 @@ static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_FREE; } dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res); @@ -2849,7 +2849,7 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL; } dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res); @@ -2868,7 +2868,7 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - n = be32_to_cpup(p++); + n = be32_to_cpup(p); if (n == 0) goto root_path; dprintk("path "); @@ -2925,7 +2925,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - n = be32_to_cpup(p++); + n = be32_to_cpup(p); if (n <= 0) goto out_eio; res->nlocations = 0; @@ -2936,7 +2936,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - m = be32_to_cpup(p++); + m = be32_to_cpup(p); loc->nservers = 0; dprintk("%s: servers ", __func__); @@ -2994,7 +2994,7 @@ static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uin p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE; } dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res); @@ -3016,7 +3016,7 @@ static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *maxlink = be32_to_cpup(p++); + *maxlink = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_MAXLINK; } dprintk("%s: maxlink=%u\n", __func__, *maxlink); @@ -3038,7 +3038,7 @@ static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *maxname = be32_to_cpup(p++); + *maxname = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_MAXNAME; } dprintk("%s: maxname=%u\n", __func__, *maxname); @@ -3061,7 +3061,7 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, &maxread); + xdr_decode_hyper(p, &maxread); if (maxread > 0x7FFFFFFF) maxread = 0x7FFFFFFF; *res = (uint32_t)maxread; @@ -3087,7 +3087,7 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, &maxwrite); + xdr_decode_hyper(p, &maxwrite); if (maxwrite > 0x7FFFFFFF) maxwrite = 0x7FFFFFFF; *res = (uint32_t)maxwrite; @@ -3113,7 +3113,7 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - tmp = be32_to_cpup(p++); + tmp = be32_to_cpup(p); *mode = tmp & ~S_IFMT; bitmap[1] &= ~FATTR4_WORD1_MODE; ret = NFS_ATTR_FATTR_MODE; @@ -3137,7 +3137,7 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - *nlink = be32_to_cpup(p++); + *nlink = be32_to_cpup(p); bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; ret = NFS_ATTR_FATTR_NLINK; } @@ -3161,7 +3161,7 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); p = xdr_inline_decode(xdr, len); if (unlikely(!p)) goto out_overflow; @@ -3196,7 +3196,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); p = xdr_inline_decode(xdr, len); if (unlikely(!p)) goto out_overflow; @@ -3234,7 +3234,7 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde if (unlikely(!p)) goto out_overflow; major = be32_to_cpup(p++); - minor = be32_to_cpup(p++); + minor = be32_to_cpup(p); tmp = MKDEV(major, minor); if (MAJOR(tmp) == major && MINOR(tmp) == minor) *rdev = tmp; @@ -3260,7 +3260,7 @@ static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL; } dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res); @@ -3282,7 +3282,7 @@ static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE; } dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res); @@ -3304,7 +3304,7 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, res); + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL; } dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res); @@ -3326,7 +3326,7 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, used); + xdr_decode_hyper(p, used); bitmap[1] &= ~FATTR4_WORD1_SPACE_USED; ret = NFS_ATTR_FATTR_SPACE_USED; } @@ -3348,7 +3348,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) if (unlikely(!p)) goto out_overflow; p = xdr_decode_hyper(p, &sec); - nsec = be32_to_cpup(p++); + nsec = be32_to_cpup(p); time->tv_sec = (time_t)sec; time->tv_nsec = (long)nsec; return 0; @@ -3437,7 +3437,7 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c goto out_overflow; cinfo->atomic = be32_to_cpup(p++); p = xdr_decode_hyper(p, &cinfo->before); - p = xdr_decode_hyper(p, &cinfo->after); + xdr_decode_hyper(p, &cinfo->after); return 0; out_overflow: print_overflow_msg(__func__, xdr); @@ -3457,7 +3457,7 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) if (unlikely(!p)) goto out_overflow; supp = be32_to_cpup(p++); - acc = be32_to_cpup(p++); + acc = be32_to_cpup(p); access->supported = supp; access->access = acc; return 0; @@ -3525,7 +3525,7 @@ static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - bmlen = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); p = xdr_inline_decode(xdr, bmlen << 2); if (likely(p)) return 0; @@ -3786,7 +3786,7 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); if (len > NFS4_FHSIZE) return -EIO; fh->size = len; @@ -3836,7 +3836,7 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) fl->fl_pid = 0; } p = xdr_decode_hyper(p, &clientid); - namelen = be32_to_cpup(p++); + namelen = be32_to_cpup(p); p = xdr_inline_decode(xdr, namelen); if (likely(p)) return -NFS4ERR_DENIED; @@ -3903,11 +3903,11 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) limit_type = be32_to_cpup(p++); switch (limit_type) { case 1: - p = xdr_decode_hyper(p, maxsize); + xdr_decode_hyper(p, maxsize); break; case 2: nblocks = be32_to_cpup(p++); - blocksize = be32_to_cpup(p++); + blocksize = be32_to_cpup(p); *maxsize = (uint64_t)nblocks * (uint64_t)blocksize; } return 0; @@ -3925,7 +3925,7 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - delegation_type = be32_to_cpup(p++); + delegation_type = be32_to_cpup(p); if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { res->delegation_type = 0; return 0; @@ -3936,7 +3936,7 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - res->do_recall = be32_to_cpup(p++); + res->do_recall = be32_to_cpup(p); switch (delegation_type) { case NFS4_OPEN_DELEGATE_READ: @@ -3973,7 +3973,7 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) if (unlikely(!p)) goto out_overflow; res->rflags = be32_to_cpup(p++); - bmlen = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); if (bmlen > 10) goto xdr_error; @@ -4043,7 +4043,7 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ if (unlikely(!p)) goto out_overflow; eof = be32_to_cpup(p++); - count = be32_to_cpup(p++); + count = be32_to_cpup(p); hdrlen = (u8 *) p - (u8 *) iov->iov_base; recvd = req->rq_rcv_buf.len - hdrlen; if (count > recvd) { @@ -4174,7 +4174,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); if (len >= rcvbuf->page_len || len <= 0) { dprintk("nfs: server returned giant symlink!\n"); return -ENAMETOOLONG; @@ -4301,7 +4301,7 @@ static int decode_setattr(struct xdr_stream *xdr) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - bmlen = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); p = xdr_inline_decode(xdr, bmlen << 2); if (likely(p)) return 0; @@ -4325,7 +4325,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) " %d\n", opnum); return -EIO; } - nfserr = be32_to_cpup(p++); + nfserr = be32_to_cpup(p); if (nfserr == NFS_OK) { p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE); if (unlikely(!p)) @@ -4339,7 +4339,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); p = xdr_inline_decode(xdr, len); if (unlikely(!p)) goto out_overflow; @@ -4348,7 +4348,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - len = be32_to_cpup(p++); + len = be32_to_cpup(p); p = xdr_inline_decode(xdr, len); if (unlikely(!p)) goto out_overflow; @@ -4410,7 +4410,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, &clp->cl_ex_clid); + xdr_decode_hyper(p, &clp->cl_ex_clid); p = xdr_inline_decode(xdr, 12); if (unlikely(!p)) goto out_overflow; @@ -4418,7 +4418,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, clp->cl_exchange_flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ - dummy = be32_to_cpup(p++); + dummy = be32_to_cpup(p); if (dummy != SP4_NONE) return -EIO; @@ -4463,7 +4463,7 @@ static int decode_chan_attrs(struct xdr_stream *xdr, attrs->max_resp_sz_cached = be32_to_cpup(p++); attrs->max_ops = be32_to_cpup(p++); attrs->max_reqs = be32_to_cpup(p++); - nr_attrs = be32_to_cpup(p++); + nr_attrs = be32_to_cpup(p); if (unlikely(nr_attrs > 1)) { printk(KERN_WARNING "%s: Invalid rdma channel attrs count %u\n", __func__, nr_attrs); @@ -4504,7 +4504,7 @@ static int decode_create_session(struct xdr_stream *xdr, if (unlikely(!p)) goto out_overflow; clp->cl_seqid = be32_to_cpup(p++); - session->flags = be32_to_cpup(p++); + session->flags = be32_to_cpup(p); /* Channel attributes */ status = decode_chan_attrs(xdr, &session->fc_attrs); @@ -4576,7 +4576,7 @@ static int decode_sequence(struct xdr_stream *xdr, /* target highest slot id - currently not processed */ dummy = be32_to_cpup(p++); /* result flags - currently not processed */ - dummy = be32_to_cpup(p++); + dummy = be32_to_cpup(p); status = 0; out_err: res->sr_status = status; From 96c61cbd0f30496bfa57ed80f7131a57aea3e4de Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Aug 2009 18:12:21 -0400 Subject: [PATCH 74/87] SUNRPC: Fix a typo in cache_pipefs_files We want the channel to be a regular file, so that we don't need to supply rpc_pipe_ops. Signed-off-by: Trond Myklebust --- net/sunrpc/rpc_pipe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 8dd81535e08f..3fdacaf5c708 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -887,7 +887,7 @@ static const struct rpc_filelist cache_pipefs_files[3] = { [0] = { .name = "channel", .i_fop = &cache_file_operations_pipefs, - .mode = S_IFIFO|S_IRUSR|S_IWUSR, + .mode = S_IFREG|S_IRUSR|S_IWUSR, }, [1] = { .name = "content", From e571cbf1a4f8d8b6cfd4898df718dae84c75a8e1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Aug 2009 18:12:27 -0400 Subject: [PATCH 75/87] NFS: Add a dns resolver for use with NFSv4 referrals and migration The NFSv4 and NFSv4.1 protocols both allow for the redirection of a client from one server to another in order to support filesystem migration and replication. For full protocol support, we need to add the ability to convert a DNS host name into an IP address that we can feed to the RPC client. We'll reuse the sunrpc cache, now that it has been converted to work with rpc_pipefs. Signed-off-by: Trond Myklebust --- Documentation/filesystems/nfs.txt | 98 ++++++++ Documentation/kernel-parameters.txt | 8 + fs/nfs/Makefile | 3 +- fs/nfs/cache_lib.c | 140 ++++++++++++ fs/nfs/cache_lib.h | 27 +++ fs/nfs/dns_resolve.c | 335 ++++++++++++++++++++++++++++ fs/nfs/dns_resolve.h | 14 ++ fs/nfs/inode.c | 8 + net/sunrpc/rpc_pipe.c | 7 + 9 files changed, 639 insertions(+), 1 deletion(-) create mode 100644 Documentation/filesystems/nfs.txt create mode 100644 fs/nfs/cache_lib.c create mode 100644 fs/nfs/cache_lib.h create mode 100644 fs/nfs/dns_resolve.c create mode 100644 fs/nfs/dns_resolve.h diff --git a/Documentation/filesystems/nfs.txt b/Documentation/filesystems/nfs.txt new file mode 100644 index 000000000000..f50f26ce6cd0 --- /dev/null +++ b/Documentation/filesystems/nfs.txt @@ -0,0 +1,98 @@ + +The NFS client +============== + +The NFS version 2 protocol was first documented in RFC1094 (March 1989). +Since then two more major releases of NFS have been published, with NFSv3 +being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April +2003). + +The Linux NFS client currently supports all the above published versions, +and work is in progress on adding support for minor version 1 of the NFSv4 +protocol. + +The purpose of this document is to provide information on some of the +upcall interfaces that are used in order to provide the NFS client with +some of the information that it requires in order to fully comply with +the NFS spec. + +The DNS resolver +================ + +NFSv4 allows for one server to refer the NFS client to data that has been +migrated onto another server by means of the special "fs_locations" +attribute. See + http://tools.ietf.org/html/rfc3530#section-6 +and + http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00 + +The fs_locations information can take the form of either an ip address and +a path, or a DNS hostname and a path. The latter requires the NFS client to +do a DNS lookup in order to mount the new volume, and hence the need for an +upcall to allow userland to provide this service. + +Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual +/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps: + + (1) The process checks the dns_resolve cache to see if it contains a + valid entry. If so, it returns that entry and exits. + + (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent' + (may be changed using the 'nfs.cache_getent' kernel boot parameter) + is run, with two arguments: + - the cache name, "dns_resolve" + - the hostname to resolve + + (3) After looking up the corresponding ip address, the helper script + writes the result into the rpc_pipefs pseudo-file + '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel' + in the following (text) format: + + " \n" + + Where is in the usual IPv4 (123.456.78.90) or IPv6 + (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format. + is identical to the second argument of the helper + script, and is the 'time to live' of this cache entry (in + units of seconds). + + Note: If is invalid, say the string "0", then a negative + entry is created, which will cause the kernel to treat the hostname + as having no valid DNS translation. + + + + +A basic sample /sbin/nfs_cache_getent +===================================== + +#!/bin/bash +# +ttl=600 +# +cut=/usr/bin/cut +getent=/usr/bin/getent +rpc_pipefs=/var/lib/nfs/rpc_pipefs +# +die() +{ + echo "Usage: $0 cache_name entry_name" + exit 1 +} + +[ $# -lt 2 ] && die +cachename="$1" +cache_path=${rpc_pipefs}/cache/${cachename}/channel + +case "${cachename}" in + dns_resolve) + name="$2" + result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )" + [ -z "${result}" ] && result="0" + ;; + *) + die + ;; +esac +echo "${result} ${name} ${ttl}" >${cache_path} + diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c08813dbfce2..ce8853755814 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1503,6 +1503,14 @@ and is between 256 and 4096 characters. It is defined in the file [NFS] set the TCP port on which the NFSv4 callback channel should listen. + nfs.cache_getent= + [NFS] sets the pathname to the program which is used + to update the NFS client cache entries. + + nfs.cache_getent_timeout= + [NFS] sets the timeout after which an attempt to + update a cache entry is deemed to have failed. + nfs.idmap_cache_timeout= [NFS] set the maximum lifetime for idmapper cache entries. diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 845159814de2..da7fda639eac 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o nfs-y := client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \ direct.o pagelist.o proc.o read.o symlink.o unlink.o \ - write.o namespace.o mount_clnt.o + write.o namespace.o mount_clnt.o \ + dns_resolve.o cache_lib.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c new file mode 100644 index 000000000000..b4ffd0146ea6 --- /dev/null +++ b/fs/nfs/cache_lib.c @@ -0,0 +1,140 @@ +/* + * linux/fs/nfs/cache_lib.c + * + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust + */ +#include +#include +#include +#include +#include +#include +#include + +#include "cache_lib.h" + +#define NFS_CACHE_UPCALL_PATHLEN 256 +#define NFS_CACHE_UPCALL_TIMEOUT 15 + +static char nfs_cache_getent_prog[NFS_CACHE_UPCALL_PATHLEN] = + "/sbin/nfs_cache_getent"; +static unsigned long nfs_cache_getent_timeout = NFS_CACHE_UPCALL_TIMEOUT; + +module_param_string(cache_getent, nfs_cache_getent_prog, + sizeof(nfs_cache_getent_prog), 0600); +MODULE_PARM_DESC(cache_getent, "Path to the client cache upcall program"); +module_param_named(cache_getent_timeout, nfs_cache_getent_timeout, ulong, 0600); +MODULE_PARM_DESC(cache_getent_timeout, "Timeout (in seconds) after which " + "the cache upcall is assumed to have failed"); + +int nfs_cache_upcall(struct cache_detail *cd, char *entry_name) +{ + static char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + char *argv[] = { + nfs_cache_getent_prog, + cd->name, + entry_name, + NULL + }; + int ret = -EACCES; + + if (nfs_cache_getent_prog[0] == '\0') + goto out; + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + /* + * Disable the upcall mechanism if we're getting an ENOENT or + * EACCES error. The admin can re-enable it on the fly by using + * sysfs to set the 'cache_getent' parameter once the problem + * has been fixed. + */ + if (ret == -ENOENT || ret == -EACCES) + nfs_cache_getent_prog[0] = '\0'; +out: + return ret > 0 ? 0 : ret; +} + +/* + * Deferred request handling + */ +void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq) +{ + if (atomic_dec_and_test(&dreq->count)) + kfree(dreq); +} + +static void nfs_dns_cache_revisit(struct cache_deferred_req *d, int toomany) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(d, struct nfs_cache_defer_req, deferred_req); + + complete_all(&dreq->completion); + nfs_cache_defer_req_put(dreq); +} + +static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(req, struct nfs_cache_defer_req, req); + dreq->deferred_req.revisit = nfs_dns_cache_revisit; + atomic_inc(&dreq->count); + + return &dreq->deferred_req; +} + +struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void) +{ + struct nfs_cache_defer_req *dreq; + + dreq = kzalloc(sizeof(*dreq), GFP_KERNEL); + if (dreq) { + init_completion(&dreq->completion); + atomic_set(&dreq->count, 1); + dreq->req.defer = nfs_dns_cache_defer; + } + return dreq; +} + +int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq) +{ + if (wait_for_completion_timeout(&dreq->completion, + nfs_cache_getent_timeout * HZ) == 0) + return -ETIMEDOUT; + return 0; +} + +int nfs_cache_register(struct cache_detail *cd) +{ + struct nameidata nd; + struct vfsmount *mnt; + int ret; + + mnt = rpc_get_mount(); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &nd); + if (ret) + goto err; + ret = sunrpc_cache_register_pipefs(nd.path.dentry, + cd->name, 0600, cd); + path_put(&nd.path); + if (!ret) + return ret; +err: + rpc_put_mount(); + return ret; +} + +void nfs_cache_unregister(struct cache_detail *cd) +{ + sunrpc_cache_unregister_pipefs(cd); + rpc_put_mount(); +} + diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h new file mode 100644 index 000000000000..76f856e284e4 --- /dev/null +++ b/fs/nfs/cache_lib.h @@ -0,0 +1,27 @@ +/* + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust + */ + +#include +#include +#include + +/* + * Deferred request handling + */ +struct nfs_cache_defer_req { + struct cache_req req; + struct cache_deferred_req deferred_req; + struct completion completion; + atomic_t count; +}; + +extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name); +extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void); +extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq); +extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq); + +extern int nfs_cache_register(struct cache_detail *cd); +extern void nfs_cache_unregister(struct cache_detail *cd); diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c new file mode 100644 index 000000000000..f4d54ba97cc6 --- /dev/null +++ b/fs/nfs/dns_resolve.c @@ -0,0 +1,335 @@ +/* + * linux/fs/nfs/dns_resolve.c + * + * Copyright (c) 2009 Trond Myklebust + * + * Resolves DNS hostnames into valid ip addresses + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dns_resolve.h" +#include "cache_lib.h" + +#define NFS_DNS_HASHBITS 4 +#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS) + +static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE]; + +struct nfs_dns_ent { + struct cache_head h; + + char *hostname; + size_t namelen; + + struct sockaddr_storage addr; + size_t addrlen; +}; + + +static void nfs_dns_ent_init(struct cache_head *cnew, + struct cache_head *ckey) +{ + struct nfs_dns_ent *new; + struct nfs_dns_ent *key; + + new = container_of(cnew, struct nfs_dns_ent, h); + key = container_of(ckey, struct nfs_dns_ent, h); + + kfree(new->hostname); + new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL); + if (new->hostname) { + new->namelen = key->namelen; + memcpy(&new->addr, &key->addr, key->addrlen); + new->addrlen = key->addrlen; + } else { + new->namelen = 0; + new->addrlen = 0; + } +} + +static void nfs_dns_ent_put(struct kref *ref) +{ + struct nfs_dns_ent *item; + + item = container_of(ref, struct nfs_dns_ent, h.ref); + kfree(item->hostname); + kfree(item); +} + +static struct cache_head *nfs_dns_ent_alloc(void) +{ + struct nfs_dns_ent *item = kmalloc(sizeof(*item), GFP_KERNEL); + + if (item != NULL) { + item->hostname = NULL; + item->namelen = 0; + item->addrlen = 0; + return &item->h; + } + return NULL; +}; + +static unsigned int nfs_dns_hash(const struct nfs_dns_ent *key) +{ + return hash_str(key->hostname, NFS_DNS_HASHBITS); +} + +static void nfs_dns_request(struct cache_detail *cd, + struct cache_head *ch, + char **bpp, int *blen) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + + qword_add(bpp, blen, key->hostname); + (*bpp)[-1] = '\n'; +} + +static int nfs_dns_upcall(struct cache_detail *cd, + struct cache_head *ch) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + int ret; + + ret = nfs_cache_upcall(cd, key->hostname); + if (ret) + ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request); + return ret; +} + +static int nfs_dns_match(struct cache_head *ca, + struct cache_head *cb) +{ + struct nfs_dns_ent *a; + struct nfs_dns_ent *b; + + a = container_of(ca, struct nfs_dns_ent, h); + b = container_of(cb, struct nfs_dns_ent, h); + + if (a->namelen == 0 || a->namelen != b->namelen) + return 0; + return memcmp(a->hostname, b->hostname, a->namelen) == 0; +} + +static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd, + struct cache_head *h) +{ + struct nfs_dns_ent *item; + long ttl; + + if (h == NULL) { + seq_puts(m, "# ip address hostname ttl\n"); + return 0; + } + item = container_of(h, struct nfs_dns_ent, h); + ttl = (long)item->h.expiry_time - (long)get_seconds(); + if (ttl < 0) + ttl = 0; + + if (!test_bit(CACHE_NEGATIVE, &h->flags)) { + char buf[INET6_ADDRSTRLEN+IPV6_SCOPE_ID_LEN+1]; + + rpc_ntop((struct sockaddr *)&item->addr, buf, sizeof(buf)); + seq_printf(m, "%15s ", buf); + } else + seq_puts(m, " "); + seq_printf(m, "%15s %ld\n", item->hostname, ttl); + return 0; +} + +struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_lookup(cd, + &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd, + struct nfs_dns_ent *new, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_update(cd, + &new->h, &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) +{ + char buf1[NFS_DNS_HOSTNAME_MAXLEN+1]; + struct nfs_dns_ent key, *item; + unsigned long ttl; + ssize_t len; + int ret = -EINVAL; + + if (buf[buflen-1] != '\n') + goto out; + buf[buflen-1] = '\0'; + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + key.addrlen = rpc_pton(buf1, len, + (struct sockaddr *)&key.addr, + sizeof(key.addr)); + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + + key.hostname = buf1; + key.namelen = len; + memset(&key.h, 0, sizeof(key.h)); + + ttl = get_expiry(&buf); + if (ttl == 0) + goto out; + key.h.expiry_time = ttl + get_seconds(); + + ret = -ENOMEM; + item = nfs_dns_lookup(cd, &key); + if (item == NULL) + goto out; + + if (key.addrlen == 0) + set_bit(CACHE_NEGATIVE, &key.h.flags); + + item = nfs_dns_update(cd, &key, item); + if (item == NULL) + goto out; + + ret = 0; + cache_put(&item->h, cd); +out: + return ret; +} + +static struct cache_detail nfs_dns_resolve = { + .owner = THIS_MODULE, + .hash_size = NFS_DNS_HASHTBL_SIZE, + .hash_table = nfs_dns_table, + .name = "dns_resolve", + .cache_put = nfs_dns_ent_put, + .cache_upcall = nfs_dns_upcall, + .cache_parse = nfs_dns_parse, + .cache_show = nfs_dns_show, + .match = nfs_dns_match, + .init = nfs_dns_ent_init, + .update = nfs_dns_ent_init, + .alloc = nfs_dns_ent_alloc, +}; + +static int do_cache_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item, + struct nfs_cache_defer_req *dreq) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (*item) { + ret = cache_check(cd, &(*item)->h, &dreq->req); + if (ret) + *item = NULL; + } + return ret; +} + +static int do_cache_lookup_nowait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (!*item) + goto out_err; + ret = -ETIMEDOUT; + if (!test_bit(CACHE_VALID, &(*item)->h.flags) + || (*item)->h.expiry_time < get_seconds() + || cd->flush_time > (*item)->h.last_refresh) + goto out_put; + ret = -ENOENT; + if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags)) + goto out_put; + return 0; +out_put: + cache_put(&(*item)->h, cd); +out_err: + *item = NULL; + return ret; +} + +static int do_cache_lookup_wait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + struct nfs_cache_defer_req *dreq; + int ret = -ENOMEM; + + dreq = nfs_cache_defer_req_alloc(); + if (!dreq) + goto out; + ret = do_cache_lookup(cd, key, item, dreq); + if (ret == -EAGAIN) { + ret = nfs_cache_wait_for_upcall(dreq); + if (!ret) + ret = do_cache_lookup_nowait(cd, key, item); + } + nfs_cache_defer_req_put(dreq); +out: + return ret; +} + +ssize_t nfs_dns_resolve_name(char *name, size_t namelen, + struct sockaddr *sa, size_t salen) +{ + struct nfs_dns_ent key = { + .hostname = name, + .namelen = namelen, + }; + struct nfs_dns_ent *item = NULL; + ssize_t ret; + + ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item); + if (ret == 0) { + if (salen >= item->addrlen) { + memcpy(sa, &item->addr, item->addrlen); + ret = item->addrlen; + } else + ret = -EOVERFLOW; + cache_put(&item->h, &nfs_dns_resolve); + } else if (ret == -ENOENT) + ret = -ESRCH; + return ret; +} + +int nfs_dns_resolver_init(void) +{ + return nfs_cache_register(&nfs_dns_resolve); +} + +void nfs_dns_resolver_destroy(void) +{ + nfs_cache_unregister(&nfs_dns_resolve); +} + diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h new file mode 100644 index 000000000000..a3f0938babf7 --- /dev/null +++ b/fs/nfs/dns_resolve.h @@ -0,0 +1,14 @@ +/* + * Resolve DNS hostnames into valid ip addresses + */ +#ifndef __LINUX_FS_NFS_DNS_RESOLVE_H +#define __LINUX_FS_NFS_DNS_RESOLVE_H + +#define NFS_DNS_HOSTNAME_MAXLEN (128) + +extern int nfs_dns_resolver_init(void); +extern void nfs_dns_resolver_destroy(void); +extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen, + struct sockaddr *sa, size_t salen); + +#endif diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fe5a8b45d867..060022b4651c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -46,6 +46,7 @@ #include "iostat.h" #include "internal.h" #include "fscache.h" +#include "dns_resolve.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -1506,6 +1507,10 @@ static int __init init_nfs_fs(void) { int err; + err = nfs_dns_resolver_init(); + if (err < 0) + goto out8; + err = nfs_fscache_register(); if (err < 0) goto out7; @@ -1564,6 +1569,8 @@ out5: out6: nfs_fscache_unregister(); out7: + nfs_dns_resolver_destroy(); +out8: return err; } @@ -1575,6 +1582,7 @@ static void __exit exit_nfs_fs(void) nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); nfs_fscache_unregister(); + nfs_dns_resolver_destroy(); #ifdef CONFIG_PROC_FS rpc_proc_unregister("nfs"); #endif diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 3fdacaf5c708..7f676bdf70d3 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -416,11 +416,13 @@ struct vfsmount *rpc_get_mount(void) return ERR_PTR(err); return rpc_mount; } +EXPORT_SYMBOL_GPL(rpc_get_mount); void rpc_put_mount(void) { simple_release_fs(&rpc_mount, &rpc_mount_count); } +EXPORT_SYMBOL_GPL(rpc_put_mount); static int rpc_delete_dentry(struct dentry *dentry) { @@ -946,6 +948,7 @@ enum { RPCAUTH_portmap, RPCAUTH_statd, RPCAUTH_nfsd4_cb, + RPCAUTH_cache, RPCAUTH_RootEOF }; @@ -974,6 +977,10 @@ static const struct rpc_filelist files[] = { .name = "nfsd4_cb", .mode = S_IFDIR | S_IRUGO | S_IXUGO, }, + [RPCAUTH_cache] = { + .name = "cache", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, }; static int From 7d7ea882898f23989209d0359691b356f73240dc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Aug 2009 18:12:34 -0400 Subject: [PATCH 76/87] NFS: Use the DNS resolver in the mount code. In the referral code, use it to look up the new server's ip address if the fs_locations attribute contains a hostname. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4namespace.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index ef22ee89aa77..2636c26d56fa 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -17,6 +17,7 @@ #include #include "internal.h" #include "nfs4_fs.h" +#include "dns_resolve.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -95,6 +96,20 @@ static int nfs4_validate_fspath(const struct vfsmount *mnt_parent, return 0; } +static size_t nfs_parse_server_name(char *string, size_t len, + struct sockaddr *sa, size_t salen) +{ + ssize_t ret; + + ret = rpc_pton(string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(string, len, sa, salen); + if (ret < 0) + ret = 0; + } + return ret; +} + static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, char *page, char *page2, const struct nfs4_fs_location *location) @@ -121,7 +136,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len)) continue; - mountdata->addrlen = rpc_pton(buf->data, buf->len, + mountdata->addrlen = nfs_parse_server_name(buf->data, + buf->len, mountdata->addr, mountdata->addrlen); if (mountdata->addrlen == 0) continue; From f7e86ab92f2198d30828a1a327ad2085e4a7ff7d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Aug 2009 18:13:00 -0400 Subject: [PATCH 77/87] SUNRPC: cache must take a reference to the cache detail's module on open() Otherwise we Oops if the module containing the cache detail is removed before all cache readers have closed the file. Signed-off-by: Trond Myklebust --- net/sunrpc/cache.c | 80 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 76 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index db7720e453c3..45cdaff9b361 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -836,6 +836,8 @@ static int cache_open(struct inode *inode, struct file *filp, { struct cache_reader *rp = NULL; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { rp = kmalloc(sizeof(*rp), GFP_KERNEL); @@ -879,6 +881,7 @@ static int cache_release(struct inode *inode, struct file *filp, cd->last_close = get_seconds(); atomic_dec(&cd->readers); } + module_put(cd->owner); return 0; } @@ -1215,6 +1218,8 @@ static int content_open(struct inode *inode, struct file *file, { struct handle *han; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); if (han == NULL) return -ENOMEM; @@ -1223,6 +1228,29 @@ static int content_open(struct inode *inode, struct file *file, return 0; } +static int content_release(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + int ret = seq_release_private(inode, file); + module_put(cd->owner); + return ret; +} + +static int open_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + if (!cd || !try_module_get(cd->owner)) + return -EACCES; + return nonseekable_open(inode, file); +} + +static int release_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + module_put(cd->owner); + return 0; +} + static ssize_t read_flush(struct file *file, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) @@ -1331,13 +1359,34 @@ static int content_open_procfs(struct inode *inode, struct file *filp) return content_open(inode, filp, cd); } +static int content_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_release(inode, filp, cd); +} + static const struct file_operations content_file_operations_procfs = { .open = content_open_procfs, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = content_release_procfs, }; +static int open_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return open_flush(inode, filp, cd); +} + +static int release_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return release_flush(inode, filp, cd); +} + static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { @@ -1356,9 +1405,10 @@ static ssize_t write_flush_procfs(struct file *filp, } static const struct file_operations cache_flush_operations_procfs = { - .open = nonseekable_open, + .open = open_flush_procfs, .read = read_flush_procfs, .write = write_flush_procfs, + .release = release_flush_procfs, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1503,13 +1553,34 @@ static int content_open_pipefs(struct inode *inode, struct file *filp) return content_open(inode, filp, cd); } +static int content_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_release(inode, filp, cd); +} + const struct file_operations content_file_operations_pipefs = { .open = content_open_pipefs, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = content_release_pipefs, }; +static int open_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return open_flush(inode, filp, cd); +} + +static int release_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return release_flush(inode, filp, cd); +} + static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { @@ -1528,9 +1599,10 @@ static ssize_t write_flush_pipefs(struct file *filp, } const struct file_operations cache_flush_operations_pipefs = { - .open = nonseekable_open, + .open = open_flush_pipefs, .read = read_flush_pipefs, .write = write_flush_pipefs, + .release = release_flush_pipefs, }; int sunrpc_cache_register_pipefs(struct dentry *parent, From e1af88a1ad8f4dea3a2d6c5637d94a3fc3c62994 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Aug 2009 18:04:43 +0200 Subject: [PATCH 78/87] nfs: Remove reference to generic_osync_inode from a comment generic_file_direct_write() no longer calls generic_osync_inode() so remove the comment. CC: linux-nfs@vger.kernel.org CC: Neil Brown CC: "J. Bruce Fields" Signed-off-by: Jan Kara Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e4e089a8f294..6c3210099d51 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -934,9 +934,6 @@ out: * back into its cache. We let the server do generic write * parameter checking and report problems. * - * We also avoid an unnecessary invocation of generic_osync_inode(), - * as it is fairly meaningless to sync the metadata of an NFS file. - * * We eliminate local atime updates, see direct read above. * * We avoid unnecessary page cache invalidations for normal cached From 4dceef96756b667360741712a8e37490f8458516 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 20 Aug 2009 17:08:39 -0400 Subject: [PATCH 79/87] nfs: fix compile error in rpc_pipefs.h This include is needed for the definition of delayed_work. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index a92571a34556..cf14db975da0 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include + struct rpc_pipe_msg { struct list_head list; void *data; From 405d8f8b1d936414da2093d4149ff790ff3f84a5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 21 Aug 2009 08:17:56 -0400 Subject: [PATCH 80/87] SUNRPC: Ensure that sunrpc gets initialised before nfs, lockd, etc... We can oops if rpc_pipefs isn't properly initialised before we start to set up objects that depend upon it. Signed-off-by: Trond Myklebust --- net/sunrpc/sunrpc_syms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index adaa81982f74..8cce92189019 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -69,5 +69,5 @@ cleanup_sunrpc(void) rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); -module_init(init_sunrpc); +fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); From 5eecfde615894dc1c2e3f85b515a96ae2e408fb5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 21 Aug 2009 17:50:30 -0400 Subject: [PATCH 81/87] NFS: Handle a zero-length auth flavor list Some releases of Linux rpc.mountd (nfs-utils 1.1.4 and later) return an empty auth flavor list if no sec= was specified for the export. This is notably broken server behavior. The new auth flavor list checking added in a recent commit rejects this case. The OpenSolaris client does too. The broken mountd implementation is already widely deployed. To avoid a behavioral regression, the kernel's mount client skips flavor checking (ie reverts to the pre-2.6.32 behavior) if mountd returns an empty flavor list. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 9c85cdb353aa..f3a95df4b95f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1337,6 +1337,16 @@ static int nfs_walk_authlist(struct nfs_parsed_mount_data *args, { unsigned int i, j, server_authlist_len = *(request->auth_flav_len); + /* + * Certain releases of Linux's mountd return an empty + * flavor list. To prevent behavioral regression with + * these servers (ie. rejecting mounts that used to + * succeed), revert to pre-2.6.32 behavior (no checking) + * if the returned flavor list is empty. + */ + if (server_authlist_len == 0) + return 0; + /* * We avoid sophisticated negotiating here, as there are * plenty of cases where we can get it wrong, providing From dbab8360ed8abca38121109feab47c4bea895994 Mon Sep 17 00:00:00 2001 From: Harshula Jayasuriya Date: Tue, 8 Sep 2009 19:49:33 -0400 Subject: [PATCH 82/87] NFS: out of date comment regarding O_EXCL above nfs3_proc_create() Hi Trond, Recently we were observing the behaviour difference between a 2.4.x and 2.6.x kernel with respect to O_EXCL. A comment from 2.4.x era, "For now, we don't implement O_EXCL." seems inaccurate in TOT. If so, here's a patch to remove the comment. This patch is against: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 Signed-off-by: Harshula Jayasuriya Signed-off-by: Trond Myklebust --- fs/nfs/nfs3proc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index d0cc5ce0edfe..ee6a13f05443 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -299,7 +299,6 @@ static void nfs3_free_createdata(struct nfs3_createdata *data) /* * Create a regular file. - * For now, we don't implement O_EXCL. */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, From 4cfd74fc99a41fdc161f243e1c16199656d33ab1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 8 Sep 2009 19:49:47 -0400 Subject: [PATCH 83/87] NFS: Mount option parser should detect missing "port=" The meaning of not specifying the "port=" mount option is different for "-t nfs" and "-t nfs4" mounts. The default port value for NFSv2/v3 mounts is 0, but the default for NFSv4 mounts is 2049. To support "-t nfs -o vers=4", the mount option parser must detect when "port=" is missing so that the correct default port value can be set depending on which NFS version is requested. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 9 ++++++-- fs/nfs/super.c | 55 +++++++++++++++++++++++++---------------------- 2 files changed, 36 insertions(+), 28 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2e485677019c..5e686a4d744e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -48,6 +48,11 @@ struct nfs_clone_mount { */ #define NFS_MAX_SECFLAVORS (12) +/* + * Value used if the user did not specify a port value. + */ +#define NFS_UNSPEC_PORT (-1) + /* * In-kernel mount arguments */ @@ -71,7 +76,7 @@ struct nfs_parsed_mount_data { size_t addrlen; char *hostname; u32 version; - unsigned short port; + int port; unsigned short protocol; } mount_server; @@ -80,7 +85,7 @@ struct nfs_parsed_mount_data { size_t addrlen; char *hostname; char *export_path; - unsigned short port; + int port; unsigned short protocol; } nfs_server; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index f3a95df4b95f..05544336f7de 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -746,6 +746,21 @@ static int nfs_verify_server_address(struct sockaddr *addr) return 0; } +/* + * Select between a default port value and a user-specified port value. + * If a zero value is set, then autobind will be used. + */ +static void nfs_set_default_port(struct sockaddr *sap, const int parsed_port, + const unsigned short default_port) +{ + unsigned short port = default_port; + + if (parsed_port != NFS_UNSPEC_PORT) + port = parsed_port; + + rpc_set_port(sap, port); +} + /* * Sanity check the NFS transport protocol. * @@ -1415,11 +1430,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, args->mount_server.addrlen = args->nfs_server.addrlen; } request.salen = args->mount_server.addrlen; - - /* - * autobind will be used if mount_server.port == 0 - */ - rpc_set_port(request.sap, args->mount_server.port); + nfs_set_default_port(request.sap, args->mount_server.port, 0); /* * Now ask the mount server to map our export path @@ -1597,6 +1608,7 @@ static int nfs_validate_mount_data(void *options, const char *dev_name) { struct nfs_mount_data *data = (struct nfs_mount_data *)options; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; if (data == NULL) goto out_no_data; @@ -1608,8 +1620,8 @@ static int nfs_validate_mount_data(void *options, args->acregmax = NFS_DEF_ACREGMAX; args->acdirmin = NFS_DEF_ACDIRMIN; args->acdirmax = NFS_DEF_ACDIRMAX; - args->mount_server.port = 0; /* autobind unless user sets port */ - args->nfs_server.port = 0; /* autobind unless user sets port */ + args->mount_server.port = NFS_UNSPEC_PORT; + args->nfs_server.port = NFS_UNSPEC_PORT; args->nfs_server.protocol = XPRT_TRANSPORT_TCP; args->auth_flavors[0] = RPC_AUTH_UNIX; args->auth_flavor_len = 1; @@ -1657,11 +1669,9 @@ static int nfs_validate_mount_data(void *options, args->acdirmin = data->acdirmin; args->acdirmax = data->acdirmax; - memcpy(&args->nfs_server.address, &data->addr, - sizeof(data->addr)); + memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) @@ -1709,12 +1719,10 @@ static int nfs_validate_mount_data(void *options, if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; - rpc_set_port((struct sockaddr *)&args->nfs_server.address, - args->nfs_server.port); + nfs_set_default_port(sap, args->nfs_server.port, 0); nfs_set_mount_transport_protocol(args); @@ -2261,7 +2269,7 @@ static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name) { - struct sockaddr_in *ap; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; char *c; @@ -2274,23 +2282,21 @@ static int nfs4_validate_mount_data(void *options, args->acregmax = NFS_DEF_ACREGMAX; args->acdirmin = NFS_DEF_ACDIRMIN; args->acdirmax = NFS_DEF_ACDIRMAX; - args->nfs_server.port = NFS_PORT; /* 2049 unless user set port= */ + args->nfs_server.port = NFS_UNSPEC_PORT; args->auth_flavors[0] = RPC_AUTH_UNIX; args->auth_flavor_len = 1; args->minorversion = 0; switch (data->version) { case 1: - ap = (struct sockaddr_in *)&args->nfs_server.address; if (data->host_addrlen > sizeof(args->nfs_server.address)) goto out_no_address; if (data->host_addrlen == 0) goto out_no_address; args->nfs_server.addrlen = data->host_addrlen; - if (copy_from_user(ap, data->host_addr, data->host_addrlen)) + if (copy_from_user(sap, data->host_addr, data->host_addrlen)) return -EFAULT; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; if (data->auth_flavourlen) { @@ -2342,12 +2348,9 @@ static int nfs4_validate_mount_data(void *options, if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) return -EINVAL; - - rpc_set_port((struct sockaddr *)&args->nfs_server.address, - args->nfs_server.port); + nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT); nfs_validate_transport_protocol(args); From 7630c852e19c7fffb85b50d98eeb5516fec7c088 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 8 Sep 2009 19:49:57 -0400 Subject: [PATCH 84/87] NFS: Refactor NFSv4 text-based mount option validation Clean up: Refactor the part of nfs4_validate_mount_options() that handles text-based options, so we can call it from the NFSv2/v3 option validation function. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 63 ++++++++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 05544336f7de..599e8c5fe6ce 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -272,6 +272,8 @@ static const struct super_operations nfs_sops = { }; #ifdef CONFIG_NFS_V4 +static int nfs4_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, const char *dev_name); static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); static int nfs4_remote_get_sb(struct file_system_type *fs_type, @@ -2262,6 +2264,37 @@ static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3); } +static int nfs4_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, + const char *dev_name) +{ + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + + nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT); + + nfs_validate_transport_protocol(args); + + nfs4_validate_mount_flags(args); + + if (args->auth_flavor_len > 1) { + dfprintk(MOUNT, + "NFS4: Too many RPC auth flavours specified\n"); + return -EINVAL; + } + + if (args->client_address == NULL) { + dfprintk(MOUNT, + "NFS4: mount program didn't pass callback address\n"); + return -EINVAL; + } + + return nfs_parse_devname(dev_name, + &args->nfs_server.hostname, + NFS4_MAXNAMLEN, + &args->nfs_server.export_path, + NFS4_MAXPATHLEN); +} + /* * Validate NFSv4 mount options */ @@ -2342,36 +2375,14 @@ static int nfs4_validate_mount_data(void *options, nfs_validate_transport_protocol(args); break; - default: { - int status; - + default: if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; if (!nfs_verify_server_address(sap)) return -EINVAL; - nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT); - nfs_validate_transport_protocol(args); - - nfs4_validate_mount_flags(args); - - if (args->auth_flavor_len > 1) - goto out_inval_auth; - - if (args->client_address == NULL) - goto out_no_client_address; - - status = nfs_parse_devname(dev_name, - &args->nfs_server.hostname, - NFS4_MAXNAMLEN, - &args->nfs_server.export_path, - NFS4_MAXPATHLEN); - if (status < 0) - return status; - - break; - } + return nfs4_validate_text_mount_data(options, args, dev_name); } return 0; @@ -2388,10 +2399,6 @@ out_inval_auth: out_no_address: dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n"); return -EINVAL; - -out_no_client_address: - dfprintk(MOUNT, "NFS4: mount program didn't pass callback address\n"); - return -EINVAL; } /* From a6fe23be90aa78783523a25330e09bfaa43a1581 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 8 Sep 2009 19:50:00 -0400 Subject: [PATCH 85/87] NFS: Move details of nfs4_get_sb() to a helper Clean up: Refactor nfs4_get_sb() to allow its guts to be invoked by nfs_get_sb(). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 599e8c5fe6ce..c105e12197c2 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -274,6 +274,8 @@ static const struct super_operations nfs_sops = { #ifdef CONFIG_NFS_V4 static int nfs4_validate_text_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); +static int nfs4_try_mount(int flags, const char *dev_name, + struct nfs_parsed_mount_data *data, struct vfsmount *mnt); static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); static int nfs4_remote_get_sb(struct file_system_type *fs_type, @@ -2565,25 +2567,15 @@ out_err: return ret; } -/* - * Get the superblock for an NFS4 mountpoint - */ -static int nfs4_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) +static int nfs4_try_mount(int flags, const char *dev_name, + struct nfs_parsed_mount_data *data, + struct vfsmount *mnt) { - struct nfs_parsed_mount_data *data; char *export_path; struct vfsmount *root_mnt; - int error = -ENOMEM; + int error; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (data == NULL) - goto out_free_data; - - /* Validate the mount data */ - error = nfs4_validate_mount_data(raw_data, data, dev_name); - if (error < 0) - goto out; + dfprintk(MOUNT, "--> nfs4_try_mount()\n"); export_path = data->nfs_server.export_path; data->nfs_server.export_path = "/"; @@ -2597,6 +2589,32 @@ static int nfs4_get_sb(struct file_system_type *fs_type, error = nfs_follow_remote_path(root_mnt, export_path, mnt); +out: + dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", error, + error != 0 ? " [error]" : ""); + return error; +} + +/* + * Get the superblock for an NFS4 mountpoint + */ +static int nfs4_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) +{ + struct nfs_parsed_mount_data *data; + int error = -ENOMEM; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + goto out_free_data; + + /* Validate the mount data */ + error = nfs4_validate_mount_data(raw_data, data, dev_name); + if (error < 0) + goto out; + + error = nfs4_try_mount(flags, dev_name, data, mnt); + out: kfree(data->client_address); kfree(data->nfs_server.export_path); From 764302ccb88dd0df062eccd507b6c6de24f1c560 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 8 Sep 2009 19:50:03 -0400 Subject: [PATCH 86/87] NFS: Allow the "nfs" file system type to support NFSv4 When mounting an "nfs" type file system, recognize "v4," "vers=4," or "nfsvers=4" mount options, and convert the file system to "nfs4" under the covers. Signed-off-by: Chuck Lever [trondmy: fixed up binary mount code so it sets the 'version' field too] Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 1 + fs/nfs/super.c | 48 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/nfs4.h | 1 + 3 files changed, 48 insertions(+), 2 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5e686a4d744e..e21b1bb9972f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -68,6 +68,7 @@ struct nfs_parsed_mount_data { unsigned int auth_flavor_len; rpc_authflavor_t auth_flavors[1]; char *client_address; + unsigned int version; unsigned int minorversion; char *fscache_uniq; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index c105e12197c2..34b1ccf51adf 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,7 +73,7 @@ enum { Opt_cto, Opt_nocto, Opt_ac, Opt_noac, Opt_lock, Opt_nolock, - Opt_v2, Opt_v3, + Opt_v2, Opt_v3, Opt_v4, Opt_udp, Opt_tcp, Opt_rdma, Opt_acl, Opt_noacl, Opt_rdirplus, Opt_nordirplus, @@ -127,6 +127,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_nolock, "nolock" }, { Opt_v2, "v2" }, { Opt_v3, "v3" }, + { Opt_v4, "v4" }, { Opt_udp, "udp" }, { Opt_tcp, "tcp" }, { Opt_rdma, "rdma" }, @@ -934,10 +935,18 @@ static int nfs_parse_mount_options(char *raw, break; case Opt_v2: mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 2; break; case Opt_v3: mnt->flags |= NFS_MOUNT_VER3; + mnt->version = 3; break; +#ifdef CONFIG_NFS_V4 + case Opt_v4: + mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 4; + break; +#endif case Opt_udp: mnt->flags &= ~NFS_MOUNT_TCP; mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; @@ -1151,10 +1160,18 @@ static int nfs_parse_mount_options(char *raw, switch (option) { case NFS2_VERSION: mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 2; break; case NFS3_VERSION: mnt->flags |= NFS_MOUNT_VER3; + mnt->version = 3; break; +#ifdef CONFIG_NFS_V4 + case NFS4_VERSION: + mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 4; + break; +#endif default: goto out_invalid_value; } @@ -1629,6 +1646,7 @@ static int nfs_validate_mount_data(void *options, args->nfs_server.protocol = XPRT_TRANSPORT_TCP; args->auth_flavors[0] = RPC_AUTH_UNIX; args->auth_flavor_len = 1; + args->minorversion = 0; switch (data->version) { case 1: @@ -1650,8 +1668,11 @@ static int nfs_validate_mount_data(void *options, if (data->root.size > NFS3_FHSIZE || data->root.size == 0) goto out_invalid_fh; mntfh->size = data->root.size; - } else + args->version = 3; + } else { mntfh->size = NFS2_FHSIZE; + args->version = 2; + } memcpy(mntfh->data, data->root.data, mntfh->size); @@ -1726,6 +1747,14 @@ static int nfs_validate_mount_data(void *options, if (!nfs_verify_server_address(sap)) goto out_no_address; + if (args->version == 4) +#ifdef CONFIG_NFS_V4 + return nfs4_validate_text_mount_data(options, + args, dev_name); +#else + goto out_v4_not_compiled; +#endif + nfs_set_default_port(sap, args->nfs_server.port, 0); nfs_set_mount_transport_protocol(args); @@ -1774,6 +1803,12 @@ out_v3_not_compiled: return -EPROTONOSUPPORT; #endif /* !CONFIG_NFS_V3 */ +#ifndef CONFIG_NFS_V4 +out_v4_not_compiled: + dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); + return -EPROTONOSUPPORT; +#endif /* !CONFIG_NFS_V4 */ + out_nomem: dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n"); return -ENOMEM; @@ -2069,6 +2104,14 @@ static int nfs_get_sb(struct file_system_type *fs_type, if (error < 0) goto out; +#ifdef CONFIG_NFS_V4 + if (data->version == 4) { + error = nfs4_try_mount(flags, dev_name, data, mnt); + kfree(data->client_address); + goto out; + } +#endif /* CONFIG_NFS_V4 */ + /* Get a volume representation */ server = nfs_create_server(data, mntfh); if (IS_ERR(server)) { @@ -2320,6 +2363,7 @@ static int nfs4_validate_mount_data(void *options, args->nfs_server.port = NFS_UNSPEC_PORT; args->auth_flavors[0] = RPC_AUTH_UNIX; args->auth_flavor_len = 1; + args->version = 4; args->minorversion = 0; switch (data->version) { diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index bd2eba530667..33b283601f62 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -472,6 +472,7 @@ enum lock_type4 { #define NFSPROC4_NULL 0 #define NFSPROC4_COMPOUND 1 +#define NFS4_VERSION 4 #define NFS4_MINOR_VERSION 0 #if defined(CONFIG_NFS_V4_1) From 2ecda72b49a0849ce41e7fa1fa974a245b9119f8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 8 Sep 2009 19:50:07 -0400 Subject: [PATCH 87/87] NFSv4: Disallow 'mount -t nfs4 -overs=2' and 'mount -t nfs4 -overs=3' Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 34b1ccf51adf..867f70504531 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2321,6 +2321,12 @@ static int nfs4_validate_text_mount_data(void *options, nfs4_validate_mount_flags(args); + if (args->version != 4) { + dfprintk(MOUNT, + "NFS4: Illegal mount version\n"); + return -EINVAL; + } + if (args->auth_flavor_len > 1) { dfprintk(MOUNT, "NFS4: Too many RPC auth flavours specified\n");