From 2a369153c82e0c83621b3e71d8f0c53394705bda Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2012 18:54:45 -0400 Subject: NFS: Clean up helper function nfs4_select_rw_stateid() We want to be able to pass on the information that the page was not dirtied under a lock. Instead of adding a flag parameter, do this by passing a pointer to a 'struct nfs_lock_owner' that may be NULL. Also reuse this structure in struct nfs_lock_context to carry the fl_owner_t and pid_t. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 4b03f56e280e..869eac0c2635 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -81,12 +81,16 @@ struct nfs_access_entry { int mask; }; +struct nfs_lockowner { + fl_owner_t l_owner; + pid_t l_pid; +}; + struct nfs_lock_context { atomic_t count; struct list_head list; struct nfs_open_context *open_context; - fl_owner_t lockowner; - pid_t pid; + struct nfs_lockowner lockowner; }; struct nfs4_state; -- cgit From 05990d1bf2708b9e84d67074551f964d3738eedc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 11 Sep 2012 16:01:22 -0400 Subject: NFS: Fix fdatasync/fsync() when confronted with a server reboot If the server reboots before it can commit the unstable writes to disk, then nfs_commit_release_pages() will detect this when it compares the verifier returned by COMMIT to the one returned by WRITE. When this happens, the client needs to resend those writes in order to guarantee that they make it to stable storage. This patch adds a signalling mechanism to notify fsync() that it needs to retry all writes before it can exit. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 869eac0c2635..383f3313f053 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -103,6 +103,7 @@ struct nfs_open_context { unsigned long flags; #define NFS_CONTEXT_ERROR_WRITE (0) +#define NFS_CONTEXT_RESEND_WRITES (1) int error; struct list_head list; -- cgit From d19751e7b9bd8a01d00372325439589886674f79 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 11 Sep 2012 17:21:25 -0400 Subject: SUNRPC: Get rid of the redundant xprt->shutdown bit field It is only set after everyone has dereferenced the transport, and serves no useful purpose: setting it is racy, so all the socket code, etc still needs to be able to cope with the cases where they miss reading it. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bf8c49ff7530..951cb9b7d02b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -173,8 +173,7 @@ struct rpc_xprt { unsigned int min_reqs; /* min number of slots */ atomic_t num_reqs; /* total slots */ unsigned long state; /* transport state */ - unsigned char shutdown : 1, /* being shut down */ - resvport : 1; /* use a reserved port */ + unsigned char resvport : 1; /* use a reserved port */ unsigned int swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ -- cgit From a0b0a6e39bd1bb4a0922086feee73627cbd53ba4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Sep 2012 17:12:15 -0400 Subject: NFS: Clean up the pNFS layoutget interface Ensure that we do return errors from nfs4_proc_layoutget() and that we don't mark the layout as having failed if the error was due to a signal or resource problem on the client side. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index be9cf3c7e79e..5da789fdf25b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -251,7 +251,6 @@ struct nfs4_layoutget_res { struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; - struct pnfs_layout_segment **lsegpp; gfp_t gfp_flags; }; -- cgit From 6168f62cbde8dcf4f58255794efbcdb8df603959 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Mon, 10 Sep 2012 14:00:46 -0400 Subject: NFSv4: Add ACCESS operation to OPEN compound The OPEN operation has no way to differentiate an open for read and an open for execution - both look like read to the server. This allowed users to read files that didn't have READ access but did have EXEC access, which is obviously wrong. This patch adds an ACCESS call to the OPEN compound to handle the difference between OPENs for reading and execution. Since we're going through the trouble of calling ACCESS, we check all possible access bits and cache the results hopefully avoiding an ACCESS call in the future. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 ++ include/linux/nfs_xdr.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 383f3313f053..334a2f5f6bf1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -360,6 +360,8 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5da789fdf25b..655490dae953 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -334,6 +334,7 @@ struct nfs_openargs { struct nfs_seqid * seqid; int open_flags; fmode_t fmode; + u32 access; __u64 clientid; struct stateowner_id id; union { @@ -368,6 +369,8 @@ struct nfs_openres { struct nfs4_string *owner; struct nfs4_string *group_owner; struct nfs4_sequence_res seq_res; + __u32 access_supported; + __u32 access_result; }; /* -- cgit From ba9b584c1dc37851d9c6ca6d0d2ccba55d9aad04 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Sep 2012 17:24:02 -0400 Subject: SUNRPC: Introduce rpc_clone_client_set_auth() An ULP is supposed to be able to replace a GSS rpc_auth object with another GSS rpc_auth object using rpcauth_create(). However, rpcauth_create() in 3.5 reliably fails with -EEXIST in this case. This is because when gss_create() attempts to create the upcall pipes, sometimes they are already there. For example if a pipe FS mount event occurs, or a previous GSS flavor was in use for this rpc_clnt. It turns out that's not the only problem here. While working on a fix for the above problem, we noticed that replacing an rpc_clnt's rpc_auth is not safe, since dereferencing the cl_auth field is not protected in any way. So we're deprecating the ability of rpcauth_create() to switch an rpc_clnt's security flavor during normal operation. Instead, let's add a fresh API that clones an rpc_clnt and gives the clone a new flavor before it's used. This makes immediate use of the new __rpc_clone_client() helper. This can be used in a similar fashion to rpcauth_create() when a client is hunting for the correct security flavor. Instead of replacing an rpc_clnt's security flavor in a loop, the ULP replaces the whole rpc_clnt. To fix the -EEXIST problem, any ULP logic that relies on replacing an rpc_clnt's rpc_auth with rpcauth_create() must be changed to use this API instead. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 523547ecfee2..34206b84d8da 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -130,6 +130,8 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, const struct rpc_program *, u32); void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt); struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); +struct rpc_clnt *rpc_clone_client_set_auth(struct rpc_clnt *, + rpc_authflavor_t); void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); void rpc_task_release_client(struct rpc_task *); -- cgit From 896526174ce2b6a773e187ebe5a047b68230e2c4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Sep 2012 17:24:11 -0400 Subject: NFS: Introduce "migration" mount option Currently, the Linux client uses a unique nfs_client_id4.id string when identifying itself to distinct NFS servers. To support transparent state migration, the Linux client will have to use the same nfs_client_id4 string for all servers it communicates with (also known as the "uniform client string" approach). Otherwise NFS servers can not recognize that open and lock state need to be merged after a file system transition. Unfortunately, there are some NFSv4.0 servers currently in the field that do not tolerate the uniform client string approach. Thus, by default, our NFSv4.0 mounts will continue to use the current approach, and we introduce a mount option that switches them to use the uniform model. Client administrators must identify which servers can be mounted with this option. Eventually most NFSv4.0 servers will be able to handle the uniform approach, and we can change the default. The first mount of a server controls the behavior for all subsequent mounts for the lifetime of that set of mounts of that server. After the last mount of that server is gone, the client erases the data structure that tracks the lease. A subsequent lease may then honor a different "migration" setting. This patch adds only the infrastructure for parsing the new mount option. Support for uniform client strings is added in a subsequent patch. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 310c63c8ab2c..2e22fc7e47cf 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -39,6 +39,7 @@ struct nfs_client { unsigned long cl_flags; /* behavior switches */ #define NFS_CS_NORESVPORT 0 /* - use ephemeral src port */ #define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */ +#define NFS_CS_MIGRATION 2 /* - transparent state migr */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -125,6 +126,7 @@ struct nfs_server { unsigned int namelen; unsigned int options; /* extra options enabled by mount */ #define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */ +#define NFS_OPTION_MIGRATION 0x00000002 /* - NFSv4 migration enabled */ struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ -- cgit From 05f4c350ee02e9461c6ae3a880ea326a06835e37 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Sep 2012 17:24:32 -0400 Subject: NFS: Discover NFSv4 server trunking when mounting "Server trunking" is a fancy named for a multi-homed NFS server. Trunking might occur if a client sends NFS requests for a single workload to multiple network interfaces on the same server. There are some implications for NFSv4 state management that make it useful for a client to know if a single NFSv4 server instance is multi-homed. (Note this is only a consideration for NFSv4, not for legacy versions of NFS, which are stateless). If a client cares about server trunking, no NFSv4 operations can proceed until that client determines who it is talking to. Thus server IP trunking discovery must be done when the client first encounters an unfamiliar server IP address. The nfs_get_client() function walks the nfs_client_list and matches on server IP address. The outcome of that walk tells us immediately if we have an unfamiliar server IP address. It invokes nfs_init_client() in this case. Thus, nfs4_init_client() is a good spot to perform trunking discovery. Discovery requires a client to establish a fresh client ID, so our client will now send SETCLIENTID or EXCHANGE_ID as the first NFS operation after a successful ping, rather than waiting for an application to perform an operation that requires NFSv4 state. The exact process for detecting trunking is different for NFSv4.0 and NFSv4.1, so a minorversion-specific init_client callout method is introduced. CLID_INUSE recovery is important for the trunking discovery process. CLID_INUSE is a sign the server recognizes the client's nfs_client_id4 id string, but the client is using the wrong principal this time for the SETCLIENTID operation. The SETCLIENTID must be retried with a series of different principals until one works, and then the rest of trunking discovery can proceed. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2e22fc7e47cf..a9e76ee1adca 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -82,6 +82,7 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ + bool cl_preserve_clid; struct nfs41_server_owner *cl_serverowner; struct nfs41_server_scope *cl_serverscope; struct nfs41_impl_id *cl_implid; -- cgit From ae2bb03236fc978bdf673c19d39832500793b83c Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 2 Oct 2012 14:49:52 -0700 Subject: NFSv4: don't put ACCESS in OPEN compound if O_EXCL Don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS will return permission denied for all bits until close. Fixes a regression due to commit 6168f62c (NFSv4: Add ACCESS operation to OPEN compound) Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 655490dae953..a73ea89789d1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -369,6 +369,7 @@ struct nfs_openres { struct nfs4_string *owner; struct nfs4_string *group_owner; struct nfs4_sequence_res seq_res; + __u32 access_request; __u32 access_supported; __u32 access_result; }; -- cgit