nfsd: implement pNFS operations

Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and
LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage
outstanding layouts and devices.

Layout management is very straight forward, with a nfs4_layout_stateid
structure that extends nfs4_stid to manage layout stateids as the
top-level structure.  It is linked into the nfs4_file and nfs4_client
structures like the other stateids, and contains a linked list of
layouts that hang of the stateid.  The actual layout operations are
implemented in layout drivers that are not part of this commit, but
will be added later.

The worst part of this commit is the management of the pNFS device IDs,
which suffers from a specification that is not sanely implementable due
to the fact that the device-IDs are global and not bound to an export,
and have a small enough size so that we can't store the fsid portion of
a file handle, and must never be reused.  As we still do need perform all
export authentication and validation checks on a device ID passed to
GETDEVICEINFO we are caught between a rock and a hard place.  To work
around this issue we add a new hash that maps from a 64-bit integer to a
fsid so that we can look up the export to authenticate against it,
a 32-bit integer as a generation that we can bump when changing the device,
and a currently unused 32-bit integer that could be used in the future
to handle more than a single device per export.  Entries in this hash
table are never deleted as we can't reuse the ids anyway, and would have
a severe lifetime problem anyway as Linux export structures are temporary
structures that can go away under load.

Parts of the XDR data, structures and marshaling/unmarshaling code, as
well as many concepts are derived from the old pNFS server implementation
from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman,
Mike Sager, Ricardo Labiaga and many others.

Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 21 insertions, 0 deletions

diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 38ebb1268b59..5f66b7fd0297 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -92,6 +92,7 @@ struct nfs4_stid {
 /* For a deleg stateid kept around only to process free_stateid's: */
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
+#define NFS4_LAYOUT_STID 64
         unsigned char sc_type;
         stateid_t sc_stateid;
         struct nfs4_client *sc_client;
@@ -297,6 +298,9 @@ struct nfs4_client {
         struct list_head        cl_delegations;
         struct list_head        cl_revoked;     /* unacknowledged, revoked 4.1 state */
         struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+        struct list_head        cl_lo_states;   /* outstanding layout states */
+#endif
         struct xdr_netobj       cl_name;        /* id generated by client */
         nfs4_verifier           cl_verifier;    /* generated by client */
         time_t                  cl_time;        /* time of last lease renewal */
@@ -496,6 +500,9 @@ struct nfs4_file {
         int                     fi_delegees;
         struct knfsd_fh         fi_fhandle;
         bool                    fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+        struct list_head        fi_lo_states;
+#endif
 };
 
 /*
@@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
         return container_of(s, struct nfs4_ol_stateid, st_stid);
 }
 
+struct nfs4_layout_stateid {
+        struct nfs4_stid                ls_stid;
+        struct list_head                ls_perclnt;
+        struct list_head                ls_perfile;
+        spinlock_t                      ls_lock;
+        struct list_head                ls_layouts;
+        u32                             ls_layout_type;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+        return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
 /* flags for preprocess_seqid_op() */
 #define RD_STATE                0x00000010
 #define WR_STATE                0x00000020