1 files changed, 221 insertions, 42 deletions

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 3fd23f7aceca..24e8d78f8dde 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -43,25 +43,30 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svcsock.h>
 #include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/state.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs4.h>
+#include <linux/sunrpc/xprtsock.h>
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
 #define NFSPROC4_CB_NULL 0
 #define NFSPROC4_CB_COMPOUND 1
+#define NFS4_STATEID_SIZE 16
 
 /* Index of predefined Linux callback client operations */
 
 enum {
-        NFSPROC4_CLNT_CB_NULL = 0,
+        NFSPROC4_CLNT_CB_NULL = 0,
         NFSPROC4_CLNT_CB_RECALL,
+        NFSPROC4_CLNT_CB_SEQUENCE,
 };
 
 enum nfs_cb_opnum4 {
         OP_CB_RECALL            = 4,
+        OP_CB_SEQUENCE          = 11,
 };
 
 #define NFS4_MAXTAGLEN          20
@@ -70,17 +75,29 @@ enum nfs_cb_opnum4 {
 #define NFS4_dec_cb_null_sz             0
 #define cb_compound_enc_hdr_sz          4
 #define cb_compound_dec_hdr_sz          (3 + (NFS4_MAXTAGLEN >> 2))
+#define sessionid_sz                    (NFS4_MAX_SESSIONID_LEN >> 2)
+#define cb_sequence_enc_sz              (sessionid_sz + 4 +             \
+                                        1 /* no referring calls list yet */)
+#define cb_sequence_dec_sz              (op_dec_sz + sessionid_sz + 4)
+
 #define op_enc_sz                       1
 #define op_dec_sz                       2
 #define enc_nfs4_fh_sz                  (1 + (NFS4_FHSIZE >> 2))
 #define enc_stateid_sz                  (NFS4_STATEID_SIZE >> 2)
 #define NFS4_enc_cb_recall_sz           (cb_compound_enc_hdr_sz +       \
+                                        cb_sequence_enc_sz +            \
                                         1 + enc_stateid_sz +            \
                                         enc_nfs4_fh_sz)
 
 #define NFS4_dec_cb_recall_sz           (cb_compound_dec_hdr_sz  +      \
+                                        cb_sequence_dec_sz +            \
                                         op_dec_sz)
 
+struct nfs4_rpc_args {
+        void                            *args_op;
+        struct nfsd4_cb_sequence        args_seq;
+};
+
 /*
 * Generic encode routines from fs/nfs/nfs4xdr.c
 */
@@ -137,11 +154,13 @@ xdr_error:                                      \
 } while (0)
 
 struct nfs4_cb_compound_hdr {
-        int             status;
-        u32             ident;
+        /* args */
+        u32             ident;  /* minorversion 0 only */
         u32             nops;
         __be32          *nops_p;
         u32             minorversion;
+        /* res */
+        int             status;
         u32             taglen;
         char            *tag;
 };
@@ -238,6 +257,27 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp,
         hdr->nops++;
 }
 
+static void
+encode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *args,
+                   struct nfs4_cb_compound_hdr *hdr)
+{
+        __be32 *p;
+
+        if (hdr->minorversion == 0)
+                return;
+
+        RESERVE_SPACE(1 + NFS4_MAX_SESSIONID_LEN + 20);
+
+        WRITE32(OP_CB_SEQUENCE);
+        WRITEMEM(args->cbs_clp->cl_sessionid.data, NFS4_MAX_SESSIONID_LEN);
+        WRITE32(args->cbs_clp->cl_cb_seq_nr);
+        WRITE32(0);             /* slotid, always 0 */
+        WRITE32(0);             /* highest slotid always 0 */
+        WRITE32(0);             /* cachethis always 0 */
+        WRITE32(0); /* FIXME: support referring_call_lists */
+        hdr->nops++;
+}
+
 static int
 nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
 {
@@ -249,15 +289,19 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
 }
 
 static int
-nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_delegation *args)
+nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p,
+                struct nfs4_rpc_args *rpc_args)
 {
         struct xdr_stream xdr;
+        struct nfs4_delegation *args = rpc_args->args_op;
         struct nfs4_cb_compound_hdr hdr = {
                 .ident = args->dl_ident,
+                .minorversion = rpc_args->args_seq.cbs_minorversion,
         };
 
         xdr_init_encode(&xdr, &req->rq_snd_buf, p);
         encode_cb_compound_hdr(&xdr, &hdr);
+        encode_cb_sequence(&xdr, &rpc_args->args_seq, &hdr);
         encode_cb_recall(&xdr, args, &hdr);
         encode_cb_nops(&hdr);
         return 0;
@@ -299,6 +343,57 @@ decode_cb_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
         return 0;
 }
 
+/*
+ * Our current back channel implmentation supports a single backchannel
+ * with a single slot.
+ */
+static int
+decode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *res,
+                   struct rpc_rqst *rqstp)
+{
+        struct nfs4_sessionid id;
+        int status;
+        u32 dummy;
+        __be32 *p;
+
+        if (res->cbs_minorversion == 0)
+                return 0;
+
+        status = decode_cb_op_hdr(xdr, OP_CB_SEQUENCE);
+        if (status)
+                return status;
+
+        /*
+         * If the server returns different values for sessionID, slotID or
+         * sequence number, the server is looney tunes.
+         */
+        status = -ESERVERFAULT;
+
+        READ_BUF(NFS4_MAX_SESSIONID_LEN + 16);
+        memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN);
+        p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN);
+        if (memcmp(id.data, res->cbs_clp->cl_sessionid.data,
+                   NFS4_MAX_SESSIONID_LEN)) {
+                dprintk("%s Invalid session id\n", __func__);
+                goto out;
+        }
+        READ32(dummy);
+        if (dummy != res->cbs_clp->cl_cb_seq_nr) {
+                dprintk("%s Invalid sequence number\n", __func__);
+                goto out;
+        }
+        READ32(dummy);  /* slotid must be 0 */
+        if (dummy != 0) {
+                dprintk("%s Invalid slotid\n", __func__);
+                goto out;
+        }
+        /* FIXME: process highest slotid and target highest slotid */
+        status = 0;
+out:
+        return status;
+}
+
+
 static int
 nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p)
 {
@@ -306,7 +401,8 @@ nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p)
 }
 
 static int
-nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p)
+nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p,
+                struct nfsd4_cb_sequence *seq)
 {
         struct xdr_stream xdr;
         struct nfs4_cb_compound_hdr hdr;
@@ -316,6 +412,11 @@ nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p)
         status = decode_cb_compound_hdr(&xdr, &hdr);
         if (status)
                 goto out;
+        if (seq) {
+                status = decode_cb_sequence(&xdr, seq, rqstp);
+                if (status)
+                        goto out;
+        }
         status = decode_cb_op_hdr(&xdr, OP_CB_RECALL);
 out:
         return status;
@@ -377,16 +478,15 @@ static int max_cb_time(void)
 
 int setup_callback_client(struct nfs4_client *clp)
 {
-        struct sockaddr_in      addr;
         struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
         struct rpc_timeout      timeparms = {
                 .to_initval     = max_cb_time(),
                 .to_retries     = 0,
         };
         struct rpc_create_args args = {
-                .protocol       = IPPROTO_TCP,
-                .address        = (struct sockaddr *)&addr,
-                .addrsize       = sizeof(addr),
+                .protocol       = XPRT_TRANSPORT_TCP,
+                .address        = (struct sockaddr *) &cb->cb_addr,
+                .addrsize       = cb->cb_addrlen,
                 .timeout        = &timeparms,
                 .program        = &cb_program,
                 .prognumber     = cb->cb_prog,
@@ -399,13 +499,10 @@ int setup_callback_client(struct nfs4_client *clp)
 
         if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
                 return -EINVAL;
-
-        /* Initialize address */
-        memset(&addr, 0, sizeof(addr));
-        addr.sin_family = AF_INET;
-        addr.sin_port = htons(cb->cb_port);
-        addr.sin_addr.s_addr = htonl(cb->cb_addr);
-
+        if (cb->cb_minorversion) {
+                args.bc_xprt = clp->cl_cb_xprt;
+                args.protocol = XPRT_TRANSPORT_BC_TCP;
+        }
         /* Create RPC client */
         client = rpc_create(&args);
         if (IS_ERR(client)) {
@@ -439,42 +536,29 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
         .rpc_call_done = nfsd4_cb_probe_done,
 };
 
-static struct rpc_cred *lookup_cb_cred(struct nfs4_cb_conn *cb)
-{
-        struct auth_cred acred = {
-                .machine_cred = 1
-        };
+static struct rpc_cred *callback_cred;
 
-        /*
-         * Note in the gss case this doesn't actually have to wait for a
-         * gss upcall (or any calls to the client); this just creates a
-         * non-uptodate cred which the rpc state machine will fill in with
-         * a refresh_upcall later.
-         */
-        return rpcauth_lookup_credcache(cb->cb_client->cl_auth, &acred,
-                                                        RPCAUTH_LOOKUP_NEW);
+int set_callback_cred(void)
+{
+        callback_cred = rpc_lookup_machine_cred();
+        if (!callback_cred)
+                return -ENOMEM;
+        return 0;
 }
 
+
 void do_probe_callback(struct nfs4_client *clp)
 {
         struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
                 .rpc_argp       = clp,
+                .rpc_cred       = callback_cred
         };
-        struct rpc_cred *cred;
         int status;
 
-        cred = lookup_cb_cred(cb);
-        if (IS_ERR(cred)) {
-                status = PTR_ERR(cred);
-                goto out;
-        }
-        cb->cb_cred = cred;
-        msg.rpc_cred = cb->cb_cred;
         status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_SOFT,
                                 &nfsd4_cb_probe_ops, (void *)clp);
-out:
         if (status) {
                 warn_no_callback_path(clp, status);
                 put_nfs4_client(clp);
@@ -503,11 +587,95 @@ nfsd4_probe_callback(struct nfs4_client *clp)
         do_probe_callback(clp);
 }
 
+/*
+ * There's currently a single callback channel slot.
+ * If the slot is available, then mark it busy.  Otherwise, set the
+ * thread for sleeping on the callback RPC wait queue.
+ */
+static int nfsd41_cb_setup_sequence(struct nfs4_client *clp,
+                struct rpc_task *task)
+{
+        struct nfs4_rpc_args *args = task->tk_msg.rpc_argp;
+        u32 *ptr = (u32 *)clp->cl_sessionid.data;
+        int status = 0;
+
+        dprintk("%s: %u:%u:%u:%u\n", __func__,
+                ptr[0], ptr[1], ptr[2], ptr[3]);
+
+        if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+                rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
+                dprintk("%s slot is busy\n", __func__);
+                status = -EAGAIN;
+                goto out;
+        }
+
+        /*
+         * We'll need the clp during XDR encoding and decoding,
+         * and the sequence during decoding to verify the reply
+         */
+        args->args_seq.cbs_clp = clp;
+        task->tk_msg.rpc_resp = &args->args_seq;
+
+out:
+        dprintk("%s status=%d\n", __func__, status);
+        return status;
+}
+
+/*
+ * TODO: cb_sequence should support referring call lists, cachethis, multiple
+ * slots, and mark callback channel down on communication errors.
+ */
+static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_delegation *dp = calldata;
+        struct nfs4_client *clp = dp->dl_client;
+        struct nfs4_rpc_args *args = task->tk_msg.rpc_argp;
+        u32 minorversion = clp->cl_cb_conn.cb_minorversion;
+        int status = 0;
+
+        args->args_seq.cbs_minorversion = minorversion;
+        if (minorversion) {
+                status = nfsd41_cb_setup_sequence(clp, task);
+                if (status) {
+                        if (status != -EAGAIN) {
+                                /* terminate rpc task */
+                                task->tk_status = status;
+                                task->tk_action = NULL;
+                        }
+                        return;
+                }
+        }
+        rpc_call_start(task);
+}
+
+static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_delegation *dp = calldata;
+        struct nfs4_client *clp = dp->dl_client;
+
+        dprintk("%s: minorversion=%d\n", __func__,
+                clp->cl_cb_conn.cb_minorversion);
+
+        if (clp->cl_cb_conn.cb_minorversion) {
+                /* No need for lock, access serialized in nfsd4_cb_prepare */
+                ++clp->cl_cb_seq_nr;
+                clear_bit(0, &clp->cl_cb_slot_busy);
+                rpc_wake_up_next(&clp->cl_cb_waitq);
+                dprintk("%s: freed slot, new seqid=%d\n", __func__,
+                        clp->cl_cb_seq_nr);
+
+                /* We're done looking into the sequence information */
+                task->tk_msg.rpc_resp = NULL;
+        }
+}
+
 static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 {
         struct nfs4_delegation *dp = calldata;
         struct nfs4_client *clp = dp->dl_client;
 
+        nfsd4_cb_done(task, calldata);
+
         switch (task->tk_status) {
         case -EIO:
                 /* Network partition? */
@@ -520,16 +688,19 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
                 break;
         default:
                 /* success, or error we can't handle */
-                return;
+                goto done;
         }
         if (dp->dl_retries--) {
                 rpc_delay(task, 2*HZ);
                 task->tk_status = 0;
                 rpc_restart_call(task);
+                return;
         } else {
                 atomic_set(&clp->cl_cb_conn.cb_set, 0);
                 warn_no_callback_path(clp, task->tk_status);
         }
+done:
+        kfree(task->tk_msg.rpc_argp);
 }
 
 static void nfsd4_cb_recall_release(void *calldata)
@@ -542,6 +713,7 @@ static void nfsd4_cb_recall_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+        .rpc_call_prepare = nfsd4_cb_prepare,
         .rpc_call_done = nfsd4_cb_recall_done,
         .rpc_release = nfsd4_cb_recall_release,
 };
@@ -554,17 +726,24 @@ nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
         struct nfs4_client *clp = dp->dl_client;
         struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
+        struct nfs4_rpc_args *args;
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL],
-                .rpc_argp = dp,
-                .rpc_cred = clp->cl_cb_conn.cb_cred
+                .rpc_cred = callback_cred
         };
-        int status;
+        int status = -ENOMEM;
 
+        args = kzalloc(sizeof(*args), GFP_KERNEL);
+        if (!args)
+                goto out;
+        args->args_op = dp;
+        msg.rpc_argp = args;
         dp->dl_retries = 1;
         status = rpc_call_async(clnt, &msg, RPC_TASK_SOFT,
                                 &nfsd4_cb_recall_ops, dp);
+out:
         if (status) {
+                kfree(args);
                 put_nfs4_client(clp);
                 nfs4_put_delegation(dp);
         }