5 files changed, 165 insertions, 112 deletions

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7c8801769a3c..6fde431df9ee 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -123,6 +123,35 @@ nfsd4_check_open_attributes(struct svc_rqst *rqstp,
         return status;
 }
 
+static int
+is_create_with_attrs(struct nfsd4_open *open)
+{
+        return open->op_create == NFS4_OPEN_CREATE
+                && (open->op_createmode == NFS4_CREATE_UNCHECKED
+                    || open->op_createmode == NFS4_CREATE_GUARDED
+                    || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
+}
+
+/*
+ * if error occurs when setting the acl, just clear the acl bit
+ * in the returned attr bitmap.
+ */
+static void
+do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
+                struct nfs4_acl *acl, u32 *bmval)
+{
+        __be32 status;
+
+        status = nfsd4_set_nfs4_acl(rqstp, fhp, acl);
+        if (status)
+                /*
+                 * We should probably fail the whole open at this point,
+                 * but we've already created the file, so it's too late;
+                 * So this seems the least of evils:
+                 */
+                bmval[0] &= ~FATTR4_WORD0_ACL;
+}
+
 static inline void
 fh_dup2(struct svc_fh *dst, struct svc_fh *src)
 {
@@ -206,6 +235,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
         if (status)
                 goto out;
 
+        if (is_create_with_attrs(open) && open->op_acl != NULL)
+                do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
+
         set_change_info(&open->op_cinfo, current_fh);
         fh_dup2(current_fh, &resfh);
 
@@ -536,12 +568,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                 status = nfserr_badtype;
         }
 
-        if (!status) {
-                fh_unlock(&cstate->current_fh);
-                set_change_info(&create->cr_cinfo, &cstate->current_fh);
-                fh_dup2(&cstate->current_fh, &resfh);
-        }
+        if (status)
+                goto out;
 
+        if (create->cr_acl != NULL)
+                do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
+                                create->cr_bmval);
+
+        fh_unlock(&cstate->current_fh);
+        set_change_info(&create->cr_cinfo, &cstate->current_fh);
+        fh_dup2(&cstate->current_fh, &resfh);
+out:
         fh_put(&resfh);
         return status;
 }
@@ -947,34 +984,6 @@ static struct nfsd4_operation nfsd4_ops[];
 static const char *nfsd4_op_name(unsigned opnum);
 
 /*
- * This is a replay of a compound for which no cache entry pages
- * were used. Encode the sequence operation, and if cachethis is FALSE
- * encode the uncache rep error on the next operation.
- */
-static __be32
-nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
-                         struct nfsd4_compoundres *resp)
-{
-        struct nfsd4_op *op;
-
-        dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
-                resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
-
-        /* Encode the replayed sequence operation */
-        BUG_ON(resp->opcnt != 1);
-        op = &args->ops[resp->opcnt - 1];
-        nfsd4_encode_operation(resp, op);
-
-        /*return nfserr_retry_uncached_rep in next operation. */
-        if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
-                op = &args->ops[resp->opcnt++];
-                op->status = nfserr_retry_uncached_rep;
-                nfsd4_encode_operation(resp, op);
-        }
-        return op->status;
-}
-
-/*
  * Enforce NFSv4.1 COMPOUND ordering rules.
  *
  * TODO:
@@ -1083,13 +1092,10 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
                         BUG_ON(op->status == nfs_ok);
 
 encode_op:
-                /* Only from SEQUENCE or CREATE_SESSION */
+                /* Only from SEQUENCE */
                 if (resp->cstate.status == nfserr_replay_cache) {
                         dprintk("%s NFS4.1 replay from cache\n", __func__);
-                        if (nfsd4_not_cached(resp))
-                                status = nfsd4_enc_uncached_replay(args, resp);
-                        else
-                                status = op->status;
+                        status = op->status;
                         goto out;
                 }
                 if (op->status == nfserr_replay_me) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 980a216a48c8..9295c4b56bce 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -414,35 +414,34 @@ gen_sessionid(struct nfsd4_session *ses)
 
 /*
  * Give the client the number of slots it requests bound by
- * NFSD_MAX_SLOTS_PER_SESSION and by sv_drc_max_pages.
+ * NFSD_MAX_SLOTS_PER_SESSION and by nfsd_drc_max_mem.
  *
- * If we run out of pages (sv_drc_pages_used == sv_drc_max_pages) we
- * should (up to a point) re-negotiate active sessions and reduce their
- * slot usage to make rooom for new connections. For now we just fail the
- * create session.
+ * If we run out of reserved DRC memory we should (up to a point) re-negotiate
+ * active sessions and reduce their slot usage to make rooom for new
+ * connections. For now we just fail the create session.
  */
 static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan)
 {
-        int status = 0, np = fchan->maxreqs * NFSD_PAGES_PER_SLOT;
+        int mem;
 
         if (fchan->maxreqs < 1)
                 return nfserr_inval;
         else if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
                 fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
 
-        spin_lock(&nfsd_serv->sv_lock);
-        if (np + nfsd_serv->sv_drc_pages_used > nfsd_serv->sv_drc_max_pages)
-                np = nfsd_serv->sv_drc_max_pages - nfsd_serv->sv_drc_pages_used;
-        nfsd_serv->sv_drc_pages_used += np;
-        spin_unlock(&nfsd_serv->sv_lock);
+        mem = fchan->maxreqs * NFSD_SLOT_CACHE_SIZE;
 
-        if (np <= 0) {
-                status = nfserr_resource;
-                fchan->maxreqs = 0;
-        } else
-                fchan->maxreqs = np / NFSD_PAGES_PER_SLOT;
+        spin_lock(&nfsd_drc_lock);
+        if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem)
+                mem = ((nfsd_drc_max_mem - nfsd_drc_mem_used) /
+                                NFSD_SLOT_CACHE_SIZE) * NFSD_SLOT_CACHE_SIZE;
+        nfsd_drc_mem_used += mem;
+        spin_unlock(&nfsd_drc_lock);
 
-        return status;
+        fchan->maxreqs = mem / NFSD_SLOT_CACHE_SIZE;
+        if (fchan->maxreqs == 0)
+                return nfserr_resource;
+        return 0;
 }
 
 /*
@@ -466,9 +465,7 @@ static int init_forechannel_attrs(struct svc_rqst *rqstp,
                 fchan->maxresp_sz = maxcount;
         session_fchan->maxresp_sz = fchan->maxresp_sz;
 
-        /* Set the max response cached size our default which is
-         * a multiple of PAGE_SIZE and small */
-        session_fchan->maxresp_cached = NFSD_PAGES_PER_SLOT * PAGE_SIZE;
+        session_fchan->maxresp_cached = NFSD_SLOT_CACHE_SIZE;
         fchan->maxresp_cached = session_fchan->maxresp_cached;
 
         /* Use the client's maxops if possible */
@@ -476,10 +473,6 @@ static int init_forechannel_attrs(struct svc_rqst *rqstp,
                 fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
         session_fchan->maxops = fchan->maxops;
 
-        /* try to use the client requested number of slots */
-        if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
-                fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
-
         /* FIXME: Error means no more DRC pages so the server should
          * recover pages from existing sessions. For now fail session
          * creation.
@@ -585,6 +578,9 @@ free_session(struct kref *kref)
                 struct nfsd4_cache_entry *e = &ses->se_slots[i].sl_cache_entry;
                 nfsd4_release_respages(e->ce_respages, e->ce_resused);
         }
+        spin_lock(&nfsd_drc_lock);
+        nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
+        spin_unlock(&nfsd_drc_lock);
         kfree(ses);
 }
 
@@ -657,8 +653,6 @@ static inline void
 free_client(struct nfs4_client *clp)
 {
         shutdown_callback_client(clp);
-        nfsd4_release_respages(clp->cl_slot.sl_cache_entry.ce_respages,
-                             clp->cl_slot.sl_cache_entry.ce_resused);
         if (clp->cl_cred.cr_group_info)
                 put_group_info(clp->cl_cred.cr_group_info);
         kfree(clp->cl_principal);
@@ -1115,6 +1109,36 @@ nfsd41_copy_replay_data(struct nfsd4_compoundres *resp,
 }
 
 /*
+ * Encode the replay sequence operation from the slot values.
+ * If cachethis is FALSE encode the uncached rep error on the next
+ * operation which sets resp->p and increments resp->opcnt for
+ * nfs4svc_encode_compoundres.
+ *
+ */
+static __be32
+nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
+                          struct nfsd4_compoundres *resp)
+{
+        struct nfsd4_op *op;
+        struct nfsd4_slot *slot = resp->cstate.slot;
+
+        dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
+                resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
+
+        /* Encode the replayed sequence operation */
+        op = &args->ops[resp->opcnt - 1];
+        nfsd4_encode_operation(resp, op);
+
+        /* Return nfserr_retry_uncached_rep in next operation. */
+        if (args->opcnt > 1 && slot->sl_cache_entry.ce_cachethis == 0) {
+                op = &args->ops[resp->opcnt++];
+                op->status = nfserr_retry_uncached_rep;
+                nfsd4_encode_operation(resp, op);
+        }
+        return op->status;
+}
+
+/*
  * Keep the first page of the replay. Copy the NFSv4.1 data from the first
  * cached page.  Replace any futher replay pages from the cache.
  */
@@ -1137,10 +1161,12 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
          * session inactivity timer fires and a solo sequence operation
          * is sent (lease renewal).
          */
-        if (seq && nfsd4_not_cached(resp)) {
-                seq->maxslots = resp->cstate.session->se_fchannel.maxreqs;
-                return nfs_ok;
-        }
+        seq->maxslots = resp->cstate.session->se_fchannel.maxreqs;
+
+        /* Either returns 0 or nfserr_retry_uncached */
+        status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
+        if (status == nfserr_retry_uncached_rep)
+                return status;
 
         if (!nfsd41_copy_replay_data(resp, entry)) {
                 /*
@@ -1297,12 +1323,11 @@ out_copy:
         exid->clientid.cl_boot = new->cl_clientid.cl_boot;
         exid->clientid.cl_id = new->cl_clientid.cl_id;
 
-        new->cl_slot.sl_seqid = 0;
         exid->seqid = 1;
         nfsd4_set_ex_flags(new, exid);
 
         dprintk("nfsd4_exchange_id seqid %d flags %x\n",
-                new->cl_slot.sl_seqid, new->cl_exchange_flags);
+                new->cl_cs_slot.sl_seqid, new->cl_exchange_flags);
         status = nfs_ok;
 
 out:
@@ -1313,40 +1338,60 @@ error:
 }
 
 static int
-check_slot_seqid(u32 seqid, struct nfsd4_slot *slot)
+check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
 {
-        dprintk("%s enter. seqid %d slot->sl_seqid %d\n", __func__, seqid,
-                slot->sl_seqid);
+        dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid,
+                slot_seqid);
 
         /* The slot is in use, and no response has been sent. */
-        if (slot->sl_inuse) {
-                if (seqid == slot->sl_seqid)
+        if (slot_inuse) {
+                if (seqid == slot_seqid)
                         return nfserr_jukebox;
                 else
                         return nfserr_seq_misordered;
         }
         /* Normal */
-        if (likely(seqid == slot->sl_seqid + 1))
+        if (likely(seqid == slot_seqid + 1))
                 return nfs_ok;
         /* Replay */
-        if (seqid == slot->sl_seqid)
+        if (seqid == slot_seqid)
                 return nfserr_replay_cache;
         /* Wraparound */
-        if (seqid == 1 && (slot->sl_seqid + 1) == 0)
+        if (seqid == 1 && (slot_seqid + 1) == 0)
                 return nfs_ok;
         /* Misordered replay or misordered new request */
         return nfserr_seq_misordered;
 }
 
+/*
+ * Cache the create session result into the create session single DRC
+ * slot cache by saving the xdr structure. sl_seqid has been set.
+ * Do this for solo or embedded create session operations.
+ */
+static void
+nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses,
+                           struct nfsd4_clid_slot *slot, int nfserr)
+{
+        slot->sl_status = nfserr;
+        memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses));
+}
+
+static __be32
+nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
+                            struct nfsd4_clid_slot *slot)
+{
+        memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses));
+        return slot->sl_status;
+}
+
 __be32
 nfsd4_create_session(struct svc_rqst *rqstp,
                      struct nfsd4_compound_state *cstate,
                      struct nfsd4_create_session *cr_ses)
 {
         u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr;
-        struct nfsd4_compoundres *resp = rqstp->rq_resp;
         struct nfs4_client *conf, *unconf;
-        struct nfsd4_slot *slot = NULL;
+        struct nfsd4_clid_slot *cs_slot = NULL;
         int status = 0;
 
         nfs4_lock_state();
@@ -1354,24 +1399,22 @@ nfsd4_create_session(struct svc_rqst *rqstp,
         conf = find_confirmed_client(&cr_ses->clientid);
 
         if (conf) {
-                slot = &conf->cl_slot;
-                status = check_slot_seqid(cr_ses->seqid, slot);
+                cs_slot = &conf->cl_cs_slot;
+                status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
                 if (status == nfserr_replay_cache) {
                         dprintk("Got a create_session replay! seqid= %d\n",
-                                slot->sl_seqid);
-                        cstate->slot = slot;
-                        cstate->status = status;
+                                cs_slot->sl_seqid);
                         /* Return the cached reply status */
-                        status = nfsd4_replay_cache_entry(resp, NULL);
+                        status = nfsd4_replay_create_session(cr_ses, cs_slot);
                         goto out;
-                } else if (cr_ses->seqid != conf->cl_slot.sl_seqid + 1) {
+                } else if (cr_ses->seqid != cs_slot->sl_seqid + 1) {
                         status = nfserr_seq_misordered;
                         dprintk("Sequence misordered!\n");
                         dprintk("Expected seqid= %d but got seqid= %d\n",
-                                slot->sl_seqid, cr_ses->seqid);
+                                cs_slot->sl_seqid, cr_ses->seqid);
                         goto out;
                 }
-                conf->cl_slot.sl_seqid++;
+                cs_slot->sl_seqid++;
         } else if (unconf) {
                 if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
                     (ip_addr != unconf->cl_addr)) {
@@ -1379,15 +1422,15 @@ nfsd4_create_session(struct svc_rqst *rqstp,
                         goto out;
                 }
 
-                slot = &unconf->cl_slot;
-                status = check_slot_seqid(cr_ses->seqid, slot);
+                cs_slot = &unconf->cl_cs_slot;
+                status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
                 if (status) {
                         /* an unconfirmed replay returns misordered */
                         status = nfserr_seq_misordered;
-                        goto out;
+                        goto out_cache;
                 }
 
-                slot->sl_seqid++; /* from 0 to 1 */
+                cs_slot->sl_seqid++; /* from 0 to 1 */
                 move_to_confirmed(unconf);
 
                 /*
@@ -1408,12 +1451,11 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 
         memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data,
                NFS4_MAX_SESSIONID_LEN);
-        cr_ses->seqid = slot->sl_seqid;
+        cr_ses->seqid = cs_slot->sl_seqid;
 
-        slot->sl_inuse = true;
-        cstate->slot = slot;
-        /* Ensure a page is used for the cache */
-        slot->sl_cache_entry.ce_cachethis = 1;
+out_cache:
+        /* cache solo and embedded create sessions under the state lock */
+        nfsd4_cache_create_session(cr_ses, cs_slot, status);
 out:
         nfs4_unlock_state();
         dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -1481,7 +1523,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
         slot = &session->se_slots[seq->slotid];
         dprintk("%s: slotid %d\n", __func__, seq->slotid);
 
-        status = check_slot_seqid(seq->seqid, slot);
+        status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
         if (status == nfserr_replay_cache) {
                 cstate->slot = slot;
                 cstate->session = session;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2dcc7feaa6ff..fdf632bf1cfe 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3313,8 +3313,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
                         dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
                         resp->cstate.slot->sl_inuse = 0;
                 }
-                if (resp->cstate.session)
-                        nfsd4_put_session(resp->cstate.session);
+                nfsd4_put_session(resp->cstate.session);
         }
         return 1;
 }
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7e906c5b7671..b764d7d898e9 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -776,10 +776,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
                 size -= len;
                 mesg += len;
         }
-
-        mutex_unlock(&nfsd_mutex);
-        return (mesg-buf);
-
+        rv = mesg - buf;
 out_free:
         kfree(nthreads);
         mutex_unlock(&nfsd_mutex);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 492c79b7800b..d68cd056b281 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -66,6 +66,16 @@ struct timeval			nfssvc_boot;
 DEFINE_MUTEX(nfsd_mutex);
 struct svc_serv                 *nfsd_serv;
 
+/*
+ * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
+ * nfsd_drc_max_pages limits the total amount of memory available for
+ * version 4.1 DRC caches.
+ * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
+ */
+spinlock_t      nfsd_drc_lock;
+unsigned int    nfsd_drc_max_mem;
+unsigned int    nfsd_drc_mem_used;
+
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat  nfsd_acl_svcstats;
 static struct svc_version *     nfsd_acl_version[] = {
@@ -235,13 +245,12 @@ void nfsd_reset_versions(void)
  */
 static void set_max_drc(void)
 {
-        /* The percent of nr_free_buffer_pages used by the V4.1 server DRC */
-        #define NFSD_DRC_SIZE_SHIFT     7
-        nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages()
-                                                >> NFSD_DRC_SIZE_SHIFT;
-        nfsd_serv->sv_drc_pages_used = 0;
-        dprintk("%s svc_drc_max_pages %u\n", __func__,
-                nfsd_serv->sv_drc_max_pages);
+        #define NFSD_DRC_SIZE_SHIFT     10
+        nfsd_drc_max_mem = (nr_free_buffer_pages()
+                                        >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
+        nfsd_drc_mem_used = 0;
+        spin_lock_init(&nfsd_drc_lock);
+        dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
 }
 
 int nfsd_create_serv(void)