Merge tag 'nfsd-4.4' of git://linux-nfs.org/~bfields/linux
Pull nfsd updates from Bruce Fields:
"Apologies for coming a little late in the merge window. Fortunately
this is another fairly quiet one:
Mainly smaller bugfixes and cleanup. We're still finding some bugs
from the breakup of the big NFSv4 state lock in 3.17 -- thanks
especially to Andrew Elble and Jeff Layton for tracking down some of
the remaining races"
* tag 'nfsd-4.4' of git://linux-nfs.org/~bfields/linux:
svcrpc: document lack of some memory barriers
nfsd: fix race with open / open upgrade stateids
nfsd: eliminate sending duplicate and repeated delegations
nfsd: remove recurring workqueue job to clean DRC
SUNRPC: drop stale comment in svc_setup_socket()
nfsd: ensure that seqid morphing operations are atomic wrt to copies
nfsd: serialize layout stateid morphing operations
nfsd: improve client_has_state to check for unused openowners
nfsd: fix clid_inuse on mount with security change
sunrpc/cache: make cache flushing more reliable.
nfsd: move include of state.h from trace.c to trace.h
sunrpc: avoid warning in gss_key_timeout
lockd: get rid of reference-counted NSM RPC clients
SUNRPC: Use MSG_SENDPAGE_NOTLAST when calling sendpage()
lockd: create NSM handles per net namespace
nfsd: switch unsigned char flags in svc_fh to bools
nfsd: move svc_fh->fh_maxsize to just after fh_handle
nfsd: drop null test before destroy functions
nfsd: serialize state seqid morphing operations
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 969d589..d716c99 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -116,7 +116,7 @@
atomic_inc(&nsm->sm_count);
else {
host = NULL;
- nsm = nsm_get_handle(ni->sap, ni->salen,
+ nsm = nsm_get_handle(ni->net, ni->sap, ni->salen,
ni->hostname, ni->hostname_len);
if (unlikely(nsm == NULL)) {
dprintk("lockd: %s failed; no nsm handle\n",
@@ -161,6 +161,7 @@
host->h_nsmhandle = nsm;
host->h_addrbuf = nsm->sm_addrbuf;
host->net = ni->net;
+ strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename));
out:
return host;
@@ -534,17 +535,18 @@
/**
* nlm_host_rebooted - Release all resources held by rebooted host
+ * @net: network namespace
* @info: pointer to decoded results of NLM_SM_NOTIFY call
*
* We were notified that the specified host has rebooted. Release
* all resources held by that peer.
*/
-void nlm_host_rebooted(const struct nlm_reboot *info)
+void nlm_host_rebooted(const struct net *net, const struct nlm_reboot *info)
{
struct nsm_handle *nsm;
struct nlm_host *host;
- nsm = nsm_reboot_lookup(info);
+ nsm = nsm_reboot_lookup(net, info);
if (unlikely(nsm == NULL))
return;
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 47a32b6..19166d4 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -42,7 +42,7 @@
u32 proc;
char *mon_name;
- char *nodename;
+ const char *nodename;
};
struct nsm_res {
@@ -51,7 +51,6 @@
};
static const struct rpc_program nsm_program;
-static LIST_HEAD(nsm_handles);
static DEFINE_SPINLOCK(nsm_lock);
/*
@@ -87,69 +86,18 @@
return rpc_create(&args);
}
-static struct rpc_clnt *nsm_client_set(struct lockd_net *ln,
- struct rpc_clnt *clnt)
-{
- spin_lock(&ln->nsm_clnt_lock);
- if (ln->nsm_users == 0) {
- if (clnt == NULL)
- goto out;
- ln->nsm_clnt = clnt;
- }
- clnt = ln->nsm_clnt;
- ln->nsm_users++;
-out:
- spin_unlock(&ln->nsm_clnt_lock);
- return clnt;
-}
-
-static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
-{
- struct rpc_clnt *clnt, *new;
- struct lockd_net *ln = net_generic(net, lockd_net_id);
-
- clnt = nsm_client_set(ln, NULL);
- if (clnt != NULL)
- goto out;
-
- clnt = new = nsm_create(net, nodename);
- if (IS_ERR(clnt))
- goto out;
-
- clnt = nsm_client_set(ln, new);
- if (clnt != new)
- rpc_shutdown_client(new);
-out:
- return clnt;
-}
-
-static void nsm_client_put(struct net *net)
-{
- struct lockd_net *ln = net_generic(net, lockd_net_id);
- struct rpc_clnt *clnt = NULL;
-
- spin_lock(&ln->nsm_clnt_lock);
- ln->nsm_users--;
- if (ln->nsm_users == 0) {
- clnt = ln->nsm_clnt;
- ln->nsm_clnt = NULL;
- }
- spin_unlock(&ln->nsm_clnt_lock);
- if (clnt != NULL)
- rpc_shutdown_client(clnt);
-}
-
static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
- struct rpc_clnt *clnt)
+ const struct nlm_host *host)
{
int status;
+ struct rpc_clnt *clnt;
struct nsm_args args = {
.priv = &nsm->sm_priv,
.prog = NLM_PROGRAM,
.vers = 3,
.proc = NLMPROC_NSM_NOTIFY,
.mon_name = nsm->sm_mon_name,
- .nodename = clnt->cl_nodename,
+ .nodename = host->nodename,
};
struct rpc_message msg = {
.rpc_argp = &args,
@@ -158,6 +106,13 @@
memset(res, 0, sizeof(*res));
+ clnt = nsm_create(host->net, host->nodename);
+ if (IS_ERR(clnt)) {
+ dprintk("lockd: failed to create NSM upcall transport, "
+ "status=%ld, net=%p\n", PTR_ERR(clnt), host->net);
+ return PTR_ERR(clnt);
+ }
+
msg.rpc_proc = &clnt->cl_procinfo[proc];
status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
if (status == -ECONNREFUSED) {
@@ -171,6 +126,8 @@
status);
else
status = 0;
+
+ rpc_shutdown_client(clnt);
return status;
}
@@ -190,32 +147,19 @@
struct nsm_handle *nsm = host->h_nsmhandle;
struct nsm_res res;
int status;
- struct rpc_clnt *clnt;
- const char *nodename = NULL;
dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
if (nsm->sm_monitored)
return 0;
- if (host->h_rpcclnt)
- nodename = host->h_rpcclnt->cl_nodename;
-
/*
* Choose whether to record the caller_name or IP address of
* this peer in the local rpc.statd's database.
*/
nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
- clnt = nsm_client_get(host->net, nodename);
- if (IS_ERR(clnt)) {
- status = PTR_ERR(clnt);
- dprintk("lockd: failed to create NSM upcall transport, "
- "status=%d, net=%p\n", status, host->net);
- return status;
- }
-
- status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, clnt);
+ status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host);
if (unlikely(res.status != 0))
status = -EIO;
if (unlikely(status < 0)) {
@@ -247,11 +191,9 @@
if (atomic_read(&nsm->sm_count) == 1
&& nsm->sm_monitored && !nsm->sm_sticky) {
- struct lockd_net *ln = net_generic(host->net, lockd_net_id);
-
dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
- status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, ln->nsm_clnt);
+ status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host);
if (res.status != 0)
status = -EIO;
if (status < 0)
@@ -259,38 +201,38 @@
nsm->sm_name);
else
nsm->sm_monitored = 0;
-
- nsm_client_put(host->net);
}
}
-static struct nsm_handle *nsm_lookup_hostname(const char *hostname,
- const size_t len)
+static struct nsm_handle *nsm_lookup_hostname(const struct list_head *nsm_handles,
+ const char *hostname, const size_t len)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (strlen(nsm->sm_name) == len &&
memcmp(nsm->sm_name, hostname, len) == 0)
return nsm;
return NULL;
}
-static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
+static struct nsm_handle *nsm_lookup_addr(const struct list_head *nsm_handles,
+ const struct sockaddr *sap)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (rpc_cmp_addr(nsm_addr(nsm), sap))
return nsm;
return NULL;
}
-static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv)
+static struct nsm_handle *nsm_lookup_priv(const struct list_head *nsm_handles,
+ const struct nsm_private *priv)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (memcmp(nsm->sm_priv.data, priv->data,
sizeof(priv->data)) == 0)
return nsm;
@@ -353,6 +295,7 @@
/**
* nsm_get_handle - Find or create a cached nsm_handle
+ * @net: network namespace
* @sap: pointer to socket address of handle to find
* @salen: length of socket address
* @hostname: pointer to C string containing hostname to find
@@ -365,11 +308,13 @@
* @hostname cannot be found in the handle cache. Returns NULL if
* an error occurs.
*/
-struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+struct nsm_handle *nsm_get_handle(const struct net *net,
+ const struct sockaddr *sap,
const size_t salen, const char *hostname,
const size_t hostname_len)
{
struct nsm_handle *cached, *new = NULL;
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
if (printk_ratelimit()) {
@@ -384,9 +329,10 @@
spin_lock(&nsm_lock);
if (nsm_use_hostnames && hostname != NULL)
- cached = nsm_lookup_hostname(hostname, hostname_len);
+ cached = nsm_lookup_hostname(&ln->nsm_handles,
+ hostname, hostname_len);
else
- cached = nsm_lookup_addr(sap);
+ cached = nsm_lookup_addr(&ln->nsm_handles, sap);
if (cached != NULL) {
atomic_inc(&cached->sm_count);
@@ -400,7 +346,7 @@
}
if (new != NULL) {
- list_add(&new->sm_link, &nsm_handles);
+ list_add(&new->sm_link, &ln->nsm_handles);
spin_unlock(&nsm_lock);
dprintk("lockd: created nsm_handle for %s (%s)\n",
new->sm_name, new->sm_addrbuf);
@@ -417,19 +363,22 @@
/**
* nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle
+ * @net: network namespace
* @info: pointer to NLMPROC_SM_NOTIFY arguments
*
* Returns a matching nsm_handle if found in the nsm cache. The returned
* nsm_handle's reference count is bumped. Otherwise returns NULL if some
* error occurred.
*/
-struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info)
+struct nsm_handle *nsm_reboot_lookup(const struct net *net,
+ const struct nlm_reboot *info)
{
struct nsm_handle *cached;
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
spin_lock(&nsm_lock);
- cached = nsm_lookup_priv(&info->priv);
+ cached = nsm_lookup_priv(&ln->nsm_handles, &info->priv);
if (unlikely(cached == NULL)) {
spin_unlock(&nsm_lock);
dprintk("lockd: never saw rebooted peer '%.*s' before\n",
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 097bfa3..5426189 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -12,9 +12,7 @@
struct delayed_work grace_period_end;
struct lock_manager lockd_manager;
- spinlock_t nsm_clnt_lock;
- unsigned int nsm_users;
- struct rpc_clnt *nsm_clnt;
+ struct list_head nsm_handles;
};
extern int lockd_net_id;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index d678bcc..5f31ebd 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -592,7 +592,7 @@
INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
INIT_LIST_HEAD(&ln->lockd_manager.list);
ln->lockd_manager.block_opens = false;
- spin_lock_init(&ln->nsm_clnt_lock);
+ INIT_LIST_HEAD(&ln->nsm_handles);
return 0;
}
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index b147d1a..09c576f 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -421,7 +421,7 @@
return rpc_system_err;
}
- nlm_host_rebooted(argp);
+ nlm_host_rebooted(SVC_NET(rqstp), argp);
return rpc_success;
}
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 21171f0..fb26b9f 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -464,7 +464,7 @@
return rpc_system_err;
}
- nlm_host_rebooted(argp);
+ nlm_host_rebooted(SVC_NET(rqstp), argp);
return rpc_success;
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index f6e7cba..00575d7 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -262,11 +262,11 @@
err = fh_getattr(fhp, &fhp->fh_post_attr);
fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version;
if (err) {
- fhp->fh_post_saved = 0;
+ fhp->fh_post_saved = false;
/* Grab the ctime anyway - set_change_info might use it */
fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime;
} else
- fhp->fh_post_saved = 1;
+ fhp->fh_post_saved = true;
}
/*
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index ebf90e4..9ffef06 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -201,6 +201,7 @@
INIT_LIST_HEAD(&ls->ls_perfile);
spin_lock_init(&ls->ls_lock);
INIT_LIST_HEAD(&ls->ls_layouts);
+ mutex_init(&ls->ls_mutex);
ls->ls_layout_type = layout_type;
nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
NFSPROC4_CLNT_CB_LAYOUT);
@@ -262,19 +263,23 @@
status = nfserr_jukebox;
if (!ls)
goto out;
+ mutex_lock(&ls->ls_mutex);
} else {
ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
status = nfserr_bad_stateid;
+ mutex_lock(&ls->ls_mutex);
if (stateid->si_generation > stid->sc_stateid.si_generation)
- goto out_put_stid;
+ goto out_unlock_stid;
if (layout_type != ls->ls_layout_type)
- goto out_put_stid;
+ goto out_unlock_stid;
}
*lsp = ls;
return 0;
+out_unlock_stid:
+ mutex_unlock(&ls->ls_mutex);
out_put_stid:
nfs4_put_stid(stid);
out:
@@ -296,8 +301,6 @@
trace_layout_recall(&ls->ls_stid.sc_stateid);
atomic_inc(&ls->ls_stid.sc_count);
- update_stateid(&ls->ls_stid.sc_stateid);
- memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
nfsd4_run_cb(&ls->ls_recall);
out_unlock:
@@ -406,8 +409,7 @@
list_add_tail(&new->lo_perstate, &ls->ls_layouts);
new = NULL;
done:
- update_stateid(&ls->ls_stid.sc_stateid);
- memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid);
spin_unlock(&ls->ls_lock);
out:
spin_unlock(&fp->fi_lock);
@@ -481,11 +483,8 @@
}
}
if (!list_empty(&ls->ls_layouts)) {
- if (found) {
- update_stateid(&ls->ls_stid.sc_stateid);
- memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
- sizeof(stateid_t));
- }
+ if (found)
+ nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid);
lrp->lrs_present = 1;
} else {
trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
@@ -494,6 +493,7 @@
}
spin_unlock(&ls->ls_lock);
+ mutex_unlock(&ls->ls_mutex);
nfs4_put_stid(&ls->ls_stid);
nfsd4_free_layouts(&reaplist);
return nfs_ok;
@@ -608,6 +608,16 @@
}
}
+static void
+nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
+{
+ struct nfs4_layout_stateid *ls =
+ container_of(cb, struct nfs4_layout_stateid, ls_recall);
+
+ mutex_lock(&ls->ls_mutex);
+ nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
+}
+
static int
nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
{
@@ -649,12 +659,14 @@
trace_layout_recall_release(&ls->ls_stid.sc_stateid);
+ mutex_unlock(&ls->ls_mutex);
nfsd4_return_all_layouts(ls, &reaplist);
nfsd4_free_layouts(&reaplist);
nfs4_put_stid(&ls->ls_stid);
}
static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+ .prepare = nfsd4_cb_layout_prepare,
.done = nfsd4_cb_layout_done,
.release = nfsd4_cb_layout_release,
};
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4ce6b97..a9f096c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1309,6 +1309,7 @@
nfserr = nfsd4_insert_layout(lgp, ls);
out_put_stid:
+ mutex_unlock(&ls->ls_mutex);
nfs4_put_stid(&ls->ls_stid);
out:
return nfserr;
@@ -1362,6 +1363,9 @@
goto out;
}
+ /* LAYOUTCOMMIT does not require any serialization */
+ mutex_unlock(&ls->ls_mutex);
+
if (new_size > i_size_read(inode)) {
lcp->lc_size_chg = 1;
lcp->lc_newsize = new_size;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0f1d569..6b800b5b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -575,6 +575,7 @@
stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
/* Will be incremented before return to client: */
atomic_set(&stid->sc_count, 1);
+ spin_lock_init(&stid->sc_lock);
/*
* It shouldn't be a problem to reuse an opaque stateid value.
@@ -745,6 +746,18 @@
put_nfs4_file(fp);
}
+void
+nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid)
+{
+ stateid_t *src = &stid->sc_stateid;
+
+ spin_lock(&stid->sc_lock);
+ if (unlikely(++src->si_generation == 0))
+ src->si_generation = 1;
+ memcpy(dst, src, sizeof(*dst));
+ spin_unlock(&stid->sc_lock);
+}
+
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
struct file *filp = NULL;
@@ -765,16 +778,68 @@
s->sc_type = 0;
}
-static void
-hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
+/**
+ * nfs4_get_existing_delegation - Discover if this delegation already exists
+ * @clp: a pointer to the nfs4_client we're granting a delegation to
+ * @fp: a pointer to the nfs4_file we're granting a delegation on
+ *
+ * Return:
+ * On success: NULL if an existing delegation was not found.
+ *
+ * On error: -EAGAIN if one was previously granted to this nfs4_client
+ * for this nfs4_file.
+ *
+ */
+
+static int
+nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp)
{
+ struct nfs4_delegation *searchdp = NULL;
+ struct nfs4_client *searchclp = NULL;
+
lockdep_assert_held(&state_lock);
lockdep_assert_held(&fp->fi_lock);
+ list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) {
+ searchclp = searchdp->dl_stid.sc_client;
+ if (clp == searchclp) {
+ return -EAGAIN;
+ }
+ }
+ return 0;
+}
+
+/**
+ * hash_delegation_locked - Add a delegation to the appropriate lists
+ * @dp: a pointer to the nfs4_delegation we are adding.
+ * @fp: a pointer to the nfs4_file we're granting a delegation on
+ *
+ * Return:
+ * On success: NULL if the delegation was successfully hashed.
+ *
+ * On error: -EAGAIN if one was previously granted to this
+ * nfs4_client for this nfs4_file. Delegation is not hashed.
+ *
+ */
+
+static int
+hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
+{
+ int status;
+ struct nfs4_client *clp = dp->dl_stid.sc_client;
+
+ lockdep_assert_held(&state_lock);
+ lockdep_assert_held(&fp->fi_lock);
+
+ status = nfs4_get_existing_delegation(clp, fp);
+ if (status)
+ return status;
+ ++fp->fi_delegees;
atomic_inc(&dp->dl_stid.sc_count);
dp->dl_stid.sc_type = NFS4_DELEG_STID;
list_add(&dp->dl_perfile, &fp->fi_delegations);
- list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+ list_add(&dp->dl_perclnt, &clp->cl_delegations);
+ return 0;
}
static bool
@@ -2256,15 +2321,20 @@
clid->flags = new->cl_exchange_flags;
}
+static bool client_has_openowners(struct nfs4_client *clp)
+{
+ struct nfs4_openowner *oo;
+
+ list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) {
+ if (!list_empty(&oo->oo_owner.so_stateids))
+ return true;
+ }
+ return false;
+}
+
static bool client_has_state(struct nfs4_client *clp)
{
- /*
- * Note clp->cl_openowners check isn't quite right: there's no
- * need to count owners without stateid's.
- *
- * Also note we should probably be using this in 4.0 case too.
- */
- return !list_empty(&clp->cl_openowners)
+ return client_has_openowners(clp)
#ifdef CONFIG_NFSD_PNFS
|| !list_empty(&clp->cl_lo_states)
#endif
@@ -3049,7 +3119,7 @@
/* Cases below refer to rfc 3530 section 14.2.33: */
spin_lock(&nn->client_lock);
conf = find_confirmed_client_by_name(&clname, nn);
- if (conf) {
+ if (conf && client_has_state(conf)) {
/* case 0: */
status = nfserr_clid_inuse;
if (clp_used_exchangeid(conf))
@@ -3136,6 +3206,11 @@
} else { /* case 3: normal case; new or rebooted client */
old = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (old) {
+ status = nfserr_clid_inuse;
+ if (client_has_state(old)
+ && !same_creds(&unconf->cl_cred,
+ &old->cl_cred))
+ goto out;
status = mark_client_expired_locked(old);
if (status) {
old = NULL;
@@ -3317,6 +3392,27 @@
.so_free = nfs4_free_openowner,
};
+static struct nfs4_ol_stateid *
+nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+ struct nfs4_ol_stateid *local, *ret = NULL;
+ struct nfs4_openowner *oo = open->op_openowner;
+
+ lockdep_assert_held(&fp->fi_lock);
+
+ list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
+ /* ignore lock owners */
+ if (local->st_stateowner->so_is_open_owner == 0)
+ continue;
+ if (local->st_stateowner == &oo->oo_owner) {
+ ret = local;
+ atomic_inc(&ret->st_stid.sc_count);
+ break;
+ }
+ }
+ return ret;
+}
+
static struct nfs4_openowner *
alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
@@ -3348,9 +3444,20 @@
return ret;
}
-static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
- struct nfs4_openowner *oo = open->op_openowner;
+static struct nfs4_ol_stateid *
+init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
+ struct nfsd4_open *open)
+{
+ struct nfs4_openowner *oo = open->op_openowner;
+ struct nfs4_ol_stateid *retstp = NULL;
+
+ spin_lock(&oo->oo_owner.so_client->cl_lock);
+ spin_lock(&fp->fi_lock);
+
+ retstp = nfsd4_find_existing_open(fp, open);
+ if (retstp)
+ goto out_unlock;
atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
@@ -3360,12 +3467,14 @@
stp->st_access_bmap = 0;
stp->st_deny_bmap = 0;
stp->st_openstp = NULL;
- spin_lock(&oo->oo_owner.so_client->cl_lock);
+ init_rwsem(&stp->st_rwsem);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
- spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
+
+out_unlock:
spin_unlock(&fp->fi_lock);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
+ return retstp;
}
/*
@@ -3776,27 +3885,6 @@
return nfs_ok;
}
-static struct nfs4_ol_stateid *
-nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
-{
- struct nfs4_ol_stateid *local, *ret = NULL;
- struct nfs4_openowner *oo = open->op_openowner;
-
- spin_lock(&fp->fi_lock);
- list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
- /* ignore lock owners */
- if (local->st_stateowner->so_is_open_owner == 0)
- continue;
- if (local->st_stateowner == &oo->oo_owner) {
- ret = local;
- atomic_inc(&ret->st_stid.sc_count);
- break;
- }
- }
- spin_unlock(&fp->fi_lock);
- return ret;
-}
-
static inline int nfs4_access_to_access(u32 nfs4_access)
{
int flags = 0;
@@ -3945,6 +4033,18 @@
return fl;
}
+/**
+ * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer
+ * @dp: a pointer to the nfs4_delegation we're adding.
+ *
+ * Return:
+ * On success: Return code will be 0 on success.
+ *
+ * On error: -EAGAIN if there was an existing delegation.
+ * nonzero if there is an error in other cases.
+ *
+ */
+
static int nfs4_setlease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -3976,16 +4076,19 @@
goto out_unlock;
/* Race breaker */
if (fp->fi_deleg_file) {
- status = 0;
- ++fp->fi_delegees;
- hash_delegation_locked(dp, fp);
+ status = hash_delegation_locked(dp, fp);
goto out_unlock;
}
fp->fi_deleg_file = filp;
- fp->fi_delegees = 1;
- hash_delegation_locked(dp, fp);
+ fp->fi_delegees = 0;
+ status = hash_delegation_locked(dp, fp);
spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
+ if (status) {
+ /* Should never happen, this is a new fi_deleg_file */
+ WARN_ON_ONCE(1);
+ goto out_fput;
+ }
return 0;
out_unlock:
spin_unlock(&fp->fi_lock);
@@ -4005,6 +4108,15 @@
if (fp->fi_had_conflict)
return ERR_PTR(-EAGAIN);
+ spin_lock(&state_lock);
+ spin_lock(&fp->fi_lock);
+ status = nfs4_get_existing_delegation(clp, fp);
+ spin_unlock(&fp->fi_lock);
+ spin_unlock(&state_lock);
+
+ if (status)
+ return ERR_PTR(status);
+
dp = alloc_init_deleg(clp, fh, odstate);
if (!dp)
return ERR_PTR(-ENOMEM);
@@ -4023,9 +4135,7 @@
status = -EAGAIN;
goto out_unlock;
}
- ++fp->fi_delegees;
- hash_delegation_locked(dp, fp);
- status = 0;
+ status = hash_delegation_locked(dp, fp);
out_unlock:
spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
@@ -4160,6 +4270,7 @@
struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
struct nfs4_file *fp = NULL;
struct nfs4_ol_stateid *stp = NULL;
+ struct nfs4_ol_stateid *swapstp = NULL;
struct nfs4_delegation *dp = NULL;
__be32 status;
@@ -4173,7 +4284,9 @@
status = nfs4_check_deleg(cl, open, &dp);
if (status)
goto out;
+ spin_lock(&fp->fi_lock);
stp = nfsd4_find_existing_open(fp, open);
+ spin_unlock(&fp->fi_lock);
} else {
open->op_file = NULL;
status = nfserr_bad_stateid;
@@ -4187,15 +4300,32 @@
*/
if (stp) {
/* Stateid was found, this is an OPEN upgrade */
+ down_read(&stp->st_rwsem);
status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
- if (status)
+ if (status) {
+ up_read(&stp->st_rwsem);
goto out;
+ }
} else {
stp = open->op_stp;
open->op_stp = NULL;
- init_open_stateid(stp, fp, open);
+ swapstp = init_open_stateid(stp, fp, open);
+ if (swapstp) {
+ nfs4_put_stid(&stp->st_stid);
+ stp = swapstp;
+ down_read(&stp->st_rwsem);
+ status = nfs4_upgrade_open(rqstp, fp, current_fh,
+ stp, open);
+ if (status) {
+ up_read(&stp->st_rwsem);
+ goto out;
+ }
+ goto upgrade_out;
+ }
+ down_read(&stp->st_rwsem);
status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
if (status) {
+ up_read(&stp->st_rwsem);
release_open_stateid(stp);
goto out;
}
@@ -4205,8 +4335,9 @@
if (stp->st_clnt_odstate == open->op_odstate)
open->op_odstate = NULL;
}
- update_stateid(&stp->st_stid.sc_stateid);
- memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+upgrade_out:
+ nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
+ up_read(&stp->st_rwsem);
if (nfsd4_has_session(&resp->cstate)) {
if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4819,10 +4950,13 @@
* revoked delegations are kept only for free_stateid.
*/
return nfserr_bad_stateid;
+ down_write(&stp->st_rwsem);
status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
- if (status)
- return status;
- return nfs4_check_fh(current_fh, &stp->st_stid);
+ if (status == nfs_ok)
+ status = nfs4_check_fh(current_fh, &stp->st_stid);
+ if (status != nfs_ok)
+ up_write(&stp->st_rwsem);
+ return status;
}
/*
@@ -4869,6 +5003,7 @@
return status;
oo = openowner(stp->st_stateowner);
if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
+ up_write(&stp->st_rwsem);
nfs4_put_stid(&stp->st_stid);
return nfserr_bad_stateid;
}
@@ -4899,11 +5034,13 @@
goto out;
oo = openowner(stp->st_stateowner);
status = nfserr_bad_stateid;
- if (oo->oo_flags & NFS4_OO_CONFIRMED)
+ if (oo->oo_flags & NFS4_OO_CONFIRMED) {
+ up_write(&stp->st_rwsem);
goto put_stateid;
+ }
oo->oo_flags |= NFS4_OO_CONFIRMED;
- update_stateid(&stp->st_stid.sc_stateid);
- memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
+ up_write(&stp->st_rwsem);
dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
@@ -4975,13 +5112,11 @@
goto put_stateid;
}
nfs4_stateid_downgrade(stp, od->od_share_access);
-
reset_union_bmap_deny(od->od_share_deny, stp);
-
- update_stateid(&stp->st_stid.sc_stateid);
- memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
status = nfs_ok;
put_stateid:
+ up_write(&stp->st_rwsem);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
@@ -5033,8 +5168,8 @@
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
- update_stateid(&stp->st_stid.sc_stateid);
- memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
+ up_write(&stp->st_rwsem);
nfsd4_close_open_stateid(stp);
@@ -5260,6 +5395,7 @@
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
+ init_rwsem(&stp->st_rwsem);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
spin_lock(&fp->fi_lock);
@@ -5428,6 +5564,7 @@
&open_stp, nn);
if (status)
goto out;
+ up_write(&open_stp->st_rwsem);
open_sop = openowner(open_stp->st_stateowner);
status = nfserr_bad_stateid;
if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5435,6 +5572,8 @@
goto out;
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new);
+ if (status == nfs_ok)
+ down_write(&lock_stp->st_rwsem);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
@@ -5512,9 +5651,7 @@
err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
switch (-err) {
case 0: /* success! */
- update_stateid(&lock_stp->st_stid.sc_stateid);
- memcpy(&lock->lk_resp_stateid, &lock_stp->st_stid.sc_stateid,
- sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid);
status = 0;
break;
case (EAGAIN): /* conflock holds conflicting lock */
@@ -5540,6 +5677,8 @@
seqid_mutating_err(ntohl(status)))
lock_sop->lo_owner.so_seqid++;
+ up_write(&lock_stp->st_rwsem);
+
/*
* If this is a new, never-before-used stateid, and we are
* returning an error, then just go ahead and release it.
@@ -5704,11 +5843,11 @@
dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n");
goto out_nfserr;
}
- update_stateid(&stp->st_stid.sc_stateid);
- memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+ nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid);
fput:
fput(filp);
put_stateid:
+ up_write(&stp->st_rwsem);
nfs4_put_stid(&stp->st_stid);
out:
nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 46ec934..54cde9a 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -63,7 +63,6 @@
static unsigned int longest_chain_cachesize;
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
-static void cache_cleaner_func(struct work_struct *unused);
static unsigned long nfsd_reply_cache_count(struct shrinker *shrink,
struct shrink_control *sc);
static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink,
@@ -76,13 +75,6 @@
};
/*
- * locking for the reply cache:
- * A cache entry is "single use" if c_state == RC_INPROG
- * Otherwise, it when accessing _prev or _next, the lock must be held.
- */
-static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
-
-/*
* Put a cap on the size of the DRC based on the amount of available
* low memory in the machine.
*
@@ -203,7 +195,6 @@
unsigned int i;
unregister_shrinker(&nfsd_reply_cache_shrinker);
- cancel_delayed_work_sync(&cache_cleaner);
for (i = 0; i < drc_hashsize; i++) {
struct list_head *head = &drc_hashtbl[i].lru_head;
@@ -217,10 +208,8 @@
drc_hashtbl = NULL;
drc_hashsize = 0;
- if (drc_slab) {
- kmem_cache_destroy(drc_slab);
- drc_slab = NULL;
- }
+ kmem_cache_destroy(drc_slab);
+ drc_slab = NULL;
}
/*
@@ -232,7 +221,6 @@
{
rp->c_timestamp = jiffies;
list_move_tail(&rp->c_lru, &b->lru_head);
- schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
static long
@@ -266,7 +254,6 @@
{
unsigned int i;
long freed = 0;
- bool cancel = true;
for (i = 0; i < drc_hashsize; i++) {
struct nfsd_drc_bucket *b = &drc_hashtbl[i];
@@ -275,26 +262,11 @@
continue;
spin_lock(&b->cache_lock);
freed += prune_bucket(b);
- if (!list_empty(&b->lru_head))
- cancel = false;
spin_unlock(&b->cache_lock);
}
-
- /*
- * Conditionally rearm the job to run in RC_EXPIRE since we just
- * ran the pruner.
- */
- if (!cancel)
- mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
return freed;
}
-static void
-cache_cleaner_func(struct work_struct *unused)
-{
- prune_cache_entries();
-}
-
static unsigned long
nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 350041a..c1681ce 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -631,10 +631,7 @@
fh_unlock(fhp);
fhp->fh_dentry = NULL;
dput(dentry);
-#ifdef CONFIG_NFSD_V3
- fhp->fh_pre_saved = 0;
- fhp->fh_post_saved = 0;
-#endif
+ fh_clear_wcc(fhp);
}
fh_drop_write(fhp);
if (exp) {
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 1e90dad..2087bae 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -26,16 +26,16 @@
*/
typedef struct svc_fh {
struct knfsd_fh fh_handle; /* FH data */
+ int fh_maxsize; /* max size for fh_handle */
struct dentry * fh_dentry; /* validated dentry */
struct svc_export * fh_export; /* export pointer */
- int fh_maxsize; /* max size for fh_handle */
- unsigned char fh_locked; /* inode locked by us */
- unsigned char fh_want_write; /* remount protection taken */
+ bool fh_locked; /* inode locked by us */
+ bool fh_want_write; /* remount protection taken */
#ifdef CONFIG_NFSD_V3
- unsigned char fh_post_saved; /* post-op attrs saved */
- unsigned char fh_pre_saved; /* pre-op attrs saved */
+ bool fh_post_saved; /* post-op attrs saved */
+ bool fh_pre_saved; /* pre-op attrs saved */
/* Pre-op attributes saved during fh_lock */
__u64 fh_pre_size; /* size before operation */
@@ -213,8 +213,8 @@
static inline void
fh_clear_wcc(struct svc_fh *fhp)
{
- fhp->fh_post_saved = 0;
- fhp->fh_pre_saved = 0;
+ fhp->fh_post_saved = false;
+ fhp->fh_pre_saved = false;
}
/*
@@ -231,7 +231,7 @@
fhp->fh_pre_ctime = inode->i_ctime;
fhp->fh_pre_size = inode->i_size;
fhp->fh_pre_change = inode->i_version;
- fhp->fh_pre_saved = 1;
+ fhp->fh_pre_saved = true;
}
}
@@ -267,7 +267,7 @@
inode = d_inode(dentry);
mutex_lock_nested(&inode->i_mutex, subclass);
fill_pre_wcc(fhp);
- fhp->fh_locked = 1;
+ fhp->fh_locked = true;
}
static inline void
@@ -285,7 +285,7 @@
if (fhp->fh_locked) {
fill_post_wcc(fhp);
mutex_unlock(&d_inode(fhp->fh_dentry)->i_mutex);
- fhp->fh_locked = 0;
+ fhp->fh_locked = false;
}
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 583ffc1..77fdf4d 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -84,7 +84,7 @@
* fields that are of general use to any stateid.
*/
struct nfs4_stid {
- atomic_t sc_count;
+ atomic_t sc_count;
#define NFS4_OPEN_STID 1
#define NFS4_LOCK_STID 2
#define NFS4_DELEG_STID 4
@@ -94,11 +94,12 @@
#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;
- struct nfs4_file *sc_file;
- void (*sc_free)(struct nfs4_stid *);
+ unsigned char sc_type;
+ stateid_t sc_stateid;
+ spinlock_t sc_lock;
+ struct nfs4_client *sc_client;
+ struct nfs4_file *sc_file;
+ void (*sc_free)(struct nfs4_stid *);
};
/*
@@ -364,15 +365,6 @@
char cr_recdir[HEXDIR_LEN]; /* recover dir */
};
-static inline void
-update_stateid(stateid_t *stateid)
-{
- stateid->si_generation++;
- /* Wraparound recommendation from 3530bis-13 9.1.3.2: */
- if (stateid->si_generation == 0)
- stateid->si_generation = 1;
-}
-
/* A reasonable value for REPLAY_ISIZE was estimated as follows:
* The OPEN response, typically the largest, requires
* 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) +
@@ -534,15 +526,16 @@
* Better suggestions welcome.
*/
struct nfs4_ol_stateid {
- struct nfs4_stid st_stid; /* must be first field */
- struct list_head st_perfile;
- struct list_head st_perstateowner;
- struct list_head st_locks;
- struct nfs4_stateowner * st_stateowner;
- struct nfs4_clnt_odstate * st_clnt_odstate;
- unsigned char st_access_bmap;
- unsigned char st_deny_bmap;
- struct nfs4_ol_stateid * st_openstp;
+ struct nfs4_stid st_stid;
+ struct list_head st_perfile;
+ struct list_head st_perstateowner;
+ struct list_head st_locks;
+ struct nfs4_stateowner *st_stateowner;
+ struct nfs4_clnt_odstate *st_clnt_odstate;
+ unsigned char st_access_bmap;
+ unsigned char st_deny_bmap;
+ struct nfs4_ol_stateid *st_openstp;
+ struct rw_semaphore st_rwsem;
};
static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
@@ -561,6 +554,7 @@
struct nfsd4_callback ls_recall;
stateid_t ls_recall_sid;
bool ls_recalled;
+ struct mutex ls_mutex;
};
static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
@@ -593,6 +587,7 @@
struct kmem_cache *slab);
void nfs4_unhash_stid(struct nfs4_stid *s);
void nfs4_put_stid(struct nfs4_stid *s);
+void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
extern void nfs4_release_reclaim(struct nfsd_net *);
extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c
index 82f8907..9096746 100644
--- a/fs/nfsd/trace.c
+++ b/fs/nfsd/trace.c
@@ -1,5 +1,3 @@
-#include "state.h"
-
#define CREATE_TRACE_POINTS
#include "trace.h"
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index c668520..0befe76 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -9,6 +9,8 @@
#include <linux/tracepoint.h>
+#include "state.h"
+
DECLARE_EVENT_CLASS(nfsd_stateid_class,
TP_PROTO(stateid_t *stp),
TP_ARGS(stp),
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 45c0497..994d66f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1631,7 +1631,7 @@
/* cannot use fh_lock as we need deadlock protective ordering
* so do it by hand */
trap = lock_rename(tdentry, fdentry);
- ffhp->fh_locked = tfhp->fh_locked = 1;
+ ffhp->fh_locked = tfhp->fh_locked = true;
fill_pre_wcc(ffhp);
fill_pre_wcc(tfhp);
@@ -1681,7 +1681,7 @@
fill_post_wcc(ffhp);
fill_post_wcc(tfhp);
unlock_rename(tdentry, fdentry);
- ffhp->fh_locked = tfhp->fh_locked = 0;
+ ffhp->fh_locked = tfhp->fh_locked = false;
fh_drop_write(ffhp);
out:
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fee2451..fcfc48c 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -112,14 +112,14 @@
int ret = mnt_want_write(fh->fh_export->ex_path.mnt);
if (!ret)
- fh->fh_want_write = 1;
+ fh->fh_want_write = true;
return ret;
}
static inline void fh_drop_write(struct svc_fh *fh)
{
if (fh->fh_want_write) {
- fh->fh_want_write = 0;
+ fh->fh_want_write = false;
mnt_drop_write(fh->fh_export->ex_path.mnt);
}
}
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 9f99100..ce7362c 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -632,7 +632,7 @@
set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
{
BUG_ON(!fhp->fh_pre_saved);
- cinfo->atomic = fhp->fh_post_saved;
+ cinfo->atomic = (u32)fhp->fh_post_saved;
cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry));
cinfo->before_change = fhp->fh_pre_change;
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index ff82a32..c153738 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -68,6 +68,7 @@
struct nsm_handle *h_nsmhandle; /* NSM status handle */
char *h_addrbuf; /* address eyecatcher */
struct net *net; /* host net */
+ char nodename[UNX_MAXNODENAME + 1];
};
/*
@@ -235,7 +236,8 @@
struct nlm_host * nlm_get_host(struct nlm_host *);
void nlm_shutdown_hosts(void);
void nlm_shutdown_hosts_net(struct net *net);
-void nlm_host_rebooted(const struct nlm_reboot *);
+void nlm_host_rebooted(const struct net *net,
+ const struct nlm_reboot *);
/*
* Host monitoring
@@ -243,11 +245,13 @@
int nsm_monitor(const struct nlm_host *host);
void nsm_unmonitor(const struct nlm_host *host);
-struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+struct nsm_handle *nsm_get_handle(const struct net *net,
+ const struct sockaddr *sap,
const size_t salen,
const char *hostname,
const size_t hostname_len);
-struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info);
+struct nsm_handle *nsm_reboot_lookup(const struct net *net,
+ const struct nlm_reboot *info);
void nsm_release(struct nsm_handle *nsm);
/*
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 03d3b4c..ed03c9f 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -48,8 +48,10 @@
struct cache_head {
struct hlist_node cache_list;
time_t expiry_time; /* After time time, don't use the data */
- time_t last_refresh; /* If CACHE_PENDING, this is when upcall
- * was sent, else this is when update was received
+ time_t last_refresh; /* If CACHE_PENDING, this is when upcall was
+ * sent, else this is when update was
+ * received, though it is alway set to
+ * be *after* ->flush_time.
*/
struct kref ref;
unsigned long flags;
@@ -105,8 +107,12 @@
/* fields below this comment are for internal use
* and should not be touched by cache owners
*/
- time_t flush_time; /* flush all cache items with last_refresh
- * earlier than this */
+ time_t flush_time; /* flush all cache items with
+ * last_refresh at or earlier
+ * than this. last_refresh
+ * is never set at or earlier
+ * than this.
+ */
struct list_head others;
time_t nextcheck;
int entries;
@@ -203,7 +209,7 @@
static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h)
{
return (h->expiry_time < seconds_since_boot()) ||
- (detail->flush_time > h->last_refresh);
+ (detail->flush_time >= h->last_refresh);
}
extern int cache_check(struct cache_detail *detail,
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index dace13d..799e65b 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1411,17 +1411,16 @@
{
struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base);
struct gss_cl_ctx *ctx;
- unsigned long now = jiffies;
- unsigned long expire;
+ unsigned long timeout = jiffies + (gss_key_expire_timeo * HZ);
+ int ret = 0;
rcu_read_lock();
ctx = rcu_dereference(gss_cred->gc_ctx);
- if (ctx)
- expire = ctx->gc_expiry - (gss_key_expire_timeo * HZ);
+ if (!ctx || time_after(timeout, ctx->gc_expiry))
+ ret = -EACCES;
rcu_read_unlock();
- if (!ctx || time_after(now, expire))
- return -EACCES;
- return 0;
+
+ return ret;
}
static int
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 4a2340a..5e4f815 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -41,13 +41,16 @@
static bool cache_defer_req(struct cache_req *req, struct cache_head *item);
static void cache_revisit_request(struct cache_head *item);
-static void cache_init(struct cache_head *h)
+static void cache_init(struct cache_head *h, struct cache_detail *detail)
{
time_t now = seconds_since_boot();
INIT_HLIST_NODE(&h->cache_list);
h->flags = 0;
kref_init(&h->ref);
h->expiry_time = now + CACHE_NEW_EXPIRY;
+ if (now <= detail->flush_time)
+ /* ensure it isn't already expired */
+ now = detail->flush_time + 1;
h->last_refresh = now;
}
@@ -81,7 +84,7 @@
* we might get lose if we need to
* cache_put it soon.
*/
- cache_init(new);
+ cache_init(new, detail);
detail->init(new, key);
write_lock(&detail->hash_lock);
@@ -116,10 +119,15 @@
static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
-static void cache_fresh_locked(struct cache_head *head, time_t expiry)
+static void cache_fresh_locked(struct cache_head *head, time_t expiry,
+ struct cache_detail *detail)
{
+ time_t now = seconds_since_boot();
+ if (now <= detail->flush_time)
+ /* ensure it isn't immediately treated as expired */
+ now = detail->flush_time + 1;
head->expiry_time = expiry;
- head->last_refresh = seconds_since_boot();
+ head->last_refresh = now;
smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */
set_bit(CACHE_VALID, &head->flags);
}
@@ -149,7 +157,7 @@
set_bit(CACHE_NEGATIVE, &old->flags);
else
detail->update(old, new);
- cache_fresh_locked(old, new->expiry_time);
+ cache_fresh_locked(old, new->expiry_time, detail);
write_unlock(&detail->hash_lock);
cache_fresh_unlocked(old, detail);
return old;
@@ -162,7 +170,7 @@
cache_put(old, detail);
return NULL;
}
- cache_init(tmp);
+ cache_init(tmp, detail);
detail->init(tmp, old);
write_lock(&detail->hash_lock);
@@ -173,8 +181,8 @@
hlist_add_head(&tmp->cache_list, &detail->hash_table[hash]);
detail->entries++;
cache_get(tmp);
- cache_fresh_locked(tmp, new->expiry_time);
- cache_fresh_locked(old, 0);
+ cache_fresh_locked(tmp, new->expiry_time, detail);
+ cache_fresh_locked(old, 0, detail);
write_unlock(&detail->hash_lock);
cache_fresh_unlocked(tmp, detail);
cache_fresh_unlocked(old, detail);
@@ -219,7 +227,8 @@
rv = cache_is_valid(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
- cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
+ cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY,
+ detail);
rv = -ENOENT;
}
write_unlock(&detail->hash_lock);
@@ -487,10 +496,13 @@
void cache_purge(struct cache_detail *detail)
{
- detail->flush_time = LONG_MAX;
+ time_t now = seconds_since_boot();
+ if (detail->flush_time >= now)
+ now = detail->flush_time + 1;
+ /* 'now' is the maximum value any 'last_refresh' can have */
+ detail->flush_time = now;
detail->nextcheck = seconds_since_boot();
cache_flush();
- detail->flush_time = 1;
}
EXPORT_SYMBOL_GPL(cache_purge);
@@ -1436,6 +1448,7 @@
{
char tbuf[20];
char *bp, *ep;
+ time_t then, now;
if (*ppos || count > sizeof(tbuf)-1)
return -EINVAL;
@@ -1447,8 +1460,22 @@
return -EINVAL;
bp = tbuf;
- cd->flush_time = get_expiry(&bp);
- cd->nextcheck = seconds_since_boot();
+ then = get_expiry(&bp);
+ now = seconds_since_boot();
+ cd->nextcheck = now;
+ /* Can only set flush_time to 1 second beyond "now", or
+ * possibly 1 second beyond flushtime. This is because
+ * flush_time never goes backwards so it mustn't get too far
+ * ahead of time.
+ */
+ if (then >= now) {
+ /* Want to flush everything, so behave like cache_purge() */
+ if (cd->flush_time >= now)
+ now = cd->flush_time + 1;
+ then = now;
+ }
+
+ cd->flush_time = then;
cache_flush();
*ppos += count;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0c81202..1413cdc 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -181,7 +181,7 @@
struct page **ppage = xdr->pages;
size_t base = xdr->page_base;
unsigned int pglen = xdr->page_len;
- unsigned int flags = MSG_MORE;
+ unsigned int flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
int slen;
int len = 0;
@@ -399,6 +399,31 @@
return svc_port_is_privileged(svc_addr(rqstp));
}
+static bool sunrpc_waitqueue_active(wait_queue_head_t *wq)
+{
+ if (!wq)
+ return false;
+ /*
+ * There should normally be a memory * barrier here--see
+ * wq_has_sleeper().
+ *
+ * It appears that isn't currently necessary, though, basically
+ * because callers all appear to have sufficient memory barriers
+ * between the time the relevant change is made and the
+ * time they call these callbacks.
+ *
+ * The nfsd code itself doesn't actually explicitly wait on
+ * these waitqueues, but it may wait on them for example in
+ * sendpage() or sendmsg() calls. (And those may be the only
+ * places, since it it uses nonblocking reads.)
+ *
+ * Maybe we should add the memory barriers anyway, but these are
+ * hot paths so we'd need to be convinced there's no sigificant
+ * penalty.
+ */
+ return waitqueue_active(wq);
+}
+
/*
* INET callback when data has been received on the socket.
*/
@@ -414,7 +439,7 @@
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (wq && waitqueue_active(wq))
+ if (sunrpc_waitqueue_active(wq))
wake_up_interruptible(wq);
}
@@ -432,7 +457,7 @@
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (wq && waitqueue_active(wq)) {
+ if (sunrpc_waitqueue_active(wq)) {
dprintk("RPC svc_write_space: someone sleeping on %p\n",
svsk);
wake_up_interruptible(wq);
@@ -787,7 +812,7 @@
}
wq = sk_sleep(sk);
- if (wq && waitqueue_active(wq))
+ if (sunrpc_waitqueue_active(wq))
wake_up_interruptible_all(wq);
}
@@ -808,7 +833,7 @@
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (wq && waitqueue_active(wq))
+ if (sunrpc_waitqueue_active(wq))
wake_up_interruptible_all(wq);
}
@@ -823,7 +848,7 @@
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (wq && waitqueue_active(wq))
+ if (sunrpc_waitqueue_active(wq))
wake_up_interruptible(wq);
}
@@ -1367,7 +1392,6 @@
/*
* Initialize socket for RPC use and create svc_sock struct
- * XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF.
*/
static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
struct socket *sock,
@@ -1594,7 +1618,7 @@
sk->sk_write_space = svsk->sk_owspace;
wq = sk_sleep(sk);
- if (wq && waitqueue_active(wq))
+ if (sunrpc_waitqueue_active(wq))
wake_up_interruptible(wq);
}