summaryrefslogtreecommitdiff
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/Kconfig2
-rw-r--r--fs/nfs/client.c15
-rw-r--r--fs/nfs/delegation.c25
-rw-r--r--fs/nfs/dir.c15
-rw-r--r--fs/nfs/direct.c2
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c6
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c8
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c8
-rw-r--r--fs/nfs/fscache.c1
-rw-r--r--fs/nfs/inode.c51
-rw-r--r--fs/nfs/internal.h8
-rw-r--r--fs/nfs/localio.c51
-rw-r--r--fs/nfs/namespace.c1
-rw-r--r--fs/nfs/netns.h6
-rw-r--r--fs/nfs/nfs3acl.c2
-rw-r--r--fs/nfs/nfs42.h1
-rw-r--r--fs/nfs/nfs42proc.c29
-rw-r--r--fs/nfs/nfs42xdr.c64
-rw-r--r--fs/nfs/nfs4_fs.h3
-rw-r--r--fs/nfs/nfs4file.c10
-rw-r--r--fs/nfs/nfs4proc.c93
-rw-r--r--fs/nfs/nfs4session.h4
-rw-r--r--fs/nfs/nfs4trace.h34
-rw-r--r--fs/nfs/nfs4xdr.c1
-rw-r--r--fs/nfs/pnfs.c51
-rw-r--r--fs/nfs/pnfs.h4
-rw-r--r--fs/nfs/pnfs_nfs.c43
-rw-r--r--fs/nfs/read.c3
-rw-r--r--fs/nfs/super.c19
-rw-r--r--fs/nfs/symlink.c20
-rw-r--r--fs/nfs/sysfs.c28
-rw-r--r--fs/nfs/unlink.c11
-rw-r--r--fs/nfs/write.c54
33 files changed, 469 insertions, 204 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index d3f76101ad4b..07932ce9246c 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -2,6 +2,7 @@
config NFS_FS
tristate "NFS client support"
depends on INET && FILE_LOCKING && MULTIUSER
+ select CRC32
select LOCKD
select SUNRPC
select NFS_COMMON
@@ -196,7 +197,6 @@ config NFS_USE_KERNEL_DNS
config NFS_DEBUG
bool
depends on NFS_FS && SUNRPC_DEBUG
- select CRC32
default y
config NFS_DISABLE_UDP_SUPPORT
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 02c916a55020..cf35ad3f818a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -180,7 +180,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
clp->cl_proto = cl_init->proto;
clp->cl_nconnect = cl_init->nconnect;
clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
- clp->cl_net = get_net(cl_init->net);
+ clp->cl_net = get_net_track(cl_init->net, &clp->cl_ns_tracker, GFP_KERNEL);
#if IS_ENABLED(CONFIG_NFS_LOCALIO)
seqlock_init(&clp->cl_boot_lock);
@@ -250,7 +250,7 @@ void nfs_free_client(struct nfs_client *clp)
if (!IS_ERR(clp->cl_rpcclient))
rpc_shutdown_client(clp->cl_rpcclient);
- put_net(clp->cl_net);
+ put_net_track(clp->cl_net, &clp->cl_ns_tracker);
put_nfs_version(clp->cl_nfs_mod);
kfree(clp->cl_hostname);
kfree(clp->cl_acceptor);
@@ -439,7 +439,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
spin_unlock(&nn->nfs_client_lock);
new = rpc_ops->init_client(new, cl_init);
if (!IS_ERR(new))
- nfs_local_probe(new);
+ nfs_local_probe_async(new);
return new;
}
@@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
server->namelen = NFS2_MAXNAMLEN;
}
+ /* Linux 'subtree_check' borkenness mandates this setting */
+ server->fh_expire_type = NFS_FH_VOL_RENAME;
if (!(fattr->valid & NFS_ATTR_FATTR)) {
error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
@@ -1200,6 +1202,10 @@ void nfs_clients_init(struct net *net)
#if IS_ENABLED(CONFIG_NFS_V4)
idr_init(&nn->cb_ident_idr);
#endif
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
+ spin_lock_init(&nn->nfs4_data_server_lock);
+#endif
spin_lock_init(&nn->nfs_client_lock);
nn->boot_time = ktime_get_real();
memset(&nn->rpcstats, 0, sizeof(nn->rpcstats));
@@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net)
nfs_cleanup_cb_ident_idr(net);
WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
+#endif
}
#ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 8bdbc4dca89c..10ef46e29b25 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1021,13 +1021,6 @@ out:
nfs_inode_find_state_and_recover(inode, stateid);
}
-void nfs_remove_bad_delegation(struct inode *inode,
- const nfs4_stateid *stateid)
-{
- nfs_revoke_delegation(inode, stateid);
-}
-EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
-
void nfs_delegation_mark_returned(struct inode *inode,
const nfs4_stateid *stateid)
{
@@ -1070,6 +1063,24 @@ out_rcu_unlock:
}
/**
+ * nfs_remove_bad_delegation - handle delegations that are unusable
+ * @inode: inode to process
+ * @stateid: the delegation's stateid
+ *
+ * If the server ACK-ed our FREE_STATEID then clean
+ * up the delegation, else mark and keep the revoked state.
+ */
+void nfs_remove_bad_delegation(struct inode *inode,
+ const nfs4_stateid *stateid)
+{
+ if (stateid && stateid->type == NFS4_FREED_STATEID_TYPE)
+ nfs_delegation_mark_returned(inode, stateid);
+ else
+ nfs_revoke_delegation(inode, stateid);
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
+/**
* nfs_expire_unused_delegation_types
* @clp: client to process
* @flags: delegation types to expire
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bd23fc736b39..d0e0b435a843 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
unblock_revalidate(new_dentry);
}
+static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry,
+ struct dentry *new_dentry)
+{
+ struct nfs_server *server = NFS_SB(old_dentry->d_sb);
+
+ if (old_dentry->d_parent != new_dentry->d_parent)
+ return false;
+ if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE)
+ return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN);
+ return true;
+}
+
/*
* RENAME
* FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
}
- if (S_ISREG(old_inode->i_mode))
+ if (S_ISREG(old_inode->i_mode) &&
+ nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry))
nfs_sync_inode(old_inode);
task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
must_unblock ? nfs_unblock_rename : NULL);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f32f8d7c9122..48d89716193a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_direct_req *dreq = hdr->dreq;
struct nfs_commit_info cinfo;
- struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct inode *inode = dreq->inode;
int flags = NFS_ODIRECT_DONE;
@@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
spin_unlock(&inode->i_lock);
while (!list_empty(&hdr->pages)) {
+ struct nfs_page *req;
req = nfs_list_entry(hdr->pages.next);
nfs_list_remove_request(req);
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4fa304fa5bc4..29d9234d5c08 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
struct page *scratch;
struct list_head dsaddrs;
struct nfs4_pnfs_ds_addr *da;
+ struct net *net = server->nfs_client->cl_net;
/* set up xdr stream */
scratch = alloc_page(gfp_flags);
@@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
- da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
- &stream, gfp_flags);
+ da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
goto out_err_free_deviceid;
}
- dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+ dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
if (!dsaddr->ds_list[i])
goto out_err_drain_dsaddrs;
trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 61ad269c825f..df4807460596 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1129,6 +1129,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
break;
case -NFS4ERR_DELAY:
+ nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+ fallthrough;
case -NFS4ERR_GRACE:
rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
break;
@@ -1329,7 +1331,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_READ,
task->tk_status);
- trace_ff_layout_read_error(hdr);
+ trace_ff_layout_read_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1502,7 +1504,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_WRITE,
task->tk_status);
- trace_ff_layout_write_error(hdr);
+ trace_ff_layout_write_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1551,7 +1553,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
data->args.offset, data->args.count,
&data->res.op_status, OP_COMMIT,
task->tk_status);
- trace_ff_layout_commit_error(data);
+ trace_ff_layout_commit_error(data, task->tk_status);
}
err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e58bedfb1dcc..656d5c50bbce 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
struct nfs4_pnfs_ds_addr *da;
struct nfs4_ff_layout_ds *new_ds = NULL;
struct nfs4_ff_ds_version *ds_versions = NULL;
+ struct net *net = server->nfs_client->cl_net;
u32 mp_count;
u32 version_count;
__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
for (i = 0; i < mp_count; i++) {
/* multipath ds */
- da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
- &stream, gfp_flags);
+ da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
new_ds->ds_versions = ds_versions;
new_ds->ds_versions_cnt = version_count;
- new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+ new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
if (!new_ds->ds)
goto out_err_drain_dsaddrs;
@@ -400,7 +400,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
* keep ds_clp even if DS is local, so that if local IO cannot
* proceed somehow, we can fall back to NFS whenever we want.
*/
- nfs_local_probe(ds->ds_clp);
+ nfs_local_probe_async(ds->ds_clp);
max_payload =
nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
NULL);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index e278a1ad1ca3..8b0785178731 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -367,6 +367,7 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
sreq = netfs->sreq;
if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+ sreq->rreq->origin != NETFS_UNBUFFERED_READ &&
sreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 119e447758b9..8ab7868807a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -557,6 +557,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
set_nlink(inode, fattr->nlink);
else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
+ else
+ set_nlink(inode, 1);
if (fattr->valid & NFS_ATTR_FATTR_OWNER)
inode->i_uid = fattr->uid;
else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
@@ -633,6 +635,34 @@ nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr)
}
}
+static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr)
+{
+ unsigned int cache_flags = 0;
+
+ if (attr->ia_valid & ATTR_MTIME_SET) {
+ struct timespec64 ctime = inode_get_ctime(inode);
+ struct timespec64 mtime = inode_get_mtime(inode);
+ struct timespec64 now;
+ int updated = 0;
+
+ now = inode_set_ctime_current(inode);
+ if (!timespec64_equal(&now, &ctime))
+ updated |= S_CTIME;
+
+ inode_set_mtime_to_ts(inode, attr->ia_mtime);
+ if (!timespec64_equal(&now, &mtime))
+ updated |= S_MTIME;
+
+ inode_maybe_inc_iversion(inode, updated);
+ cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+ }
+ if (attr->ia_valid & ATTR_ATIME_SET) {
+ inode_set_atime_to_ts(inode, attr->ia_atime);
+ cache_flags |= NFS_INO_INVALID_ATIME;
+ }
+ NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid)
{
enum file_time_flags time_flags = 0;
@@ -701,14 +731,27 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
spin_lock(&inode->i_lock);
- nfs_update_timestamps(inode, attr->ia_valid);
+ if (attr->ia_valid & ATTR_MTIME_SET) {
+ nfs_set_timestamps_to_ts(inode, attr);
+ attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+ ATTR_ATIME|ATTR_ATIME_SET);
+ } else {
+ nfs_update_timestamps(inode, attr->ia_valid);
+ attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
+ }
spin_unlock(&inode->i_lock);
- attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME);
} else if (nfs_have_delegated_atime(inode) &&
attr->ia_valid & ATTR_ATIME &&
!(attr->ia_valid & ATTR_MTIME)) {
- nfs_update_delegated_atime(inode);
- attr->ia_valid &= ~ATTR_ATIME;
+ if (attr->ia_valid & ATTR_ATIME_SET) {
+ spin_lock(&inode->i_lock);
+ nfs_set_timestamps_to_ts(inode, attr);
+ spin_unlock(&inode->i_lock);
+ attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+ } else {
+ nfs_update_delegated_atime(inode);
+ attr->ia_valid &= ~ATTR_ATIME;
+ }
}
/* Optimization: if the end result is no change, don't RPC */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index ec8d32d0e2e9..69c2c10ee658 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -455,7 +455,6 @@ extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
#if IS_ENABLED(CONFIG_NFS_LOCALIO)
/* localio.c */
-extern void nfs_local_probe(struct nfs_client *);
extern void nfs_local_probe_async(struct nfs_client *);
extern void nfs_local_probe_async_work(struct work_struct *);
extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *,
@@ -899,18 +898,11 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts)
return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
}
-#ifdef CONFIG_CRC32
static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
{
return ~crc32_le(0xFFFFFFFF, &stateid->other[0],
NFS4_STATEID_OTHER_SIZE);
}
-#else
-static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
-{
- return 0;
-}
-#endif
static inline bool nfs_current_task_exiting(void)
{
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 5c21caeae075..510d0a16cfe9 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -171,7 +171,7 @@ static bool nfs_server_uuid_is_local(struct nfs_client *clp)
* - called after alloc_client and init_client (so cl_rpcclient exists)
* - this function is idempotent, it can be called for old or new clients
*/
-void nfs_local_probe(struct nfs_client *clp)
+static void nfs_local_probe(struct nfs_client *clp)
{
/* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */
if (!localio_enabled ||
@@ -191,14 +191,16 @@ void nfs_local_probe(struct nfs_client *clp)
nfs_localio_enable_client(clp);
nfs_uuid_end(&clp->cl_uuid);
}
-EXPORT_SYMBOL_GPL(nfs_local_probe);
void nfs_local_probe_async_work(struct work_struct *work)
{
struct nfs_client *clp =
container_of(work, struct nfs_client, cl_local_probe_work);
+ if (!refcount_inc_not_zero(&clp->cl_count))
+ return;
nfs_local_probe(clp);
+ nfs_put_client(clp);
}
void nfs_local_probe_async(struct nfs_client *clp)
@@ -207,14 +209,16 @@ void nfs_local_probe_async(struct nfs_client *clp)
}
EXPORT_SYMBOL_GPL(nfs_local_probe_async);
-static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf)
+static inline void nfs_local_file_put(struct nfsd_file *localio)
{
- return nfs_to->nfsd_file_get(nf);
-}
+ /* nfs_to_nfsd_file_put_local() expects an __rcu pointer
+ * but we have a __kernel pointer. It is always safe
+ * to cast a __kernel pointer to an __rcu pointer
+ * because the cast only weakens what is known about the pointer.
+ */
+ struct nfsd_file __rcu *nf = (struct nfsd_file __rcu*) localio;
-static inline void nfs_local_file_put(struct nfsd_file *nf)
-{
- nfs_to->nfsd_file_put(nf);
+ nfs_to_nfsd_file_put_local(&nf);
}
/*
@@ -226,12 +230,13 @@ static inline void nfs_local_file_put(struct nfsd_file *nf)
static struct nfsd_file *
__nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
struct nfs_fh *fh, struct nfs_file_localio *nfl,
+ struct nfsd_file __rcu **pnf,
const fmode_t mode)
{
struct nfsd_file *localio;
localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
- cred, fh, nfl, mode);
+ cred, fh, nfl, pnf, mode);
if (IS_ERR(localio)) {
int status = PTR_ERR(localio);
trace_nfs_local_open_fh(fh, mode, status);
@@ -258,7 +263,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
struct nfs_fh *fh, struct nfs_file_localio *nfl,
const fmode_t mode)
{
- struct nfsd_file *nf, *new, __rcu **pnf;
+ struct nfsd_file *nf, __rcu **pnf;
if (!nfs_server_is_local(clp))
return NULL;
@@ -270,29 +275,9 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
else
pnf = &nfl->ro_file;
- new = NULL;
- rcu_read_lock();
- nf = rcu_dereference(*pnf);
- if (!nf) {
- rcu_read_unlock();
- new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
- if (IS_ERR(new))
- return NULL;
- /* try to swap in the pointer */
- spin_lock(&clp->cl_uuid.lock);
- nf = rcu_dereference_protected(*pnf, 1);
- if (!nf) {
- nf = new;
- new = NULL;
- rcu_assign_pointer(*pnf, nf);
- }
- spin_unlock(&clp->cl_uuid.lock);
- rcu_read_lock();
- }
- nf = nfs_local_file_get(nf);
- rcu_read_unlock();
- if (new)
- nfs_to_nfsd_file_put_local(new);
+ nf = __nfs_local_open_fh(clp, cred, fh, nfl, pnf, mode);
+ if (IS_ERR(nf))
+ return NULL;
return nf;
}
EXPORT_SYMBOL_GPL(nfs_local_open_fh);
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 973aed9cc5fe..7f1ec9c67ff2 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -195,7 +195,6 @@ struct vfsmount *nfs_d_automount(struct path *path)
if (IS_ERR(mnt))
goto out_fc;
- mntget(mnt); /* prevent immediate expiration */
if (timeout <= 0)
goto out_fc;
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index a68b21603ea9..6ba3ea39e928 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -31,7 +31,11 @@ struct nfs_net {
unsigned short nfs_callback_tcpport;
unsigned short nfs_callback_tcpport6;
int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif
+#endif /* CONFIG_NFS_V4 */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ struct list_head nfs4_data_server_cache;
+ spinlock_t nfs4_data_server_lock;
+#endif /* CONFIG_NFS_V4_1 */
struct nfs_netns_client *nfs_client;
spinlock_t nfs_client_lock;
ktime_t boot_time;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 18d8f6529f61..a126eb31f62f 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
switch (status) {
case 0:
- status = nfs_refresh_inode(inode, res.fattr);
+ nfs_refresh_inode(inode, res.fattr);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 0282d93c8bcc..aafd15a4afce 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -21,6 +21,7 @@ int nfs42_proc_allocate(struct file *, loff_t, loff_t);
ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t,
struct nl4_server *, nfs4_stateid *, bool);
int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
+int nfs42_proc_zero_range(struct file *, loff_t, loff_t);
loff_t nfs42_proc_llseek(struct file *, loff_t, int);
int nfs42_proc_layoutstats_generic(struct nfs_server *,
struct nfs42_layoutstat_data *);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5cf52ece96ac..01c01f45358b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -146,7 +146,8 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
err = nfs42_proc_fallocate(&msg, filep, offset, len);
if (err == -EOPNOTSUPP)
- NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
+ NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE |
+ NFS_CAP_ZERO_RANGE);
inode_unlock(inode);
return err;
@@ -169,7 +170,31 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
if (err == 0)
truncate_pagecache_range(inode, offset, (offset + len) -1);
if (err == -EOPNOTSUPP)
- NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
+ NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE |
+ NFS_CAP_ZERO_RANGE);
+
+ inode_unlock(inode);
+ return err;
+}
+
+int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
+{
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE],
+ };
+ struct inode *inode = file_inode(filep);
+ int err;
+
+ if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE))
+ return -EOPNOTSUPP;
+
+ inode_lock(inode);
+
+ err = nfs42_proc_fallocate(&msg, filep, offset, len);
+ if (err == 0)
+ truncate_pagecache_range(inode, offset, (offset + len) -1);
+ if (err == -EOPNOTSUPP)
+ NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE;
inode_unlock(inode);
return err;
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index b1b663468249..4cc915d5741d 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -174,6 +174,18 @@
decode_putfh_maxsz + \
decode_deallocate_maxsz + \
decode_getattr_maxsz)
+#define NFS4_enc_zero_range_sz (compound_encode_hdr_maxsz + \
+ encode_sequence_maxsz + \
+ encode_putfh_maxsz + \
+ encode_deallocate_maxsz + \
+ encode_allocate_maxsz + \
+ encode_getattr_maxsz)
+#define NFS4_dec_zero_range_sz (compound_decode_hdr_maxsz + \
+ decode_sequence_maxsz + \
+ decode_putfh_maxsz + \
+ decode_deallocate_maxsz + \
+ decode_allocate_maxsz + \
+ decode_getattr_maxsz)
#define NFS4_enc_read_plus_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -649,6 +661,27 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
}
/*
+ * Encode ZERO_RANGE request
+ */
+static void nfs4_xdr_enc_zero_range(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ const struct nfs42_falloc_args *args = data;
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+ };
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->seq_args, &hdr);
+ encode_putfh(xdr, args->falloc_fh, &hdr);
+ encode_deallocate(xdr, args, &hdr);
+ encode_allocate(xdr, args, &hdr);
+ encode_getfattr(xdr, args->falloc_bitmask, &hdr);
+ encode_nops(&hdr);
+}
+
+/*
* Encode READ_PLUS request
*/
static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
@@ -1511,6 +1544,37 @@ out:
}
/*
+ * Decode ZERO_RANGE request
+ */
+static int nfs4_xdr_dec_zero_range(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ void *data)
+{
+ struct nfs42_falloc_res *res = data;
+ struct compound_hdr hdr;
+ int status;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_deallocate(xdr, res);
+ if (status)
+ goto out;
+ status = decode_allocate(xdr, res);
+ if (status)
+ goto out;
+ decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
+out:
+ return status;
+}
+
+/*
* Decode READ_PLUS request
*/
static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 7d383d29a995..d3ca91f60fc1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -67,8 +67,7 @@ struct nfs4_minor_version_ops {
void (*free_lock_state)(struct nfs_server *,
struct nfs4_lock_state *);
int (*test_and_free_expired)(struct nfs_server *,
- const nfs4_stateid *,
- const struct cred *);
+ nfs4_stateid *, const struct cred *);
struct nfs_seqid *
(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
void (*session_trunk)(struct rpc_clnt *clnt,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1cd9652f3c28..5e9d66f3466c 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -225,8 +225,14 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
- if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE)))
+ switch (mode) {
+ case 0:
+ case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+ case FALLOC_FL_ZERO_RANGE:
+ break;
+ default:
return -EOPNOTSUPP;
+ }
ret = inode_newsize_ok(inode, offset + len);
if (ret < 0)
@@ -234,6 +240,8 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
if (mode & FALLOC_FL_PUNCH_HOLE)
return nfs42_proc_deallocate(filep, offset, len);
+ else if (mode & FALLOC_FL_ZERO_RANGE)
+ return nfs42_proc_zero_range(filep, offset ,len);
return nfs42_proc_allocate(filep, offset, len);
}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 970f28dbf253..341740fa293d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -105,7 +105,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
bool is_privileged);
static int nfs41_test_stateid(struct nfs_server *, const nfs4_stateid *,
const struct cred *);
-static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
+static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *,
const struct cred *, bool);
#endif
@@ -325,14 +325,14 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
if (nfs_have_delegated_mtime(inode)) {
if (!(cache_validity & NFS_INO_INVALID_ATIME))
- dst[1] &= ~FATTR4_WORD1_TIME_ACCESS;
+ dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
if (!(cache_validity & NFS_INO_INVALID_MTIME))
- dst[1] &= ~FATTR4_WORD1_TIME_MODIFY;
+ dst[1] &= ~(FATTR4_WORD1_TIME_MODIFY|FATTR4_WORD1_TIME_MODIFY_SET);
if (!(cache_validity & NFS_INO_INVALID_CTIME))
- dst[1] &= ~FATTR4_WORD1_TIME_METADATA;
+ dst[1] &= ~(FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY_SET);
} else if (nfs_have_delegated_atime(inode)) {
if (!(cache_validity & NFS_INO_INVALID_ATIME))
- dst[1] &= ~FATTR4_WORD1_TIME_ACCESS;
+ dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
}
}
@@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
struct nfs_client *clp = server->nfs_client;
int ret;
+ if ((task->tk_rpc_status == -ENETDOWN ||
+ task->tk_rpc_status == -ENETUNREACH) &&
+ task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+ exception->delay = 0;
+ exception->recovering = 0;
+ exception->retry = 0;
+ return -EIO;
+ }
+
ret = nfs4_do_handle_exception(server, errorcode, exception);
if (exception->delay) {
int ret2 = nfs4_exception_should_retrans(server, exception);
@@ -2894,16 +2903,14 @@ static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
}
static int nfs40_test_and_free_expired_stateid(struct nfs_server *server,
- const nfs4_stateid *stateid,
- const struct cred *cred)
+ nfs4_stateid *stateid, const struct cred *cred)
{
return -NFS4ERR_BAD_STATEID;
}
#if defined(CONFIG_NFS_V4_1)
static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
- const nfs4_stateid *stateid,
- const struct cred *cred)
+ nfs4_stateid *stateid, const struct cred *cred)
{
int status;
@@ -2912,6 +2919,7 @@ static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
break;
case NFS4_INVALID_STATEID_TYPE:
case NFS4_SPECIAL_STATEID_TYPE:
+ case NFS4_FREED_STATEID_TYPE:
return -NFS4ERR_BAD_STATEID;
case NFS4_REVOKED_STATEID_TYPE:
goto out_free;
@@ -3967,8 +3975,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
FATTR4_WORD0_CASE_INSENSITIVE |
FATTR4_WORD0_CASE_PRESERVING;
if (minorversion)
- bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT |
- FATTR4_WORD2_OPEN_ARGUMENTS;
+ bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT;
+ if (minorversion > 1)
+ bitmask[2] |= FATTR4_WORD2_OPEN_ARGUMENTS;
status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
if (status == 0) {
@@ -5155,13 +5164,15 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
}
static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
- struct nfs4_createdata *data)
+ struct nfs4_createdata *data, int *statusp)
{
- int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
+ struct dentry *ret;
+
+ *statusp = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
&data->arg.seq_args, &data->res.seq_res, 1);
- if (status)
- return ERR_PTR(status);
+ if (*statusp)
+ return NULL;
spin_lock(&dir->i_lock);
/* Creating a directory bumps nlink in the parent */
@@ -5170,7 +5181,11 @@ static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
data->res.fattr->time_start,
NFS_INO_INVALID_DATA);
spin_unlock(&dir->i_lock);
- return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+ ret = nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+ if (!IS_ERR(ret))
+ return ret;
+ *statusp = PTR_ERR(ret);
+ return NULL;
}
static void nfs4_free_createdata(struct nfs4_createdata *data)
@@ -5231,17 +5246,18 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
static struct dentry *_nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
struct iattr *sattr,
- struct nfs4_label *label)
+ struct nfs4_label *label, int *statusp)
{
struct nfs4_createdata *data;
- struct dentry *ret = ERR_PTR(-ENOMEM);
+ struct dentry *ret = NULL;
+ *statusp = -ENOMEM;
data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR);
if (data == NULL)
goto out;
data->arg.label = label;
- ret = nfs4_do_mkdir(dir, dentry, data);
+ ret = nfs4_do_mkdir(dir, dentry, data, statusp);
nfs4_free_createdata(data);
out:
@@ -5264,11 +5280,12 @@ static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
sattr->ia_mode &= ~current_umask();
do {
- alias = _nfs4_proc_mkdir(dir, dentry, sattr, label);
- err = PTR_ERR_OR_ZERO(alias);
+ alias = _nfs4_proc_mkdir(dir, dentry, sattr, label, &err);
trace_nfs4_mkdir(dir, &dentry->d_name, err);
- err = nfs4_handle_exception(NFS_SERVER(dir), err,
- &exception);
+ if (err)
+ alias = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir),
+ err,
+ &exception));
} while (exception.retry);
nfs4_label_release_security(label);
@@ -6202,6 +6219,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen,
struct nfs_server *server = NFS_SERVER(inode);
int ret;
+ if (unlikely(NFS_FH(inode)->size == 0))
+ return -ENODATA;
if (!nfs4_server_supports_acls(server, type))
return -EOPNOTSUPP;
ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
@@ -6276,6 +6295,9 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf,
{
struct nfs4_exception exception = { };
int err;
+
+ if (unlikely(NFS_FH(inode)->size == 0))
+ return -ENODATA;
do {
err = __nfs4_proc_set_acl(inode, buf, buflen, type);
trace_nfs4_set_acl(inode, err);
@@ -7074,10 +7096,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
struct nfs4_unlockdata *p;
struct nfs4_state *state = lsp->ls_state;
struct inode *inode = state->inode;
+ struct nfs_lock_context *l_ctx;
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (p == NULL)
return NULL;
+ l_ctx = nfs_get_lock_context(ctx);
+ if (!IS_ERR(l_ctx)) {
+ p->l_ctx = l_ctx;
+ } else {
+ kfree(p);
+ return NULL;
+ }
p->arg.fh = NFS_FH(inode);
p->arg.fl = &p->fl;
p->arg.seqid = seqid;
@@ -7085,7 +7115,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
p->lsp = lsp;
/* Ensure we don't close file until we're done freeing locks! */
p->ctx = get_nfs_open_context(ctx);
- p->l_ctx = nfs_get_lock_context(ctx);
locks_init_lock(&p->fl);
locks_copy_lock(&p->fl, fl);
p->server = NFS_SERVER(inode);
@@ -10595,7 +10624,7 @@ static const struct rpc_call_ops nfs41_free_stateid_ops = {
* Note: this function is always asynchronous.
*/
static int nfs41_free_stateid(struct nfs_server *server,
- const nfs4_stateid *stateid,
+ nfs4_stateid *stateid,
const struct cred *cred,
bool privileged)
{
@@ -10635,6 +10664,7 @@ static int nfs41_free_stateid(struct nfs_server *server,
if (IS_ERR(task))
return PTR_ERR(task);
rpc_put_task(task);
+ stateid->type = NFS4_FREED_STATEID_TYPE;
return 0;
}
@@ -10801,6 +10831,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_OFFLOAD_CANCEL
| NFS_CAP_COPY_NOTIFY
| NFS_CAP_DEALLOCATE
+ | NFS_CAP_ZERO_RANGE
| NFS_CAP_SEEK
| NFS_CAP_LAYOUTSTATS
| NFS_CAP_CLONE
@@ -10836,7 +10867,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
{
- ssize_t error, error2, error3;
+ ssize_t error, error2, error3, error4;
size_t left = size;
error = generic_listxattr(dentry, list, left);
@@ -10859,8 +10890,16 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left);
if (error3 < 0)
return error3;
+ if (list) {
+ list += error3;
+ left -= error3;
+ }
+
+ error4 = security_inode_listsecurity(d_inode(dentry), list, left);
+ if (error4 < 0)
+ return error4;
- error += error2 + error3;
+ error += error2 + error3 + error4;
if (size && error > size)
return -ERANGE;
return error;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 351616c61df5..f9c291e2165c 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -148,16 +148,12 @@ static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst,
memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN);
}
-#ifdef CONFIG_CRC32
/*
* nfs_session_id_hash - calculate the crc32 hash for the session id
* @session - pointer to session
*/
#define nfs_session_id_hash(sess_id) \
(~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data)))
-#else
-#define nfs_session_id_hash(session) (0)
-#endif
#else /* defined(CONFIG_NFS_V4_1) */
static inline int nfs4_init_session(struct nfs_client *clp)
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index bc67fe6801b1..deab4c0e21a0 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -2051,13 +2051,15 @@ TRACE_EVENT(fl_getdevinfo,
DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_PROTO(
- const struct nfs_pgio_header *hdr
+ const struct nfs_pgio_header *hdr,
+ int error
),
- TP_ARGS(hdr),
+ TP_ARGS(hdr, error),
TP_STRUCT__entry(
__field(unsigned long, error)
+ __field(unsigned long, nfs_error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -2073,7 +2075,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_fast_assign(
const struct inode *inode = hdr->inode;
- __entry->error = hdr->res.op_status;
+ __entry->error = -error;
+ __entry->nfs_error = hdr->res.op_status;
__entry->fhandle = nfs_fhandle_hash(hdr->args.fh);
__entry->fileid = NFS_FILEID(inode);
__entry->dev = inode->i_sb->s_dev;
@@ -2088,7 +2091,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
- "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s",
+ "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s "
+ "nfs_error=%lu (%s)",
-__entry->error,
show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -2096,28 +2100,32 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
__entry->fhandle,
__entry->offset, __entry->count,
__entry->stateid_seq, __entry->stateid_hash,
- __get_str(dstaddr)
+ __get_str(dstaddr), __entry->nfs_error,
+ show_nfs4_status(__entry->nfs_error)
)
);
#define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \
DEFINE_EVENT(nfs4_flexfiles_io_event, name, \
TP_PROTO( \
- const struct nfs_pgio_header *hdr \
+ const struct nfs_pgio_header *hdr, \
+ int error \
), \
- TP_ARGS(hdr))
+ TP_ARGS(hdr, error))
DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error);
DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error);
TRACE_EVENT(ff_layout_commit_error,
TP_PROTO(
- const struct nfs_commit_data *data
+ const struct nfs_commit_data *data,
+ int error
),
- TP_ARGS(data),
+ TP_ARGS(data, error),
TP_STRUCT__entry(
__field(unsigned long, error)
+ __field(unsigned long, nfs_error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -2131,7 +2139,8 @@ TRACE_EVENT(ff_layout_commit_error,
TP_fast_assign(
const struct inode *inode = data->inode;
- __entry->error = data->res.op_status;
+ __entry->error = -error;
+ __entry->nfs_error = data->res.op_status;
__entry->fhandle = nfs_fhandle_hash(data->args.fh);
__entry->fileid = NFS_FILEID(inode);
__entry->dev = inode->i_sb->s_dev;
@@ -2142,14 +2151,15 @@ TRACE_EVENT(ff_layout_commit_error,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
- "offset=%llu count=%u dstaddr=%s",
+ "offset=%llu count=%u dstaddr=%s nfs_error=%lu (%s)",
-__entry->error,
show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
__entry->offset, __entry->count,
- __get_str(dstaddr)
+ __get_str(dstaddr), __entry->nfs_error,
+ show_nfs4_status(__entry->nfs_error)
)
);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 55bef5fbfa47..318afde38057 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7711,6 +7711,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
PROC42(LISTXATTRS, enc_listxattrs, dec_listxattrs),
PROC42(REMOVEXATTR, enc_removexattr, dec_removexattr),
PROC42(READ_PLUS, enc_read_plus, dec_read_plus),
+ PROC42(ZERO_RANGE, enc_zero_range, dec_zero_range),
};
static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5f582713bf05..3adb7d0dbec7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -745,6 +745,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
return remaining;
}
+static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo)
+{
+ struct pnfs_layout_segment *lseg;
+
+ list_for_each_entry(lseg, &lo->plh_return_segs, pls_list)
+ pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+}
+
static void
pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
struct list_head *free_me,
@@ -1246,21 +1254,15 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
static void
pnfs_layoutreturn_retry_later_locked(struct pnfs_layout_hdr *lo,
const nfs4_stateid *arg_stateid,
- const struct pnfs_layout_range *range)
+ const struct pnfs_layout_range *range,
+ struct list_head *freeme)
{
- const struct pnfs_layout_segment *lseg;
- u32 seq = be32_to_cpu(arg_stateid->seqid);
-
if (pnfs_layout_is_valid(lo) &&
- nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) {
- list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) {
- if (pnfs_seqid_is_newer(lseg->pls_seq, seq) ||
- !pnfs_should_free_range(&lseg->pls_range, range))
- continue;
- pnfs_set_plh_return_info(lo, range->iomode, seq);
- break;
- }
- }
+ nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+ pnfs_reset_return_info(lo);
+ else
+ pnfs_mark_layout_stateid_invalid(lo, freeme);
+ pnfs_clear_layoutreturn_waitbit(lo);
}
void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
@@ -1268,11 +1270,12 @@ void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
const struct pnfs_layout_range *range)
{
struct inode *inode = lo->plh_inode;
+ LIST_HEAD(freeme);
spin_lock(&inode->i_lock);
- pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range);
- pnfs_clear_layoutreturn_waitbit(lo);
+ pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range, &freeme);
spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&freeme);
}
void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
@@ -1292,6 +1295,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
pnfs_free_returned_lsegs(lo, &freeme, range, seq);
pnfs_set_layout_stateid(lo, stateid, NULL, true);
+ pnfs_reset_return_info(lo);
} else
pnfs_mark_layout_stateid_invalid(lo, &freeme);
out_unlock:
@@ -1661,6 +1665,18 @@ int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
/* Was there an RPC level error? If not, retry */
if (task->tk_rpc_status == 0)
break;
+ /*
+ * Is there a fatal network level error?
+ * If so release the layout, but flag the error.
+ */
+ if ((task->tk_rpc_status == -ENETDOWN ||
+ task->tk_rpc_status == -ENETUNREACH) &&
+ task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+ *ret = 0;
+ (*respp)->lrs_present = 0;
+ retval = -EIO;
+ break;
+ }
/* If the call was not sent, let caller handle it */
if (!RPC_WAS_SENT(task))
return 0;
@@ -1695,6 +1711,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct inode *inode = args->inode;
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
+ LIST_HEAD(freeme);
switch (ret) {
case -NFS4ERR_BADSESSION:
@@ -1703,9 +1720,9 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
case -NFS4ERR_NOMATCHING_LAYOUT:
spin_lock(&inode->i_lock);
pnfs_layoutreturn_retry_later_locked(lo, &args->stateid,
- &args->range);
- pnfs_clear_layoutreturn_waitbit(lo);
+ &args->range, &freeme);
spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&freeme);
break;
case 0:
if (res->lrs_present)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 30d2613e912b..91ff877185c8 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -60,6 +60,7 @@ struct nfs4_pnfs_ds {
struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */
char *ds_remotestr; /* comma sep list of addrs */
struct list_head ds_addrs;
+ const struct net *ds_net;
struct nfs_client *ds_clp;
refcount_t ds_count;
unsigned long ds_state;
@@ -415,7 +416,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode,
int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
-struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net,
+ struct list_head *dsaddrs,
gfp_t gfp_flags);
void nfs4_pnfs_v3_ds_connect_unload(void);
int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index dbef837e871a..b4ccdf78d4dd 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -16,6 +16,7 @@
#include "nfs4session.h"
#include "internal.h"
#include "pnfs.h"
+#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
@@ -504,14 +505,14 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
/*
* Data server cache
*
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
+ * Data servers can be mapped to different device ids, but should
+ * never be shared between net namespaces.
+ *
+ * nfs4_pnfs_ds reference counting:
* - set to 1 on allocation
* - incremented when a device id maps a data server already in the cache.
* - decremented when deviceid is removed from the cache.
*/
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
/* Debug routines */
static void
@@ -604,11 +605,11 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1,
* Lookup DS by addresses. nfs4_ds_cache_lock is held
*/
static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
+_data_server_lookup_locked(const struct nfs_net *nn, const struct list_head *dsaddrs)
{
struct nfs4_pnfs_ds *ds;
- list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+ list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node)
if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
return ds;
return NULL;
@@ -653,10 +654,11 @@ static void destroy_ds(struct nfs4_pnfs_ds *ds)
void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
{
- if (refcount_dec_and_lock(&ds->ds_count,
- &nfs4_ds_cache_lock)) {
+ struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id);
+
+ if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) {
list_del_init(&ds->ds_node);
- spin_unlock(&nfs4_ds_cache_lock);
+ spin_unlock(&nn->nfs4_data_server_lock);
destroy_ds(ds);
}
}
@@ -716,8 +718,9 @@ out_err:
* uncached and return cached struct nfs4_pnfs_ds.
*/
struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags)
{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
char *remotestr;
@@ -733,16 +736,17 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
/* this is only used for debugging, so it's ok if its NULL */
remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
- spin_lock(&nfs4_ds_cache_lock);
- tmp_ds = _data_server_lookup_locked(dsaddrs);
+ spin_lock(&nn->nfs4_data_server_lock);
+ tmp_ds = _data_server_lookup_locked(nn, dsaddrs);
if (tmp_ds == NULL) {
INIT_LIST_HEAD(&ds->ds_addrs);
list_splice_init(dsaddrs, &ds->ds_addrs);
ds->ds_remotestr = remotestr;
refcount_set(&ds->ds_count, 1);
INIT_LIST_HEAD(&ds->ds_node);
+ ds->ds_net = net;
ds->ds_clp = NULL;
- list_add(&ds->ds_node, &nfs4_data_server_cache);
+ list_add(&ds->ds_node, &nn->nfs4_data_server_cache);
dprintk("%s add new data server %s\n", __func__,
ds->ds_remotestr);
} else {
@@ -754,7 +758,7 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
refcount_read(&tmp_ds->ds_count));
ds = tmp_ds;
}
- spin_unlock(&nfs4_ds_cache_lock);
+ spin_unlock(&nn->nfs4_data_server_lock);
out:
return ds;
}
@@ -826,10 +830,16 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
.servername = clp->cl_hostname,
.connect_timeout = connect_timeout,
.reconnect_timeout = connect_timeout,
+ .xprtsec = clp->cl_xprtsec,
};
- if (da->da_transport != clp->cl_proto)
+ if (da->da_transport != clp->cl_proto &&
+ clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
continue;
+ if (da->da_transport == XPRT_TRANSPORT_TCP &&
+ mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+ xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
+
if (da->da_addr.ss_family != clp->cl_addr.ss_family)
continue;
/* Add this address as an alias */
@@ -837,6 +847,9 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
rpc_clnt_test_and_add_xprt, NULL);
continue;
}
+ if (da->da_transport == XPRT_TRANSPORT_TCP &&
+ mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+ da->da_transport = XPRT_TRANSPORT_TCP_TLS;
clp = get_v3_ds_connect(mds_srv,
&da->da_addr,
da->da_addrlen, da->da_transport,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 81bd1b9aba17..3c1fa320b3f1 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -56,7 +56,8 @@ static int nfs_return_empty_folio(struct folio *folio)
{
folio_zero_segment(folio, 0, folio_size(folio));
folio_mark_uptodate(folio);
- folio_unlock(folio);
+ if (nfs_netfs_folio_unlock(folio))
+ folio_unlock(folio);
return 0;
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 9eea9e62afc9..91b5503b6f74 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1052,6 +1052,16 @@ int nfs_reconfigure(struct fs_context *fc)
sync_filesystem(sb);
/*
+ * The SB_RDONLY flag has been removed from the superblock during
+ * mounts to prevent interference between different filesystems.
+ * Similarly, it is also necessary to ignore the SB_RDONLY flag
+ * during reconfiguration; otherwise, it may also result in the
+ * creation of redundant superblocks when mounting a directory with
+ * different rw and ro flags multiple times.
+ */
+ fc->sb_flags_mask &= ~SB_RDONLY;
+
+ /*
* Userspace mount programs that send binary options generally send
* them populated with default values. We have no way to know which
* ones were explicitly specified. Fall back to legacy behavior and
@@ -1308,8 +1318,17 @@ int nfs_get_tree_common(struct fs_context *fc)
if (IS_ERR(server))
return PTR_ERR(server);
+ /*
+ * When NFS_MOUNT_UNSHARED is not set, NFS forces the sharing of a
+ * superblock among each filesystem that mounts sub-directories
+ * belonging to a single exported root path.
+ * To prevent interference between different filesystems, the
+ * SB_RDONLY flag should be removed from the superblock.
+ */
if (server->flags & NFS_MOUNT_UNSHARED)
compare_super = NULL;
+ else
+ fc->sb_flags &= ~SB_RDONLY;
/* -o noac implies -o sync */
if (server->flags & NFS_MOUNT_NOAC)
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 1c62a5a9f51d..58146e935402 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -40,31 +40,31 @@ static const char *nfs_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- struct page *page;
+ struct folio *folio;
void *err;
if (!dentry) {
err = ERR_PTR(nfs_revalidate_mapping_rcu(inode));
if (err)
return err;
- page = find_get_page(inode->i_mapping, 0);
- if (!page)
+ folio = filemap_get_folio(inode->i_mapping, 0);
+ if (IS_ERR(folio))
return ERR_PTR(-ECHILD);
- if (!PageUptodate(page)) {
- put_page(page);
+ if (!folio_test_uptodate(folio)) {
+ folio_put(folio);
return ERR_PTR(-ECHILD);
}
} else {
err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
if (err)
return err;
- page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler,
+ folio = read_cache_folio(&inode->i_data, 0, nfs_symlink_filler,
NULL);
- if (IS_ERR(page))
- return ERR_CAST(page);
+ if (IS_ERR(folio))
+ return ERR_CAST(folio);
}
- set_delayed_call(done, page_put_link, page);
- return page_address(page);
+ set_delayed_call(done, page_put_link, folio);
+ return folio_address(folio);
}
/*
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 37cb2b776435..545148d42dcc 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -387,6 +387,33 @@ static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
}
#endif /* CONFIG_NFS_V4_1 */
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+static ssize_t
+localio_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+ bool localio = nfs_server_is_local(server->nfs_client);
+ return sysfs_emit(buf, "%d\n", localio);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_localio = __ATTR_RO(localio);
+
+static void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+ int ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_localio.attr,
+ nfs_netns_server_namespace(&server->kobj));
+ if (ret < 0)
+ pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+ server->s_sysfs_id, ret);
+}
+#else
+static inline void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+}
+#endif /* IS_ENABLED(CONFIG_NFS_LOCALIO) */
+
void nfs_sysfs_add_server(struct nfs_server *server)
{
int ret;
@@ -405,6 +432,7 @@ void nfs_sysfs_add_server(struct nfs_server *server)
server->s_sysfs_id, ret);
nfs_sysfs_add_nfsv41_server(server);
+ nfs_sysfs_add_nfs_localio_server(server);
}
EXPORT_SYMBOL_GPL(nfs_sysfs_add_server);
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index bf77399696a7..b55467911648 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -464,18 +464,17 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
sdentry = NULL;
do {
- int slen;
dput(sdentry);
sillycounter++;
- slen = scnprintf(silly, sizeof(silly),
- SILLYNAME_PREFIX "%0*llx%0*x",
- SILLYNAME_FILEID_LEN, fileid,
- SILLYNAME_COUNTER_LEN, sillycounter);
+ scnprintf(silly, sizeof(silly),
+ SILLYNAME_PREFIX "%0*llx%0*x",
+ SILLYNAME_FILEID_LEN, fileid,
+ SILLYNAME_COUNTER_LEN, sillycounter);
dfprintk(VFS, "NFS: trying to rename %pd to %s\n",
dentry, silly);
- sdentry = lookup_one_len(silly, dentry->d_parent, slen);
+ sdentry = lookup_noperm(&QSTR(silly), dentry->d_parent);
/*
* N.B. Better to return EBUSY here ... it could be
* dangerous to delete the file while it's in use.
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 23df8b214474..374fc6b34c79 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -632,19 +632,19 @@ static void nfs_write_error(struct nfs_page *req, int error)
* Find an associated nfs write request, and prepare to flush it out
* May return an error if the user signalled nfs_wait_on_request().
*/
-static int nfs_page_async_flush(struct folio *folio,
- struct writeback_control *wbc,
- struct nfs_pageio_descriptor *pgio)
+static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
+ struct nfs_pageio_descriptor *pgio)
{
struct nfs_page *req;
- int ret = 0;
+ int ret;
+
+ nfs_pageio_cond_complete(pgio, folio->index);
req = nfs_lock_and_join_requests(folio);
if (!req)
- goto out;
- ret = PTR_ERR(req);
+ return 0;
if (IS_ERR(req))
- goto out;
+ return PTR_ERR(req);
nfs_folio_set_writeback(folio);
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
@@ -654,7 +654,6 @@ static int nfs_page_async_flush(struct folio *folio,
if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
- ret = 0;
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
@@ -662,28 +661,20 @@ static int nfs_page_async_flush(struct folio *folio,
*/
if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
- if (wbc->sync_mode == WB_SYNC_NONE)
- ret = AOP_WRITEPAGE_ACTIVATE;
folio_redirty_for_writepage(wbc, folio);
nfs_redirty_request(req);
pgio->pg_error = 0;
- } else
- nfs_add_stats(folio->mapping->host,
- NFSIOS_WRITEPAGES, 1);
-out:
- return ret;
+ return ret;
+ }
+
+ nfs_add_stats(folio->mapping->host, NFSIOS_WRITEPAGES, 1);
+ return 0;
+
out_launder:
nfs_write_error(req, ret);
return 0;
}
-static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
- struct nfs_pageio_descriptor *pgio)
-{
- nfs_pageio_cond_complete(pgio, folio->index);
- return nfs_page_async_flush(folio, wbc, pgio);
-}
-
/*
* Write an mmapped page to the server.
*/
@@ -703,17 +694,6 @@ static int nfs_writepage_locked(struct folio *folio,
return err;
}
-static int nfs_writepages_callback(struct folio *folio,
- struct writeback_control *wbc, void *data)
-{
- int ret;
-
- ret = nfs_do_writepage(folio, wbc, data);
- if (ret != AOP_WRITEPAGE_ACTIVATE)
- folio_unlock(folio);
- return ret;
-}
-
static void nfs_io_completion_commit(void *inode)
{
nfs_commit_inode(inode, 0);
@@ -749,11 +729,15 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
}
do {
+ struct folio *folio = NULL;
+
nfs_pageio_init_write(&pgio, inode, priority, false,
&nfs_async_write_completion_ops);
pgio.pg_io_completion = ioc;
- err = write_cache_pages(mapping, wbc, nfs_writepages_callback,
- &pgio);
+ while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+ err = nfs_do_writepage(folio, wbc, &pgio);
+ folio_unlock(folio);
+ }
pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
if (err == -EAGAIN && mntflags & NFS_MOUNT_SOFTERR)
generated by cgit (git 2.34.1) at 2025-06-04 06:15:22 +0000