summaryrefslogtreecommitdiffstats
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--fs/nfs/Kconfig4
-rw-r--r--fs/nfs/blocklayout/dev.c3
-rw-r--r--fs/nfs/blocklayout/rpc_pipefs.c2
-rw-r--r--fs/nfs/callback.c13
-rw-r--r--fs/nfs/callback.h24
-rw-r--r--fs/nfs/callback_proc.c55
-rw-r--r--fs/nfs/callback_xdr.c5
-rw-r--r--fs/nfs/client.c13
-rw-r--r--fs/nfs/dir.c6
-rw-r--r--fs/nfs/direct.c6
-rw-r--r--fs/nfs/file.c3
-rw-r--r--fs/nfs/fscache.c7
-rw-r--r--fs/nfs/fscache.h2
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs42xattr.c8
-rw-r--r--fs/nfs/nfs4file.c5
-rw-r--r--fs/nfs/nfs4sysctl.c1
-rw-r--r--fs/nfs/nfs4xdr.c23
-rw-r--r--fs/nfs/nfstrace.h22
-rw-r--r--fs/nfs/sysctl.c1
-rw-r--r--fs/nfs/unlink.c2
-rw-r--r--fs/nfs/write.c27
-rw-r--r--fs/nfsd/Kconfig16
-rw-r--r--fs/nfsd/filecache.c6
-rw-r--r--fs/nfsd/netns.h11
-rw-r--r--fs/nfsd/nfs4callback.c26
-rw-r--r--fs/nfsd/nfs4proc.c7
-rw-r--r--fs/nfsd/nfs4recover.c97
-rw-r--r--fs/nfsd/nfs4state.c9
-rw-r--r--fs/nfsd/nfs4xdr.c60
-rw-r--r--fs/nfsd/nfscache.c6
-rw-r--r--fs/nfsd/nfsctl.c98
-rw-r--r--fs/nfsd/nfsd.h2
-rw-r--r--fs/nfsd/nfssvc.c69
-rw-r--r--fs/nfsd/trace.h22
-rw-r--r--fs/nfsd/vfs.c58
-rw-r--r--fs/nfsd/vfs.h1
-rw-r--r--fs/nfsd/xdr4.h1
38 files changed, 336 insertions, 386 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 01ac733a63..f7e32d76e3 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -169,8 +169,8 @@ config ROOT_NFS
config NFS_FSCACHE
bool "Provide NFS client caching support"
- depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
- select NETFS_SUPPORT
+ depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y
+ select FSCACHE
help
Say Y here if you want NFS data to be cached locally on disc through
the general filesystem cache manager
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index f318a05a80..c97ebc42ec 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -351,6 +351,9 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
d->map = bl_map_simple;
d->pr_key = v->scsi.pr_key;
+ if (d->len == 0)
+ return -ENODEV;
+
pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index 6c977288cc..d8d50a88de 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -75,7 +75,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
msg->len = sizeof(*bl_msg) + b->simple.len;
msg->data = kzalloc(msg->len, gfp_mask);
if (!msg->data)
- goto out_free_data;
+ goto out_unlock;
bl_msg = msg->data;
bl_msg->type = BL_DEVICE_MOUNT;
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 4ffa1f469e..760d27dd72 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -187,7 +187,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
* Check whether we're already up and running.
*/
if (cb_info->serv)
- return svc_get(cb_info->serv);
+ return cb_info->serv;
/*
* Sanity check: if there's no task,
@@ -245,9 +245,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
cb_info->users++;
err_net:
- if (!cb_info->users)
- cb_info->serv = NULL;
- svc_put(serv);
+ if (!cb_info->users) {
+ svc_set_num_threads(cb_info->serv, NULL, 0);
+ svc_destroy(&cb_info->serv);
+ }
err_create:
mutex_unlock(&nfs_callback_mutex);
return ret;
@@ -271,11 +272,9 @@ void nfs_callback_down(int minorversion, struct net *net)
nfs_callback_down_net(minorversion, serv, net);
cb_info->users--;
if (cb_info->users == 0) {
- svc_get(serv);
svc_set_num_threads(serv, NULL, 0);
- svc_put(serv);
dprintk("nfs_callback_down: service destroyed\n");
- cb_info->serv = NULL;
+ svc_destroy(&cb_info->serv);
}
mutex_unlock(&nfs_callback_mutex);
}
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ccd4f245ca..650758ee0d 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -19,32 +19,14 @@ enum nfs4_callback_procnum {
CB_COMPOUND = 1,
};
-enum nfs4_callback_opnum {
- OP_CB_GETATTR = 3,
- OP_CB_RECALL = 4,
-/* Callback operations new to NFSv4.1 */
- OP_CB_LAYOUTRECALL = 5,
- OP_CB_NOTIFY = 6,
- OP_CB_PUSH_DELEG = 7,
- OP_CB_RECALL_ANY = 8,
- OP_CB_RECALLABLE_OBJ_AVAIL = 9,
- OP_CB_RECALL_SLOT = 10,
- OP_CB_SEQUENCE = 11,
- OP_CB_WANTS_CANCELLED = 12,
- OP_CB_NOTIFY_LOCK = 13,
- OP_CB_NOTIFY_DEVICEID = 14,
-/* Callback operations new to NFSv4.2 */
- OP_CB_OFFLOAD = 15,
- OP_CB_ILLEGAL = 10044,
-};
-
struct nfs4_slot;
struct cb_process_state {
- __be32 drc_status;
struct nfs_client *clp;
struct nfs4_slot *slot;
- u32 minorversion;
struct net *net;
+ u32 minorversion;
+ __be32 drc_status;
+ unsigned int referring_calls;
};
struct cb_compound_hdr_arg {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 96a4923080..76cea34477 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -207,7 +207,8 @@ static struct inode *nfs_layout_find_inode(struct nfs_client *clp,
* Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing)
*/
static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
- const nfs4_stateid *new)
+ const nfs4_stateid *new,
+ struct cb_process_state *cps)
{
u32 oldseq, newseq;
@@ -221,28 +222,29 @@ static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
newseq = be32_to_cpu(new->seqid);
/* Are we already in a layout recall situation? */
- if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) &&
- lo->plh_return_seq != 0) {
- if (newseq < lo->plh_return_seq)
- return NFS4ERR_OLD_STATEID;
- if (newseq > lo->plh_return_seq)
- return NFS4ERR_DELAY;
- goto out;
- }
+ if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+ return NFS4ERR_DELAY;
- /* Check that the stateid matches what we think it should be. */
+ /*
+ * Check that the stateid matches what we think it should be.
+ * Note that if the server sent us a list of referring calls,
+ * and we know that those have completed, then we trust the
+ * stateid argument is correct.
+ */
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
- if (newseq > oldseq + 1)
+ if (newseq > oldseq + 1 && !cps->referring_calls)
return NFS4ERR_DELAY;
+
/* Crazy server! */
if (newseq <= oldseq)
return NFS4ERR_OLD_STATEID;
-out:
+
return NFS_OK;
}
static u32 initiate_file_draining(struct nfs_client *clp,
- struct cb_layoutrecallargs *args)
+ struct cb_layoutrecallargs *args,
+ struct cb_process_state *cps)
{
struct inode *ino;
struct pnfs_layout_hdr *lo;
@@ -266,7 +268,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
goto out;
}
pnfs_get_layout_hdr(lo);
- rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid);
+ rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid, cps);
if (rv != NFS_OK)
goto unlock;
@@ -326,10 +328,11 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
}
static u32 do_callback_layoutrecall(struct nfs_client *clp,
- struct cb_layoutrecallargs *args)
+ struct cb_layoutrecallargs *args,
+ struct cb_process_state *cps)
{
if (args->cbl_recall_type == RETURN_FILE)
- return initiate_file_draining(clp, args);
+ return initiate_file_draining(clp, args, cps);
return initiate_bulk_draining(clp, args);
}
@@ -340,11 +343,12 @@ __be32 nfs4_callback_layoutrecall(void *argp, void *resp,
u32 res = NFS4ERR_OP_NOT_IN_SESSION;
if (cps->clp)
- res = do_callback_layoutrecall(cps->clp, args);
+ res = do_callback_layoutrecall(cps->clp, args, cps);
return cpu_to_be32(res);
}
-static void pnfs_recall_all_layouts(struct nfs_client *clp)
+static void pnfs_recall_all_layouts(struct nfs_client *clp,
+ struct cb_process_state *cps)
{
struct cb_layoutrecallargs args;
@@ -352,7 +356,7 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
memset(&args, 0, sizeof(args));
args.cbl_recall_type = RETURN_ALL;
/* FIXME we ignore errors, what should we do? */
- do_callback_layoutrecall(clp, &args);
+ do_callback_layoutrecall(clp, &args, cps);
}
__be32 nfs4_callback_devicenotify(void *argp, void *resp,
@@ -450,6 +454,7 @@ static int referring_call_exists(struct nfs_client *clp,
__acquires(lock)
{
int status = 0;
+ int found = 0;
int i, j;
struct nfs4_session *session;
struct nfs4_slot_table *tbl;
@@ -478,11 +483,12 @@ static int referring_call_exists(struct nfs_client *clp,
spin_lock(lock);
if (status)
goto out;
+ found++;
}
}
out:
- return status;
+ return status < 0 ? status : found;
}
__be32 nfs4_callback_sequence(void *argp, void *resp,
@@ -493,6 +499,7 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
struct nfs4_slot_table *tbl;
struct nfs4_slot *slot;
struct nfs_client *clp;
+ int ret;
int i;
__be32 status = htonl(NFS4ERR_BADSESSION);
@@ -552,11 +559,13 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
* related callback was received before the response to the original
* call.
*/
- if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
- &tbl->slot_tbl_lock) < 0) {
+ ret = referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
+ &tbl->slot_tbl_lock);
+ if (ret < 0) {
status = htonl(NFS4ERR_DELAY);
goto out_unlock;
}
+ cps->referring_calls = ret;
/*
* RFC5661 20.9.3
@@ -617,7 +626,7 @@ __be32 nfs4_callback_recallany(void *argp, void *resp,
nfs_expire_unused_delegation_types(cps->clp, flags);
if (args->craa_type_mask & BIT(RCA4_TYPE_MASK_FILE_LAYOUT))
- pnfs_recall_all_layouts(cps->clp);
+ pnfs_recall_all_layouts(cps->clp, cps);
if (args->craa_type_mask & BIT(PNFS_FF_RCA4_TYPE_MASK_READ)) {
set_bit(NFS4CLNT_RECALL_ANY_LAYOUT_READ, &cps->clp->cl_state);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 321af81c45..9369488f2e 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -967,6 +967,11 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
nops--;
}
+ if (svc_is_backchannel(rqstp) && cps.clp) {
+ rqstp->bc_to_initval = cps.clp->cl_rpcclient->cl_timeout->to_initval;
+ rqstp->bc_to_retries = cps.clp->cl_rpcclient->cl_timeout->to_retries;
+ }
+
*hdr_res.status = status;
*hdr_res.nops = htonl(nops);
nfs4_cb_free_slot(&cps);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 44eca51b28..fbdc9ca80f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -246,7 +246,7 @@ void nfs_free_client(struct nfs_client *clp)
put_nfs_version(clp->cl_nfs_mod);
kfree(clp->cl_hostname);
kfree(clp->cl_acceptor);
- kfree(clp);
+ kfree_rcu(clp, rcu);
}
EXPORT_SYMBOL_GPL(nfs_free_client);
@@ -1006,6 +1006,14 @@ struct nfs_server *nfs_alloc_server(void)
}
EXPORT_SYMBOL_GPL(nfs_alloc_server);
+static void delayed_free(struct rcu_head *p)
+{
+ struct nfs_server *server = container_of(p, struct nfs_server, rcu);
+
+ nfs_free_iostats(server->io_stats);
+ kfree(server);
+}
+
/*
* Free up a server record
*/
@@ -1031,10 +1039,9 @@ void nfs_free_server(struct nfs_server *server)
ida_destroy(&server->lockowner_id);
ida_destroy(&server->openowner_id);
- nfs_free_iostats(server->io_stats);
put_cred(server->cred);
- kfree(server);
nfs_release_automount_timer();
+ call_rcu(&server->rcu, delayed_free);
}
EXPORT_SYMBOL_GPL(nfs_free_server);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 273c0b68ab..ac505671ef 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1431,9 +1431,9 @@ static bool nfs_verifier_is_delegated(struct dentry *dentry)
static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
{
struct inode *inode = d_inode(dentry);
- struct inode *dir = d_inode(dentry->d_parent);
+ struct inode *dir = d_inode_rcu(dentry->d_parent);
- if (!nfs_verify_change_attribute(dir, verf))
+ if (!dir || !nfs_verify_change_attribute(dir, verf))
return;
if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
nfs_set_verifier_delegated(&verf);
@@ -2194,6 +2194,8 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
{
struct inode *inode;
+ trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
+
if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
goto full_reval;
if (d_mountpoint(dentry))
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b6f801e73b..d8cd4f69e3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -369,7 +369,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
bytes -= req_len;
requested_bytes += req_len;
pos += req_len;
- dreq->bytes_left -= req_len;
}
nfs_direct_release_pages(pagevec, npages);
kvfree(pagevec);
@@ -441,7 +440,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
goto out;
dreq->inode = inode;
- dreq->bytes_left = dreq->max_count = count;
+ dreq->max_count = count;
dreq->io_start = iocb->ki_pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -881,7 +880,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
bytes -= req_len;
requested_bytes += req_len;
pos += req_len;
- dreq->bytes_left -= req_len;
if (defer) {
nfs_mark_request_commit(req, NULL, &cinfo, 0);
@@ -988,7 +986,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
goto out;
dreq->inode = inode;
- dreq->bytes_left = dreq->max_count = count;
+ dreq->max_count = count;
dreq->io_start = pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3f97688104..8577ccf621 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -558,7 +558,6 @@ const struct address_space_operations nfs_file_aops = {
.read_folio = nfs_read_folio,
.readahead = nfs_readahead,
.dirty_folio = filemap_dirty_folio,
- .writepage = nfs_writepage,
.writepages = nfs_writepages,
.write_begin = nfs_write_begin,
.write_end = nfs_write_end,
@@ -567,7 +566,7 @@ const struct address_space_operations nfs_file_aops = {
.migrate_folio = nfs_migrate_folio,
.launder_folio = nfs_launder_folio,
.is_dirty_writeback = nfs_check_dirty_writeback,
- .error_remove_page = generic_error_remove_page,
+ .error_remove_folio = generic_error_remove_folio,
.swap_activate = nfs_swap_activate,
.swap_deactivate = nfs_swap_deactivate,
.swap_rw = nfs_swap_rw,
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 60a3c28784..ddc1ee0319 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -274,12 +274,6 @@ static void nfs_netfs_free_request(struct netfs_io_request *rreq)
put_nfs_open_context(rreq->netfs_priv);
}
-static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq)
-{
- return fscache_begin_read_operation(&rreq->cache_resources,
- netfs_i_cookie(netfs_inode(rreq->inode)));
-}
-
static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq)
{
struct nfs_netfs_io_data *netfs;
@@ -382,7 +376,6 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
const struct netfs_request_ops nfs_netfs_ops = {
.init_request = nfs_netfs_init_request,
.free_request = nfs_netfs_free_request,
- .begin_cache_operation = nfs_netfs_begin_cache_operation,
.issue_read = nfs_netfs_issue_read,
.clamp_length = nfs_netfs_clamp_length
};
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 5407ab8c87..e3cb492331 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -80,7 +80,7 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
}
static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
{
- netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops);
+ netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
}
extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b1fa81c9df..e3722ce672 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -936,7 +936,6 @@ struct nfs_direct_req {
loff_t io_start; /* Start offset for I/O */
ssize_t count, /* bytes actually processed */
max_count, /* max expected count */
- bytes_left, /* bytes left to be sent */
error; /* any reported error */
struct completion completion; /* wait for i/o completion */
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 2ad66a8922..49aaf28a69 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -132,7 +132,7 @@ nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry)
lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
&nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
- return list_lru_add(lru, &entry->lru);
+ return list_lru_add_obj(lru, &entry->lru);
}
static bool
@@ -143,7 +143,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
&nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
- return list_lru_del(lru, &entry->lru);
+ return list_lru_del_obj(lru, &entry->lru);
}
/*
@@ -349,7 +349,7 @@ nfs4_xattr_cache_unlink(struct inode *inode)
oldcache = nfsi->xattr_cache;
if (oldcache != NULL) {
- list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru);
+ list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru);
oldcache->inode = NULL;
}
nfsi->xattr_cache = NULL;
@@ -474,7 +474,7 @@ nfs4_xattr_get_cache(struct inode *inode, int add)
kref_get(&cache->ref);
nfsi->xattr_cache = cache;
cache->inode = inode;
- list_lru_add(&nfs4_xattr_cache_lru, &cache->lru);
+ list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru);
}
spin_unlock(&inode->i_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 02788c3c85..e238abc78a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -10,6 +10,7 @@
#include <linux/mount.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_ssc.h>
+#include <linux/splice.h>
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
@@ -195,8 +196,8 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
flags);
if (ret == -EOPNOTSUPP || ret == -EXDEV)
- ret = generic_copy_file_range(file_in, pos_in, file_out,
- pos_out, count, flags);
+ ret = splice_copy_file_range(file_in, pos_in, file_out,
+ pos_out, count);
return ret;
}
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index e776200e9a..886a7c4c60 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -34,7 +34,6 @@ static struct ctl_table nfs4_cb_sysctls[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
int nfs4_register_sysctl(void)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index deec76cf5a..69406e60f3 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1602,7 +1602,8 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args
static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
{
uint32_t attrs[3] = {
- FATTR4_WORD0_RDATTR_ERROR,
+ FATTR4_WORD0_TYPE
+ | FATTR4_WORD0_RDATTR_ERROR,
FATTR4_WORD1_MOUNTED_ON_FILEID,
};
uint32_t dircount = readdir->count;
@@ -1612,12 +1613,20 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
unsigned int i;
if (readdir->plus) {
- attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
- FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE|FATTR4_WORD0_FILEID;
- attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER|
- FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV|
- FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
- FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+ attrs[0] |= FATTR4_WORD0_CHANGE
+ | FATTR4_WORD0_SIZE
+ | FATTR4_WORD0_FSID
+ | FATTR4_WORD0_FILEHANDLE
+ | FATTR4_WORD0_FILEID;
+ attrs[1] |= FATTR4_WORD1_MODE
+ | FATTR4_WORD1_NUMLINKS
+ | FATTR4_WORD1_OWNER
+ | FATTR4_WORD1_OWNER_GROUP
+ | FATTR4_WORD1_RAWDEV
+ | FATTR4_WORD1_SPACE_USED
+ | FATTR4_WORD1_TIME_ACCESS
+ | FATTR4_WORD1_TIME_METADATA
+ | FATTR4_WORD1_TIME_MODIFY;
attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
}
/* Use mounted_on_fileid only if the server supports it */
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 4e90ca5311..afedb449b5 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -400,6 +400,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
__field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
+ __field(u64, fileid)
__string(name, dentry->d_name.name)
),
@@ -407,16 +408,18 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->flags = flags;
+ __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
__assign_str(name, dentry->d_name.name);
),
TP_printk(
- "flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+ "flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
__entry->flags,
show_fs_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
- __get_str(name)
+ __get_str(name),
+ __entry->fileid
)
);
@@ -444,6 +447,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
__field(unsigned long, flags)
__field(dev_t, dev)
__field(u64, dir)
+ __field(u64, fileid)
__string(name, dentry->d_name.name)
),
@@ -452,17 +456,19 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
__entry->dir = NFS_FILEID(dir);
__entry->error = error < 0 ? -error : 0;
__entry->flags = flags;
+ __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
__assign_str(name, dentry->d_name.name);
),
TP_printk(
- "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+ "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
-__entry->error, show_nfs_status(__entry->error),
__entry->flags,
show_fs_lookup_flags(__entry->flags),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->dir,
- __get_str(name)
+ __get_str(name),
+ __entry->fileid
)
);
@@ -893,7 +899,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done,
DEFINE_NFS_RENAME_EVENT(nfs_rename_enter);
DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit);
-DEFINE_NFS_RENAME_EVENT_DONE(nfs_sillyrename_rename);
+DEFINE_NFS_RENAME_EVENT_DONE(nfs_async_rename_done);
TRACE_EVENT(nfs_sillyrename_unlink,
TP_PROTO(
@@ -1539,7 +1545,6 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
__field(u32, fhandle)
__field(loff_t, offset)
__field(ssize_t, count)
- __field(ssize_t, bytes_left)
__field(ssize_t, error)
__field(int, flags)
),
@@ -1554,19 +1559,18 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
__entry->fhandle = nfs_fhandle_hash(fh);
__entry->offset = dreq->io_start;
__entry->count = dreq->count;
- __entry->bytes_left = dreq->bytes_left;
__entry->error = dreq->error;
__entry->flags = dreq->flags;
),
TP_printk(
"error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x "
- "offset=%lld count=%zd bytes_left=%zd flags=%s",
+ "offset=%lld count=%zd flags=%s",
__entry->error, MAJOR(__entry->dev),
MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle, __entry->offset,
- __entry->count, __entry->bytes_left,
+ __entry->count,
nfs_show_direct_req_flags(__entry->flags)
)
);
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index f39e2089bc..e645be1a33 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -29,7 +29,6 @@ static struct ctl_table nfs_cb_sysctls[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
int nfs_register_sysctl(void)
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 150a953a8b..0110299643 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -267,7 +267,7 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
struct inode *new_dir = data->new_dir;
struct dentry *old_dentry = data->old_dentry;
- trace_nfs_sillyrename_rename(old_dir, old_dentry,
+ trace_nfs_async_rename_done(old_dir, old_dentry,
new_dir, data->new_dentry, task->tk_status);
if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
rpc_restart_call_prepare(task);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5c2ff4a31a..5d9dc6c053 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -192,13 +192,13 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio)
if (!folio_test_private(folio))
return NULL;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
req = nfs_folio_private_request(folio);
if (req) {
WARN_ON_ONCE(req->wb_head != req);
kref_get(&req->wb_kref);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return req;
}
@@ -668,10 +668,8 @@ static int nfs_writepage_locked(struct folio *folio,
int err;
if (wbc->sync_mode == WB_SYNC_NONE &&
- NFS_SERVER(inode)->write_congested) {
- folio_redirty_for_writepage(wbc, folio);
+ NFS_SERVER(inode)->write_congested)
return AOP_WRITEPAGE_ACTIVATE;
- }
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_pageio_init_write(&pgio, inode, 0, false,
@@ -682,17 +680,6 @@ static int nfs_writepage_locked(struct folio *folio,
return err;
}
-int nfs_writepage(struct page *page, struct writeback_control *wbc)
-{
- struct folio *folio = page_folio(page);
- int ret;
-
- ret = nfs_writepage_locked(folio, wbc);
- if (ret != AOP_WRITEPAGE_ACTIVATE)
- unlock_page(page);
- return ret;
-}
-
static int nfs_writepages_callback(struct folio *folio,
struct writeback_control *wbc, void *data)
{
@@ -771,13 +758,13 @@ static void nfs_inode_add_request(struct nfs_page *req)
* Swap-space should not get truncated. Hence no need to plug the race
* with invalidate/truncate.
*/
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (likely(!folio_test_swapcache(folio))) {
set_bit(PG_MAPPED, &req->wb_flags);
folio_set_private(folio);
folio->private = req;
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
atomic_long_inc(&nfsi->nrequests);
/* this a head request for a page group - mark it as having an
* extra reference so sub groups can follow suit.
@@ -798,13 +785,13 @@ static void nfs_inode_remove_request(struct nfs_page *req)
struct folio *folio = nfs_page_to_folio(req->wb_head);
struct address_space *mapping = folio_file_mapping(folio);
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
if (likely(folio && !folio_test_swapcache(folio))) {
folio->private = NULL;
folio_clear_private(folio);
clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
}
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 43b88eaf06..272ab8d5c4 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -158,3 +158,19 @@ config NFSD_V4_SECURITY_LABEL
If you do not wish to enable fine-grained security labels SELinux or
Smack policies on NFSv4 files, say N.
+
+config NFSD_LEGACY_CLIENT_TRACKING
+ bool "Support legacy NFSv4 client tracking methods (DEPRECATED)"
+ depends on NFSD_V4
+ default n
+ help
+ The NFSv4 server needs to store a small amount of information on
+ stable storage in order to handle state recovery after reboot. Most
+ modern deployments upcall to a userland daemon for this (nfsdcld),
+ but older NFS servers may store information directly in a
+ recoverydir, or spawn a process directly using a usermodehelper
+ upcall.
+
+ These legacy client tracking methods have proven to be probelmatic
+ and will be removed in the future. Say Y here if you need support
+ for them in the interim.
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ef063f93fd..9cb7f0c33d 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -322,7 +322,7 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
static bool nfsd_file_lru_add(struct nfsd_file *nf)
{
set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
- if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) {
+ if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_add(nf);
return true;
}
@@ -331,7 +331,7 @@ static bool nfsd_file_lru_add(struct nfsd_file *nf)
static bool nfsd_file_lru_remove(struct nfsd_file *nf)
{
- if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) {
+ if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_del(nf);
return true;
}
@@ -717,7 +717,7 @@ nfsd_file_cache_init(void)
return ret;
ret = -ENOMEM;
- nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0);
+ nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", WQ_UNBOUND, 0);
if (!nfsd_filecache_wq)
goto out;
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index ab303a8b77..74b4360779 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -123,14 +123,9 @@ struct nfsd_net {
u32 clientid_counter;
u32 clverifier_counter;
- struct svc_serv *nfsd_serv;
- /* When a listening socket is added to nfsd, keep_active is set
- * and this justifies a reference on nfsd_serv. This stops
- * nfsd_serv from being freed. When the number of threads is
- * set, keep_active is cleared and the reference is dropped. So
- * when the last thread exits, the service will be destroyed.
- */
- int keep_active;
+ struct svc_info nfsd_info;
+#define nfsd_serv nfsd_info.serv
+
/*
* clientid and stateid data for construction of net unique COPY
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 4039ffcf90..926c29879c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -31,6 +31,7 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/nfs4.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/svc_xprt.h>
@@ -87,31 +88,6 @@ static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
}
-/*
- * nfs_cb_opnum4
- *
- * enum nfs_cb_opnum4 {
- * OP_CB_GETATTR = 3,
- * ...
- * };
- */
-enum nfs_cb_opnum4 {
- OP_CB_GETATTR = 3,
- OP_CB_RECALL = 4,
- OP_CB_LAYOUTRECALL = 5,
- OP_CB_NOTIFY = 6,
- OP_CB_PUSH_DELEG = 7,
- OP_CB_RECALL_ANY = 8,
- OP_CB_RECALLABLE_OBJ_AVAIL = 9,
- OP_CB_RECALL_SLOT = 10,
- OP_CB_SEQUENCE = 11,
- OP_CB_WANTS_CANCELLED = 12,
- OP_CB_NOTIFY_LOCK = 13,
- OP_CB_NOTIFY_DEVICEID = 14,
- OP_CB_OFFLOAD = 15,
- OP_CB_ILLEGAL = 10044
-};
-
static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
{
__be32 *p;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6f2d4aa497..14712fa08f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -970,8 +970,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* To ensure proper ordering, we therefore turn off zero copy if
* the client wants us to do more in this compound:
*/
- if (!nfsd4_last_compound_op(rqstp))
- clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ if (!nfsd4_last_compound_op(rqstp)) {
+ struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+ argp->splice_ok = false;
+ }
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 3509e73abe..2c060e0b16 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -66,6 +66,7 @@ struct nfsd4_client_tracking_ops {
static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops;
static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
/* Globals */
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
@@ -720,6 +721,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
.version = 1,
.msglen = 0,
};
+#endif /* CONFIG_NFSD_LEGACY_CLIENT_TRACKING */
/* Globals */
#define NFSD_PIPE_DIR "nfsd"
@@ -731,8 +733,10 @@ struct cld_net {
spinlock_t cn_lock;
struct list_head cn_list;
unsigned int cn_xid;
- bool cn_has_legacy;
struct crypto_shash *cn_tfm;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+ bool cn_has_legacy;
+#endif
};
struct cld_upcall {
@@ -793,7 +797,6 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
uint8_t cmd, princhashlen;
struct xdr_netobj name, princhash = { .len = 0, .data = NULL };
uint16_t namelen;
- struct cld_net *cn = nn->cld_net;
if (get_user(cmd, &cmsg->cm_cmd)) {
dprintk("%s: error when copying cmd from userspace", __func__);
@@ -833,11 +836,15 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
return PTR_ERR(name.data);
name.len = namelen;
}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) {
+ struct cld_net *cn = nn->cld_net;
+
name.len = name.len - 5;
memmove(name.data, name.data + 5, name.len);
cn->cn_has_legacy = true;
}
+#endif
if (!nfs4_client_to_reclaim(name, princhash, nn)) {
kfree(name.data);
kfree(princhash.data);
@@ -1010,7 +1017,9 @@ __nfsd4_init_cld_pipe(struct net *net)
}
cn->cn_pipe->dentry = dentry;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
cn->cn_has_legacy = false;
+#endif
nn->cld_net = cn;
return 0;
@@ -1282,10 +1291,6 @@ nfsd4_cld_check(struct nfs4_client *clp)
{
struct nfs4_client_reclaim *crp;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- struct cld_net *cn = nn->cld_net;
- int status;
- char dname[HEXDIR_LEN];
- struct xdr_netobj name;
/* did we already find that this client is stable? */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
@@ -1296,7 +1301,12 @@ nfsd4_cld_check(struct nfs4_client *clp)
if (crp)
goto found;
- if (cn->cn_has_legacy) {
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
+ if (nn->cld_net->cn_has_legacy) {
+ int status;
+ char dname[HEXDIR_LEN];
+ struct xdr_netobj name;
+
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return -ENOENT;
@@ -1314,6 +1324,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
goto found;
}
+#endif
return -ENOENT;
found:
crp->cr_clp = clp;
@@ -1327,8 +1338,6 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
int status;
- char dname[HEXDIR_LEN];
- struct xdr_netobj name;
struct crypto_shash *tfm = cn->cn_tfm;
struct xdr_netobj cksum;
char *principal = NULL;
@@ -1342,7 +1351,11 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
if (crp)
goto found;
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
if (cn->cn_has_legacy) {
+ struct xdr_netobj name;
+ char dname[HEXDIR_LEN];
+
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return -ENOENT;
@@ -1360,6 +1373,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
goto found;
}
+#endif
return -ENOENT;
found:
if (crp->cr_princhash.len) {
@@ -1663,6 +1677,7 @@ static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v2 = {
.msglen = sizeof(struct cld_msg_v2),
};
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
/* upcall via usermodehelper */
static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack";
module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog),
@@ -2007,28 +2022,10 @@ static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
.msglen = 0,
};
-int
-nfsd4_client_tracking_init(struct net *net)
+static inline int check_for_legacy_methods(int status, struct net *net)
{
- int status;
- struct path path;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
- /* just run the init if it the method is already decided */
- if (nn->client_tracking_ops)
- goto do_init;
-
- /* First, try to use nfsdcld */
- nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
- status = nn->client_tracking_ops->init(net);
- if (!status)
- return status;
- if (status != -ETIMEDOUT) {
- nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
- status = nn->client_tracking_ops->init(net);
- if (!status)
- return status;
- }
+ struct path path;
/*
* Next, try the UMH upcall.
@@ -2045,14 +2042,46 @@ nfsd4_client_tracking_init(struct net *net)
nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
if (!status) {
- status = d_is_dir(path.dentry);
+ status = !d_is_dir(path.dentry);
path_put(&path);
- if (!status) {
- status = -EINVAL;
- goto out;
- }
+ if (status)
+ return -ENOTDIR;
+ status = nn->client_tracking_ops->init(net);
+ }
+ return status;
+}
+#else
+static inline int check_for_legacy_methods(int status, struct net *net)
+{
+ return status;
+}
+#endif /* CONFIG_LEGACY_NFSD_CLIENT_TRACKING */
+
+int
+nfsd4_client_tracking_init(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int status;
+
+ /* just run the init if it the method is already decided */
+ if (nn->client_tracking_ops)
+ goto do_init;
+
+ /* First, try to use nfsdcld */
+ nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
+ status = nn->client_tracking_ops->init(net);
+ if (!status)
+ return status;
+ if (status != -ETIMEDOUT) {
+ nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0;
+ status = nn->client_tracking_ops->init(net);
+ if (!status)
+ return status;
}
+ status = check_for_legacy_methods(status, net);
+ if (status)
+ goto out;
do_init:
status = nn->client_tracking_ops->init(net);
out:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 57968484c3..692ede4882 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2888,12 +2888,9 @@ static void
nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
{
struct nfs4_client *clp = cb->cb_clp;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- spin_lock(&nn->client_lock);
clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
- put_client_renew_locked(clp);
- spin_unlock(&nn->client_lock);
+ drop_client(clp);
}
static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
@@ -6274,7 +6271,7 @@ deleg_reaper(struct nfsd_net *nn)
list_add(&clp->cl_ra_cblist, &cblist);
/* release in nfsd4_cb_recall_any_release */
- atomic_inc(&clp->cl_rpc_users);
+ kref_get(&clp->cl_nfsdfs.cl_ref);
set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
clp->cl_ra_time = ktime_get_boottime_seconds();
}
@@ -6574,7 +6571,7 @@ unlock:
spin_unlock(&nn->s2s_cp_lock);
if (!state)
return nfserr_bad_stateid;
- if (!clp && state)
+ if (!clp)
*cps = state;
return 0;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index b499fe9caa..c17bdf973c 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2524,8 +2524,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
svc_reserve(argp->rqstp, max_reply + readbytes);
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
+ argp->splice_ok = nfsd_read_splice_ok(argp->rqstp);
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ argp->splice_ok = false;
return true;
}
@@ -3489,11 +3490,13 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
struct dentry *dentry, const u32 *bmval,
int ignore_crossmnt)
{
+ DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
struct nfsd4_fattr_args args;
struct svc_fh *tempfh = NULL;
int starting_len = xdr->buf->len;
__be32 *attrlen_p, status;
int attrlen_offset;
+ u32 attrmask[3];
int err;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
u32 minorversion = resp->cstate.minorversion;
@@ -3501,10 +3504,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
.mnt = exp->ex_path.mnt,
.dentry = dentry,
};
- union {
- u32 attrmask[3];
- unsigned long mask[2];
- } u;
unsigned long bit;
WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
@@ -3518,20 +3517,19 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
/*
* Make a local copy of the attribute bitmap that can be modified.
*/
- memset(&u, 0, sizeof(u));
- u.attrmask[0] = bmval[0];
- u.attrmask[1] = bmval[1];
- u.attrmask[2] = bmval[2];
+ attrmask[0] = bmval[0];
+ attrmask[1] = bmval[1];
+ attrmask[2] = bmval[2];
args.rdattr_err = 0;
if (exp->ex_fslocs.migrated) {
- status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1],
- &u.attrmask[2], &args.rdattr_err);
+ status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1],
+ &attrmask[2], &args.rdattr_err);
if (status)
goto out;
}
args.size = 0;
- if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
+ if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry));
if (status)
goto out;
@@ -3546,16 +3544,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
if (!(args.stat.result_mask & STATX_BTIME))
/* underlying FS does not offer btime so we can't share it */
- u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
- if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+ attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+ if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
- (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
+ (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
err = vfs_statfs(&path, &args.statfs);
if (err)
goto out_nfserr;
}
- if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
+ if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
!fhp) {
tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
status = nfserr_jukebox;
@@ -3570,10 +3568,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
args.fhp = fhp;
args.acl = NULL;
- if (u.attrmask[0] & FATTR4_WORD0_ACL) {
+ if (attrmask[0] & FATTR4_WORD0_ACL) {
err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl);
if (err == -EOPNOTSUPP)
- u.attrmask[0] &= ~FATTR4_WORD0_ACL;
+ attrmask[0] &= ~FATTR4_WORD0_ACL;
else if (err == -EINVAL) {
status = nfserr_attrnotsupp;
goto out;
@@ -3585,17 +3583,17 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
args.context = NULL;
- if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
- u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+ if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
+ attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
if (exp->ex_flags & NFSEXP_SECURITY_LABEL)
err = security_inode_getsecctx(d_inode(dentry),
&args.context, &args.contextlen);
else
err = -EOPNOTSUPP;
args.contextsupport = (err == 0);
- if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) {
+ if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) {
if (err == -EOPNOTSUPP)
- u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+ attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
else if (err)
goto out_nfserr;
}
@@ -3603,8 +3601,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
/* attrmask */
- status = nfsd4_encode_bitmap4(xdr, u.attrmask[0],
- u.attrmask[1], u.attrmask[2]);
+ status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1],
+ attrmask[2]);
if (status)
goto out;
@@ -3613,7 +3611,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
attrlen_p = xdr_reserve_space(xdr, XDR_UNIT);
if (!attrlen_p)
goto out_resource;
- for_each_set_bit(bit, (const unsigned long *)&u.mask,
+ bitmap_from_arr32(attr_bitmap, attrmask,
+ ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+ for_each_set_bit(bit, attr_bitmap,
ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args);
if (status != nfs_ok)
@@ -4375,12 +4375,13 @@ static __be32
nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
union nfsd4_op_u *u)
{
+ struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
struct nfsd4_read *read = &u->read;
- bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
- unsigned long maxcount;
struct xdr_stream *xdr = resp->xdr;
- struct file *file;
int starting_len = xdr->buf->len;
+ bool splice_ok = argp->splice_ok;
+ unsigned long maxcount;
+ struct file *file;
__be32 *p;
if (nfserr)
@@ -5201,9 +5202,10 @@ static __be32
nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
struct nfsd4_read *read)
{
- bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
+ struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
struct file *file = read->rd_nf->nf_file;
struct xdr_stream *xdr = resp->xdr;
+ bool splice_ok = argp->splice_ok;
unsigned long maxcount;
__be32 nfserr, *p;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index d3273a3966..5c1a4a0aa6 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -364,8 +364,6 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
if (freed > sc->nr_to_scan)
break;
}
-
- trace_nfsd_drc_gc(nn, freed);
return freed;
}
@@ -508,7 +506,6 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
__wsum csum;
struct nfsd_drc_bucket *b;
int type = rqstp->rq_cachetype;
- unsigned long freed;
LIST_HEAD(dispose);
int rtn = RC_DOIT;
@@ -538,8 +535,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
nfsd_prune_bucket_locked(nn, b, 3, &dispose);
spin_unlock(&b->cache_lock);
- freed = nfsd_cacherep_dispose(&dispose);
- trace_nfsd_drc_gc(nn, freed);
+ nfsd_cacherep_dispose(&dispose);
nfsd_stats_rc_misses_inc();
atomic_inc(&nn->num_drc_entries);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 87fed75808..f206ca32e7 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -48,10 +48,6 @@ enum {
NFSD_MaxBlkSize,
NFSD_MaxConnections,
NFSD_Filecache,
- /*
- * The below MUST come last. Otherwise we leave a hole in nfsd_files[]
- * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops
- */
#ifdef CONFIG_NFSD_V4
NFSD_Leasetime,
NFSD_Gracetime,
@@ -76,7 +72,9 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
#ifdef CONFIG_NFSD_V4
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+#endif
static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
#endif
@@ -93,7 +91,9 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
#ifdef CONFIG_NFSD_V4
[NFSD_Leasetime] = write_leasetime,
[NFSD_Gracetime] = write_gracetime,
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
[NFSD_RecoveryDir] = write_recoverydir,
+#endif
[NFSD_V4EndGrace] = write_v4_end_grace,
#endif
};
@@ -179,7 +179,7 @@ static const struct file_operations pool_stats_operations = {
.open = nfsd_pool_stats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = nfsd_pool_stats_release,
+ .release = seq_release,
};
DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
@@ -707,12 +707,9 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
serv = nn->nfsd_serv;
err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
- if (err < 0 && !serv->sv_nrthreads && !nn->keep_active)
- nfsd_last_thread(net);
- else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(serv);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- svc_put(serv);
return err;
}
@@ -750,10 +747,6 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
- if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(serv);
-
- svc_put(serv);
return 0;
out_close:
xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
@@ -762,10 +755,9 @@ out_close:
svc_xprt_put(xprt);
}
out_err:
- if (!serv->sv_nrthreads && !nn->keep_active)
- nfsd_last_thread(net);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- svc_put(serv);
return err;
}
@@ -1021,6 +1013,7 @@ static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
struct nfsd_net *nn)
{
@@ -1081,6 +1074,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
mutex_unlock(&nfsd_mutex);
return rv;
}
+#endif
/*
* write_v4_end_grace - release grace period for nfsd's v4.x lock manager
@@ -1244,63 +1238,34 @@ static inline void _nfsd_symlink(struct dentry *parent, const char *name,
#endif
-static void clear_ncl(struct inode *inode)
+static void clear_ncl(struct dentry *dentry)
{
+ struct inode *inode = d_inode(dentry);
struct nfsdfs_client *ncl = inode->i_private;
+ spin_lock(&inode->i_lock);
inode->i_private = NULL;
+ spin_unlock(&inode->i_lock);
kref_put(&ncl->cl_ref, ncl->cl_release);
}
-static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
-{
- struct nfsdfs_client *nc = inode->i_private;
-
- if (nc)
- kref_get(&nc->cl_ref);
- return nc;
-}
-
struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc;
- inode_lock_shared(inode);
- nc = __get_nfsdfs_client(inode);
- inode_unlock_shared(inode);
+ spin_lock(&inode->i_lock);
+ nc = inode->i_private;
+ if (nc)
+ kref_get(&nc->cl_ref);
+ spin_unlock(&inode->i_lock);
return nc;
}
-/* from __rpc_unlink */
-static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
-{
- int ret;
-
- clear_ncl(d_inode(dentry));
- dget(dentry);
- ret = simple_unlink(dir, dentry);
- d_drop(dentry);
- fsnotify_unlink(dir, dentry);
- dput(dentry);
- WARN_ON_ONCE(ret);
-}
-
-static void nfsdfs_remove_files(struct dentry *root)
-{
- struct dentry *dentry, *tmp;
-
- list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) {
- if (!simple_positive(dentry)) {
- WARN_ON_ONCE(1); /* I think this can't happen? */
- continue;
- }
- nfsdfs_remove_file(d_inode(root), dentry);
- }
-}
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
static int nfsdfs_create_files(struct dentry *root,
const struct tree_descr *files,
+ struct nfsdfs_client *ncl,
struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
@@ -1319,8 +1284,9 @@ static int nfsdfs_create_files(struct dentry *root,
dput(dentry);
goto out;
}
+ kref_get(&ncl->cl_ref);
inode->i_fop = files->ops;
- inode->i_private = __get_nfsdfs_client(dir);
+ inode->i_private = ncl;
d_add(dentry, inode);
fsnotify_create(dir, dentry);
if (fdentries)
@@ -1329,7 +1295,6 @@ static int nfsdfs_create_files(struct dentry *root,
inode_unlock(dir);
return 0;
out:
- nfsdfs_remove_files(root);
inode_unlock(dir);
return -ENOMEM;
}
@@ -1349,7 +1314,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
if (IS_ERR(dentry)) /* XXX: tossing errors? */
return NULL;
- ret = nfsdfs_create_files(dentry, files, fdentries);
+ ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
if (ret) {
nfsd_client_rmdir(dentry);
return NULL;
@@ -1360,20 +1325,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
/* Taken from __rpc_rmdir: */
void nfsd_client_rmdir(struct dentry *dentry)
{
- struct inode *dir = d_inode(dentry->d_parent);
- struct inode *inode = d_inode(dentry);
- int ret;
-
- inode_lock(dir);
- nfsdfs_remove_files(dentry);
- clear_ncl(inode);
- dget(dentry);
- ret = simple_rmdir(dir, dentry);
- WARN_ON_ONCE(ret);
- d_drop(dentry);
- fsnotify_rmdir(dir, dentry);
- dput(dentry);
- inode_unlock(dir);
+ simple_recursive_removal(dentry, clear_ncl);
}
static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 9ed0e08d16..304e9728b9 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -148,7 +148,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
void nfsd_reset_versions(struct nfsd_net *nn);
int nfsd_create_serv(struct net *net);
-void nfsd_last_thread(struct net *net);
+void nfsd_destroy_serv(struct net *net);
extern int nfsd_max_blksize;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 7a2bc8e82a..a667802e08 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -59,15 +59,6 @@ static __be32 nfsd_init_request(struct svc_rqst *,
* nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members
* of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks.
*
- * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
- * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
- * nn->keep_active is set). That number of nfsd threads must
- * exist and each must be listed in ->sp_all_threads in some entry of
- * ->sv_pools[].
- *
- * Each active thread holds a counted reference on nn->nfsd_serv, as does
- * the nn->keep_active flag and various transient calls to svc_get().
- *
* Finally, the nfsd_mutex also protects some of the global variables that are
* accessed when nfsd starts and that are settable via the write_* routines in
* nfsctl.c. In particular:
@@ -359,13 +350,12 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
*/
void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn)
{
- int seq = 0;
+ unsigned int seq;
do {
- read_seqbegin_or_lock(&nn->writeverf_lock, &seq);
+ seq = read_seqbegin(&nn->writeverf_lock);
memcpy(verf, nn->writeverf, sizeof(nn->writeverf));
- } while (need_seqretry(&nn->writeverf_lock, seq));
- done_seqretry(&nn->writeverf_lock, seq);
+ } while (read_seqretry(&nn->writeverf_lock, seq));
}
static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn)
@@ -542,7 +532,11 @@ static struct notifier_block nfsd_inet6addr_notifier = {
/* Only used under nfsd_mutex, so this atomic may be overkill: */
static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
-void nfsd_last_thread(struct net *net)
+/**
+ * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace
+ * @net: network namespace the NFS service is associated with
+ */
+void nfsd_destroy_serv(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct svc_serv *serv = nn->nfsd_serv;
@@ -564,7 +558,7 @@ void nfsd_last_thread(struct net *net)
/*
* write_ports can create the server without actually starting
* any threads--if we get shut down before any threads are
- * started, then nfsd_last_thread will be run before any of this
+ * started, then nfsd_destroy_serv will be run before any of this
* other initialization has been done except the rpcb information.
*/
svc_rpcb_cleanup(serv, net);
@@ -573,6 +567,7 @@ void nfsd_last_thread(struct net *net)
nfsd_shutdown_net(net);
nfsd_export_flush(net);
+ svc_destroy(&serv);
}
void nfsd_reset_versions(struct nfsd_net *nn)
@@ -647,11 +642,9 @@ void nfsd_shutdown_threads(struct net *net)
return;
}
- svc_get(serv);
/* Kill outstanding nfsd threads */
svc_set_num_threads(serv, NULL, 0);
- nfsd_last_thread(net);
- svc_put(serv);
+ nfsd_destroy_serv(net);
mutex_unlock(&nfsd_mutex);
}
@@ -667,10 +660,9 @@ int nfsd_create_serv(struct net *net)
struct svc_serv *serv;
WARN_ON(!mutex_is_locked(&nfsd_mutex));
- if (nn->nfsd_serv) {
- svc_get(nn->nfsd_serv);
+ if (nn->nfsd_serv)
return 0;
- }
+
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions(nn);
@@ -681,10 +673,11 @@ int nfsd_create_serv(struct net *net)
serv->sv_maxconn = nn->max_connections;
error = svc_bind(serv, net);
if (error < 0) {
- svc_put(serv);
+ svc_destroy(&serv);
return error;
}
spin_lock(&nfsd_notifier_lock);
+ nn->nfsd_info.mutex = &nfsd_mutex;
nn->nfsd_serv = serv;
spin_unlock(&nfsd_notifier_lock);
@@ -764,7 +757,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
nthreads[0] = 1;
/* apply the new numbers */
- svc_get(nn->nfsd_serv);
for (i = 0; i < n; i++) {
err = svc_set_num_threads(nn->nfsd_serv,
&nn->nfsd_serv->sv_pools[i],
@@ -772,7 +764,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
if (err)
break;
}
- svc_put(nn->nfsd_serv);
return err;
}
@@ -814,13 +805,8 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
goto out_put;
error = serv->sv_nrthreads;
out_put:
- /* Threads now hold service active */
- if (xchg(&nn->keep_active, 0))
- svc_put(serv);
-
if (serv->sv_nrthreads == 0)
- nfsd_last_thread(net);
- svc_put(serv);
+ nfsd_destroy_serv(net);
out:
mutex_unlock(&nfsd_mutex);
return error;
@@ -1083,28 +1069,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
- int ret;
struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
- mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv == NULL) {
- mutex_unlock(&nfsd_mutex);
- return -ENODEV;
- }
- svc_get(nn->nfsd_serv);
- ret = svc_pool_stats_open(nn->nfsd_serv, file);
- mutex_unlock(&nfsd_mutex);
- return ret;
-}
-
-int nfsd_pool_stats_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq = file->private_data;
- struct svc_serv *serv = seq->private;
- int ret = seq_release(inode, file);
-
- mutex_lock(&nfsd_mutex);
- svc_put(serv);
- mutex_unlock(&nfsd_mutex);
- return ret;
+ return svc_pool_stats_open(&nn->nfsd_info, file);
}
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 4c7a296c41..2cd5703379 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1262,28 +1262,6 @@ TRACE_EVENT(nfsd_drc_mismatch,
__entry->ingress)
);
-TRACE_EVENT_CONDITION(nfsd_drc_gc,
- TP_PROTO(
- const struct nfsd_net *nn,
- unsigned long freed
- ),
- TP_ARGS(nn, freed),
- TP_CONDITION(freed > 0),
- TP_STRUCT__entry(
- __field(unsigned long long, boot_time)
- __field(unsigned long, freed)
- __field(int, total)
- ),
- TP_fast_assign(
- __entry->boot_time = nn->boot_time;
- __entry->freed = freed;
- __entry->total = atomic_read(&nn->num_drc_entries);
- ),
- TP_printk("boot_time=%16llx total=%d freed=%lu",
- __entry->boot_time, __entry->total, __entry->freed
- )
-);
-
TRACE_EVENT(nfsd_cb_args,
TP_PROTO(
const struct nfs4_client *clp,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index e01e4e2acb..4ed1e83def 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1039,7 +1039,10 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
ssize_t host_err;
trace_nfsd_read_splice(rqstp, fhp, offset, *count);
- host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+ host_err = rw_verify_area(READ, file, &offset, *count);
+ if (!host_err)
+ host_err = splice_direct_to_actor(file, &sd,
+ nfsd_direct_splice_actor);
return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
}
@@ -1176,9 +1179,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
since = READ_ONCE(file->f_wb_err);
if (verf)
nfsd_copy_write_verifier(verf, nn);
- file_start_write(file);
host_err = vfs_iter_write(file, &iter, &pos, flags);
- file_end_write(file);
if (host_err < 0) {
commit_reset_write_verifier(nn, rqstp, host_err);
goto out_nfserr;
@@ -1210,6 +1211,30 @@ out_nfserr:
}
/**
+ * nfsd_read_splice_ok - check if spliced reading is supported
+ * @rqstp: RPC transaction context
+ *
+ * Return values:
+ * %true: nfsd_splice_read() may be used
+ * %false: nfsd_splice_read() must not be used
+ *
+ * NFS READ normally uses splice to send data in-place. However the
+ * data in cache can change after the reply's MIC is computed but
+ * before the RPC reply is sent. To prevent the client from
+ * rejecting the server-computed MIC in this somewhat rare case, do
+ * not use splice with the GSS integrity and privacy services.
+ */
+bool nfsd_read_splice_ok(struct svc_rqst *rqstp)
+{
+ switch (svc_auth_flavor(rqstp)) {
+ case RPC_AUTH_GSS_KRB5I:
+ case RPC_AUTH_GSS_KRB5P:
+ return false;
+ }
+ return true;
+}
+
+/**
* nfsd_read - Read data from a file
* @rqstp: RPC transaction context
* @fhp: file handle of file to be read
@@ -1238,7 +1263,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
return err;
file = nf->nf_file;
- if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
+ if (file->f_op->splice_read && nfsd_read_splice_ok(rqstp))
err = nfsd_splice_read(rqstp, fhp, file, offset, count, eof);
else
err = nfsd_iter_read(rqstp, fhp, file, offset, count, 0, eof);
@@ -1806,6 +1831,10 @@ retry:
}
trap = lock_rename(tdentry, fdentry);
+ if (IS_ERR(trap)) {
+ err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
+ goto out_want_write;
+ }
err = fh_fill_pre_attrs(ffhp);
if (err != nfs_ok)
goto out_unlock;
@@ -1874,6 +1903,7 @@ retry:
}
out_unlock:
unlock_rename(tdentry, fdentry);
+out_want_write:
fh_drop_write(ffhp);
/*
@@ -2102,9 +2132,23 @@ static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
return cdp->err;
}
-/*
- * Read entries from a directory.
- * The NFSv3/4 verifier we ignore for now.
+/**
+ * nfsd_readdir - Read entries from a directory
+ * @rqstp: RPC transaction context
+ * @fhp: NFS file handle of directory to be read
+ * @offsetp: OUT: seek offset of final entry that was read
+ * @cdp: OUT: an eof error value
+ * @func: entry filler actor
+ *
+ * This implementation ignores the NFSv3/4 verifier cookie.
+ *
+ * NB: normal system calls hold file->f_pos_lock when calling
+ * ->iterate_shared and ->llseek, but nfsd_readdir() does not.
+ * Because the struct file acquired here is not visible to other
+ * threads, it's internal state does not need mutex protection.
+ *
+ * Returns nfs_ok on success, otherwise an nfsstat code is
+ * returned.
*/
__be32
nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e3c29596f4..702fbc4483 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -114,6 +114,7 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct file *file, loff_t offset,
unsigned long *count, unsigned int base,
u32 *eof);
+bool nfsd_read_splice_ok(struct svc_rqst *rqstp);
__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
loff_t offset, unsigned long *count,
u32 *eof);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 80e859dc84..415516c1b2 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -840,6 +840,7 @@ struct nfsd4_compoundargs {
u32 minorversion;
u32 client_opcnt;
u32 opcnt;
+ bool splice_ok;
struct nfsd4_op *ops;
struct nfsd4_op iops[8];
};