aboutsummaryrefslogtreecommitdiffstats
path: root/fs/nfsd
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd')
-rw-r--r--fs/nfsd/Kconfig10
-rw-r--r--fs/nfsd/filecache.c313
-rw-r--r--fs/nfsd/filecache.h7
-rw-r--r--fs/nfsd/netns.h6
-rw-r--r--fs/nfsd/nfs3proc.c5
-rw-r--r--fs/nfsd/nfs3xdr.c36
-rw-r--r--fs/nfsd/nfs4callback.c11
-rw-r--r--fs/nfsd/nfs4layouts.c2
-rw-r--r--fs/nfsd/nfs4proc.c462
-rw-r--r--fs/nfsd/nfs4recover.c8
-rw-r--r--fs/nfsd/nfs4state.c262
-rw-r--r--fs/nfsd/nfs4xdr.c161
-rw-r--r--fs/nfsd/nfsctl.c19
-rw-r--r--fs/nfsd/nfsd.h34
-rw-r--r--fs/nfsd/nfsfh.h9
-rw-r--r--fs/nfsd/nfsproc.c8
-rw-r--r--fs/nfsd/nfssvc.c21
-rw-r--r--fs/nfsd/state.h44
-rw-r--r--fs/nfsd/stats.c12
-rw-r--r--fs/nfsd/trace.h22
-rw-r--r--fs/nfsd/vfs.c109
-rw-r--r--fs/nfsd/vfs.h18
-rw-r--r--fs/nfsd/xdr3.h4
-rw-r--r--fs/nfsd/xdr4.h39
24 files changed, 1304 insertions, 318 deletions
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index f2f81561ebb6..f368f3215f88 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -134,6 +134,16 @@ config NFSD_FLEXFILELAYOUT
If unsure, say N.
+config NFSD_V4_2_INTER_SSC
+ bool "NFSv4.2 inter server to server COPY"
+ depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+ help
+ This option enables support for NFSv4.2 inter server to
+ server copy where the destination server calls the NFSv4.2
+ client to read the data to copy from the source server.
+
+ If unsure, say N.
+
config NFSD_V4_SECURITY_LABEL
bool "Provide Security Label support for NFSv4 server"
depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 32a9bf22ac08..22e77ede9f14 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -27,7 +27,6 @@
#define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS)
#define NFSD_LAUNDRETTE_DELAY (2 * HZ)
-#define NFSD_FILE_LRU_RESCAN (0)
#define NFSD_FILE_SHUTDOWN (1)
#define NFSD_FILE_LRU_THRESHOLD (4096UL)
#define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2)
@@ -44,6 +43,17 @@ struct nfsd_fcache_bucket {
static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
+struct nfsd_fcache_disposal {
+ struct list_head list;
+ struct work_struct work;
+ struct net *net;
+ spinlock_t lock;
+ struct list_head freeme;
+ struct rcu_head rcu;
+};
+
+static struct workqueue_struct *nfsd_filecache_wq __read_mostly;
+
static struct kmem_cache *nfsd_file_slab;
static struct kmem_cache *nfsd_file_mark_slab;
static struct nfsd_fcache_bucket *nfsd_file_hashtbl;
@@ -52,32 +62,21 @@ static long nfsd_file_lru_flags;
static struct fsnotify_group *nfsd_file_fsnotify_group;
static atomic_long_t nfsd_filecache_count;
static struct delayed_work nfsd_filecache_laundrette;
+static DEFINE_SPINLOCK(laundrette_lock);
+static LIST_HEAD(laundrettes);
-enum nfsd_file_laundrette_ctl {
- NFSD_FILE_LAUNDRETTE_NOFLUSH = 0,
- NFSD_FILE_LAUNDRETTE_MAY_FLUSH
-};
+static void nfsd_file_gc(void);
static void
-nfsd_file_schedule_laundrette(enum nfsd_file_laundrette_ctl ctl)
+nfsd_file_schedule_laundrette(void)
{
long count = atomic_long_read(&nfsd_filecache_count);
if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags))
return;
- /* Be more aggressive about scanning if over the threshold */
- if (count > NFSD_FILE_LRU_THRESHOLD)
- mod_delayed_work(system_wq, &nfsd_filecache_laundrette, 0);
- else
- schedule_delayed_work(&nfsd_filecache_laundrette, NFSD_LAUNDRETTE_DELAY);
-
- if (ctl == NFSD_FILE_LAUNDRETTE_NOFLUSH)
- return;
-
- /* ...and don't delay flushing if we're out of control */
- if (count >= NFSD_FILE_LRU_LIMIT)
- flush_delayed_work(&nfsd_filecache_laundrette);
+ queue_delayed_work(system_wq, &nfsd_filecache_laundrette,
+ NFSD_LAUNDRETTE_DELAY);
}
static void
@@ -101,7 +100,7 @@ nfsd_file_mark_free(struct fsnotify_mark *mark)
static struct nfsd_file_mark *
nfsd_file_mark_get(struct nfsd_file_mark *nfm)
{
- if (!atomic_inc_not_zero(&nfm->nfm_ref))
+ if (!refcount_inc_not_zero(&nfm->nfm_ref))
return NULL;
return nfm;
}
@@ -109,8 +108,7 @@ nfsd_file_mark_get(struct nfsd_file_mark *nfm)
static void
nfsd_file_mark_put(struct nfsd_file_mark *nfm)
{
- if (atomic_dec_and_test(&nfm->nfm_ref)) {
-
+ if (refcount_dec_and_test(&nfm->nfm_ref)) {
fsnotify_destroy_mark(&nfm->nfm_mark, nfsd_file_fsnotify_group);
fsnotify_put_mark(&nfm->nfm_mark);
}
@@ -133,9 +131,13 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf)
struct nfsd_file_mark,
nfm_mark));
mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex);
- fsnotify_put_mark(mark);
- if (likely(nfm))
+ if (nfm) {
+ fsnotify_put_mark(mark);
break;
+ }
+ /* Avoid soft lockup race with nfsd_file_mark_put() */
+ fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group);
+ fsnotify_put_mark(mark);
} else
mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex);
@@ -145,7 +147,7 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf)
return NULL;
fsnotify_init_mark(&new->nfm_mark, nfsd_file_fsnotify_group);
new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF;
- atomic_set(&new->nfm_ref, 1);
+ refcount_set(&new->nfm_ref, 1);
err = fsnotify_add_inode_mark(&new->nfm_mark, inode, 0);
@@ -183,7 +185,7 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
nf->nf_flags = 0;
nf->nf_inode = inode;
nf->nf_hashval = hashval;
- atomic_set(&nf->nf_ref, 1);
+ refcount_set(&nf->nf_ref, 1);
nf->nf_may = may & NFSD_FILE_MAY_MASK;
if (may & NFSD_MAY_NOT_BREAK_LEASE) {
if (may & NFSD_MAY_WRITE)
@@ -192,6 +194,7 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
__set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
}
nf->nf_mark = NULL;
+ init_rwsem(&nf->nf_rwsem);
trace_nfsd_file_alloc(nf);
}
return nf;
@@ -238,13 +241,6 @@ nfsd_file_check_write_error(struct nfsd_file *nf)
return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err));
}
-static bool
-nfsd_file_in_use(struct nfsd_file *nf)
-{
- return nfsd_file_check_writeback(nf) ||
- nfsd_file_check_write_error(nf);
-}
-
static void
nfsd_file_do_unhash(struct nfsd_file *nf)
{
@@ -256,8 +252,6 @@ nfsd_file_do_unhash(struct nfsd_file *nf)
nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id));
--nfsd_file_hashtbl[nf->nf_hashval].nfb_count;
hlist_del_rcu(&nf->nf_node);
- if (!list_empty(&nf->nf_lru))
- list_lru_del(&nfsd_file_lru, &nf->nf_lru);
atomic_long_dec(&nfsd_filecache_count);
}
@@ -266,6 +260,8 @@ nfsd_file_unhash(struct nfsd_file *nf)
{
if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
nfsd_file_do_unhash(nf);
+ if (!list_empty(&nf->nf_lru))
+ list_lru_del(&nfsd_file_lru, &nf->nf_lru);
return true;
}
return false;
@@ -283,42 +279,48 @@ nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *disp
if (!nfsd_file_unhash(nf))
return false;
/* keep final reference for nfsd_file_lru_dispose */
- if (atomic_add_unless(&nf->nf_ref, -1, 1))
+ if (refcount_dec_not_one(&nf->nf_ref))
return true;
list_add(&nf->nf_lru, dispose);
return true;
}
-static int
+static void
nfsd_file_put_noref(struct nfsd_file *nf)
{
- int count;
trace_nfsd_file_put(nf);
- count = atomic_dec_return(&nf->nf_ref);
- if (!count) {
+ if (refcount_dec_and_test(&nf->nf_ref)) {
WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags));
nfsd_file_free(nf);
}
- return count;
}
void
nfsd_file_put(struct nfsd_file *nf)
{
- bool is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0;
- bool unused = !nfsd_file_in_use(nf);
+ bool is_hashed;
set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
- if (nfsd_file_put_noref(nf) == 1 && is_hashed && unused)
- nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_MAY_FLUSH);
+ if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) {
+ nfsd_file_put_noref(nf);
+ return;
+ }
+
+ filemap_flush(nf->nf_file->f_mapping);
+ is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0;
+ nfsd_file_put_noref(nf);
+ if (is_hashed)
+ nfsd_file_schedule_laundrette();
+ if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT)
+ nfsd_file_gc();
}
struct nfsd_file *
nfsd_file_get(struct nfsd_file *nf)
{
- if (likely(atomic_inc_not_zero(&nf->nf_ref)))
+ if (likely(refcount_inc_not_zero(&nf->nf_ref)))
return nf;
return NULL;
}
@@ -344,7 +346,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose)
while(!list_empty(dispose)) {
nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
list_del(&nf->nf_lru);
- if (!atomic_dec_and_test(&nf->nf_ref))
+ if (!refcount_dec_and_test(&nf->nf_ref))
continue;
if (nfsd_file_free(nf))
flush = true;
@@ -353,6 +355,58 @@ nfsd_file_dispose_list_sync(struct list_head *dispose)
flush_delayed_fput();
}
+static void
+nfsd_file_list_remove_disposal(struct list_head *dst,
+ struct nfsd_fcache_disposal *l)
+{
+ spin_lock(&l->lock);
+ list_splice_init(&l->freeme, dst);
+ spin_unlock(&l->lock);
+}
+
+static void
+nfsd_file_list_add_disposal(struct list_head *files, struct net *net)
+{
+ struct nfsd_fcache_disposal *l;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(l, &laundrettes, list) {
+ if (l->net == net) {
+ spin_lock(&l->lock);
+ list_splice_tail_init(files, &l->freeme);
+ spin_unlock(&l->lock);
+ queue_work(nfsd_filecache_wq, &l->work);
+ break;
+ }
+ }
+ rcu_read_unlock();
+}
+
+static void
+nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src,
+ struct net *net)
+{
+ struct nfsd_file *nf, *tmp;
+
+ list_for_each_entry_safe(nf, tmp, src, nf_lru) {
+ if (nf->nf_net == net)
+ list_move_tail(&nf->nf_lru, dst);
+ }
+}
+
+static void
+nfsd_file_dispose_list_delayed(struct list_head *dispose)
+{
+ LIST_HEAD(list);
+ struct nfsd_file *nf;
+
+ while(!list_empty(dispose)) {
+ nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
+ nfsd_file_list_add_pernet(&list, dispose, nf->nf_net);
+ nfsd_file_list_add_disposal(&list, nf->nf_net);
+ }
+}
+
/*
* Note this can deadlock with nfsd_file_cache_purge.
*/
@@ -375,7 +429,7 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
* counter. Here we check the counter and then test and clear the flag.
* That order is deliberate to ensure that we can do this locklessly.
*/
- if (atomic_read(&nf->nf_ref) > 1)
+ if (refcount_read(&nf->nf_ref) > 1)
goto out_skip;
/*
@@ -386,31 +440,51 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
goto out_skip;
if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags))
- goto out_rescan;
+ goto out_skip;
if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags))
goto out_skip;
list_lru_isolate_move(lru, &nf->nf_lru, head);
return LRU_REMOVED;
-out_rescan:
- set_bit(NFSD_FILE_LRU_RESCAN, &nfsd_file_lru_flags);
out_skip:
return LRU_SKIP;
}
-static void
-nfsd_file_lru_dispose(struct list_head *head)
+static unsigned long
+nfsd_file_lru_walk_list(struct shrink_control *sc)
{
- while(!list_empty(head)) {
- struct nfsd_file *nf = list_first_entry(head,
- struct nfsd_file, nf_lru);
- list_del_init(&nf->nf_lru);
+ LIST_HEAD(head);
+ struct nfsd_file *nf;
+ unsigned long ret;
+
+ if (sc)
+ ret = list_lru_shrink_walk(&nfsd_file_lru, sc,
+ nfsd_file_lru_cb, &head);
+ else
+ ret = list_lru_walk(&nfsd_file_lru,
+ nfsd_file_lru_cb,
+ &head, LONG_MAX);
+ list_for_each_entry(nf, &head, nf_lru) {
spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock);
nfsd_file_do_unhash(nf);
spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock);
- nfsd_file_put_noref(nf);
}
+ nfsd_file_dispose_list_delayed(&head);
+ return ret;
+}
+
+static void
+nfsd_file_gc(void)
+{
+ nfsd_file_lru_walk_list(NULL);
+}
+
+static void
+nfsd_file_gc_worker(struct work_struct *work)
+{
+ nfsd_file_gc();
+ nfsd_file_schedule_laundrette();
}
static unsigned long
@@ -422,12 +496,7 @@ nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc)
static unsigned long
nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc)
{
- LIST_HEAD(head);
- unsigned long ret;
-
- ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &head);
- nfsd_file_lru_dispose(&head);
- return ret;
+ return nfsd_file_lru_walk_list(sc);
}
static struct shrinker nfsd_file_shrinker = {
@@ -489,7 +558,7 @@ nfsd_file_close_inode(struct inode *inode)
__nfsd_file_close_inode(inode, hashval, &dispose);
trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose));
- nfsd_file_dispose_list(&dispose);
+ nfsd_file_dispose_list_delayed(&dispose);
}
/**
@@ -505,16 +574,11 @@ static void
nfsd_file_delayed_close(struct work_struct *work)
{
LIST_HEAD(head);
+ struct nfsd_fcache_disposal *l = container_of(work,
+ struct nfsd_fcache_disposal, work);
- list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, &head, LONG_MAX);
-
- if (test_and_clear_bit(NFSD_FILE_LRU_RESCAN, &nfsd_file_lru_flags))
- nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_NOFLUSH);
-
- if (!list_empty(&head)) {
- nfsd_file_lru_dispose(&head);
- flush_delayed_fput();
- }
+ nfsd_file_list_remove_disposal(&head, l);
+ nfsd_file_dispose_list(&head);
}
static int
@@ -575,6 +639,10 @@ nfsd_file_cache_init(void)
if (nfsd_file_hashtbl)
return 0;
+ nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0);
+ if (!nfsd_filecache_wq)
+ goto out;
+
nfsd_file_hashtbl = kcalloc(NFSD_FILE_HASH_SIZE,
sizeof(*nfsd_file_hashtbl), GFP_KERNEL);
if (!nfsd_file_hashtbl) {
@@ -628,7 +696,7 @@ nfsd_file_cache_init(void)
spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock);
}
- INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_delayed_close);
+ INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker);
out:
return ret;
out_notifier:
@@ -644,6 +712,8 @@ out_err:
nfsd_file_mark_slab = NULL;
kfree(nfsd_file_hashtbl);
nfsd_file_hashtbl = NULL;
+ destroy_workqueue(nfsd_filecache_wq);
+ nfsd_filecache_wq = NULL;
goto out;
}
@@ -682,6 +752,88 @@ nfsd_file_cache_purge(struct net *net)
}
}
+static struct nfsd_fcache_disposal *
+nfsd_alloc_fcache_disposal(struct net *net)
+{
+ struct nfsd_fcache_disposal *l;
+
+ l = kmalloc(sizeof(*l), GFP_KERNEL);
+ if (!l)
+ return NULL;
+ INIT_WORK(&l->work, nfsd_file_delayed_close);
+ l->net = net;
+ spin_lock_init(&l->lock);
+ INIT_LIST_HEAD(&l->freeme);
+ return l;
+}
+
+static void
+nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l)
+{
+ rcu_assign_pointer(l->net, NULL);
+ cancel_work_sync(&l->work);
+ nfsd_file_dispose_list(&l->freeme);
+ kfree_rcu(l, rcu);
+}
+
+static void
+nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l)
+{
+ spin_lock(&laundrette_lock);
+ list_add_tail_rcu(&l->list, &laundrettes);
+ spin_unlock(&laundrette_lock);
+}
+
+static void
+nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l)
+{
+ spin_lock(&laundrette_lock);
+ list_del_rcu(&l->list);
+ spin_unlock(&laundrette_lock);
+}
+
+static int
+nfsd_alloc_fcache_disposal_net(struct net *net)
+{
+ struct nfsd_fcache_disposal *l;
+
+ l = nfsd_alloc_fcache_disposal(net);
+ if (!l)
+ return -ENOMEM;
+ nfsd_add_fcache_disposal(l);
+ return 0;
+}
+
+static void
+nfsd_free_fcache_disposal_net(struct net *net)
+{
+ struct nfsd_fcache_disposal *l;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(l, &laundrettes, list) {
+ if (l->net != net)
+ continue;
+ nfsd_del_fcache_disposal(l);
+ rcu_read_unlock();
+ nfsd_free_fcache_disposal(l);
+ return;
+ }
+ rcu_read_unlock();
+}
+
+int
+nfsd_file_cache_start_net(struct net *net)
+{
+ return nfsd_alloc_fcache_disposal_net(net);
+}
+
+void
+nfsd_file_cache_shutdown_net(struct net *net)
+{
+ nfsd_file_cache_purge(net);
+ nfsd_free_fcache_disposal_net(net);
+}
+
void
nfsd_file_cache_shutdown(void)
{
@@ -706,6 +858,8 @@ nfsd_file_cache_shutdown(void)
nfsd_file_mark_slab = NULL;
kfree(nfsd_file_hashtbl);
nfsd_file_hashtbl = NULL;
+ destroy_workqueue(nfsd_filecache_wq);
+ nfsd_filecache_wq = NULL;
}
static bool
@@ -789,6 +943,7 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct nfsd_file *nf, *new;
struct inode *inode;
unsigned int hashval;
+ bool retry = true;
/* FIXME: skip this if fh_dentry is already set? */
status = fh_verify(rqstp, fhp, S_IFREG,
@@ -824,6 +979,11 @@ wait_for_construction:
/* Did construction of this file fail? */
if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+ if (!retry) {
+ status = nfserr_jukebox;
+ goto out;
+ }
+ retry = false;
nfsd_file_put_noref(nf);
goto retry;
}
@@ -858,7 +1018,7 @@ out:
open_file:
nf = new;
/* Take reference for the hashtable */
- atomic_inc(&nf->nf_ref);
+ refcount_inc(&nf->nf_ref);
__set_bit(NFSD_FILE_HASHED, &nf->nf_flags);
__set_bit(NFSD_FILE_PENDING, &nf->nf_flags);
list_lru_add(&nfsd_file_lru, &nf->nf_lru);
@@ -867,7 +1027,8 @@ open_file:
nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount,
nfsd_file_hashtbl[hashval].nfb_count);
spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock);
- atomic_long_inc(&nfsd_filecache_count);
+ if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD)
+ nfsd_file_gc();
nf->nf_mark = nfsd_file_mark_find_or_create(nf);
if (nf->nf_mark)
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 851d9abf54c2..7872df5a0fe3 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -19,7 +19,7 @@
*/
struct nfsd_file_mark {
struct fsnotify_mark nfm_mark;
- atomic_t nfm_ref;
+ refcount_t nfm_ref;
};
/*
@@ -43,14 +43,17 @@ struct nfsd_file {
unsigned long nf_flags;
struct inode *nf_inode;
unsigned int nf_hashval;
- atomic_t nf_ref;
+ refcount_t nf_ref;
unsigned char nf_may;
struct nfsd_file_mark *nf_mark;
+ struct rw_semaphore nf_rwsem;
};
int nfsd_file_cache_init(void);
void nfsd_file_cache_purge(struct net *);
void nfsd_file_cache_shutdown(void);
+int nfsd_file_cache_start_net(struct net *net);
+void nfsd_file_cache_shutdown_net(struct net *net);
void nfsd_file_put(struct nfsd_file *nf);
struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
void nfsd_file_close_inode_sync(struct inode *inode);
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 9a4ef815fb8c..2baf32311e00 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -40,7 +40,7 @@ struct nfsd_net {
struct lock_manager nfsd4_manager;
bool grace_ended;
- time_t boot_time;
+ time64_t boot_time;
/* internal mount of the "nfsd" pseudofilesystem: */
struct vfsmount *nfsd_mnt;
@@ -92,8 +92,8 @@ struct nfsd_net {
bool in_grace;
const struct nfsd4_client_tracking_ops *client_tracking_ops;
- time_t nfsd4_lease;
- time_t nfsd4_grace;
+ time64_t nfsd4_lease;
+ time64_t nfsd4_grace;
bool somebody_reclaimed;
bool track_reclaim_completes;
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index cea68d8411ac..288bc76b4574 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -203,7 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
RETURN_STATUS(nfserr_io);
nfserr = nfsd_write(rqstp, &resp->fh, argp->offset,
rqstp->rq_vec, nvecs, &cnt,
- resp->committed);
+ resp->committed, resp->verf);
resp->count = cnt;
RETURN_STATUS(nfserr);
}
@@ -683,7 +683,8 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
RETURN_STATUS(nfserr_inval);
fh_copy(&resp->fh, &argp->fh);
- nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count);
+ nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count,
+ resp->verf);
RETURN_STATUS(nfserr);
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 195ab7a0fc89..aae514d40b64 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -32,14 +32,14 @@ static u32 nfs3_ftypes[] = {
* XDR functions for basic NFS types
*/
static __be32 *
-encode_time3(__be32 *p, struct timespec *time)
+encode_time3(__be32 *p, struct timespec64 *time)
{
*p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec);
return p;
}
static __be32 *
-decode_time3(__be32 *p, struct timespec *time)
+decode_time3(__be32 *p, struct timespec64 *time)
{
time->tv_sec = ntohl(*p++);
time->tv_nsec = ntohl(*p++);
@@ -167,7 +167,6 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
struct kstat *stat)
{
struct user_namespace *userns = nfsd_user_namespace(rqstp);
- struct timespec ts;
*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
*p++ = htonl((u32) (stat->mode & S_IALLUGO));
*p++ = htonl((u32) stat->nlink);
@@ -183,12 +182,9 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
*p++ = htonl((u32) MINOR(stat->rdev));
p = encode_fsid(p, fhp);
p = xdr_encode_hyper(p, stat->ino);
- ts = timespec64_to_timespec(stat->atime);
- p = encode_time3(p, &ts);
- ts = timespec64_to_timespec(stat->mtime);
- p = encode_time3(p, &ts);
- ts = timespec64_to_timespec(stat->ctime);
- p = encode_time3(p, &ts);
+ p = encode_time3(p, &stat->atime);
+ p = encode_time3(p, &stat->mtime);
+ p = encode_time3(p, &stat->ctime);
return p;
}
@@ -277,8 +273,8 @@ void fill_pre_wcc(struct svc_fh *fhp)
stat.size = inode->i_size;
}
- fhp->fh_pre_mtime = timespec64_to_timespec(stat.mtime);
- fhp->fh_pre_ctime = timespec64_to_timespec(stat.ctime);
+ fhp->fh_pre_mtime = stat.mtime;
+ fhp->fh_pre_ctime = stat.ctime;
fhp->fh_pre_size = stat.size;
fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
fhp->fh_pre_saved = true;
@@ -330,7 +326,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp));
if ((args->check_guard = ntohl(*p++)) != 0) {
- struct timespec time;
+ struct timespec64 time;
p = decode_time3(p, &time);
args->guardtime = time.tv_sec;
}
@@ -751,17 +747,13 @@ int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd3_writeres *resp = rqstp->rq_resp;
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- __be32 verf[2];
p = encode_wcc_data(rqstp, p, &resp->fh);
if (resp->status == 0) {
*p++ = htonl(resp->count);
*p++ = htonl(resp->committed);
- /* unique identifier, y2038 overflow can be ignored */
- nfsd_copy_boot_verifier(verf, nn);
- *p++ = verf[0];
- *p++ = verf[1];
+ *p++ = resp->verf[0];
+ *p++ = resp->verf[1];
}
return xdr_ressize_check(rqstp, p);
}
@@ -1125,16 +1117,12 @@ int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd3_commitres *resp = rqstp->rq_resp;
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- __be32 verf[2];
p = encode_wcc_data(rqstp, p, &resp->fh);
/* Write verifier */
if (resp->status == 0) {
- /* unique identifier, y2038 overflow can be ignored */
- nfsd_copy_boot_verifier(verf, nn);
- *p++ = verf[0];
- *p++ = verf[1];
+ *p++ = resp->verf[0];
+ *p++ = resp->verf[1];
}
return xdr_ressize_check(rqstp, p);
}
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 24534db87e86..c3b11a715082 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -823,7 +823,16 @@ static const struct rpc_program cb_program = {
static int max_cb_time(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
+
+ /*
+ * nfsd4_lease is set to at most one hour in __nfsd4_write_time,
+ * so we can use 32-bit math on it. Warn if that assumption
+ * ever stops being true.
+ */
+ if (WARN_ON_ONCE(nn->nfsd4_lease > 3600))
+ return 360 * HZ;
+
+ return max(((u32)nn->nfsd4_lease)/10, 1u) * HZ;
}
static struct workqueue_struct *callback_wq;
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 2681c70283ce..e12409eca7cc 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -675,7 +675,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
/* Client gets 2 lease periods to return it */
cutoff = ktime_add_ns(task->tk_start,
- nn->nfsd4_lease * NSEC_PER_SEC * 2);
+ (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2);
if (ktime_before(now, cutoff)) {
rpc_delay(task, HZ/100); /* 10 mili-seconds */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4798667af647..0e75f7fb5fec 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -37,6 +37,7 @@
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/kthread.h>
+#include <linux/sunrpc/addr.h>
#include "idmap.h"
#include "cache.h"
@@ -232,7 +233,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
if (!*resfh)
return nfserr_jukebox;
fh_init(*resfh, NFS4_FHSIZE);
- open->op_truncate = 0;
+ open->op_truncate = false;
if (open->op_create) {
/* FIXME: check session persistence and pnfs flags.
@@ -365,7 +366,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
return nfserr_inval;
- open->op_created = 0;
+ open->op_created = false;
/*
* RFC5661 18.51.3
* Before RECLAIM_COMPLETE done, server should deny new lock
@@ -503,12 +504,20 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_putfh *putfh = &u->putfh;
+ __be32 ret;
fh_put(&cstate->current_fh);
cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
putfh->pf_fhlen);
- return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
+ ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+ if (ret == nfserr_stale && putfh->no_verify) {
+ SET_FH_FLAG(&cstate->current_fh, NFSD4_FH_FOREIGN);
+ ret = 0;
+ }
+#endif
+ return ret;
}
static __be32
@@ -530,9 +539,9 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_restorefh;
fh_dup2(&cstate->current_fh, &cstate->save_fh);
- if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) {
+ if (HAS_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG)) {
memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
- SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+ SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
}
return nfs_ok;
}
@@ -542,9 +551,9 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
fh_dup2(&cstate->save_fh, &cstate->current_fh);
- if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) {
+ if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG)) {
memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
- SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG);
+ SET_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG);
}
return nfs_ok;
}
@@ -581,9 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct nfsd4_commit *commit = &u->commit;
- gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp));
return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
- commit->co_count);
+ commit->co_count,
+ (__be32 *)commit->co_verf.data);
}
static __be32
@@ -776,7 +785,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
&read->rd_stateid, RD_STATE,
- &read->rd_nf);
+ &read->rd_nf, NULL);
if (status) {
dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
goto out;
@@ -948,7 +957,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
status = nfs4_preprocess_stateid_op(rqstp, cstate,
&cstate->current_fh, &setattr->sa_stateid,
- WR_STATE, NULL);
+ WR_STATE, NULL, NULL);
if (status) {
dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
return status;
@@ -975,7 +984,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
- 0, (time_t)0);
+ 0, (time64_t)0);
out:
fh_drop_write(&cstate->current_fh);
return status;
@@ -999,22 +1008,22 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
trace_nfsd_write_start(rqstp, &cstate->current_fh,
write->wr_offset, cnt);
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
- stateid, WR_STATE, &nf);
+ stateid, WR_STATE, &nf, NULL);
if (status) {
dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
return status;
}
write->wr_how_written = write->wr_stable_how;
- gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp));
nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist,
&write->wr_head, write->wr_buflen);
WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
- status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf->nf_file,
+ status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
- write->wr_how_written);
+ write->wr_how_written,
+ (__be32 *)write->wr_verifier.data);
nfsd_file_put(nf);
write->wr_bytes_written = cnt;
@@ -1034,14 +1043,14 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_nofilehandle;
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
- src_stateid, RD_STATE, src);
+ src_stateid, RD_STATE, src, NULL);
if (status) {
dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
goto out;
}
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
- dst_stateid, WR_STATE, dst);
+ dst_stateid, WR_STATE, dst, NULL);
if (status) {
dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
goto out_put_src;
@@ -1076,8 +1085,8 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
- status = nfsd4_clone_file_range(src->nf_file, clone->cl_src_pos,
- dst->nf_file, clone->cl_dst_pos, clone->cl_count,
+ status = nfsd4_clone_file_range(src, clone->cl_src_pos,
+ dst, clone->cl_dst_pos, clone->cl_count,
EX_ISSYNC(cstate->current_fh.fh_export));
nfsd_file_put(dst);
@@ -1135,6 +1144,207 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp)
while ((copy = nfsd4_get_copy(clp)) != NULL)
nfsd4_stop_copy(copy);
}
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+
+extern struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+ struct nfs_fh *src_fh,
+ nfs4_stateid *stateid);
+extern void nfs42_ssc_close(struct file *filep);
+
+extern void nfs_sb_deactive(struct super_block *sb);
+
+#define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys"
+
+/**
+ * Support one copy source server for now.
+ */
+static __be32
+nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp,
+ struct vfsmount **mount)
+{
+ struct file_system_type *type;
+ struct vfsmount *ss_mnt;
+ struct nfs42_netaddr *naddr;
+ struct sockaddr_storage tmp_addr;
+ size_t tmp_addrlen, match_netid_len = 3;
+ char *startsep = "", *endsep = "", *match_netid = "tcp";
+ char *ipaddr, *dev_name, *raw_data;
+ int len, raw_len;
+ __be32 status = nfserr_inval;
+
+ naddr = &nss->u.nl4_addr;
+ tmp_addrlen = rpc_uaddr2sockaddr(SVC_NET(rqstp), naddr->addr,
+ naddr->addr_len,
+ (struct sockaddr *)&tmp_addr,
+ sizeof(tmp_addr));
+ if (tmp_addrlen == 0)
+ goto out_err;
+
+ if (tmp_addr.ss_family == AF_INET6) {
+ startsep = "[";
+ endsep = "]";
+ match_netid = "tcp6";
+ match_netid_len = 4;
+ }
+
+ if (naddr->netid_len != match_netid_len ||
+ strncmp(naddr->netid, match_netid, naddr->netid_len))
+ goto out_err;
+
+ /* Construct the raw data for the vfs_kern_mount call */
+ len = RPC_MAX_ADDRBUFLEN + 1;
+ ipaddr = kzalloc(len, GFP_KERNEL);
+ if (!ipaddr)
+ goto out_err;
+
+ rpc_ntop((struct sockaddr *)&tmp_addr, ipaddr, len);
+
+ /* 2 for ipv6 endsep and startsep. 3 for ":/" and trailing '/0'*/
+
+ raw_len = strlen(NFSD42_INTERSSC_MOUNTOPS) + strlen(ipaddr);
+ raw_data = kzalloc(raw_len, GFP_KERNEL);
+ if (!raw_data)
+ goto out_free_ipaddr;
+
+ snprintf(raw_data, raw_len, NFSD42_INTERSSC_MOUNTOPS, ipaddr);
+
+ status = nfserr_nodev;
+ type = get_fs_type("nfs");
+ if (!type)
+ goto out_free_rawdata;
+
+ /* Set the server:<export> for the vfs_kern_mount call */
+ dev_name = kzalloc(len + 5, GFP_KERNEL);
+ if (!dev_name)
+ goto out_free_rawdata;
+ snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep);
+
+ /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */
+ ss_mnt = vfs_kern_mount(type, SB_KERNMOUNT, dev_name, raw_data);
+ module_put(type->owner);
+ if (IS_ERR(ss_mnt))
+ goto out_free_devname;
+
+ status = 0;
+ *mount = ss_mnt;
+
+out_free_devname:
+ kfree(dev_name);
+out_free_rawdata:
+ kfree(raw_data);
+out_free_ipaddr:
+ kfree(ipaddr);
+out_err:
+ return status;
+}
+
+static void
+nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
+{
+ nfs_sb_deactive(ss_mnt->mnt_sb);
+ mntput(ss_mnt);
+}
+
+/**
+ * nfsd4_setup_inter_ssc
+ *
+ * Verify COPY destination stateid.
+ * Connect to the source server with NFSv4.1.
+ * Create the source struct file for nfsd_copy_range.
+ * Called with COPY cstate:
+ * SAVED_FH: source filehandle
+ * CURRENT_FH: destination filehandle
+ */
+static __be32
+nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_copy *copy, struct vfsmount **mount)
+{
+ struct svc_fh *s_fh = NULL;
+ stateid_t *s_stid = &copy->cp_src_stateid;
+ __be32 status = nfserr_inval;
+
+ /* Verify the destination stateid and set dst struct file*/
+ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+ &copy->cp_dst_stateid,
+ WR_STATE, &copy->nf_dst, NULL);
+ if (status)
+ goto out;
+
+ status = nfsd4_interssc_connect(&copy->cp_src, rqstp, mount);
+ if (status)
+ goto out;
+
+ s_fh = &cstate->save_fh;
+
+ copy->c_fh.size = s_fh->fh_handle.fh_size;
+ memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size);
+ copy->stateid.seqid = cpu_to_be32(s_stid->si_generation);
+ memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
+ sizeof(stateid_opaque_t));
+
+ status = 0;
+out:
+ return status;
+}
+
+static void
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
+ struct nfsd_file *dst)
+{
+ nfs42_ssc_close(src->nf_file);
+ nfsd_file_put(src);
+ nfsd_file_put(dst);
+ mntput(ss_mnt);
+}
+
+#else /* CONFIG_NFSD_V4_2_INTER_SSC */
+
+static __be32
+nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_copy *copy,
+ struct vfsmount **mount)
+{
+ *mount = NULL;
+ return nfserr_inval;
+}
+
+static void
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
+ struct nfsd_file *dst)
+{
+}
+
+static void
+nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
+{
+}
+
+static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+ struct nfs_fh *src_fh,
+ nfs4_stateid *stateid)
+{
+ return NULL;
+}
+#endif /* CONFIG_NFSD_V4_2_INTER_SSC */
+
+static __be32
+nfsd4_setup_intra_ssc(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_copy *copy)
+{
+ return nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
+ &copy->nf_src, &copy->cp_dst_stateid,
+ &copy->nf_dst);
+}
+
+static void
+nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst)
+{
+ nfsd_file_put(src);
+ nfsd_file_put(dst);
+}
static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
{
@@ -1200,12 +1410,16 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
status = nfs_ok;
}
- nfsd_file_put(copy->nf_src);
- nfsd_file_put(copy->nf_dst);
+ if (!copy->cp_intra) /* Inter server SSC */
+ nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src,
+ copy->nf_dst);
+ else
+ nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
+
return status;
}
-static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
+static int dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
{
dst->cp_src_pos = src->cp_src_pos;
dst->cp_dst_pos = src->cp_dst_pos;
@@ -1215,15 +1429,25 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
memcpy(&dst->fh, &src->fh, sizeof(src->fh));
dst->cp_clp = src->cp_clp;
dst->nf_dst = nfsd_file_get(src->nf_dst);
- dst->nf_src = nfsd_file_get(src->nf_src);
+ dst->cp_intra = src->cp_intra;
+ if (src->cp_intra) /* for inter, file_src doesn't exist yet */
+ dst->nf_src = nfsd_file_get(src->nf_src);
+
memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid));
+ memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server));
+ memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid));
+ memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh));
+ dst->ss_mnt = src->ss_mnt;
+
+ return 0;
}
static void cleanup_async_copy(struct nfsd4_copy *copy)
{
- nfs4_free_cp_state(copy);
+ nfs4_free_copy_state(copy);
nfsd_file_put(copy->nf_dst);
- nfsd_file_put(copy->nf_src);
+ if (copy->cp_intra)
+ nfsd_file_put(copy->nf_src);
spin_lock(&copy->cp_clp->async_lock);
list_del(&copy->copies);
spin_unlock(&copy->cp_clp->async_lock);
@@ -1235,7 +1459,24 @@ static int nfsd4_do_async_copy(void *data)
struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
struct nfsd4_copy *cb_copy;
+ if (!copy->cp_intra) { /* Inter server SSC */
+ copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL);
+ if (!copy->nf_src) {
+ copy->nfserr = nfserr_serverfault;
+ nfsd4_interssc_disconnect(copy->ss_mnt);
+ goto do_callback;
+ }
+ copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
+ &copy->stateid);
+ if (IS_ERR(copy->nf_src->nf_file)) {
+ copy->nfserr = nfserr_offload_denied;
+ nfsd4_interssc_disconnect(copy->ss_mnt);
+ goto do_callback;
+ }
+ }
+
copy->nfserr = nfsd4_do_copy(copy, 0);
+do_callback:
cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
if (!cb_copy)
goto out;
@@ -1247,6 +1488,8 @@ static int nfsd4_do_async_copy(void *data)
&nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD);
nfsd4_run_cb(&cb_copy->cp_cb);
out:
+ if (!copy->cp_intra)
+ kfree(copy->nf_src);
cleanup_async_copy(copy);
return 0;
}
@@ -1259,11 +1502,20 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfsd4_copy *async_copy = NULL;
- status = nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
- &copy->nf_src, &copy->cp_dst_stateid,
- &copy->nf_dst);
- if (status)
- goto out;
+ if (!copy->cp_intra) { /* Inter server SSC */
+ if (!inter_copy_offload_enable || copy->cp_synchronous) {
+ status = nfserr_notsupp;
+ goto out;
+ }
+ status = nfsd4_setup_inter_ssc(rqstp, cstate, copy,
+ &copy->ss_mnt);
+ if (status)
+ return nfserr_offload_denied;
+ } else {
+ status = nfsd4_setup_intra_ssc(rqstp, cstate, copy);
+ if (status)
+ return status;
+ }
copy->cp_clp = cstate->clp;
memcpy(&copy->fh, &cstate->current_fh.fh_handle,
@@ -1274,15 +1526,15 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfserrno(-ENOMEM);
async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
if (!async_copy)
- goto out;
- if (!nfs4_init_cp_state(nn, copy)) {
- kfree(async_copy);
- goto out;
- }
+ goto out_err;
+ if (!nfs4_init_copy_state(nn, copy))
+ goto out_err;
refcount_set(&async_copy->refcount, 1);
memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid,
sizeof(copy->cp_stateid));
- dup_copy_fields(copy, async_copy);
+ status = dup_copy_fields(copy, async_copy);
+ if (status)
+ goto out_err;
async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
async_copy, "%s", "copy thread");
if (IS_ERR(async_copy->copy_task))
@@ -1293,13 +1545,17 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
spin_unlock(&async_copy->cp_clp->async_lock);
wake_up_process(async_copy->copy_task);
status = nfs_ok;
- } else
+ } else {
status = nfsd4_do_copy(copy, 1);
+ }
out:
return status;
out_err:
if (async_copy)
cleanup_async_copy(async_copy);
+ status = nfserrno(-ENOMEM);
+ if (!copy->cp_intra)
+ nfsd4_interssc_disconnect(copy->ss_mnt);
goto out;
}
@@ -1310,7 +1566,7 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid)
spin_lock(&clp->async_lock);
list_for_each_entry(copy, &clp->async_copies, copies) {
- if (memcmp(&copy->cp_stateid, stateid, NFS4_STATEID_SIZE))
+ if (memcmp(&copy->cp_stateid.stid, stateid, NFS4_STATEID_SIZE))
continue;
refcount_inc(&copy->refcount);
spin_unlock(&clp->async_lock);
@@ -1326,16 +1582,61 @@ nfsd4_offload_cancel(struct svc_rqst *rqstp,
union nfsd4_op_u *u)
{
struct nfsd4_offload_status *os = &u->offload_status;
- __be32 status = 0;
struct nfsd4_copy *copy;
struct nfs4_client *clp = cstate->clp;
copy = find_async_copy(clp, &os->stateid);
- if (copy)
+ if (!copy) {
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+ return manage_cpntf_state(nn, &os->stateid, clp, NULL);
+ } else
nfsd4_stop_copy(copy);
- else
- status = nfserr_bad_stateid;
+ return nfs_ok;
+}
+
+static __be32
+nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+ union nfsd4_op_u *u)
+{
+ struct nfsd4_copy_notify *cn = &u->copy_notify;
+ __be32 status;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfs4_stid *stid;
+ struct nfs4_cpntf_state *cps;
+ struct nfs4_client *clp = cstate->clp;
+
+ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+ &cn->cpn_src_stateid, RD_STATE, NULL,
+ &stid);
+ if (status)
+ return status;
+
+ cn->cpn_sec = nn->nfsd4_lease;
+ cn->cpn_nsec = 0;
+
+ status = nfserrno(-ENOMEM);
+ cps = nfs4_alloc_init_cpntf_state(nn, stid);
+ if (!cps)
+ goto out;
+ memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t));
+ memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t));
+ memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t));
+
+ /* For now, only return one server address in cpn_src, the
+ * address used by the client to connect to this server.
+ */
+ cn->cpn_src.nl4_type = NL4_NETADDR;
+ status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr,
+ &cn->cpn_src.u.nl4_addr);
+ WARN_ON_ONCE(status);
+ if (status) {
+ nfs4_put_cpntf_state(nn, cps);
+ goto out;
+ }
+out:
+ nfs4_put_stid(stid);
return status;
}
@@ -1348,7 +1649,7 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
&fallocate->falloc_stateid,
- WR_STATE, &nf);
+ WR_STATE, &nf, NULL);
if (status != nfs_ok) {
dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
return status;
@@ -1407,7 +1708,7 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
&seek->seek_stateid,
- RD_STATE, &nf);
+ RD_STATE, &nf, NULL);
if (status) {
dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
return status;
@@ -1912,6 +2213,45 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
- rqstp->rq_auth_slack;
}
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+static void
+check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
+{
+ struct nfsd4_op *op, *current_op = NULL, *saved_op = NULL;
+ struct nfsd4_copy *copy;
+ struct nfsd4_putfh *putfh;
+ int i;
+
+ /* traverse all operation and if it's a COPY compound, mark the
+ * source filehandle to skip verification
+ */
+ for (i = 0; i < args->opcnt; i++) {
+ op = &args->ops[i];
+ if (op->opnum == OP_PUTFH)
+ current_op = op;
+ else if (op->opnum == OP_SAVEFH)
+ saved_op = current_op;
+ else if (op->opnum == OP_RESTOREFH)
+ current_op = saved_op;
+ else if (op->opnum == OP_COPY) {
+ copy = (struct nfsd4_copy *)&op->u;
+ if (!saved_op) {
+ op->status = nfserr_nofilehandle;
+ return;
+ }
+ putfh = (struct nfsd4_putfh *)&saved_op->u;
+ if (!copy->cp_intra)
+ putfh->no_verify = true;
+ }
+ }
+}
+#else
+static void
+check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
+{
+}
+#endif
+
/*
* COMPOUND call.
*/
@@ -1960,6 +2300,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
resp->opcnt = 1;
goto encode_op;
}
+ check_if_stalefh_allowed(args);
trace_nfsd_compound(rqstp, args->opcnt);
while (!status && resp->opcnt < args->opcnt) {
@@ -1975,13 +2316,14 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
op->status = nfsd4_open_omfg(rqstp, cstate, op);
goto encode_op;
}
-
- if (!current_fh->fh_dentry) {
+ if (!current_fh->fh_dentry &&
+ !HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) {
if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
op->status = nfserr_nofilehandle;
goto encode_op;
}
- } else if (current_fh->fh_export->ex_fslocs.migrated &&
+ } else if (current_fh->fh_export &&
+ current_fh->fh_export->ex_fslocs.migrated &&
!(op->opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) {
op->status = nfserr_moved;
goto encode_op;
@@ -2025,7 +2367,8 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
if (op->opdesc->op_flags & OP_CLEAR_STATEID)
clear_current_stateid(cstate);
- if (need_wrongsec_check(rqstp))
+ if (current_fh->fh_export &&
+ need_wrongsec_check(rqstp))
op->status = check_nfsd_access(current_fh->fh_export, rqstp);
}
encode_op:
@@ -2292,6 +2635,21 @@ static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp,
1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32);
}
+static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp,
+ struct nfsd4_op *op)
+{
+ return (op_encode_hdr_size +
+ 3 /* cnr_lease_time */ +
+ 1 /* We support one cnr_source_server */ +
+ 1 /* cnr_stateid seq */ +
+ op_encode_stateid_maxsz /* cnr_stateid */ +
+ 1 /* num cnr_source_server*/ +
+ 1 /* nl4_type */ +
+ 1 /* nl4 size */ +
+ XDR_QUADLEN(NFS4_OPAQUE_LIMIT) /*nl4_loc + nl4_loc_sz */)
+ * sizeof(__be32);
+}
+
#ifdef CONFIG_NFSD_PNFS
static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
@@ -2716,6 +3074,12 @@ static const struct nfsd4_operation nfsd4_ops[] = {
.op_name = "OP_OFFLOAD_CANCEL",
.op_rsize_bop = nfsd4_only_status_rsize,
},
+ [OP_COPY_NOTIFY] = {
+ .op_func = nfsd4_copy_notify,
+ .op_flags = OP_MODIFIES_SOMETHING,
+ .op_name = "OP_COPY_NOTIFY",
+ .op_rsize_bop = nfsd4_copy_notify_rsize,
+ },
};
/**
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 2481e7662128..a8fb18609146 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1445,7 +1445,7 @@ nfsd4_cld_grace_done_v0(struct nfsd_net *nn)
}
cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone;
- cup->cu_u.cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time;
+ cup->cu_u.cu_msg.cm_u.cm_gracetime = nn->boot_time;
ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
if (!ret)
ret = cup->cu_u.cu_msg.cm_status;
@@ -1782,7 +1782,7 @@ nfsd4_cltrack_client_has_session(struct nfs4_client *clp)
}
static char *
-nfsd4_cltrack_grace_start(time_t grace_start)
+nfsd4_cltrack_grace_start(time64_t grace_start)
{
int copied;
size_t len;
@@ -1795,7 +1795,7 @@ nfsd4_cltrack_grace_start(time_t grace_start)
if (!result)
return result;
- copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld",
+ copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%lld",
grace_start);
if (copied >= len) {
/* just return nothing if output was truncated */
@@ -2004,7 +2004,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
char *legacy;
char timestr[22]; /* FIXME: better way to determine max size? */
- sprintf(timestr, "%ld", nn->boot_time);
+ sprintf(timestr, "%lld", nn->boot_time);
legacy = nfsd4_cltrack_legacy_topdir();
nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL);
kfree(legacy);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 369e574c5092..65cfe9ab47be 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -80,6 +80,7 @@ static u64 current_sessionid = 1;
static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
void nfsd4_end_grace(struct nfsd_net *nn);
+static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
/* Locking: */
@@ -170,7 +171,7 @@ renew_client_locked(struct nfs4_client *clp)
clp->cl_clientid.cl_boot,
clp->cl_clientid.cl_id);
list_move_tail(&clp->cl_lru, &nn->client_lru);
- clp->cl_time = get_seconds();
+ clp->cl_time = ktime_get_boottime_seconds();
}
static void put_client_renew_locked(struct nfs4_client *clp)
@@ -722,6 +723,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla
/* Will be incremented before return to client: */
refcount_set(&stid->sc_count, 1);
spin_lock_init(&stid->sc_lock);
+ INIT_LIST_HEAD(&stid->sc_cp_list);
/*
* It shouldn't be a problem to reuse an opaque stateid value.
@@ -741,30 +743,76 @@ out_free:
/*
* Create a unique stateid_t to represent each COPY.
*/
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
+ unsigned char sc_type)
{
int new_id;
+ stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
+ stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+ stid->sc_type = sc_type;
+
idr_preload(GFP_KERNEL);
spin_lock(&nn->s2s_cp_lock);
- new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, copy, 0, 0, GFP_NOWAIT);
+ new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
+ stid->stid.si_opaque.so_id = new_id;
spin_unlock(&nn->s2s_cp_lock);
idr_preload_end();
if (new_id < 0)
return 0;
- copy->cp_stateid.si_opaque.so_id = new_id;
- copy->cp_stateid.si_opaque.so_clid.cl_boot = nn->boot_time;
- copy->cp_stateid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
return 1;
}
-void nfs4_free_cp_state(struct nfsd4_copy *copy)
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+{
+ return nfs4_init_cp_state(nn, &copy->cp_stateid, NFS4_COPY_STID);
+}
+
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+ struct nfs4_stid *p_stid)
+{
+ struct nfs4_cpntf_state *cps;
+
+ cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL);
+ if (!cps)
+ return NULL;
+ cps->cpntf_time = ktime_get_boottime_seconds();
+ refcount_set(&cps->cp_stateid.sc_count, 1);
+ if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
+ goto out_free;
+ spin_lock(&nn->s2s_cp_lock);
+ list_add(&cps->cp_list, &p_stid->sc_cp_list);
+ spin_unlock(&nn->s2s_cp_lock);
+ return cps;
+out_free:
+ kfree(cps);
+ return NULL;
+}
+
+void nfs4_free_copy_state(struct nfsd4_copy *copy)
{
struct nfsd_net *nn;
+ WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
nn = net_generic(copy->cp_clp->net, nfsd_net_id);
spin_lock(&nn->s2s_cp_lock);
- idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.si_opaque.so_id);
+ idr_remove(&nn->s2s_cp_stateids,
+ copy->cp_stateid.stid.si_opaque.so_id);
+ spin_unlock(&nn->s2s_cp_lock);
+}
+
+static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid)
+{
+ struct nfs4_cpntf_state *cps;
+ struct nfsd_net *nn;
+
+ nn = net_generic(net, nfsd_net_id);
+ spin_lock(&nn->s2s_cp_lock);
+ while (!list_empty(&stid->sc_cp_list)) {
+ cps = list_first_entry(&stid->sc_cp_list,
+ struct nfs4_cpntf_state, cp_list);
+ _free_cpntf_state_locked(nn, cps);
+ }
spin_unlock(&nn->s2s_cp_lock);
}
@@ -806,7 +854,7 @@ static void nfs4_free_deleg(struct nfs4_stid *stid)
static DEFINE_SPINLOCK(blocked_delegations_lock);
static struct bloom_pair {
int entries, old_entries;
- time_t swap_time;
+ time64_t swap_time;
int new; /* index into 'set' */
DECLARE_BITMAP(set[2], 256);
} blocked_delegations;
@@ -818,15 +866,15 @@ static int delegation_blocked(struct knfsd_fh *fh)
if (bd->entries == 0)
return 0;
- if (seconds_since_boot() - bd->swap_time > 30) {
+ if (ktime_get_seconds() - bd->swap_time > 30) {
spin_lock(&blocked_delegations_lock);
- if (seconds_since_boot() - bd->swap_time > 30) {
+ if (ktime_get_seconds() - bd->swap_time > 30) {
bd->entries -= bd->old_entries;
bd->old_entries = bd->entries;
memset(bd->set[bd->new], 0,
sizeof(bd->set[0]));
bd->new = 1-bd->new;
- bd->swap_time = seconds_since_boot();
+ bd->swap_time = ktime_get_seconds();
}
spin_unlock(&blocked_delegations_lock);
}
@@ -856,7 +904,7 @@ static void block_delegations(struct knfsd_fh *fh)
__set_bit((hash>>8)&255, bd->set[bd->new]);
__set_bit((hash>>16)&255, bd->set[bd->new]);
if (bd->entries == 0)
- bd->swap_time = seconds_since_boot();
+ bd->swap_time = ktime_get_seconds();
bd->entries += 1;
spin_unlock(&blocked_delegations_lock);
}
@@ -915,6 +963,7 @@ nfs4_put_stid(struct nfs4_stid *s)
return;
}
idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+ nfs4_free_cpntf_statelist(clp->net, s);
spin_unlock(&clp->cl_lock);
s->sc_free(s);
if (fp)
@@ -1862,7 +1911,7 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
*/
if (clid->cl_boot == (u32)nn->boot_time)
return 0;
- dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
+ dprintk("NFSD stale clientid (%08x/%08x) boot_time %08llx\n",
clid->cl_boot, clid->cl_id, nn->boot_time);
return 1;
}
@@ -2215,14 +2264,14 @@ static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn)
* This is opaque to client, so no need to byte-swap. Use
* __force to keep sparse happy
*/
- verf[0] = (__force __be32)get_seconds();
+ verf[0] = (__force __be32)(u32)ktime_get_real_seconds();
verf[1] = (__force __be32)nn->clverifier_counter++;
memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}
static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
{
- clp->cl_clientid.cl_boot = nn->boot_time;
+ clp->cl_clientid.cl_boot = (u32)nn->boot_time;
clp->cl_clientid.cl_id = nn->clientid_counter++;
gen_confirm(clp, nn);
}
@@ -2292,7 +2341,7 @@ static int client_info_show(struct seq_file *m, void *v)
clp->cl_nii_domain.len);
seq_printf(m, "\nImplementation name: ");
seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len);
- seq_printf(m, "\nImplementation time: [%ld, %ld]\n",
+ seq_printf(m, "\nImplementation time: [%lld, %ld]\n",
clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec);
}
drop_client(clp);
@@ -2612,7 +2661,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
gen_clid(clp, nn);
kref_init(&clp->cl_nfsdfs.cl_ref);
nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
- clp->cl_time = get_seconds();
+ clp->cl_time = ktime_get_boottime_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
copy_verf(clp, verf);
memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
@@ -2946,8 +2995,7 @@ static __be32 copy_impl_id(struct nfs4_client *clp,
xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL);
if (!clp->cl_nii_name.data)
return nfserr_jukebox;
- clp->cl_nii_time.tv_sec = exid->nii_time.tv_sec;
- clp->cl_nii_time.tv_nsec = exid->nii_time.tv_nsec;
+ clp->cl_nii_time = exid->nii_time;
return 0;
}
@@ -3373,7 +3421,7 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir)
case NFS4_CDFC4_BACK_OR_BOTH:
*dir = NFS4_CDFC4_BOTH;
return nfs_ok;
- };
+ }
return nfserr_inval;
}
@@ -4283,7 +4331,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
last = oo->oo_last_closed_stid;
oo->oo_last_closed_stid = s;
list_move_tail(&oo->oo_close_lru, &nn->close_lru);
- oo->oo_time = get_seconds();
+ oo->oo_time = ktime_get_boottime_seconds();
spin_unlock(&nn->client_lock);
if (last)
nfs4_put_stid(&last->st_stid);
@@ -4378,7 +4426,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
*/
spin_lock(&state_lock);
if (dp->dl_time == 0) {
- dp->dl_time = get_seconds();
+ dp->dl_time = ktime_get_boottime_seconds();
list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
}
spin_unlock(&state_lock);
@@ -4490,7 +4538,8 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
static __be32 lookup_clientid(clientid_t *clid,
struct nfsd4_compound_state *cstate,
- struct nfsd_net *nn)
+ struct nfsd_net *nn,
+ bool sessions)
{
struct nfs4_client *found;
@@ -4511,7 +4560,7 @@ static __be32 lookup_clientid(clientid_t *clid,
*/
WARN_ON_ONCE(cstate->session);
spin_lock(&nn->client_lock);
- found = find_confirmed_client(clid, false, nn);
+ found = find_confirmed_client(clid, sessions, nn);
if (!found) {
spin_unlock(&nn->client_lock);
return nfserr_expired;
@@ -4544,7 +4593,7 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
if (open->op_file == NULL)
return nfserr_jukebox;
- status = lookup_clientid(clientid, cstate, nn);
+ status = lookup_clientid(clientid, cstate, nn, false);
if (status)
return status;
clp = cstate->clp;
@@ -4672,7 +4721,7 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
return 0;
if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
return nfserr_inval;
- return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0);
+ return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0);
}
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
@@ -5133,7 +5182,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
dprintk("process_renew(%08x/%08x): starting\n",
clid->cl_boot, clid->cl_id);
- status = lookup_clientid(clid, cstate, nn);
+ status = lookup_clientid(clid, cstate, nn, false);
if (status)
goto out;
clp = cstate->clp;
@@ -5184,9 +5233,8 @@ nfsd4_end_grace(struct nfsd_net *nn)
*/
static bool clients_still_reclaiming(struct nfsd_net *nn)
{
- unsigned long now = get_seconds();
- unsigned long double_grace_period_end = nn->boot_time +
- 2 * nn->nfsd4_lease;
+ time64_t double_grace_period_end = nn->boot_time +
+ 2 * nn->nfsd4_lease;
if (nn->track_reclaim_completes &&
atomic_read(&nn->nr_reclaim_complete) ==
@@ -5199,12 +5247,12 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
* If we've given them *two* lease times to reclaim, and they're
* still not done, give up:
*/
- if (time_after(now, double_grace_period_end))
+ if (ktime_get_boottime_seconds() > double_grace_period_end)
return false;
return true;
}
-static time_t
+static time64_t
nfs4_laundromat(struct nfsd_net *nn)
{
struct nfs4_client *clp;
@@ -5213,8 +5261,11 @@ nfs4_laundromat(struct nfsd_net *nn)
struct nfs4_ol_stateid *stp;
struct nfsd4_blocked_lock *nbl;
struct list_head *pos, *next, reaplist;
- time_t cutoff = get_seconds() - nn->nfsd4_lease;
- time_t t, new_timeo = nn->nfsd4_lease;
+ time64_t cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease;
+ time64_t t, new_timeo = nn->nfsd4_lease;
+ struct nfs4_cpntf_state *cps;
+ copy_stateid_t *cps_t;
+ int i;
dprintk("NFSD: laundromat service - starting\n");
@@ -5225,10 +5276,20 @@ nfs4_laundromat(struct nfsd_net *nn)
dprintk("NFSD: end of grace period\n");
nfsd4_end_grace(nn);
INIT_LIST_HEAD(&reaplist);
+
+ spin_lock(&nn->s2s_cp_lock);
+ idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
+ cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
+ if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+ cps->cpntf_time > cutoff)
+ _free_cpntf_state_locked(nn, cps);
+ }
+ spin_unlock(&nn->s2s_cp_lock);
+
spin_lock(&nn->client_lock);
list_for_each_safe(pos, next, &nn->client_lru) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
- if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
+ if (clp->cl_time > cutoff) {
t = clp->cl_time - cutoff;
new_timeo = min(new_timeo, t);
break;
@@ -5251,7 +5312,7 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
- if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) {
+ if (dp->dl_time > cutoff) {
t = dp->dl_time - cutoff;
new_timeo = min(new_timeo, t);
break;
@@ -5271,8 +5332,7 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->close_lru)) {
oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
oo_close_lru);
- if (time_after((unsigned long)oo->oo_time,
- (unsigned long)cutoff)) {
+ if (oo->oo_time > cutoff) {
t = oo->oo_time - cutoff;
new_timeo = min(new_timeo, t);
break;
@@ -5302,8 +5362,7 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->blocked_locks_lru)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
struct nfsd4_blocked_lock, nbl_lru);
- if (time_after((unsigned long)nbl->nbl_time,
- (unsigned long)cutoff)) {
+ if (nbl->nbl_time > cutoff) {
t = nbl->nbl_time - cutoff;
new_timeo = min(new_timeo, t);
break;
@@ -5320,7 +5379,7 @@ nfs4_laundromat(struct nfsd_net *nn)
free_blocked_lock(nbl);
}
out:
- new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
+ new_timeo = max_t(time64_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
return new_timeo;
}
@@ -5330,13 +5389,13 @@ static void laundromat_main(struct work_struct *);
static void
laundromat_main(struct work_struct *laundry)
{
- time_t t;
+ time64_t t;
struct delayed_work *dwork = to_delayed_work(laundry);
struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
laundromat_work);
t = nfs4_laundromat(nn);
- dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t);
+ dprintk("NFSD: laundromat_main - sleeping for %lld seconds\n", t);
queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
}
@@ -5521,7 +5580,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
CLOSE_STATEID(stateid))
return nfserr_bad_stateid;
- status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
+ status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn,
+ false);
if (status == nfserr_stale_clientid) {
if (cstate->session)
return nfserr_bad_stateid;
@@ -5600,6 +5660,85 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
out:
return status;
}
+static void
+_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+ WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
+ if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+ return;
+ list_del(&cps->cp_list);
+ idr_remove(&nn->s2s_cp_stateids,
+ cps->cp_stateid.stid.si_opaque.so_id);
+ kfree(cps);
+}
+/*
+ * A READ from an inter server to server COPY will have a
+ * copy stateid. Look up the copy notify stateid from the
+ * idr structure and take a reference on it.
+ */
+__be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+ struct nfs4_client *clp,
+ struct nfs4_cpntf_state **cps)
+{
+ copy_stateid_t *cps_t;
+ struct nfs4_cpntf_state *state = NULL;
+
+ if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id)
+ return nfserr_bad_stateid;
+ spin_lock(&nn->s2s_cp_lock);
+ cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id);
+ if (cps_t) {
+ state = container_of(cps_t, struct nfs4_cpntf_state,
+ cp_stateid);
+ if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) {
+ state = NULL;
+ goto unlock;
+ }
+ if (!clp)
+ refcount_inc(&state->cp_stateid.sc_count);
+ else
+ _free_cpntf_state_locked(nn, state);
+ }
+unlock:
+ spin_unlock(&nn->s2s_cp_lock);
+ if (!state)
+ return nfserr_bad_stateid;
+ if (!clp && state)
+ *cps = state;
+ return 0;
+}
+
+static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+ struct nfs4_stid **stid)
+{
+ __be32 status;
+ struct nfs4_cpntf_state *cps = NULL;
+ struct nfsd4_compound_state cstate;
+
+ status = manage_cpntf_state(nn, st, NULL, &cps);
+ if (status)
+ return status;
+
+ cps->cpntf_time = ktime_get_boottime_seconds();
+ memset(&cstate, 0, sizeof(cstate));
+ status = lookup_clientid(&cps->cp_p_clid, &cstate, nn, true);
+ if (status)
+ goto out;
+ status = nfsd4_lookup_stateid(&cstate, &cps->cp_p_stateid,
+ NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
+ stid, nn);
+ put_client_renew(cstate.clp);
+out:
+ nfs4_put_cpntf_state(nn, cps);
+ return status;
+}
+
+void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+ spin_lock(&nn->s2s_cp_lock);
+ _free_cpntf_state_locked(nn, cps);
+ spin_unlock(&nn->s2s_cp_lock);
+}
/*
* Checks for stateid operations
@@ -5607,7 +5746,8 @@ out:
__be32
nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
- stateid_t *stateid, int flags, struct nfsd_file **nfp)
+ stateid_t *stateid, int flags, struct nfsd_file **nfp,
+ struct nfs4_stid **cstid)
{
struct inode *ino = d_inode(fhp->fh_dentry);
struct net *net = SVC_NET(rqstp);
@@ -5629,6 +5769,8 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
status = nfsd4_lookup_stateid(cstate, stateid,
NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
&s, nn);
+ if (status == nfserr_bad_stateid)
+ status = find_cpntf_state(nn, stateid, &s);
if (status)
return status;
status = nfsd4_stid_check_stateid_generation(stateid, s,
@@ -5656,8 +5798,12 @@ done:
if (status == nfs_ok && nfp)
status = nfs4_check_file(rqstp, fhp, s, nfp, flags);
out:
- if (s)
- nfs4_put_stid(s);
+ if (s) {
+ if (!status && cstid)
+ *cstid = s;
+ else
+ nfs4_put_stid(s);
+ }
return status;
}
@@ -6550,7 +6696,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
if (fl_flags & FL_SLEEP) {
- nbl->nbl_time = jiffies;
+ nbl->nbl_time = ktime_get_boottime_seconds();
spin_lock(&nn->blocked_locks_lock);
list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
@@ -6657,7 +6803,8 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_inval;
if (!nfsd4_has_session(cstate)) {
- status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
+ status = lookup_clientid(&lockt->lt_clientid, cstate, nn,
+ false);
if (status)
goto out;
}
@@ -6841,7 +6988,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
clid->cl_boot, clid->cl_id);
- status = lookup_clientid(clid, cstate, nn);
+ status = lookup_clientid(clid, cstate, nn, false);
if (status)
return status;
@@ -6988,7 +7135,7 @@ nfs4_check_open_reclaim(clientid_t *clid,
__be32 status;
/* find clientid in conf_id_hashtbl */
- status = lookup_clientid(clid, cstate, nn);
+ status = lookup_clientid(clid, cstate, nn, false);
if (status)
return nfserr_reclaim_bad;
@@ -7641,7 +7788,7 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
nn->conf_name_tree = RB_ROOT;
nn->unconf_name_tree = RB_ROOT;
- nn->boot_time = get_seconds();
+ nn->boot_time = ktime_get_real_seconds();
nn->grace_ended = false;
nn->nfsd4_manager.block_opens = true;
INIT_LIST_HEAD(&nn->nfsd4_manager.list);
@@ -7710,7 +7857,7 @@ nfs4_state_start_net(struct net *net)
nfsd4_client_tracking_init(net);
if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0)
goto skip_grace;
- printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n",
+ printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n",
nn->nfsd4_grace, net->ns.inum);
queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
return 0;
@@ -7786,7 +7933,8 @@ nfs4_state_shutdown(void)
static void
get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
{
- if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid))
+ if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) &&
+ CURRENT_STATEID(stateid))
memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t));
}
@@ -7795,14 +7943,14 @@ put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
{
if (cstate->minorversion) {
memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t));
- SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+ SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
}
}
void
clear_current_stateid(struct nfsd4_compound_state *cstate)
{
- CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+ CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
}
/*
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index d2dc4c0e22e8..9761512674a0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -40,6 +40,7 @@
#include <linux/utsname.h>
#include <linux/pagemap.h>
#include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/addr.h>
#include "idmap.h"
#include "acl.h"
@@ -1744,10 +1745,47 @@ nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone)
DECODE_TAIL;
}
+static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
+ struct nl4_server *ns)
+{
+ DECODE_HEAD;
+ struct nfs42_netaddr *naddr;
+
+ READ_BUF(4);
+ ns->nl4_type = be32_to_cpup(p++);
+
+ /* currently support for 1 inter-server source server */
+ switch (ns->nl4_type) {
+ case NL4_NETADDR:
+ naddr = &ns->u.nl4_addr;
+
+ READ_BUF(4);
+ naddr->netid_len = be32_to_cpup(p++);
+ if (naddr->netid_len > RPCBIND_MAXNETIDLEN)
+ goto xdr_error;
+
+ READ_BUF(naddr->netid_len + 4); /* 4 for uaddr len */
+ COPYMEM(naddr->netid, naddr->netid_len);
+
+ naddr->addr_len = be32_to_cpup(p++);
+ if (naddr->addr_len > RPCBIND_MAXUADDRLEN)
+ goto xdr_error;
+
+ READ_BUF(naddr->addr_len);
+ COPYMEM(naddr->addr, naddr->addr_len);
+ break;
+ default:
+ goto xdr_error;
+ }
+ DECODE_TAIL;
+}
+
static __be32
nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
{
DECODE_HEAD;
+ struct nl4_server *ns_dummy;
+ int i, count;
status = nfsd4_decode_stateid(argp, &copy->cp_src_stateid);
if (status)
@@ -1762,7 +1800,32 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
p = xdr_decode_hyper(p, &copy->cp_count);
p++; /* ca_consecutive: we always do consecutive copies */
copy->cp_synchronous = be32_to_cpup(p++);
- /* tmp = be32_to_cpup(p); Source server list not supported */
+
+ count = be32_to_cpup(p++);
+
+ copy->cp_intra = false;
+ if (count == 0) { /* intra-server copy */
+ copy->cp_intra = true;
+ goto intra;
+ }
+
+ /* decode all the supplied server addresses but use first */
+ status = nfsd4_decode_nl4_server(argp, &copy->cp_src);
+ if (status)
+ return status;
+
+ ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL);
+ if (ns_dummy == NULL)
+ return nfserrno(-ENOMEM);
+ for (i = 0; i < count - 1; i++) {
+ status = nfsd4_decode_nl4_server(argp, ns_dummy);
+ if (status) {
+ kfree(ns_dummy);
+ return status;
+ }
+ }
+ kfree(ns_dummy);
+intra:
DECODE_TAIL;
}
@@ -1775,6 +1838,18 @@ nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp,
}
static __be32
+nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,
+ struct nfsd4_copy_notify *cn)
+{
+ int status;
+
+ status = nfsd4_decode_stateid(argp, &cn->cpn_src_stateid);
+ if (status)
+ return status;
+ return nfsd4_decode_nl4_server(argp, &cn->cpn_dst);
+}
+
+static __be32
nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
{
DECODE_HEAD;
@@ -1875,7 +1950,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = {
/* new operations for NFSv4.2 */
[OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate,
[OP_COPY] = (nfsd4_dec)nfsd4_decode_copy,
- [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify,
[OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate,
[OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp,
[OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2024,11 +2099,11 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
*/
static __be32 *encode_time_delta(__be32 *p, struct inode *inode)
{
- struct timespec ts;
+ struct timespec64 ts;
u32 ns;
ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran);
- ts = ns_to_timespec(ns);
+ ts = ns_to_timespec64(ns);
p = xdr_encode_hyper(p, ts.tv_sec);
*p++ = cpu_to_be32(ts.tv_nsec);
@@ -4244,6 +4319,46 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
}
static __be32
+nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ struct nfs42_netaddr *addr;
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, 4);
+ *p++ = cpu_to_be32(ns->nl4_type);
+
+ switch (ns->nl4_type) {
+ case NL4_NETADDR:
+ addr = &ns->u.nl4_addr;
+
+ /* netid_len, netid, uaddr_len, uaddr (port included
+ * in RPCBIND_MAXUADDRLEN)
+ */
+ p = xdr_reserve_space(xdr,
+ 4 /* netid len */ +
+ (XDR_QUADLEN(addr->netid_len) * 4) +
+ 4 /* uaddr len */ +
+ (XDR_QUADLEN(addr->addr_len) * 4));
+ if (!p)
+ return nfserr_resource;
+
+ *p++ = cpu_to_be32(addr->netid_len);
+ p = xdr_encode_opaque_fixed(p, addr->netid,
+ addr->netid_len);
+ *p++ = cpu_to_be32(addr->addr_len);
+ p = xdr_encode_opaque_fixed(p, addr->addr,
+ addr->addr_len);
+ break;
+ default:
+ WARN_ON_ONCE(ns->nl4_type != NL4_NETADDR);
+ return nfserr_inval;
+ }
+
+ return 0;
+}
+
+static __be32
nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_copy *copy)
{
@@ -4277,6 +4392,40 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,
}
static __be32
+nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
+ struct nfsd4_copy_notify *cn)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ __be32 *p;
+
+ if (nfserr)
+ return nfserr;
+
+ /* 8 sec, 4 nsec */
+ p = xdr_reserve_space(xdr, 12);
+ if (!p)
+ return nfserr_resource;
+
+ /* cnr_lease_time */
+ p = xdr_encode_hyper(p, cn->cpn_sec);
+ *p++ = cpu_to_be32(cn->cpn_nsec);
+
+ /* cnr_stateid */
+ nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid);
+ if (nfserr)
+ return nfserr;
+
+ /* cnr_src.nl_nsvr */
+ p = xdr_reserve_space(xdr, 4);
+ if (!p)
+ return nfserr_resource;
+
+ *p++ = cpu_to_be32(1);
+
+ return nfsd42_encode_nl4_server(resp, &cn->cpn_src);
+}
+
+static __be32
nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_seek *seek)
{
@@ -4373,7 +4522,7 @@ static const nfsd4_enc nfsd4_enc_ops[] = {
/* NFSv4.2 operations */
[OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop,
[OP_COPY] = (nfsd4_enc)nfsd4_encode_copy,
- [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify,
[OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop,
[OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop,
[OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop,
@@ -4500,8 +4649,6 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
__be32 *p;
struct nfs4_replay *rp = op->replay;
- BUG_ON(!rp);
-
p = xdr_reserve_space(xdr, 8 + rp->rp_buflen);
if (!p) {
WARN_ON_ONCE(1);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 11b42c523f04..e109a1007704 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -157,11 +157,11 @@ static int exports_proc_open(struct inode *inode, struct file *file)
return exports_net_open(current->nsproxy->net_ns, file);
}
-static const struct file_operations exports_proc_operations = {
- .open = exports_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
+static const struct proc_ops exports_proc_ops = {
+ .proc_open = exports_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = seq_release,
};
static int exports_nfsd_open(struct inode *inode, struct file *file)
@@ -956,7 +956,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size)
#ifdef CONFIG_NFSD_V4
static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
- time_t *time, struct nfsd_net *nn)
+ time64_t *time, struct nfsd_net *nn)
{
char *mesg = buf;
int rv, i;
@@ -984,11 +984,11 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
*time = i;
}
- return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time);
+ return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%lld\n", *time);
}
static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
- time_t *time, struct nfsd_net *nn)
+ time64_t *time, struct nfsd_net *nn)
{
ssize_t rv;
@@ -1431,8 +1431,7 @@ static int create_proc_exports_entry(void)
entry = proc_mkdir("fs/nfs", NULL);
if (!entry)
return -ENOMEM;
- entry = proc_create("exports", 0, entry,
- &exports_proc_operations);
+ entry = proc_create("exports", 0, entry, &exports_proc_ops);
if (!entry) {
remove_proc_entry("fs/nfs", NULL);
return -ENOMEM;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 57b93d95fa5c..2ab5569126b8 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -19,6 +19,7 @@
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/svc_xprt.h>
#include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/addr.h>
#include <uapi/linux/nfsd/debug.h>
@@ -142,7 +143,6 @@ int nfs4_state_start(void);
int nfs4_state_start_net(struct net *net);
void nfs4_state_shutdown(void);
void nfs4_state_shutdown_net(struct net *net);
-void nfs4_reset_lease(time_t leasetime);
int nfs4_reset_recoverydir(char *recdir);
char * nfs4_recoverydir(void);
bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
@@ -153,7 +153,6 @@ static inline int nfs4_state_start(void) { return 0; }
static inline int nfs4_state_start_net(struct net *net) { return 0; }
static inline void nfs4_state_shutdown(void) { }
static inline void nfs4_state_shutdown_net(struct net *net) { }
-static inline void nfs4_reset_lease(time_t leasetime) { }
static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
static inline char * nfs4_recoverydir(void) {return NULL; }
static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
@@ -387,6 +386,37 @@ void nfsd_lockd_shutdown(void);
extern const u32 nfsd_suppattrs[3][3];
+static inline __be32 nfsd4_set_netaddr(struct sockaddr *addr,
+ struct nfs42_netaddr *netaddr)
+{
+ struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+ unsigned int port;
+ size_t ret_addr, ret_port;
+
+ switch (addr->sa_family) {
+ case AF_INET:
+ port = ntohs(sin->sin_port);
+ sprintf(netaddr->netid, "tcp");
+ netaddr->netid_len = 3;
+ break;
+ case AF_INET6:
+ port = ntohs(sin6->sin6_port);
+ sprintf(netaddr->netid, "tcp6");
+ netaddr->netid_len = 4;
+ break;
+ default:
+ return nfserr_inval;
+ }
+ ret_addr = rpc_ntop(addr, netaddr->addr, sizeof(netaddr->addr));
+ ret_port = snprintf(netaddr->addr + ret_addr,
+ RPCBIND_MAXUADDRLEN + 1 - ret_addr,
+ ".%u.%u", port >> 8, port & 0xff);
+ WARN_ON(ret_port >= RPCBIND_MAXUADDRLEN + 1 - ret_addr);
+ netaddr->addr_len = ret_addr + ret_port;
+ return 0;
+}
+
static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
{
return !((bm1[0] & ~bm2[0]) ||
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 755e256a9103..56cfbc361561 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -35,15 +35,15 @@ typedef struct svc_fh {
bool fh_locked; /* inode locked by us */
bool fh_want_write; /* remount protection taken */
-
+ int fh_flags; /* FH flags */
#ifdef CONFIG_NFSD_V3
bool fh_post_saved; /* post-op attrs saved */
bool fh_pre_saved; /* pre-op attrs saved */
/* Pre-op attributes saved during fh_lock */
__u64 fh_pre_size; /* size before operation */
- struct timespec fh_pre_mtime; /* mtime before oper */
- struct timespec fh_pre_ctime; /* ctime before oper */
+ struct timespec64 fh_pre_mtime; /* mtime before oper */
+ struct timespec64 fh_pre_ctime; /* ctime before oper */
/*
* pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
* to find out if it is valid.
@@ -56,6 +56,9 @@ typedef struct svc_fh {
#endif /* CONFIG_NFSD_V3 */
} svc_fh;
+#define NFSD4_FH_FOREIGN (1<<0)
+#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
+#define HAS_FH_FLAG(c, f) ((c)->fh_flags & (f))
enum nfsd_fsid {
FSID_DEV = 0,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index c83ddac22f38..543bbe0a556e 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -94,7 +94,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
* Solaris, at least, doesn't seem to care what the time
* request is. We require it be within 30 minutes of now.
*/
- time_t delta = iap->ia_atime.tv_sec - get_seconds();
+ time64_t delta = iap->ia_atime.tv_sec - ktime_get_real_seconds();
nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (nfserr)
@@ -113,7 +113,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
}
}
- nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0);
+ nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0);
done:
return nfsd_return_attrs(nfserr, resp);
}
@@ -226,7 +226,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
return nfserr_io;
nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh),
argp->offset, rqstp->rq_vec, nvecs,
- &cnt, NFS_DATA_SYNC);
+ &cnt, NFS_DATA_SYNC, NULL);
return nfsd_return_attrs(nfserr, resp);
}
@@ -380,7 +380,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
*/
attr->ia_valid &= ATTR_SIZE;
if (attr->ia_valid)
- nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time_t)0);
+ nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time64_t)0);
}
out_unlock:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index e8bee8ff30c5..3b77b904212d 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -31,6 +31,12 @@
#define NFSDDBG_FACILITY NFSDDBG_SVC
+bool inter_copy_offload_enable;
+EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+ "Enable inter server to server copy offload. Default: false");
+
extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
@@ -391,20 +397,25 @@ static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cre
ret = lockd_up(net, cred);
if (ret)
goto out_socks;
- nn->lockd_up = 1;
+ nn->lockd_up = true;
}
- ret = nfs4_state_start_net(net);
+ ret = nfsd_file_cache_start_net(net);
if (ret)
goto out_lockd;
+ ret = nfs4_state_start_net(net);
+ if (ret)
+ goto out_filecache;
nn->nfsd_net_up = true;
return 0;
+out_filecache:
+ nfsd_file_cache_shutdown_net(net);
out_lockd:
if (nn->lockd_up) {
lockd_down(net);
- nn->lockd_up = 0;
+ nn->lockd_up = false;
}
out_socks:
nfsd_shutdown_generic();
@@ -415,11 +426,11 @@ static void nfsd_shutdown_net(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfsd_file_cache_purge(net);
+ nfsd_file_cache_shutdown_net(net);
nfs4_state_shutdown_net(net);
if (nn->lockd_up) {
lockd_down(net);
- nn->lockd_up = 0;
+ nn->lockd_up = false;
}
nn->nfsd_net_up = false;
nfsd_shutdown_generic();
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index d61b83b9654c..68d3f30ee760 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -56,6 +56,14 @@ typedef struct {
stateid_opaque_t si_opaque;
} stateid_t;
+typedef struct {
+ stateid_t stid;
+#define NFS4_COPY_STID 1
+#define NFS4_COPYNOTIFY_STID 2
+ unsigned char sc_type;
+ refcount_t sc_count;
+} copy_stateid_t;
+
#define STATEID_FMT "(%08x/%08x/%08x/%08x)"
#define STATEID_VAL(s) \
(s)->si_opaque.so_clid.cl_boot, \
@@ -96,6 +104,7 @@ struct nfs4_stid {
#define NFS4_REVOKED_DELEG_STID 16
#define NFS4_CLOSED_DELEG_STID 32
#define NFS4_LAYOUT_STID 64
+ struct list_head sc_cp_list;
unsigned char sc_type;
stateid_t sc_stateid;
spinlock_t sc_lock;
@@ -104,6 +113,17 @@ struct nfs4_stid {
void (*sc_free)(struct nfs4_stid *);
};
+/* Keep a list of stateids issued by the COPY_NOTIFY, associate it with the
+ * parent OPEN/LOCK/DELEG stateid.
+ */
+struct nfs4_cpntf_state {
+ copy_stateid_t cp_stateid;
+ struct list_head cp_list; /* per parent nfs4_stid */
+ stateid_t cp_p_stateid; /* copy of parent's stateid */
+ clientid_t cp_p_clid; /* copy of parent's clid */
+ time64_t cpntf_time; /* last time stateid used */
+};
+
/*
* Represents a delegation stateid. The nfs4_client holds references to these
* and they are put when it is being destroyed or when the delegation is
@@ -132,7 +152,7 @@ struct nfs4_delegation {
struct list_head dl_recall_lru; /* delegation recalled */
struct nfs4_clnt_odstate *dl_clnt_odstate;
u32 dl_type;
- time_t dl_time;
+ time64_t dl_time;
/* For recall: */
int dl_retries;
struct nfsd4_callback dl_recall;
@@ -310,7 +330,7 @@ struct nfs4_client {
#endif
struct xdr_netobj cl_name; /* id generated by client */
nfs4_verifier cl_verifier; /* generated by client */
- time_t cl_time; /* time of last lease renewal */
+ time64_t cl_time; /* time of last lease renewal */
struct sockaddr_storage cl_addr; /* client ipaddress */
bool cl_mach_cred; /* SP4_MACH_CRED in force */
struct svc_cred cl_cred; /* setclientid principal */
@@ -320,7 +340,7 @@ struct nfs4_client {
/* NFSv4.1 client implementation id: */
struct xdr_netobj cl_nii_domain;
struct xdr_netobj cl_nii_name;
- struct timespec cl_nii_time;
+ struct timespec64 cl_nii_time;
/* for v4.0 and v4.1 callbacks: */
struct nfs4_cb_conn cl_cb_conn;
@@ -449,7 +469,7 @@ struct nfs4_openowner {
*/
struct list_head oo_close_lru;
struct nfs4_ol_stateid *oo_last_closed_stid;
- time_t oo_time; /* time of placement on so_close_lru */
+ time64_t oo_time; /* time of placement on so_close_lru */
#define NFS4_OO_CONFIRMED 1
unsigned char oo_flags;
};
@@ -606,7 +626,7 @@ static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b)
struct nfsd4_blocked_lock {
struct list_head nbl_list;
struct list_head nbl_lru;
- unsigned long nbl_time;
+ time64_t nbl_time;
struct file_lock nbl_lock;
struct knfsd_fh nbl_fh;
struct nfsd4_callback nbl_cb;
@@ -618,14 +638,17 @@ struct nfsd4_copy;
extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
- stateid_t *stateid, int flags, struct nfsd_file **filp);
+ stateid_t *stateid, int flags, struct nfsd_file **filp,
+ struct nfs4_stid **cstid);
__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
stateid_t *stateid, unsigned char typemask,
struct nfs4_stid **s, struct nfsd_net *nn);
struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
void (*sc_free)(struct nfs4_stid *));
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
-void nfs4_free_cp_state(struct nfsd4_copy *copy);
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
+void nfs4_free_copy_state(struct nfsd4_copy *copy);
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+ struct nfs4_stid *p_stid);
void nfs4_unhash_stid(struct nfs4_stid *s);
void nfs4_put_stid(struct nfs4_stid *s);
void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
@@ -655,6 +678,11 @@ void put_nfs4_file(struct nfs4_file *fi);
extern void nfs4_put_copy(struct nfsd4_copy *copy);
extern struct nfsd4_copy *
find_async_copy(struct nfs4_client *clp, stateid_t *staetid);
+extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
+ struct nfs4_cpntf_state *cps);
+extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+ struct nfs4_client *clp,
+ struct nfs4_cpntf_state **cps);
static inline void get_nfs4_file(struct nfs4_file *fi)
{
refcount_inc(&fi->fi_ref);
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 9bce3b913189..b1bc582b0493 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -84,17 +84,17 @@ static int nfsd_proc_open(struct inode *inode, struct file *file)
return single_open(file, nfsd_proc_show, NULL);
}
-static const struct file_operations nfsd_proc_fops = {
- .open = nfsd_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
+static const struct proc_ops nfsd_proc_ops = {
+ .proc_open = nfsd_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
};
void
nfsd_stat_init(void)
{
- svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops);
+ svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops);
}
void
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index ffc78a0e28b2..06dd0d337049 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -166,6 +166,12 @@ DEFINE_STATEID_EVENT(layout_recall_done);
DEFINE_STATEID_EVENT(layout_recall_fail);
DEFINE_STATEID_EVENT(layout_recall_release);
+TRACE_DEFINE_ENUM(NFSD_FILE_HASHED);
+TRACE_DEFINE_ENUM(NFSD_FILE_PENDING);
+TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ);
+TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_WRITE);
+TRACE_DEFINE_ENUM(NFSD_FILE_REFERENCED);
+
#define show_nf_flags(val) \
__print_flags(val, "|", \
{ 1 << NFSD_FILE_HASHED, "HASHED" }, \
@@ -195,7 +201,7 @@ DECLARE_EVENT_CLASS(nfsd_file_class,
TP_fast_assign(
__entry->nf_hashval = nf->nf_hashval;
__entry->nf_inode = nf->nf_inode;
- __entry->nf_ref = atomic_read(&nf->nf_ref);
+ __entry->nf_ref = refcount_read(&nf->nf_ref);
__entry->nf_flags = nf->nf_flags;
__entry->nf_may = nf->nf_may;
__entry->nf_file = nf->nf_file;
@@ -228,7 +234,7 @@ TRACE_EVENT(nfsd_file_acquire,
TP_ARGS(rqstp, hash, inode, may_flags, nf, status),
TP_STRUCT__entry(
- __field(__be32, xid)
+ __field(u32, xid)
__field(unsigned int, hash)
__field(void *, inode)
__field(unsigned int, may_flags)
@@ -236,27 +242,27 @@ TRACE_EVENT(nfsd_file_acquire,
__field(unsigned long, nf_flags)
__field(unsigned char, nf_may)
__field(struct file *, nf_file)
- __field(__be32, status)
+ __field(u32, status)
),
TP_fast_assign(
- __entry->xid = rqstp->rq_xid;
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
__entry->hash = hash;
__entry->inode = inode;
__entry->may_flags = may_flags;
- __entry->nf_ref = nf ? atomic_read(&nf->nf_ref) : 0;
+ __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0;
__entry->nf_flags = nf ? nf->nf_flags : 0;
__entry->nf_may = nf ? nf->nf_may : 0;
__entry->nf_file = nf ? nf->nf_file : NULL;
- __entry->status = status;
+ __entry->status = be32_to_cpu(status);
),
TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u",
- be32_to_cpu(__entry->xid), __entry->hash, __entry->inode,
+ __entry->xid, __entry->hash, __entry->inode,
show_nf_may(__entry->may_flags), __entry->nf_ref,
show_nf_flags(__entry->nf_flags),
show_nf_may(__entry->nf_may), __entry->nf_file,
- be32_to_cpu(__entry->status))
+ __entry->status)
);
DECLARE_EVENT_CLASS(nfsd_file_search_class,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c0dc491537a6..0aa02eb18bd3 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -280,19 +280,25 @@ out:
* Commit metadata changes to stable storage.
*/
static int
-commit_metadata(struct svc_fh *fhp)
+commit_inode_metadata(struct inode *inode)
{
- struct inode *inode = d_inode(fhp->fh_dentry);
const struct export_operations *export_ops = inode->i_sb->s_export_op;
- if (!EX_ISSYNC(fhp->fh_export))
- return 0;
-
if (export_ops->commit_metadata)
return export_ops->commit_metadata(inode);
return sync_inode_metadata(inode, 1);
}
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+ struct inode *inode = d_inode(fhp->fh_dentry);
+
+ if (!EX_ISSYNC(fhp->fh_export))
+ return 0;
+ return commit_inode_metadata(inode);
+}
+
/*
* Go over the attributes and take care of the small differences between
* NFS semantics and what Linux expects.
@@ -358,7 +364,7 @@ out_nfserrno:
*/
__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
- int check_guard, time_t guardtime)
+ int check_guard, time64_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
@@ -524,23 +530,39 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
}
#endif
-__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
- u64 dst_pos, u64 count, bool sync)
+__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
+ struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync)
{
+ struct file *src = nf_src->nf_file;
+ struct file *dst = nf_dst->nf_file;
loff_t cloned;
+ __be32 ret = 0;
+ down_write(&nf_dst->nf_rwsem);
cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
- if (cloned < 0)
- return nfserrno(cloned);
- if (count && cloned != count)
- return nfserrno(-EINVAL);
+ if (cloned < 0) {
+ ret = nfserrno(cloned);
+ goto out_err;
+ }
+ if (count && cloned != count) {
+ ret = nfserrno(-EINVAL);
+ goto out_err;
+ }
if (sync) {
loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX;
int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
- if (status < 0)
- return nfserrno(status);
+
+ if (!status)
+ status = commit_inode_metadata(file_inode(src));
+ if (status < 0) {
+ nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net,
+ nfsd_net_id));
+ ret = nfserrno(status);
+ }
}
- return 0;
+out_err:
+ up_write(&nf_dst->nf_rwsem);
+ return ret;
}
ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
@@ -938,10 +960,12 @@ static int wait_for_concurrent_writes(struct file *file)
}
__be32
-nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
+nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
loff_t offset, struct kvec *vec, int vlen,
- unsigned long *cnt, int stable)
+ unsigned long *cnt, int stable,
+ __be32 *verf)
{
+ struct file *file = nf->nf_file;
struct svc_export *exp;
struct iov_iter iter;
__be32 nfserr;
@@ -972,9 +996,28 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
flags |= RWF_SYNC;
iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
- host_err = vfs_iter_write(file, &iter, &pos, flags);
- if (host_err < 0)
+ if (flags & RWF_SYNC) {
+ down_write(&nf->nf_rwsem);
+ host_err = vfs_iter_write(file, &iter, &pos, flags);
+ if (host_err < 0)
+ nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
+ nfsd_net_id));
+ up_write(&nf->nf_rwsem);
+ } else {
+ down_read(&nf->nf_rwsem);
+ if (verf)
+ nfsd_copy_boot_verifier(verf,
+ net_generic(SVC_NET(rqstp),
+ nfsd_net_id));
+ host_err = vfs_iter_write(file, &iter, &pos, flags);
+ up_read(&nf->nf_rwsem);
+ }
+ if (host_err < 0) {
+ nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
+ nfsd_net_id));
goto out_nfserr;
+ }
+ *cnt = host_err;
nfsdstats.io_write += *cnt;
fsnotify_modify(file);
@@ -1036,7 +1079,8 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
*/
__be32
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
- struct kvec *vec, int vlen, unsigned long *cnt, int stable)
+ struct kvec *vec, int vlen, unsigned long *cnt, int stable,
+ __be32 *verf)
{
struct nfsd_file *nf;
__be32 err;
@@ -1047,8 +1091,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
if (err)
goto out;
- err = nfsd_vfs_write(rqstp, fhp, nf->nf_file, offset, vec,
- vlen, cnt, stable);
+ err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec,
+ vlen, cnt, stable, verf);
nfsd_file_put(nf);
out:
trace_nfsd_write_done(rqstp, fhp, offset, *cnt);
@@ -1067,7 +1111,7 @@ out:
*/
__be32
nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
- loff_t offset, unsigned long count)
+ loff_t offset, unsigned long count, __be32 *verf)
{
struct nfsd_file *nf;
loff_t end = LLONG_MAX;
@@ -1086,10 +1130,14 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (err)
goto out;
if (EX_ISSYNC(fhp->fh_export)) {
- int err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+ int err2;
+ down_write(&nf->nf_rwsem);
+ err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
switch (err2) {
case 0:
+ nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
+ nfsd_net_id));
break;
case -EINVAL:
err = nfserr_notsupp;
@@ -1099,7 +1147,10 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
nfsd_reset_boot_verifier(net_generic(nf->nf_net,
nfsd_net_id));
}
- }
+ up_write(&nf->nf_rwsem);
+ } else
+ nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
+ nfsd_net_id));
nfsd_file_put(nf);
out:
@@ -1123,7 +1174,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
if (iap->ia_valid)
- return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
+ return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0);
/* Callers expect file metadata to be committed here */
return nfserrno(commit_metadata(resfhp));
}
@@ -1386,7 +1437,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
&& d_inode(dchild)->i_atime.tv_sec == v_atime
&& d_inode(dchild)->i_size == 0 ) {
if (created)
- *created = 1;
+ *created = true;
break;
}
/* fall through */
@@ -1395,7 +1446,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
&& d_inode(dchild)->i_atime.tv_sec == v_atime
&& d_inode(dchild)->i_size == 0 ) {
if (created)
- *created = 1;
+ *created = true;
goto set_attr;
}
/* fall through */
@@ -1412,7 +1463,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out_nfserr;
}
if (created)
- *created = 1;
+ *created = true;
nfsd_check_ignore_resizing(iap);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index cc110a10bfe8..3eb660ad80d1 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -34,6 +34,8 @@
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+struct nfsd_file;
+
/*
* Callback function for readdir
*/
@@ -48,15 +50,16 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
const char *, unsigned int,
struct svc_export **, struct dentry **);
__be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *,
- struct iattr *, int, time_t);
+ struct iattr *, int, time64_t);
int nfsd_mountpoint(struct dentry *, struct svc_export *);
#ifdef CONFIG_NFSD_V4
__be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
struct xdr_netobj *);
__be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
struct file *, loff_t, loff_t, int);
-__be32 nfsd4_clone_file_range(struct file *, u64, struct file *,
- u64, u64, bool);
+__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
+ struct nfsd_file *nf_dst, u64 dst_pos,
+ u64 count, bool sync);
#endif /* CONFIG_NFSD_V4 */
__be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
char *name, int len, struct iattr *attrs,
@@ -71,7 +74,7 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *,
struct svc_fh *res, int createmode,
u32 *verifier, bool *truncp, bool *created);
__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *,
- loff_t, unsigned long);
+ loff_t, unsigned long, __be32 *verf);
#endif /* CONFIG_NFSD_V3 */
int nfsd_open_break_lease(struct inode *, int);
__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
@@ -91,11 +94,12 @@ __be32 nfsd_read(struct svc_rqst *, struct svc_fh *,
loff_t, struct kvec *, int, unsigned long *,
u32 *eof);
__be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
- struct kvec *, int, unsigned long *, int);
+ struct kvec *, int, unsigned long *,
+ int stable, __be32 *verf);
__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct file *file, loff_t offset,
+ struct nfsd_file *nf, loff_t offset,
struct kvec *vec, int vlen, unsigned long *cnt,
- int stable);
+ int stable, __be32 *verf);
__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *,
char *, int *);
__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *,
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 99ff9f403ff1..4155fd71714c 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -14,7 +14,7 @@ struct nfsd3_sattrargs {
struct svc_fh fh;
struct iattr attrs;
int check_guard;
- time_t guardtime;
+ time64_t guardtime;
};
struct nfsd3_diropargs {
@@ -159,6 +159,7 @@ struct nfsd3_writeres {
struct svc_fh fh;
unsigned long count;
int committed;
+ __be32 verf[2];
};
struct nfsd3_renameres {
@@ -223,6 +224,7 @@ struct nfsd3_pathconfres {
struct nfsd3_commitres {
__be32 status;
struct svc_fh fh;
+ __be32 verf[2];
};
struct nfsd3_getaclres {
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index f4737d66ee98..db63d39b1507 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -46,9 +46,9 @@
#define CURRENT_STATE_ID_FLAG (1<<0)
#define SAVED_STATE_ID_FLAG (1<<1)
-#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
-#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
-#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+#define SET_CSTATE_FLAG(c, f) ((c)->sid_flags |= (f))
+#define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f))
+#define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f))
struct nfsd4_compound_state {
struct svc_fh current_fh;
@@ -221,6 +221,7 @@ struct nfsd4_lookup {
struct nfsd4_putfh {
u32 pf_fhlen; /* request */
char *pf_fhval; /* request */
+ bool no_verify; /* represents foreigh fh */
};
struct nfsd4_open {
@@ -518,11 +519,13 @@ struct nfsd42_write_res {
struct nfsd4_copy {
/* request */
- stateid_t cp_src_stateid;
- stateid_t cp_dst_stateid;
- u64 cp_src_pos;
- u64 cp_dst_pos;
- u64 cp_count;
+ stateid_t cp_src_stateid;
+ stateid_t cp_dst_stateid;
+ u64 cp_src_pos;
+ u64 cp_dst_pos;
+ u64 cp_count;
+ struct nl4_server cp_src;
+ bool cp_intra;
/* both */
bool cp_synchronous;
@@ -540,13 +543,18 @@ struct nfsd4_copy {
struct nfsd_file *nf_src;
struct nfsd_file *nf_dst;
- stateid_t cp_stateid;
+ copy_stateid_t cp_stateid;
struct list_head copies;
struct task_struct *copy_task;
refcount_t refcount;
bool stopped;
+
+ struct vfsmount *ss_mnt;
+ struct nfs_fh c_fh;
+ nfs4_stateid stateid;
};
+extern bool inter_copy_offload_enable;
struct nfsd4_seek {
/* request */
@@ -568,6 +576,18 @@ struct nfsd4_offload_status {
u32 status;
};
+struct nfsd4_copy_notify {
+ /* request */
+ stateid_t cpn_src_stateid;
+ struct nl4_server cpn_dst;
+
+ /* response */
+ stateid_t cpn_cnr_stateid;
+ u64 cpn_sec;
+ u32 cpn_nsec;
+ struct nl4_server cpn_src;
+};
+
struct nfsd4_op {
int opnum;
const struct nfsd4_operation * opdesc;
@@ -627,6 +647,7 @@ struct nfsd4_op {
struct nfsd4_clone clone;
struct nfsd4_copy copy;
struct nfsd4_offload_status offload_status;
+ struct nfsd4_copy_notify copy_notify;
struct nfsd4_seek seek;
} u;
struct nfs4_replay * replay;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.