aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/fault-injection/fault-injection.rst7
-rw-r--r--fs/lockd/svc4proc.c12
-rw-r--r--fs/lockd/svclock.c10
-rw-r--r--fs/lockd/svcproc.c5
-rw-r--r--fs/lockd/xdr4.c19
-rw-r--r--fs/nfsd/acl.h6
-rw-r--r--fs/nfsd/filecache.c749
-rw-r--r--fs/nfsd/filecache.h11
-rw-r--r--fs/nfsd/netns.h3
-rw-r--r--fs/nfsd/nfs2acl.c6
-rw-r--r--fs/nfsd/nfs3acl.c4
-rw-r--r--fs/nfsd/nfs3proc.c35
-rw-r--r--fs/nfsd/nfs4acl.c46
-rw-r--r--fs/nfsd/nfs4callback.c37
-rw-r--r--fs/nfsd/nfs4proc.c330
-rw-r--r--fs/nfsd/nfs4state.c127
-rw-r--r--fs/nfsd/nfs4xdr.c123
-rw-r--r--fs/nfsd/nfsctl.c21
-rw-r--r--fs/nfsd/nfsd.h6
-rw-r--r--fs/nfsd/nfsfh.c27
-rw-r--r--fs/nfsd/nfsfh.h58
-rw-r--r--fs/nfsd/nfsproc.c27
-rw-r--r--fs/nfsd/state.h1
-rw-r--r--fs/nfsd/trace.h327
-rw-r--r--fs/nfsd/vfs.c256
-rw-r--r--fs/nfsd/vfs.h33
-rw-r--r--fs/nfsd/xdr4.h60
-rw-r--r--include/linux/lockd/lockd.h1
-rw-r--r--include/linux/lockd/xdr.h2
-rw-r--r--include/linux/nfs_ssc.h2
-rw-r--r--include/linux/sunrpc/xdr.h4
-rw-r--r--include/trace/events/sunrpc.h14
-rw-r--r--net/sunrpc/svc_xprt.c2
33 files changed, 1426 insertions, 945 deletions
diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst
index eb9c2d9a4f5f..17779a2772e5 100644
--- a/Documentation/fault-injection/fault-injection.rst
+++ b/Documentation/fault-injection/fault-injection.rst
@@ -169,6 +169,13 @@ configuration of fault-injection capabilities.
default is 'N', setting it to 'Y' will disable disconnect
injection on the RPC server.
+- /sys/kernel/debug/fail_sunrpc/ignore-cache-wait:
+
+ Format: { 'Y' | 'N' }
+
+ default is 'N', setting it to 'Y' will disable cache wait
+ injection on the RPC server.
+
- /sys/kernel/debug/fail_function/inject:
Format: { 'function-name' | '!function-name' | '' }
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 176b468a61c7..bf274f23969b 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -32,6 +32,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
if (!nlmsvc_ops)
return nlm_lck_denied_nolocks;
+ if (lock->lock_start > OFFSET_MAX ||
+ (lock->lock_len && ((lock->lock_len - 1) > (OFFSET_MAX - lock->lock_start))))
+ return nlm4_fbig;
+
/* Obtain host handle */
if (!(host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len))
|| (argp->monitor && nsm_monitor(host) < 0))
@@ -50,6 +54,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
/* Set up the missing parts of the file_lock structure */
lock->fl.fl_file = file->f_file[mode];
lock->fl.fl_pid = current->tgid;
+ lock->fl.fl_start = (loff_t)lock->lock_start;
+ lock->fl.fl_end = lock->lock_len ?
+ (loff_t)(lock->lock_start + lock->lock_len - 1) :
+ OFFSET_MAX;
lock->fl.fl_lmops = &nlmsvc_lock_operations;
nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
if (!lock->fl.fl_owner) {
@@ -87,6 +95,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_host *host;
struct nlm_file *file;
+ struct nlm_lockowner *test_owner;
__be32 rc = rpc_success;
dprintk("lockd: TEST4 called\n");
@@ -96,6 +105,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
+ test_owner = argp->lock.fl.fl_owner;
/* Now check for conflicting locks */
resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie);
if (resp->status == nlm_drop_reply)
@@ -103,7 +113,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
else
dprintk("lockd: TEST4 status %d\n", ntohl(resp->status));
- nlmsvc_release_lockowner(&argp->lock);
+ nlmsvc_put_lockowner(test_owner);
nlmsvc_release_host(host);
nlm_release_file(file);
return rc;
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index cb3658ab9b7a..9c1aa75441e1 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -340,7 +340,7 @@ nlmsvc_get_lockowner(struct nlm_lockowner *lockowner)
return lockowner;
}
-static void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner)
+void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner)
{
if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock))
return;
@@ -590,7 +590,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
int error;
int mode;
__be32 ret;
- struct nlm_lockowner *test_owner;
dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
nlmsvc_file_inode(file)->i_sb->s_id,
@@ -604,9 +603,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
goto out;
}
- /* If there's a conflicting lock, remember to clean up the test lock */
- test_owner = (struct nlm_lockowner *)lock->fl.fl_owner;
-
mode = lock_to_openmode(&lock->fl);
error = vfs_test_lock(file->f_file[mode], &lock->fl);
if (error) {
@@ -635,10 +631,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
conflock->fl.fl_end = lock->fl.fl_end;
locks_release_private(&lock->fl);
- /* Clean up the test lock */
- lock->fl.fl_owner = NULL;
- nlmsvc_put_lockowner(test_owner);
-
ret = nlm_lck_denied;
out:
return ret;
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 4dc1b40a489a..b09ca35b527c 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -116,6 +116,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
struct nlm_args *argp = rqstp->rq_argp;
struct nlm_host *host;
struct nlm_file *file;
+ struct nlm_lockowner *test_owner;
__be32 rc = rpc_success;
dprintk("lockd: TEST called\n");
@@ -125,6 +126,8 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
+ test_owner = argp->lock.fl.fl_owner;
+
/* Now check for conflicting locks */
resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie));
if (resp->status == nlm_drop_reply)
@@ -133,7 +136,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
dprintk("lockd: TEST status %d vers %d\n",
ntohl(resp->status), rqstp->rq_vers);
- nlmsvc_release_lockowner(&argp->lock);
+ nlmsvc_put_lockowner(test_owner);
nlmsvc_release_host(host);
nlm_release_file(file);
return rc;
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 856267c0864b..712fdfeb8ef0 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -20,13 +20,6 @@
#include "svcxdr.h"
-static inline loff_t
-s64_to_loff_t(__s64 offset)
-{
- return (loff_t)offset;
-}
-
-
static inline s64
loff_t_to_s64(loff_t offset)
{
@@ -70,8 +63,6 @@ static bool
svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
{
struct file_lock *fl = &lock->fl;
- u64 len, start;
- s64 end;
if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len))
return false;
@@ -81,20 +72,14 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
return false;
if (xdr_stream_decode_u32(xdr, &lock->svid) < 0)
return false;
- if (xdr_stream_decode_u64(xdr, &start) < 0)
+ if (xdr_stream_decode_u64(xdr, &lock->lock_start) < 0)
return false;
- if (xdr_stream_decode_u64(xdr, &len) < 0)
+ if (xdr_stream_decode_u64(xdr, &lock->lock_len) < 0)
return false;
locks_init_lock(fl);
fl->fl_flags = FL_POSIX;
fl->fl_type = F_RDLCK;
- end = start + len - 1;
- fl->fl_start = s64_to_loff_t(start);
- if (len == 0 || end < 0)
- fl->fl_end = OFFSET_MAX;
- else
- fl->fl_end = s64_to_loff_t(end);
return true;
}
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index ba14d2f4b64f..4b7324458a94 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -38,6 +38,8 @@
struct nfs4_acl;
struct svc_fh;
struct svc_rqst;
+struct nfsd_attrs;
+enum nfs_ftype4;
int nfs4_acl_bytes(int entries);
int nfs4_acl_get_whotype(char *, u32);
@@ -45,7 +47,7 @@ __be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);
int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
struct nfs4_acl **acl);
-__be32 nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct nfs4_acl *acl);
+__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl,
+ struct nfsd_attrs *attr);
#endif /* LINUX_NFS4_ACL_H */
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index a605c0e39b09..eeed4ae5b4ad 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -13,6 +13,7 @@
#include <linux/fsnotify_backend.h>
#include <linux/fsnotify.h>
#include <linux/seq_file.h>
+#include <linux/rhashtable.h>
#include "vfs.h"
#include "nfsd.h"
@@ -21,28 +22,19 @@
#include "filecache.h"
#include "trace.h"
-#define NFSDDBG_FACILITY NFSDDBG_FH
-
-/* FIXME: dynamically size this for the machine somehow? */
-#define NFSD_FILE_HASH_BITS 12
-#define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS)
#define NFSD_LAUNDRETTE_DELAY (2 * HZ)
-#define NFSD_FILE_SHUTDOWN (1)
-#define NFSD_FILE_LRU_THRESHOLD (4096UL)
-#define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2)
+#define NFSD_FILE_CACHE_UP (0)
/* We only care about NFSD_MAY_READ/WRITE for this cache */
#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE)
-struct nfsd_fcache_bucket {
- struct hlist_head nfb_head;
- spinlock_t nfb_lock;
- unsigned int nfb_count;
- unsigned int nfb_maxcount;
-};
-
static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_releases);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_pages_flushed);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions);
struct nfsd_fcache_disposal {
struct work_struct work;
@@ -54,21 +46,146 @@ 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;
static struct list_lru nfsd_file_lru;
-static long nfsd_file_lru_flags;
+static unsigned long nfsd_file_flags;
static struct fsnotify_group *nfsd_file_fsnotify_group;
-static atomic_long_t nfsd_filecache_count;
static struct delayed_work nfsd_filecache_laundrette;
+static struct rhashtable nfsd_file_rhash_tbl
+ ____cacheline_aligned_in_smp;
+
+enum nfsd_file_lookup_type {
+ NFSD_FILE_KEY_INODE,
+ NFSD_FILE_KEY_FULL,
+};
+
+struct nfsd_file_lookup_key {
+ struct inode *inode;
+ struct net *net;
+ const struct cred *cred;
+ unsigned char need;
+ enum nfsd_file_lookup_type type;
+};
+
+/*
+ * The returned hash value is based solely on the address of an in-code
+ * inode, a pointer to a slab-allocated object. The entropy in such a
+ * pointer is concentrated in its middle bits.
+ */
+static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed)
+{
+ unsigned long ptr = (unsigned long)inode;
+ u32 k;
+
+ k = ptr >> L1_CACHE_SHIFT;
+ k &= 0x00ffffff;
+ return jhash2(&k, 1, seed);
+}
+
+/**
+ * nfsd_file_key_hashfn - Compute the hash value of a lookup key
+ * @data: key on which to compute the hash value
+ * @len: rhash table's key_len parameter (unused)
+ * @seed: rhash table's random seed of the day
+ *
+ * Return value:
+ * Computed 32-bit hash value
+ */
+static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct nfsd_file_lookup_key *key = data;
+
+ return nfsd_file_inode_hash(key->inode, seed);
+}
+
+/**
+ * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file
+ * @data: object on which to compute the hash value
+ * @len: rhash table's key_len parameter (unused)
+ * @seed: rhash table's random seed of the day
+ *
+ * Return value:
+ * Computed 32-bit hash value
+ */
+static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct nfsd_file *nf = data;
+
+ return nfsd_file_inode_hash(nf->nf_inode, seed);
+}
-static void nfsd_file_gc(void);
+static bool
+nfsd_match_cred(const struct cred *c1, const struct cred *c2)
+{
+ int i;
+
+ if (!uid_eq(c1->fsuid, c2->fsuid))
+ return false;
+ if (!gid_eq(c1->fsgid, c2->fsgid))
+ return false;
+ if (c1->group_info == NULL || c2->group_info == NULL)
+ return c1->group_info == c2->group_info;
+ if (c1->group_info->ngroups != c2->group_info->ngroups)
+ return false;
+ for (i = 0; i < c1->group_info->ngroups; i++) {
+ if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i]))
+ return false;
+ }
+ return true;
+}
+
+/**
+ * nfsd_file_obj_cmpfn - Match a cache item against search criteria
+ * @arg: search criteria
+ * @ptr: cache item to check
+ *
+ * Return values:
+ * %0 - Item matches search criteria
+ * %1 - Item does not match search criteria
+ */
+static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct nfsd_file_lookup_key *key = arg->key;
+ const struct nfsd_file *nf = ptr;
+
+ switch (key->type) {
+ case NFSD_FILE_KEY_INODE:
+ if (nf->nf_inode != key->inode)
+ return 1;
+ break;
+ case NFSD_FILE_KEY_FULL:
+ if (nf->nf_inode != key->inode)
+ return 1;
+ if (nf->nf_may != key->need)
+ return 1;
+ if (nf->nf_net != key->net)
+ return 1;
+ if (!nfsd_match_cred(nf->nf_cred, key->cred))
+ return 1;
+ if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0)
+ return 1;
+ break;
+ }
+ return 0;
+}
+
+static const struct rhashtable_params nfsd_file_rhash_params = {
+ .key_len = sizeof_field(struct nfsd_file, nf_inode),
+ .key_offset = offsetof(struct nfsd_file, nf_inode),
+ .head_offset = offsetof(struct nfsd_file, nf_rhash),
+ .hashfn = nfsd_file_key_hashfn,
+ .obj_hashfn = nfsd_file_obj_hashfn,
+ .obj_cmpfn = nfsd_file_obj_cmpfn,
+ /* Reduce resizing churn on light workloads */
+ .min_size = 512, /* buckets */
+ .automatic_shrinking = true,
+};
static void
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))
+ if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) ||
+ test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0)
return;
queue_delayed_work(system_wq, &nfsd_filecache_laundrette,
@@ -111,12 +228,11 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm)
}
static struct nfsd_file_mark *
-nfsd_file_mark_find_or_create(struct nfsd_file *nf)
+nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode)
{
int err;
struct fsnotify_mark *mark;
struct nfsd_file_mark *nfm = NULL, *new;
- struct inode *inode = nf->nf_inode;
do {
fsnotify_group_lock(nfsd_file_fsnotify_group);
@@ -167,31 +283,25 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf)
}
static struct nfsd_file *
-nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
- struct net *net)
+nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may)
{
struct nfsd_file *nf;
nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL);
if (nf) {
- INIT_HLIST_NODE(&nf->nf_node);
INIT_LIST_HEAD(&nf->nf_lru);
+ nf->nf_birthtime = ktime_get();
nf->nf_file = NULL;
nf->nf_cred = get_current_cred();
- nf->nf_net = net;
+ nf->nf_net = key->net;
nf->nf_flags = 0;
- nf->nf_inode = inode;
- nf->nf_hashval = hashval;
- 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)
- __set_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags);
- if (may & NFSD_MAY_READ)
- __set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
- }
+ __set_bit(NFSD_FILE_HASHED, &nf->nf_flags);
+ __set_bit(NFSD_FILE_PENDING, &nf->nf_flags);
+ nf->nf_inode = key->inode;
+ /* nf_ref is pre-incremented for hash table */
+ refcount_set(&nf->nf_ref, 2);
+ nf->nf_may = key->need;
nf->nf_mark = NULL;
- trace_nfsd_file_alloc(nf);
}
return nf;
}
@@ -199,8 +309,12 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval,
static bool
nfsd_file_free(struct nfsd_file *nf)
{
+ s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime));
bool flush = false;
+ this_cpu_inc(nfsd_file_releases);
+ this_cpu_add(nfsd_file_total_age, age);
+
trace_nfsd_file_put_final(nf);
if (nf->nf_mark)
nfsd_file_mark_put(nf->nf_mark);
@@ -210,6 +324,14 @@ nfsd_file_free(struct nfsd_file *nf)
fput(nf->nf_file);
flush = true;
}
+
+ /*
+ * If this item is still linked via nf_lru, that's a bug.
+ * WARN and leak it to preserve system stability.
+ */
+ if (WARN_ON_ONCE(!list_empty(&nf->nf_lru)))
+ return flush;
+
call_rcu(&nf->nf_rcu, nfsd_file_slab_free);
return flush;
}
@@ -240,31 +362,44 @@ nfsd_file_check_write_error(struct nfsd_file *nf)
static void
nfsd_file_flush(struct nfsd_file *nf)
{
- if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0)
+ struct file *file = nf->nf_file;
+
+ if (!file || !(file->f_mode & FMODE_WRITE))
+ return;
+ this_cpu_add(nfsd_file_pages_flushed, file->f_mapping->nrpages);
+ if (vfs_fsync(file, 1) != 0)
nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
}
-static void
-nfsd_file_do_unhash(struct nfsd_file *nf)
+static void nfsd_file_lru_add(struct nfsd_file *nf)
{
- lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock);
+ set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
+ if (list_lru_add(&nfsd_file_lru, &nf->nf_lru))
+ trace_nfsd_file_lru_add(nf);
+}
+static void nfsd_file_lru_remove(struct nfsd_file *nf)
+{
+ if (list_lru_del(&nfsd_file_lru, &nf->nf_lru))
+ trace_nfsd_file_lru_del(nf);
+}
+
+static void
+nfsd_file_hash_remove(struct nfsd_file *nf)
+{
trace_nfsd_file_unhash(nf);
if (nfsd_file_check_write_error(nf))
nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
- --nfsd_file_hashtbl[nf->nf_hashval].nfb_count;
- hlist_del_rcu(&nf->nf_node);
- atomic_long_dec(&nfsd_filecache_count);
+ rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash,
+ nfsd_file_rhash_params);
}
static bool
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);
+ nfsd_file_hash_remove(nf);
return true;
}
return false;
@@ -274,17 +409,16 @@ nfsd_file_unhash(struct nfsd_file *nf)
* Return true if the file was unhashed.
*/
static bool
-nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *dispose)
+nfsd_file_unhash_and_dispose(struct nfsd_file *nf, struct list_head *dispose)
{
- lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock);
-
- trace_nfsd_file_unhash_and_release_locked(nf);
+ trace_nfsd_file_unhash_and_dispose(nf);
if (!nfsd_file_unhash(nf))
return false;
/* keep final reference for nfsd_file_lru_dispose */
if (refcount_dec_not_one(&nf->nf_ref))
return true;
+ nfsd_file_lru_remove(nf);
list_add(&nf->nf_lru, dispose);
return true;
}
@@ -296,6 +430,7 @@ nfsd_file_put_noref(struct nfsd_file *nf)
if (refcount_dec_and_test(&nf->nf_ref)) {
WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags));
+ nfsd_file_lru_remove(nf);
nfsd_file_free(nf);
}
}
@@ -305,7 +440,7 @@ nfsd_file_put(struct nfsd_file *nf)
{
might_sleep();
- set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
+ nfsd_file_lru_add(nf);
if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) {
nfsd_file_flush(nf);
nfsd_file_put_noref(nf);
@@ -314,9 +449,24 @@ nfsd_file_put(struct nfsd_file *nf)
nfsd_file_schedule_laundrette();
} else
nfsd_file_put_noref(nf);
+}
- if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT)
- nfsd_file_gc();
+/**
+ * nfsd_file_close - Close an nfsd_file
+ * @nf: nfsd_file to close
+ *
+ * If this is the final reference for @nf, free it immediately.
+ * This reflects an on-the-wire CLOSE or DELEGRETURN into the
+ * VFS and exported filesystem.
+ */
+void nfsd_file_close(struct nfsd_file *nf)
+{
+ nfsd_file_put(nf);
+ if (refcount_dec_if_one(&nf->nf_ref)) {
+ nfsd_file_unhash(nf);
+ nfsd_file_lru_remove(nf);
+ nfsd_file_free(nf);
+ }
}
struct nfsd_file *
@@ -334,7 +484,7 @@ nfsd_file_dispose_list(struct list_head *dispose)
while(!list_empty(dispose)) {
nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
- list_del(&nf->nf_lru);
+ list_del_init(&nf->nf_lru);
nfsd_file_flush(nf);
nfsd_file_put_noref(nf);
}
@@ -348,7 +498,7 @@ 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);
+ list_del_init(&nf->nf_lru);
nfsd_file_flush(nf);
if (!refcount_dec_and_test(&nf->nf_ref))
continue;
@@ -405,8 +555,19 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
}
}
-/*
+/**
+ * nfsd_file_lru_cb - Examine an entry on the LRU list
+ * @item: LRU entry to examine
+ * @lru: controlling LRU
+ * @lock: LRU list lock (unused)
+ * @arg: dispose list
+ *
* Note this can deadlock with nfsd_file_cache_purge.
+ *
+ * Return values:
+ * %LRU_REMOVED: @item was removed from the LRU
+ * %LRU_ROTATE: @item is to be moved to the LRU tail
+ * %LRU_SKIP: @item cannot be evicted
*/
static enum lru_status
nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
@@ -427,55 +588,65 @@ 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 (refcount_read(&nf->nf_ref) > 1)
- goto out_skip;
+ if (refcount_read(&nf->nf_ref) > 1) {
+ list_lru_isolate(lru, &nf->nf_lru);
+ trace_nfsd_file_gc_in_use(nf);
+ return LRU_REMOVED;
+ }
/*
* Don't throw out files that are still undergoing I/O or
* that have uncleared errors pending.
*/
- if (nfsd_file_check_writeback(nf))
- goto out_skip;
+ if (nfsd_file_check_writeback(nf)) {
+ trace_nfsd_file_gc_writeback(nf);
+ return LRU_SKIP;
+ }
- if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags))
- goto out_skip;
+ if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) {
+ trace_nfsd_file_gc_referenced(nf);
+ return LRU_ROTATE;
+ }
- if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags))
- goto out_skip;
+ if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+ trace_nfsd_file_gc_hashed(nf);
+ return LRU_SKIP;
+ }
list_lru_isolate_move(lru, &nf->nf_lru, head);
+ this_cpu_inc(nfsd_file_evictions);
+ trace_nfsd_file_gc_disposed(nf);
return LRU_REMOVED;
-out_skip:
- return LRU_SKIP;
}
-static unsigned long
-nfsd_file_lru_walk_list(struct shrink_control *sc)
+/*
+ * Unhash items on @dispose immediately, then queue them on the
+ * disposal workqueue to finish releasing them in the background.
+ *
+ * cel: Note that between the time list_lru_shrink_walk runs and
+ * now, these items are in the hash table but marked unhashed.
+ * Why release these outside of lru_cb ? There's no lock ordering
+ * problem since lru_cb currently takes no lock.
+ */
+static void nfsd_file_gc_dispose_list(struct list_head *dispose)
{
- 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_dispose_list_delayed(&head);
- return ret;
+ list_for_each_entry(nf, dispose, nf_lru)
+ nfsd_file_hash_remove(nf);
+ nfsd_file_dispose_list_delayed(dispose);
}
static void
nfsd_file_gc(void)
{
- nfsd_file_lru_walk_list(NULL);
+ LIST_HEAD(dispose);
+ unsigned long ret;
+
+ ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb,
+ &dispose, list_lru_count(&nfsd_file_lru));
+ trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru));
+ nfsd_file_gc_dispose_list(&dispose);
}
static void
@@ -494,7 +665,14 @@ 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)
{
- return nfsd_file_lru_walk_list(sc);
+ LIST_HEAD(dispose);
+ unsigned long ret;
+
+ ret = list_lru_shrink_walk(&nfsd_file_lru, sc,
+ nfsd_file_lru_cb, &dispose);
+ trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru));
+ nfsd_file_gc_dispose_list(&dispose);
+ return ret;
}
static struct shrinker nfsd_file_shrinker = {
@@ -503,39 +681,47 @@ static struct shrinker nfsd_file_shrinker = {
.seeks = 1,
};
-static void
-__nfsd_file_close_inode(struct inode *inode, unsigned int hashval,
- struct list_head *dispose)
+/*
+ * Find all cache items across all net namespaces that match @inode and
+ * move them to @dispose. The lookup is atomic wrt nfsd_file_acquire().
+ */
+static unsigned int
+__nfsd_file_close_inode(struct inode *inode, struct list_head *dispose)
{
- struct nfsd_file *nf;
- struct hlist_node *tmp;
+ struct nfsd_file_lookup_key key = {
+ .type = NFSD_FILE_KEY_INODE,
+ .inode = inode,
+ };
+ unsigned int count = 0;
+ struct nfsd_file *nf;
- spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock);
- hlist_for_each_entry_safe(nf, tmp, &nfsd_file_hashtbl[hashval].nfb_head, nf_node) {
- if (inode == nf->nf_inode)
- nfsd_file_unhash_and_release_locked(nf, dispose);
- }
- spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock);
+ rcu_read_lock();
+ do {
+ nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
+ nfsd_file_rhash_params);
+ if (!nf)
+ break;
+ nfsd_file_unhash_and_dispose(nf, dispose);
+ count++;
+ } while (1);
+ rcu_read_unlock();
+ return count;
}
/**
* nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file
* @inode: inode of the file to attempt to remove
*
- * Walk the whole hash bucket, looking for any files that correspond to "inode".
- * If any do, then unhash them and put the hashtable reference to them and
- * destroy any that had their last reference put. Also ensure that any of the
- * fputs also have their final __fput done as well.
+ * Unhash and put, then flush and fput all cache items associated with @inode.
*/
void
nfsd_file_close_inode_sync(struct inode *inode)
{
- unsigned int hashval = (unsigned int)hash_long(inode->i_ino,
- NFSD_FILE_HASH_BITS);
LIST_HEAD(dispose);
+ unsigned int count;
- __nfsd_file_close_inode(inode, hashval, &dispose);
- trace_nfsd_file_close_inode_sync(inode, hashval, !list_empty(&dispose));
+ count = __nfsd_file_close_inode(inode, &dispose);
+ trace_nfsd_file_close_inode_sync(inode, count);
nfsd_file_dispose_list_sync(&dispose);
}
@@ -543,19 +729,16 @@ nfsd_file_close_inode_sync(struct inode *inode)
* nfsd_file_close_inode - attempt a delayed close of a nfsd_file
* @inode: inode of the file to attempt to remove
*
- * Walk the whole hash bucket, looking for any files that correspond to "inode".
- * If any do, then unhash them and put the hashtable reference to them and
- * destroy any that had their last reference put.
+ * Unhash and put all cache item associated with @inode.
*/
static void
nfsd_file_close_inode(struct inode *inode)
{
- unsigned int hashval = (unsigned int)hash_long(inode->i_ino,
- NFSD_FILE_HASH_BITS);
LIST_HEAD(dispose);
+ unsigned int count;
- __nfsd_file_close_inode(inode, hashval, &dispose);
- trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose));
+ count = __nfsd_file_close_inode(inode, &dispose);
+ trace_nfsd_file_close_inode(inode, count);
nfsd_file_dispose_list_delayed(&dispose);
}
@@ -630,25 +813,21 @@ static const struct fsnotify_ops nfsd_file_fsnotify_ops = {
int
nfsd_file_cache_init(void)
{
- int ret = -ENOMEM;
- unsigned int i;
+ int ret;
- clear_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags);
-
- if (nfsd_file_hashtbl)
+ lockdep_assert_held(&nfsd_mutex);
+ if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1)
return 0;
+ ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params);
+ if (ret)
+ return ret;
+
+ ret = -ENOMEM;
nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0);
if (!nfsd_filecache_wq)
goto out;
- nfsd_file_hashtbl = kvcalloc(NFSD_FILE_HASH_SIZE,
- sizeof(*nfsd_file_hashtbl), GFP_KERNEL);
- if (!nfsd_file_hashtbl) {
- pr_err("nfsd: unable to allocate nfsd_file_hashtbl\n");
- goto out_err;
- }
-
nfsd_file_slab = kmem_cache_create("nfsd_file",
sizeof(struct nfsd_file), 0, 0, NULL);
if (!nfsd_file_slab) {
@@ -692,11 +871,6 @@ nfsd_file_cache_init(void)
goto out_notifier;
}
- for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) {
- INIT_HLIST_HEAD(&nfsd_file_hashtbl[i].nfb_head);
- spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock);
- }
-
INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker);
out:
return ret;
@@ -711,46 +885,47 @@ out_err:
nfsd_file_slab = NULL;
kmem_cache_destroy(nfsd_file_mark_slab);
nfsd_file_mark_slab = NULL;
- kvfree(nfsd_file_hashtbl);
- nfsd_file_hashtbl = NULL;
destroy_workqueue(nfsd_filecache_wq);
nfsd_filecache_wq = NULL;
+ rhashtable_destroy(&nfsd_file_rhash_tbl);
goto out;
}
/*
* Note this can deadlock with nfsd_file_lru_cb.
*/
-void
-nfsd_file_cache_purge(struct net *net)
+static void
+__nfsd_file_cache_purge(struct net *net)
{
- unsigned int i;
- struct nfsd_file *nf;
- struct hlist_node *next;
+ struct rhashtable_iter iter;
+ struct nfsd_file *nf;
LIST_HEAD(dispose);
bool del;
- if (!nfsd_file_hashtbl)
- return;
-
- for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) {
- struct nfsd_fcache_bucket *nfb = &nfsd_file_hashtbl[i];
+ rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter);
+ do {
+ rhashtable_walk_start(&iter);
- spin_lock(&nfb->nfb_lock);
- hlist_for_each_entry_safe(nf, next, &nfb->nfb_head, nf_node) {
+ nf = rhashtable_walk_next(&iter);
+ while (!IS_ERR_OR_NULL(nf)) {
if (net && nf->nf_net != net)
continue;
- del = nfsd_file_unhash_and_release_locked(nf, &dispose);
+ del = nfsd_file_unhash_and_dispose(nf, &dispose);
/*
* Deadlock detected! Something marked this entry as
* unhased, but hasn't removed it from the hash list.
*/
WARN_ON_ONCE(!del);
+
+ nf = rhashtable_walk_next(&iter);
}
- spin_unlock(&nfb->nfb_lock);
- nfsd_file_dispose_list(&dispose);
- }
+
+ rhashtable_walk_stop(&iter);
+ } while (nf == ERR_PTR(-EAGAIN));
+ rhashtable_walk_exit(&iter);
+
+ nfsd_file_dispose_list(&dispose);
}
static struct nfsd_fcache_disposal *
@@ -793,6 +968,19 @@ nfsd_file_cache_start_net(struct net *net)
return nn->fcache_disposal ? 0 : -ENOMEM;
}
+/**
+ * nfsd_file_cache_purge - Remove all cache items associated with @net
+ * @net: target net namespace
+ *
+ */
+void
+nfsd_file_cache_purge(struct net *net)
+{
+ lockdep_assert_held(&nfsd_mutex);
+ if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1)
+ __nfsd_file_cache_purge(net);
+}
+
void
nfsd_file_cache_shutdown_net(struct net *net)
{
@@ -803,7 +991,11 @@ nfsd_file_cache_shutdown_net(struct net *net)
void
nfsd_file_cache_shutdown(void)
{
- set_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags);
+ int i;
+
+ lockdep_assert_held(&nfsd_mutex);
+ if (test_and_clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0)
+ return;
lease_unregister_notifier(&nfsd_file_lease_notifier);
unregister_shrinker(&nfsd_file_shrinker);
@@ -812,7 +1004,7 @@ nfsd_file_cache_shutdown(void)
* calling nfsd_file_cache_purge
*/
cancel_delayed_work_sync(&nfsd_filecache_laundrette);
- nfsd_file_cache_purge(NULL);
+ __nfsd_file_cache_purge(NULL);
list_lru_destroy(&nfsd_file_lru);
rcu_barrier();
fsnotify_put_group(nfsd_file_fsnotify_group);
@@ -822,124 +1014,96 @@ nfsd_file_cache_shutdown(void)
fsnotify_wait_marks_destroyed();
kmem_cache_destroy(nfsd_file_mark_slab);
nfsd_file_mark_slab = NULL;
- kvfree(nfsd_file_hashtbl);
- nfsd_file_hashtbl = NULL;
destroy_workqueue(nfsd_filecache_wq);
nfsd_filecache_wq = NULL;
-}
-
-static bool
-nfsd_match_cred(const struct cred *c1, const struct cred *c2)
-{
- int i;
-
- if (!uid_eq(c1->fsuid, c2->fsuid))
- return false;
- if (!gid_eq(c1->fsgid, c2->fsgid))
- return false;
- if (c1->group_info == NULL || c2->group_info == NULL)
- return c1->group_info == c2->group_info;
- if (c1->group_info->ngroups != c2->group_info->ngroups)
- return false;
- for (i = 0; i < c1->group_info->ngroups; i++) {
- if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i]))
- return false;
- }
- return true;
-}
-
-static struct nfsd_file *
-nfsd_file_find_locked(struct inode *inode, unsigned int may_flags,
- unsigned int hashval, struct net *net)
-{
- struct nfsd_file *nf;
- unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
-
- hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head,
- nf_node, lockdep_is_held(&nfsd_file_hashtbl[hashval].nfb_lock)) {
- if (nf->nf_may != need)
- continue;
- if (nf->nf_inode != inode)
- continue;
- if (nf->nf_net != net)
- continue;
- if (!nfsd_match_cred(nf->nf_cred, current_cred()))
- continue;
- if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags))
- continue;
- if (nfsd_file_get(nf) != NULL)
- return nf;
+ rhashtable_destroy(&nfsd_file_rhash_tbl);
+
+ for_each_possible_cpu(i) {
+ per_cpu(nfsd_file_cache_hits, i) = 0;
+ per_cpu(nfsd_file_acquisitions, i) = 0;
+ per_cpu(nfsd_file_releases, i) = 0;
+ per_cpu(nfsd_file_total_age, i) = 0;
+ per_cpu(nfsd_file_pages_flushed, i) = 0;
+ per_cpu(nfsd_file_evictions, i) = 0;
}
- return NULL;
}
/**
- * nfsd_file_is_cached - are there any cached open files for this fh?
- * @inode: inode of the file to check
+ * nfsd_file_is_cached - are there any cached open files for this inode?
+ * @inode: inode to check
+ *
+ * The lookup matches inodes in all net namespaces and is atomic wrt
+ * nfsd_file_acquire().
*
- * Scan the hashtable for open files that match this fh. Returns true if there
- * are any, and false if not.
+ * Return values:
+ * %true: filecache contains at least one file matching this inode
+ * %false: filecache contains no files matching this inode
*/
bool
nfsd_file_is_cached(struct inode *inode)
{
- bool ret = false;
- struct nfsd_file *nf;
- unsigned int hashval;
-
- hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS);
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head,
- nf_node) {
- if (inode == nf->nf_inode) {
- ret = true;
- break;
- }
- }
- rcu_read_unlock();
- trace_nfsd_file_is_cached(inode, hashval, (int)ret);
+ struct nfsd_file_lookup_key key = {
+ .type = NFSD_FILE_KEY_INODE,
+ .inode = inode,
+ };
+ bool ret = false;
+
+ if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key,
+ nfsd_file_rhash_params) != NULL)
+ ret = true;
+ trace_nfsd_file_is_cached(inode, (int)ret);
return ret;
}
static __be32
-nfsd_do_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf, bool open)
{
- __be32 status;
- struct net *net = SVC_NET(rqstp);
+ struct nfsd_file_lookup_key key = {
+ .type = NFSD_FILE_KEY_FULL,
+ .need = may_flags & NFSD_FILE_MAY_MASK,
+ .net = SVC_NET(rqstp),
+ };
struct nfsd_file *nf, *new;
- struct inode *inode;
- unsigned int hashval;
bool retry = true;
+ __be32 status;
- /* FIXME: skip this if fh_dentry is already set? */
status = fh_verify(rqstp, fhp, S_IFREG,
may_flags|NFSD_MAY_OWNER_OVERRIDE);
if (status != nfs_ok)
return status;
+ key.inode = d_inode(fhp->fh_dentry);
+ key.cred = get_current_cred();
- inode = d_inode(fhp->fh_dentry);
- hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS);
retry:
- rcu_read_lock();
- nf = nfsd_file_find_locked(inode, may_flags, hashval, net);
- rcu_read_unlock();
+ /* Avoid allocation if the item is already in cache */
+ nf = rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key,
+ nfsd_file_rhash_params);
+ if (nf)
+ nf = nfsd_file_get(nf);
if (nf)
goto wait_for_construction;
- new = nfsd_file_alloc(inode, may_flags, hashval, net);
+ new = nfsd_file_alloc(&key, may_flags);
if (!new) {
- trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags,
- NULL, nfserr_jukebox);
- return nfserr_jukebox;
+ status = nfserr_jukebox;
+ goto out_status;
}
- spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock);
- nf = nfsd_file_find_locked(inode, may_flags, hashval, net);
- if (nf == NULL)
+ nf = rhashtable_lookup_get_insert_key(&nfsd_file_rhash_tbl,
+ &key, &new->nf_rhash,
+ nfsd_file_rhash_params);
+ if (!nf) {
+ nf = new;
goto open_file;
- spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock);
+ }
+ if (IS_ERR(nf))
+ goto insert_err;
+ nf = nfsd_file_get(nf);
+ if (nf == NULL) {
+ nf = new;
+ goto open_file;
+ }
nfsd_file_slab_free(&new->nf_rcu);
wait_for_construction:
@@ -947,6 +1111,7 @@ wait_for_construction:
/* Did construction of this file fail? */
if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+ trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf);
if (!retry) {
status = nfserr_jukebox;
goto out;
@@ -956,49 +1121,29 @@ wait_for_construction:
goto retry;
}
+ nfsd_file_lru_remove(nf);
this_cpu_inc(nfsd_file_cache_hits);
- if (!(may_flags & NFSD_MAY_NOT_BREAK_LEASE)) {
- bool write = (may_flags & NFSD_MAY_WRITE);
-
- if (test_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags) ||
- (test_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags) && write)) {
- status = nfserrno(nfsd_open_break_lease(
- file_inode(nf->nf_file), may_flags));
- if (status == nfs_ok) {
- clear_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags);
- if (write)
- clear_bit(NFSD_FILE_BREAK_WRITE,
- &nf->nf_flags);
- }
- }
- }
+ status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
out:
if (status == nfs_ok) {
+ if (open)
+ this_cpu_inc(nfsd_file_acquisitions);
*pnf = nf;
} else {
nfsd_file_put(nf);
nf = NULL;
}
- trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, nf, status);
+out_status:
+ put_cred(key.cred);
+ if (open)
+ trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
return status;
+
open_file:
- nf = new;
- /* Take reference for the hashtable */
- 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);
- hlist_add_head_rcu(&nf->nf_node, &nfsd_file_hashtbl[hashval].nfb_head);
- ++nfsd_file_hashtbl[hashval].nfb_count;
- 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);
- 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);
+ trace_nfsd_file_alloc(nf);
+ nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
if (nf->nf_mark) {
if (open) {
status = nfsd_open_verified(rqstp, fhp, may_flags,
@@ -1012,18 +1157,20 @@ open_file:
* If construction failed, or we raced with a call to unlink()
* then unhash.
*/
- if (status != nfs_ok || inode->i_nlink == 0) {
- bool do_free;
- spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock);
- do_free = nfsd_file_unhash(nf);
- spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock);
- if (do_free)
+ if (status != nfs_ok || key.inode->i_nlink == 0)
+ if (nfsd_file_unhash(nf))
nfsd_file_put_noref(nf);
- }
clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags);
smp_mb__after_atomic();
wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING);
goto out;
+
+insert_err:
+ nfsd_file_slab_free(&new->nf_rcu);
+ trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, PTR_ERR(nf));
+ nf = NULL;
+ status = nfserr_jukebox;
+ goto out_status;
}
/**
@@ -1040,7 +1187,7 @@ __be32
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, true);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true);
}
/**
@@ -1057,7 +1204,7 @@ __be32
nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false);
}
/*
@@ -1067,29 +1214,49 @@ nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
*/
static int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
{
- unsigned int i, count = 0, longest = 0;
- unsigned long hits = 0;
+ unsigned long releases = 0, pages_flushed = 0, evictions = 0;
+ unsigned long hits = 0, acquisitions = 0;
+ unsigned int i, count = 0, buckets = 0;
+ unsigned long lru = 0, total_age = 0;
- /*
- * No need for spinlocks here since we're not terribly interested in
- * accuracy. We do take the nfsd_mutex simply to ensure that we
- * don't end up racing with server shutdown
- */
+ /* Serialize with server shutdown */
mutex_lock(&nfsd_mutex);
- if (nfsd_file_hashtbl) {
- for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) {
- count += nfsd_file_hashtbl[i].nfb_count;
- longest = max(longest, nfsd_file_hashtbl[i].nfb_count);
- }
+ if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) {
+ struct bucket_table *tbl;
+ struct rhashtable *ht;
+
+ lru = list_lru_count(&nfsd_file_lru);
+
+ rcu_read_lock();
+ ht = &nfsd_file_rhash_tbl;
+ count = atomic_read(&ht->nelems);
+ tbl = rht_dereference_rcu(ht->tbl, ht);
+ buckets = tbl->size;
+ rcu_read_unlock();
}
mutex_unlock(&nfsd_mutex);
- for_each_possible_cpu(i)
+ for_each_possible_cpu(i) {
hits += per_cpu(nfsd_file_cache_hits, i);
+ acquisitions += per_cpu(nfsd_file_acquisitions, i);
+ releases += per_cpu(nfsd_file_releases, i);
+ total_age += per_cpu(nfsd_file_total_age, i);
+ evictions += per_cpu(nfsd_file_evictions, i);
+ pages_flushed += per_cpu(nfsd_file_pages_flushed, i);
+ }
seq_printf(m, "total entries: %u\n", count);
- seq_printf(m, "longest chain: %u\n", longest);
+ seq_printf(m, "hash buckets: %u\n", buckets);
+ seq_printf(m, "lru entries: %lu\n", lru);
seq_printf(m, "cache hits: %lu\n", hits);
+ seq_printf(m, "acquisitions: %lu\n", acquisitions);
+ seq_printf(m, "releases: %lu\n", releases);
+ seq_printf(m, "evictions: %lu\n", evictions);
+ if (releases)
+ seq_printf(m, "mean age (ms): %ld\n", total_age / releases);
+ else
+ seq_printf(m, "mean age (ms): -\n");
+ seq_printf(m, "pages flushed: %lu\n", pages_flushed);
return 0;
}
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 1da0c79a5580..8e8c0c47d67d 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -29,7 +29,7 @@ struct nfsd_file_mark {
* never be dereferenced, only used for comparison.
*/
struct nfsd_file {
- struct hlist_node nf_node;
+ struct rhash_head nf_rhash;
struct list_head nf_lru;
struct rcu_head nf_rcu;
struct file *nf_file;
@@ -37,15 +37,13 @@ struct nfsd_file {
struct net *nf_net;
#define NFSD_FILE_HASHED (0)
#define NFSD_FILE_PENDING (1)
-#define NFSD_FILE_BREAK_READ (2)
-#define NFSD_FILE_BREAK_WRITE (3)
-#define NFSD_FILE_REFERENCED (4)
+#define NFSD_FILE_REFERENCED (2)
unsigned long nf_flags;
- struct inode *nf_inode;
- unsigned int nf_hashval;
+ struct inode *nf_inode; /* don't deref */
refcount_t nf_ref;
unsigned char nf_may;
struct nfsd_file_mark *nf_mark;
+ ktime_t nf_birthtime;
};
int nfsd_file_cache_init(void);
@@ -54,6 +52,7 @@ 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);
+void nfsd_file_close(struct nfsd_file *nf);
struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
void nfsd_file_close_inode_sync(struct inode *inode);
bool nfsd_file_is_cached(struct inode *inode);
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 1b1a962a1804..ffe17743cc74 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -189,6 +189,9 @@ struct nfsd_net {
struct nfsd_fcache_disposal *fcache_disposal;
siphash_key_t siphash_key;
+
+ atomic_t nfs4_client_count;
+ int nfs4_max_clients;
};
/* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index b5760801d377..9edd3c1a30fb 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -111,7 +111,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
if (error)
goto out_errno;
- fh_lock(fh);
+ inode_lock(inode);
error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS,
argp->acl_access);
@@ -122,7 +122,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
if (error)
goto out_drop_lock;
- fh_unlock(fh);
+ inode_unlock(inode);
fh_drop_write(fh);
@@ -136,7 +136,7 @@ out:
return rpc_success;
out_drop_lock:
- fh_unlock(fh);
+ inode_unlock(inode);
fh_drop_write(fh);
out_errno:
resp->status = nfserrno(error);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 35b2ebda14da..9446c6743664 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -101,7 +101,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
if (error)
goto out_errno;
- fh_lock(fh);
+ inode_lock(inode);
error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS,
argp->acl_access);
@@ -111,7 +111,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
argp->acl_default);
out_drop_lock:
- fh_unlock(fh);
+ inode_unlock(inode);
fh_drop_write(fh);
out_errno:
resp->status = nfserrno(error);
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 981a3a7a6e16..a41cca619338 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -67,12 +67,15 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp)
{
struct nfsd3_sattrargs *argp = rqstp->rq_argp;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
dprintk("nfsd: SETATTR(3) %s\n",
SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- resp->status = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,
+ resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs,
argp->check_guard, argp->guardtime);
return rpc_success;
}
@@ -233,6 +236,9 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
{
struct iattr *iap = &argp->attrs;
struct dentry *parent, *child;
+ struct nfsd_attrs attrs = {
+ .na_iattr = iap,
+ };
__u32 v_mtime, v_atime;
struct inode *inode;
__be32 status;
@@ -254,7 +260,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_err)
return nfserrno(host_err);
- fh_lock_nested(fhp, I_MUTEX_PARENT);
+ inode_lock_nested(inode, I_MUTEX_PARENT);
child = lookup_one_len(argp->name, parent, argp->len);
if (IS_ERR(child)) {
@@ -312,11 +318,13 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (!IS_POSIXACL(inode))
iap->ia_mode &= ~current_umask();
+ fh_fill_pre_attrs(fhp);
host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
if (host_err < 0) {
status = nfserrno(host_err);
goto out;
}
+ fh_fill_post_attrs(fhp);
/* A newly created file already has a file size of zero. */
if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
@@ -331,10 +339,10 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
}
set_attr:
- status = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+ status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs);
out:
- fh_unlock(fhp);
+ inode_unlock(inode);
if (child && !IS_ERR(child))
dput(child);
fh_drop_write(fhp);
@@ -368,6 +376,9 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp)
{
struct nfsd3_createargs *argp = rqstp->rq_argp;
struct nfsd3_diropres *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
dprintk("nfsd: MKDIR(3) %s %.*s\n",
SVCFH_fmt(&argp->fh),
@@ -378,8 +389,7 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp)
fh_copy(&resp->dirfh, &argp->fh);
fh_init(&resp->fh, NFS3_FHSIZE);
resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len,
- &argp->attrs, S_IFDIR, 0, &resp->fh);
- fh_unlock(&resp->dirfh);
+ &attrs, S_IFDIR, 0, &resp->fh);
return rpc_success;
}
@@ -388,6 +398,9 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp)
{
struct nfsd3_symlinkargs *argp = rqstp->rq_argp;
struct nfsd3_diropres *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
if (argp->tlen == 0) {
resp->status = nfserr_inval;
@@ -414,7 +427,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp)
fh_copy(&resp->dirfh, &argp->ffh);
fh_init(&resp->fh, NFS3_FHSIZE);
resp->status = nfsd_symlink(rqstp, &resp->dirfh, argp->fname,
- argp->flen, argp->tname, &resp->fh);
+ argp->flen, argp->tname, &attrs, &resp->fh);
kfree(argp->tname);
out:
return rpc_success;
@@ -428,6 +441,9 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp)
{
struct nfsd3_mknodargs *argp = rqstp->rq_argp;
struct nfsd3_diropres *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
int type;
dev_t rdev = 0;
@@ -453,8 +469,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp)
type = nfs3_ftypes[argp->ftype];
resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len,
- &argp->attrs, type, rdev, &resp->fh);
- fh_unlock(&resp->dirfh);
+ &attrs, type, rdev, &resp->fh);
out:
return rpc_success;
}
@@ -477,7 +492,6 @@ nfsd3_proc_remove(struct svc_rqst *rqstp)
fh_copy(&resp->fh, &argp->fh);
resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR,
argp->name, argp->len);
- fh_unlock(&resp->fh);
return rpc_success;
}
@@ -498,7 +512,6 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp)
fh_copy(&resp->fh, &argp->fh);
resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR,
argp->name, argp->len);
- fh_unlock(&resp->fh);
return rpc_success;
}
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index eaa3a0cf38f1..bb8e2f6d7d03 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -751,58 +751,26 @@ out_estate:
return ret;
}
-__be32
-nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct nfs4_acl *acl)
+__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl,
+ struct nfsd_attrs *attr)
{
- __be32 error;
int host_error;
- struct dentry *dentry;
- struct inode *inode;
- struct posix_acl *pacl = NULL, *dpacl = NULL;
unsigned int flags = 0;
- /* Get inode */
- error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR);
- if (error)
- return error;
-
- dentry = fhp->fh_dentry;
- inode = d_inode(dentry);
+ if (!acl)
+ return nfs_ok;
- if (S_ISDIR(inode->i_mode))
+ if (type == NF4DIR)
flags = NFS4_ACL_DIR;
- host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
+ host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl,
+ &attr->na_dpacl, flags);
if (host_error == -EINVAL)
return nfserr_attrnotsupp;
- if (host_error < 0)
- goto out_nfserr;
-
- fh_lock(fhp);
-
- host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl);
- if (host_error < 0)
- goto out_drop_lock;
-
- if (S_ISDIR(inode->i_mode)) {
- host_error = set_posix_acl(&init_user_ns, inode,
- ACL_TYPE_DEFAULT, dpacl);
- }
-
-out_drop_lock:
- fh_unlock(fhp);
-
- posix_acl_release(pacl);
- posix_acl_release(dpacl);
-out_nfserr:
- if (host_error == -EOPNOTSUPP)
- return nfserr_attrnotsupp;
else
return nfserrno(host_error);
}
-
static short
ace2type(struct nfs4_ace *ace)
{
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 11f8715d92d6..4ce328209f61 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -679,7 +679,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
* case NFS4_OK:
* write_response4 coa_resok4;
* default:
- * length4 coa_bytes_copied;
+ * length4 coa_bytes_copied;
* };
* struct CB_OFFLOAD4args {
* nfs_fh4 coa_fh;
@@ -688,21 +688,22 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
* };
*/
static void encode_offload_info4(struct xdr_stream *xdr,
- __be32 nfserr,
- const struct nfsd4_copy *cp)
+ const struct nfsd4_cb_offload *cbo)
{
__be32 *p;
p = xdr_reserve_space(xdr, 4);
- *p++ = nfserr;
- if (!nfserr) {
+ *p = cbo->co_nfserr;
+ switch (cbo->co_nfserr) {
+ case nfs_ok:
p = xdr_reserve_space(xdr, 4 + 8 + 4 + NFS4_VERIFIER_SIZE);
p = xdr_encode_empty_array(p);
- p = xdr_encode_hyper(p, cp->cp_res.wr_bytes_written);
- *p++ = cpu_to_be32(cp->cp_res.wr_stable_how);
- p = xdr_encode_opaque_fixed(p, cp->cp_res.wr_verifier.data,
+ p = xdr_encode_hyper(p, cbo->co_res.wr_bytes_written);
+ *p++ = cpu_to_be32(cbo->co_res.wr_stable_how);
+ p = xdr_encode_opaque_fixed(p, cbo->co_res.wr_verifier.data,
NFS4_VERIFIER_SIZE);
- } else {
+ break;
+ default:
p = xdr_reserve_space(xdr, 8);
/* We always return success if bytes were written */
p = xdr_encode_hyper(p, 0);
@@ -710,18 +711,16 @@ static void encode_offload_info4(struct xdr_stream *xdr,
}
static void encode_cb_offload4args(struct xdr_stream *xdr,
- __be32 nfserr,
- const struct knfsd_fh *fh,
- const struct nfsd4_copy *cp,
+ const struct nfsd4_cb_offload *cbo,
struct nfs4_cb_compound_hdr *hdr)
{
__be32 *p;
p = xdr_reserve_space(xdr, 4);
- *p++ = cpu_to_be32(OP_CB_OFFLOAD);
- encode_nfs_fh4(xdr, fh);
- encode_stateid4(xdr, &cp->cp_res.cb_stateid);
- encode_offload_info4(xdr, nfserr, cp);
+ *p = cpu_to_be32(OP_CB_OFFLOAD);
+ encode_nfs_fh4(xdr, &cbo->co_fh);
+ encode_stateid4(xdr, &cbo->co_res.cb_stateid);
+ encode_offload_info4(xdr, cbo);
hdr->nops++;
}
@@ -731,8 +730,8 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req,
const void *data)
{
const struct nfsd4_callback *cb = data;
- const struct nfsd4_copy *cp =
- container_of(cb, struct nfsd4_copy, cp_cb);
+ const struct nfsd4_cb_offload *cbo =
+ container_of(cb, struct nfsd4_cb_offload, co_cb);
struct nfs4_cb_compound_hdr hdr = {
.ident = 0,
.minorversion = cb->cb_clp->cl_minorversion,
@@ -740,7 +739,7 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req,
encode_cb_compound4args(xdr, &hdr);
encode_cb_sequence4args(xdr, cb, &hdr);
- encode_cb_offload4args(xdr, cp->nfserr, &cp->fh, cp, &hdr);
+ encode_cb_offload4args(xdr, cbo, &hdr);
encode_cb_nops(&hdr);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3895eb52d2b1..a72ab97f77ef 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -64,36 +64,6 @@ MODULE_PARM_DESC(nfsd4_ssc_umount_timeout,
"idle msecs before unmount export from source server");
#endif
-#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-#include <linux/security.h>
-
-static inline void
-nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
-{
- struct inode *inode = d_inode(resfh->fh_dentry);
- int status;
-
- inode_lock(inode);
- status = security_inode_setsecctx(resfh->fh_dentry,
- label->data, label->len);
- inode_unlock(inode);
-
- if (status)
- /*
- * XXX: We should really fail the whole open, but we may
- * already have created a new file, so it may be too
- * late. For now this seems the least of evils:
- */
- bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
-
- return;
-}
-#else
-static inline void
-nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
-{ }
-#endif
-
#define NFSDDBG_FACILITY NFSDDBG_PROC
static u32 nfsd_attrmask[] = {
@@ -158,26 +128,6 @@ is_create_with_attrs(struct nfsd4_open *open)
|| open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
}
-/*
- * if error occurs when setting the acl, just clear the acl bit
- * in the returned attr bitmap.
- */
-static void
-do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct nfs4_acl *acl, u32 *bmval)
-{
- __be32 status;
-
- status = nfsd4_set_nfs4_acl(rqstp, fhp, acl);
- if (status)
- /*
- * We should probably fail the whole open at this point,
- * but we've already created the file, so it's too late;
- * So this seems the least of evils:
- */
- bmval[0] &= ~FATTR4_WORD0_ACL;
-}
-
static inline void
fh_dup2(struct svc_fh *dst, struct svc_fh *src)
{
@@ -286,6 +236,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct svc_fh *resfhp, struct nfsd4_open *open)
{
struct iattr *iap = &open->op_iattr;
+ struct nfsd_attrs attrs = {
+ .na_iattr = iap,
+ .na_seclabel = &open->op_label,
+ };
struct dentry *parent, *child;
__u32 v_mtime, v_atime;
struct inode *inode;
@@ -307,7 +261,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_err)
return nfserrno(host_err);
- fh_lock_nested(fhp, I_MUTEX_PARENT);
+ if (is_create_with_attrs(open))
+ nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs);
+
+ inode_lock_nested(inode, I_MUTEX_PARENT);
child = lookup_one_len(open->op_fname, parent, open->op_fnamelen);
if (IS_ERR(child)) {
@@ -345,6 +302,11 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (d_really_is_positive(child)) {
status = nfs_ok;
+ /* NFSv4 protocol requires change attributes even though
+ * no change happened.
+ */
+ fh_fill_both_attrs(fhp);
+
switch (open->op_createmode) {
case NFS4_CREATE_UNCHECKED:
if (!d_is_reg(child))
@@ -386,10 +348,12 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (!IS_POSIXACL(inode))
iap->ia_mode &= ~current_umask();
+ fh_fill_pre_attrs(fhp);
status = nfsd4_vfs_create(fhp, child, open);
if (status != nfs_ok)
goto out;
open->op_created = true;
+ fh_fill_post_attrs(fhp);
/* A newly created file already has a file size of zero. */
if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
@@ -404,10 +368,15 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
}
set_attr:
- status = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+ status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs);
+ if (attrs.na_labelerr)
+ open->op_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+ if (attrs.na_aclerr)
+ open->op_bmval[0] &= ~FATTR4_WORD0_ACL;
out:
- fh_unlock(fhp);
+ inode_unlock(inode);
+ nfsd_attrs_free(&attrs);
if (child && !IS_ERR(child))
dput(child);
fh_drop_write(fhp);
@@ -447,9 +416,6 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
status = nfsd4_create_file(rqstp, current_fh, *resfh, open);
current->fs->umask = 0;
- if (!status && open->op_label.len)
- nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);
-
/*
* Following rfc 3530 14.2.16, and rfc 5661 18.16.4
* use the returned bitmask to indicate which attributes
@@ -458,24 +424,21 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0)
open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
FATTR4_WORD1_TIME_MODIFY);
- } else
- /*
- * Note this may exit with the parent still locked.
- * We will hold the lock until nfsd4_open's final
- * lookup, to prevent renames or unlinks until we've had
- * a chance to an acquire a delegation if appropriate.
- */
+ } else {
status = nfsd_lookup(rqstp, current_fh,
open->op_fname, open->op_fnamelen, *resfh);
+ if (!status)
+ /* NFSv4 protocol requires change attributes even though
+ * no change happened.
+ */
+ fh_fill_both_attrs(current_fh);
+ }
if (status)
goto out;
status = nfsd_check_obj_isreg(*resfh);
if (status)
goto out;
- if (is_create_with_attrs(open) && open->op_acl != NULL)
- do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval);
-
nfsd4_set_open_owner_reply_cache(cstate, open, *resfh);
accmode = NFSD_MAY_NOP;
if (open->op_created ||
@@ -547,6 +510,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
open->op_openowner);
open->op_filp = NULL;
+ open->op_rqstp = rqstp;
/* This check required by spec. */
if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
@@ -630,9 +594,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
status = nfsd4_process_open2(rqstp, resfh, open);
- WARN(status && open->op_created,
- "nfsd4_process_open2 failed to open newly-created file! status=%u\n",
- be32_to_cpu(status));
+ if (status && open->op_created)
+ pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n",
+ be32_to_cpu(status));
if (reclaim && !status)
nn->somebody_reclaimed = true;
out:
@@ -786,6 +750,10 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_create *create = &u->create;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &create->cr_iattr,
+ .na_seclabel = &create->cr_label,
+ };
struct svc_fh resfh;
__be32 status;
dev_t rdev;
@@ -801,12 +769,13 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
return status;
+ status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs);
current->fs->umask = create->cr_umask;
switch (create->cr_type) {
case NF4LNK:
status = nfsd_symlink(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- create->cr_data, &resfh);
+ create->cr_data, &attrs, &resfh);
break;
case NF4BLK:
@@ -817,7 +786,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out_umask;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- &create->cr_iattr, S_IFBLK, rdev, &resfh);
+ &attrs, S_IFBLK, rdev, &resfh);
break;
case NF4CHR:
@@ -828,26 +797,26 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out_umask;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- &create->cr_iattr,S_IFCHR, rdev, &resfh);
+ &attrs, S_IFCHR, rdev, &resfh);
break;
case NF4SOCK:
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- &create->cr_iattr, S_IFSOCK, 0, &resfh);
+ &attrs, S_IFSOCK, 0, &resfh);
break;
case NF4FIFO:
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- &create->cr_iattr, S_IFIFO, 0, &resfh);
+ &attrs, S_IFIFO, 0, &resfh);
break;
case NF4DIR:
create->cr_iattr.ia_valid &= ~ATTR_SIZE;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
- &create->cr_iattr, S_IFDIR, 0, &resfh);
+ &attrs, S_IFDIR, 0, &resfh);
break;
default:
@@ -857,20 +826,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
- if (create->cr_label.len)
- nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval);
-
- if (create->cr_acl != NULL)
- do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
- create->cr_bmval);
-
- fh_unlock(&cstate->current_fh);
+ if (attrs.na_labelerr)
+ create->cr_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+ if (attrs.na_aclerr)
+ create->cr_bmval[0] &= ~FATTR4_WORD0_ACL;
set_change_info(&create->cr_cinfo, &cstate->current_fh);
fh_dup2(&cstate->current_fh, &resfh);
out:
fh_put(&resfh);
out_umask:
current->fs->umask = 0;
+ nfsd_attrs_free(&attrs);
return status;
}
@@ -1043,10 +1009,8 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_grace;
status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
remove->rm_name, remove->rm_namelen);
- if (!status) {
- fh_unlock(&cstate->current_fh);
+ if (!status)
set_change_info(&remove->rm_cinfo, &cstate->current_fh);
- }
return status;
}
@@ -1086,7 +1050,6 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&exp, &dentry);
if (err)
return err;
- fh_unlock(&cstate->current_fh);
if (d_really_is_negative(dentry)) {
exp_put(exp);
err = nfserr_noent;
@@ -1141,6 +1104,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_setattr *setattr = &u->setattr;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &setattr->sa_iattr,
+ .na_seclabel = &setattr->sa_label,
+ };
+ struct inode *inode;
__be32 status = nfs_ok;
int err;
@@ -1163,19 +1131,18 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
- if (setattr->sa_acl != NULL)
- status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
- setattr->sa_acl);
- if (status)
- goto out;
- if (setattr->sa_label.len)
- status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh,
- &setattr->sa_label);
+ inode = cstate->current_fh.fh_dentry->d_inode;
+ status = nfsd4_acl_to_attr(S_ISDIR(inode->i_mode) ? NF4DIR : NF4REG,
+ setattr->sa_acl, &attrs);
+
if (status)
goto out;
- status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
+ status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs,
0, (time64_t)0);
+ if (!status)
+ status = nfserrno(attrs.na_labelerr);
out:
+ nfsd_attrs_free(&attrs);
fh_drop_write(&cstate->current_fh);
return status;
}
@@ -1285,30 +1252,17 @@ out:
return status;
}
-void nfs4_put_copy(struct nfsd4_copy *copy)
+static void nfs4_put_copy(struct nfsd4_copy *copy)
{
if (!refcount_dec_and_test(&copy->refcount))
return;
+ kfree(copy->cp_src);
kfree(copy);
}
-static bool
-check_and_set_stop_copy(struct nfsd4_copy *copy)
-{
- bool value;
-
- spin_lock(&copy->cp_clp->async_lock);
- value = copy->stopped;
- if (!copy->stopped)
- copy->stopped = true;
- spin_unlock(&copy->cp_clp->async_lock);
- return value;
-}
-
static void nfsd4_stop_copy(struct nfsd4_copy *copy)
{
- /* only 1 thread should stop the copy */
- if (!check_and_set_stop_copy(copy))
+ if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags))
kthread_stop(copy->copy_task);
nfs4_put_copy(copy);
}
@@ -1389,7 +1343,7 @@ try_again:
return 0;
}
if (work) {
- strncpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr));
+ strlcpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1);
refcount_set(&work->nsui_refcnt, 2);
work->nsui_busy = true;
list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list);
@@ -1549,7 +1503,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
if (status)
goto out;
- status = nfsd4_interssc_connect(&copy->cp_src, rqstp, mount);
+ status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount);
if (status)
goto out;
@@ -1567,7 +1521,7 @@ out:
}
static void
-nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp,
struct nfsd_file *dst)
{
bool found = false;
@@ -1576,9 +1530,9 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
struct nfsd4_ssc_umount_item *ni = NULL;
struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id);
- nfs42_ssc_close(src->nf_file);
+ nfs42_ssc_close(filp);
nfsd_file_put(dst);
- fput(src->nf_file);
+ fput(filp);
if (!nn) {
mntput(ss_mnt);
@@ -1621,7 +1575,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
}
static void
-nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src,
+nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp,
struct nfsd_file *dst)
{
}
@@ -1658,9 +1612,10 @@ nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst)
static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
{
- struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb);
+ struct nfsd4_cb_offload *cbo =
+ container_of(cb, struct nfsd4_cb_offload, co_cb);
- nfs4_put_copy(copy);
+ kfree(cbo);
}
static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
@@ -1677,15 +1632,16 @@ static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = {
static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
{
copy->cp_res.wr_stable_how =
- copy->committed ? NFS_FILE_SYNC : NFS_UNSTABLE;
- copy->cp_synchronous = sync;
+ test_bit(NFSD4_COPY_F_COMMITTED, &copy->cp_flags) ?
+ NFS_FILE_SYNC : NFS_UNSTABLE;
+ nfsd4_copy_set_sync(copy, sync);
gen_boot_verifier(&copy->cp_res.wr_verifier, copy->cp_clp->net);
}
-static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
+static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy,
+ struct file *dst,
+ struct file *src)
{
- struct file *dst = copy->nf_dst->nf_file;
- struct file *src = copy->nf_src->nf_file;
errseq_t since;
ssize_t bytes_copied = 0;
u64 bytes_total = copy->cp_count;
@@ -1707,26 +1663,29 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
copy->cp_res.wr_bytes_written += bytes_copied;
src_pos += bytes_copied;
dst_pos += bytes_copied;
- } while (bytes_total > 0 && !copy->cp_synchronous);
+ } while (bytes_total > 0 && nfsd4_copy_is_async(copy));
/* for a non-zero asynchronous copy do a commit of data */
- if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) {
+ if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) {
since = READ_ONCE(dst->f_wb_err);
status = vfs_fsync_range(dst, copy->cp_dst_pos,
copy->cp_res.wr_bytes_written, 0);
if (!status)
status = filemap_check_wb_err(dst->f_mapping, since);
if (!status)
- copy->committed = true;
+ set_bit(NFSD4_COPY_F_COMMITTED, &copy->cp_flags);
}
return bytes_copied;
}
-static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
+static __be32 nfsd4_do_copy(struct nfsd4_copy *copy,
+ struct file *src, struct file *dst,
+ bool sync)
{
__be32 status;
ssize_t bytes;
- bytes = _nfsd_copy_file_range(copy);
+ bytes = _nfsd_copy_file_range(copy, dst, src);
+
/* for async copy, we ignore the error, client can always retry
* to get the error
*/
@@ -1736,13 +1695,6 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
nfsd4_init_copy_res(copy, sync);
status = nfs_ok;
}
-
- 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;
}
@@ -1751,17 +1703,17 @@ static void 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;
dst->cp_count = src->cp_count;
- dst->cp_synchronous = src->cp_synchronous;
+ dst->cp_flags = src->cp_flags;
memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res));
memcpy(&dst->fh, &src->fh, sizeof(src->fh));
dst->cp_clp = src->cp_clp;
dst->nf_dst = nfsd_file_get(src->nf_dst);
- dst->cp_intra = src->cp_intra;
- if (src->cp_intra) /* for inter, file_src doesn't exist yet */
+ /* for inter, nf_src doesn't exist yet */
+ if (!nfsd4_ssc_is_inter(src))
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->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;
@@ -1771,7 +1723,7 @@ static void cleanup_async_copy(struct nfsd4_copy *copy)
{
nfs4_free_copy_state(copy);
nfsd_file_put(copy->nf_dst);
- if (copy->cp_intra)
+ if (!nfsd4_ssc_is_inter(copy))
nfsd_file_put(copy->nf_src);
spin_lock(&copy->cp_clp->async_lock);
list_del(&copy->copies);
@@ -1779,45 +1731,58 @@ static void cleanup_async_copy(struct nfsd4_copy *copy)
nfs4_put_copy(copy);
}
+static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr)
+{
+ struct nfsd4_cb_offload *cbo;
+
+ cbo = kzalloc(sizeof(*cbo), GFP_KERNEL);
+ if (!cbo)
+ return;
+
+ memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
+ memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
+ cbo->co_nfserr = nfserr;
+
+ nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
+ NFSPROC4_CLNT_CB_OFFLOAD);
+ trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid,
+ &cbo->co_fh, copy->cp_count, nfserr);
+ nfsd4_run_cb(&cbo->co_cb);
+}
+
+/**
+ * nfsd4_do_async_copy - kthread function for background server-side COPY
+ * @data: arguments for COPY operation
+ *
+ * Return values:
+ * %0: Copy operation is done.
+ */
static int nfsd4_do_async_copy(void *data)
{
struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
- struct nfsd4_copy *cb_copy;
+ __be32 nfserr;
- 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;
+ if (nfsd4_ssc_is_inter(copy)) {
+ struct file *filp;
+
+ filp = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
+ &copy->stateid);
+ if (IS_ERR(filp)) {
+ nfserr = nfserr_offload_denied;
nfsd4_interssc_disconnect(copy->ss_mnt);
goto do_callback;
}
+ nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file,
+ false);
+ nfsd4_cleanup_inter_ssc(copy->ss_mnt, filp, copy->nf_dst);
+ } else {
+ nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file,
+ copy->nf_dst->nf_file, false);
+ nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
}
- copy->nfserr = nfsd4_do_copy(copy, 0);
do_callback:
- cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
- if (!cb_copy)
- goto out;
- refcount_set(&cb_copy->refcount, 1);
- memcpy(&cb_copy->cp_res, &copy->cp_res, sizeof(copy->cp_res));
- cb_copy->cp_clp = copy->cp_clp;
- cb_copy->nfserr = copy->nfserr;
- memcpy(&cb_copy->fh, &copy->fh, sizeof(copy->fh));
- nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp,
- &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD);
- trace_nfsd_cb_offload(copy->cp_clp, &copy->cp_res.cb_stateid,
- &copy->fh, copy->cp_count, copy->nfserr);
- nfsd4_run_cb(&cb_copy->cp_cb);
-out:
- if (!copy->cp_intra)
- kfree(copy->nf_src);
+ nfsd4_send_cb_offload(copy, nfserr);
cleanup_async_copy(copy);
return 0;
}
@@ -1830,8 +1795,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfsd4_copy *async_copy = NULL;
- if (!copy->cp_intra) { /* Inter server SSC */
- if (!inter_copy_offload_enable || copy->cp_synchronous) {
+ if (nfsd4_ssc_is_inter(copy)) {
+ if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) {
status = nfserr_notsupp;
goto out;
}
@@ -1848,13 +1813,16 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
copy->cp_clp = cstate->clp;
memcpy(&copy->fh, &cstate->current_fh.fh_handle,
sizeof(struct knfsd_fh));
- if (!copy->cp_synchronous) {
+ if (nfsd4_copy_is_async(copy)) {
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
status = nfserrno(-ENOMEM);
async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
if (!async_copy)
goto out_err;
+ async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL);
+ if (!async_copy->cp_src)
+ goto out_err;
if (!nfs4_init_copy_state(nn, copy))
goto out_err;
refcount_set(&async_copy->refcount, 1);
@@ -1872,7 +1840,9 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
wake_up_process(async_copy->copy_task);
status = nfs_ok;
} else {
- status = nfsd4_do_copy(copy, 1);
+ status = nfsd4_do_copy(copy, copy->nf_src->nf_file,
+ copy->nf_dst->nf_file, true);
+ nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst);
}
out:
return status;
@@ -1880,7 +1850,7 @@ out_err:
if (async_copy)
cleanup_async_copy(async_copy);
status = nfserrno(-ENOMEM);
- if (!copy->cp_intra)
+ if (nfsd4_ssc_is_inter(copy))
nfsd4_interssc_disconnect(copy->ss_mnt);
goto out;
}
@@ -1953,9 +1923,9 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* 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;
+ cn->cpn_src->nl4_type = NL4_NETADDR;
status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr,
- &cn->cpn_src.u.nl4_addr);
+ &cn->cpn_src->u.nl4_addr);
WARN_ON_ONCE(status);
if (status) {
nfs4_put_cpntf_state(nn, cps);
@@ -2609,7 +2579,7 @@ check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
return;
}
putfh = (struct nfsd4_putfh *)&saved_op->u;
- if (!copy->cp_intra)
+ if (nfsd4_ssc_is_inter(copy))
putfh->no_verify = true;
}
}
@@ -2711,7 +2681,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) {
/*
* Don't execute this op if we couldn't encode a
- * succesful reply:
+ * successful reply:
*/
u32 plen = op->opdesc->op_rsize_bop(rqstp, op);
/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9409a0dc1b76..c5d199d7e6b4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -820,9 +820,9 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
swap(f2, fp->fi_fds[O_RDWR]);
spin_unlock(&fp->fi_lock);
if (f1)
- nfsd_file_put(f1);
+ nfsd_file_close(f1);
if (f2)
- nfsd_file_put(f2);
+ nfsd_file_close(f2);
}
}
@@ -1131,7 +1131,6 @@ static void block_delegations(struct knfsd_fh *fh)
static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
- struct svc_fh *current_fh,
struct nfs4_clnt_odstate *odstate)
{
struct nfs4_delegation *dp;
@@ -1141,7 +1140,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
n = atomic_long_inc_return(&num_delegations);
if (n < 0 || n > max_delegations)
goto out_dec;
- if (delegation_blocked(&current_fh->fh_handle))
+ if (delegation_blocked(&fp->fi_fhandle))
goto out_dec;
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
if (dp == NULL)
@@ -2053,11 +2052,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
* This type of memory management is somewhat inefficient, but we use it
* anyway since SETCLIENTID is not a common operation.
*/
-static struct nfs4_client *alloc_client(struct xdr_netobj name)
+static struct nfs4_client *alloc_client(struct xdr_netobj name,
+ struct nfsd_net *nn)
{
struct nfs4_client *clp;
int i;
+ if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) {
+ mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+ return NULL;
+ }
clp = kmem_cache_zalloc(client_slab, GFP_KERNEL);
if (clp == NULL)
return NULL;
@@ -2076,6 +2080,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
atomic_set(&clp->cl_rpc_users, 0);
clp->cl_cb_state = NFSD4_CB_UNKNOWN;
clp->cl_state = NFSD4_ACTIVE;
+ atomic_inc(&nn->nfs4_client_count);
atomic_set(&clp->cl_delegs_in_recall, 0);
INIT_LIST_HEAD(&clp->cl_idhash);
INIT_LIST_HEAD(&clp->cl_openowners);
@@ -2183,6 +2188,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
static void
__destroy_client(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
int i;
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
@@ -2226,6 +2232,7 @@ __destroy_client(struct nfs4_client *clp)
nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
+ atomic_add_unless(&nn->nfs4_client_count, -1, 0);
free_client(clp);
wake_up_all(&expiry_wq);
}
@@ -2564,7 +2571,7 @@ static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f)
static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f)
{
- struct inode *inode = f->nf_inode;
+ struct inode *inode = file_inode(f->nf_file);
seq_printf(s, "superblock: \"%02x:%02x:%ld\"",
MAJOR(inode->i_sb->s_dev),
@@ -2848,7 +2855,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct dentry *dentries[ARRAY_SIZE(client_files)];
- clp = alloc_client(name);
+ clp = alloc_client(name, nn);
if (clp == NULL)
return NULL;
@@ -4330,6 +4337,27 @@ out:
return -ENOMEM;
}
+void nfsd4_init_leases_net(struct nfsd_net *nn)
+{
+ struct sysinfo si;
+ u64 max_clients;
+
+ nn->nfsd4_lease = 90; /* default lease time */
+ nn->nfsd4_grace = 90;
+ nn->somebody_reclaimed = false;
+ nn->track_reclaim_completes = false;
+ nn->clverifier_counter = prandom_u32();
+ nn->clientid_base = prandom_u32();
+ nn->clientid_counter = nn->clientid_base + 1;
+ nn->s2s_cp_cl_id = nn->clientid_counter++;
+
+ atomic_set(&nn->nfs4_client_count, 0);
+ si_meminfo(&si);
+ max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024);
+ max_clients *= NFS4_CLIENTS_PER_GB;
+ nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
+}
+
static void init_nfs4_replay(struct nfs4_replay *rp)
{
rp->rp_status = nfserr_serverfault;
@@ -5032,11 +5060,14 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
.ia_valid = ATTR_SIZE,
.ia_size = 0,
};
+ struct nfsd_attrs attrs = {
+ .na_iattr = &iattr,
+ };
if (!open->op_truncate)
return 0;
if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
return nfserr_inval;
- return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0);
+ return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0);
}
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
@@ -5104,6 +5135,7 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
goto out_put_access;
nf->nf_file = open->op_filp;
open->op_filp = NULL;
+ trace_nfsd_file_create(rqstp, access, nf);
}
spin_lock(&fp->fi_lock);
@@ -5259,11 +5291,41 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
return 0;
}
+/*
+ * It's possible that between opening the dentry and setting the delegation,
+ * that it has been renamed or unlinked. Redo the lookup to verify that this
+ * hasn't happened.
+ */
+static int
+nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp,
+ struct svc_fh *parent)
+{
+ struct svc_export *exp;
+ struct dentry *child;
+ __be32 err;
+
+ err = nfsd_lookup_dentry(open->op_rqstp, parent,
+ open->op_fname, open->op_fnamelen,
+ &exp, &child);
+
+ if (err)
+ return -EAGAIN;
+
+ dput(child);
+ if (child != file_dentry(fp->fi_deleg_file->nf_file))
+ return -EAGAIN;
+
+ return 0;
+}
+
static struct nfs4_delegation *
-nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
- struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
+nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ struct svc_fh *parent)
{
int status = 0;
+ struct nfs4_client *clp = stp->st_stid.sc_client;
+ struct nfs4_file *fp = stp->st_stid.sc_file;
+ struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate;
struct nfs4_delegation *dp;
struct nfsd_file *nf;
struct file_lock *fl;
@@ -5305,7 +5367,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
return ERR_PTR(status);
status = -ENOMEM;
- dp = alloc_init_deleg(clp, fp, fh, odstate);
+ dp = alloc_init_deleg(clp, fp, odstate);
if (!dp)
goto out_delegees;
@@ -5318,6 +5380,13 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
locks_free_lock(fl);
if (status)
goto out_clnt_odstate;
+
+ if (parent) {
+ status = nfsd4_verify_deleg_dentry(open, fp, parent);
+ if (status)
+ goto out_unlock;
+ }
+
status = nfsd4_check_conflicting_opens(clp, fp);
if (status)
goto out_unlock;
@@ -5373,12 +5442,13 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
* proper support for them.
*/
static void
-nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
- struct nfs4_ol_stateid *stp)
+nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ struct svc_fh *currentfh)
{
struct nfs4_delegation *dp;
struct nfs4_openowner *oo = openowner(stp->st_stateowner);
struct nfs4_client *clp = stp->st_stid.sc_client;
+ struct svc_fh *parent = NULL;
int cb_up;
int status = 0;
@@ -5392,6 +5462,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
goto out_no_deleg;
break;
case NFS4_OPEN_CLAIM_NULL:
+ parent = currentfh;
+ fallthrough;
case NFS4_OPEN_CLAIM_FH:
/*
* Let's not give out any delegations till everyone's
@@ -5406,7 +5478,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
default:
goto out_no_deleg;
}
- dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate);
+ dp = nfs4_set_delegation(open, stp, parent);
if (IS_ERR(dp))
goto out_no_deleg;
@@ -5538,7 +5610,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
* Attempt to hand out a delegation. No error return, because the
* OPEN succeeds even if we fail.
*/
- nfs4_open_delegation(current_fh, open, stp);
+ nfs4_open_delegation(open, stp, &resp->cstate.current_fh);
nodeleg:
status = nfs_ok;
trace_nfsd_open(&stp->st_stid.sc_stateid);
@@ -5792,9 +5864,12 @@ static void
nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist,
struct laundry_time *lt)
{
+ unsigned int maxreap, reapcnt = 0;
struct list_head *pos, *next;
struct nfs4_client *clp;
+ maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ?
+ NFSD_CLIENT_MAX_TRIM_PER_RUN : 0;
INIT_LIST_HEAD(reaplist);
spin_lock(&nn->client_lock);
list_for_each_safe(pos, next, &nn->client_lru) {
@@ -5805,14 +5880,15 @@ nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist,
break;
if (!atomic_read(&clp->cl_rpc_users))
clp->cl_state = NFSD4_COURTESY;
- if (!client_has_state(clp) ||
- ktime_get_boottime_seconds() >=
- (clp->cl_time + NFSD_COURTESY_CLIENT_TIMEOUT))
+ if (!client_has_state(clp))
goto exp_client;
- if (nfs4_anylock_blockers(clp)) {
+ if (!nfs4_anylock_blockers(clp))
+ if (reapcnt >= maxreap)
+ continue;
exp_client:
- if (!mark_client_expired_locked(clp))
- list_add(&clp->cl_lru, reaplist);
+ if (!mark_client_expired_locked(clp)) {
+ list_add(&clp->cl_lru, reaplist);
+ reapcnt++;
}
}
spin_unlock(&nn->client_lock);
@@ -7321,21 +7397,22 @@ out:
static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
{
struct nfsd_file *nf;
+ struct inode *inode;
__be32 err;
err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
if (err)
return err;
- fh_lock(fhp); /* to block new leases till after test_lock: */
- err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode,
- NFSD_MAY_READ));
+ inode = fhp->fh_dentry->d_inode;
+ inode_lock(inode); /* to block new leases till after test_lock: */
+ err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
if (err)
goto out;
lock->fl_file = nf->nf_file;
err = nfserrno(vfs_test_lock(nf->nf_file, lock));
lock->fl_file = NULL;
out:
- fh_unlock(fhp);
+ inode_unlock(inode);
nfsd_file_put(nf);
return err;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2acea7792bb2..1e9690a061ec 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1810,7 +1810,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta
for (i = 0; i < test_stateid->ts_num_ids; i++) {
stateid = svcxdr_tmpalloc(argp, sizeof(*stateid));
if (!stateid)
- return nfserrno(-ENOMEM); /* XXX: not jukebox? */
+ return nfserr_jukebox;
INIT_LIST_HEAD(&stateid->ts_id_list);
list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list);
status = nfsd4_decode_stateid4(argp, &stateid->ts_id_stateid);
@@ -1896,8 +1896,8 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp,
static __be32
nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
{
+ u32 consecutive, i, count, sync;
struct nl4_server *ns_dummy;
- u32 consecutive, i, count;
__be32 status;
status = nfsd4_decode_stateid4(argp, &copy->cp_src_stateid);
@@ -1915,25 +1915,28 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
/* ca_consecutive: we always do consecutive copies */
if (xdr_stream_decode_u32(argp->xdr, &consecutive) < 0)
return nfserr_bad_xdr;
- if (xdr_stream_decode_u32(argp->xdr, &copy->cp_synchronous) < 0)
+ if (xdr_stream_decode_bool(argp->xdr, &sync) < 0)
return nfserr_bad_xdr;
+ nfsd4_copy_set_sync(copy, sync);
if (xdr_stream_decode_u32(argp->xdr, &count) < 0)
return nfserr_bad_xdr;
- copy->cp_intra = false;
+ copy->cp_src = svcxdr_tmpalloc(argp, sizeof(*copy->cp_src));
+ if (copy->cp_src == NULL)
+ return nfserr_jukebox;
if (count == 0) { /* intra-server copy */
- copy->cp_intra = true;
+ __set_bit(NFSD4_COPY_F_INTRA, &copy->cp_flags);
return nfs_ok;
}
/* decode all the supplied server addresses but use only the first */
- status = nfsd4_decode_nl4_server(argp, &copy->cp_src);
+ 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); /* XXX: jukebox? */
+ return nfserr_jukebox;
for (i = 0; i < count - 1; i++) {
status = nfsd4_decode_nl4_server(argp, ns_dummy);
if (status) {
@@ -1952,10 +1955,17 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,
{
__be32 status;
+ cn->cpn_src = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_src));
+ if (cn->cpn_src == NULL)
+ return nfserr_jukebox;
+ cn->cpn_dst = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_dst));
+ if (cn->cpn_dst == NULL)
+ return nfserr_jukebox;
+
status = nfsd4_decode_stateid4(argp, &cn->cpn_src_stateid);
if (status)
return status;
- return nfsd4_decode_nl4_server(argp, &cn->cpn_dst);
+ return nfsd4_decode_nl4_server(argp, cn->cpn_dst);
}
static __be32
@@ -2828,10 +2838,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
struct kstat stat;
struct svc_fh *tempfh = NULL;
struct kstatfs statfs;
- __be32 *p;
+ __be32 *p, *attrlen_p;
int starting_len = xdr->buf->len;
int attrlen_offset;
- __be32 attrlen;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
@@ -2919,10 +2928,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
goto out;
attrlen_offset = xdr->buf->len;
- p = xdr_reserve_space(xdr, 4);
- if (!p)
+ attrlen_p = xdr_reserve_space(xdr, XDR_UNIT);
+ if (!attrlen_p)
goto out_resource;
- p++; /* to be backfilled later */
if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
u32 supp[3];
@@ -3344,8 +3352,7 @@ out_acl:
*p++ = cpu_to_be32(err == 0);
}
- attrlen = htonl(xdr->buf->len - attrlen_offset - 4);
- write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4);
+ *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
status = nfs_ok;
out:
@@ -3882,16 +3889,15 @@ static __be32 nfsd4_encode_splice_read(
struct xdr_stream *xdr = resp->xdr;
struct xdr_buf *buf = xdr->buf;
int status, space_left;
- u32 eof;
__be32 nfserr;
- __be32 *p = xdr->p - 2;
/* Make sure there will be room for padding if needed */
if (xdr->end - xdr->p < 1)
return nfserr_resource;
nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp,
- file, read->rd_offset, &maxcount, &eof);
+ file, read->rd_offset, &maxcount,
+ &read->rd_eof);
read->rd_length = maxcount;
if (nfserr)
goto out_err;
@@ -3902,9 +3908,6 @@ static __be32 nfsd4_encode_splice_read(
goto out_err;
}
- *(p++) = htonl(eof);
- *(p++) = htonl(maxcount);
-
buf->page_len = maxcount;
buf->len += maxcount;
xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1)
@@ -3946,11 +3949,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
struct file *file, unsigned long maxcount)
{
struct xdr_stream *xdr = resp->xdr;
- u32 eof;
- int starting_len = xdr->buf->len - 8;
+ unsigned int starting_len = xdr->buf->len;
+ __be32 zero = xdr_zero;
__be32 nfserr;
- __be32 tmp;
- int pad;
read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount);
if (read->rd_vlen < 0)
@@ -3958,31 +3959,24 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
- &eof);
+ &read->rd_eof);
read->rd_length = maxcount;
if (nfserr)
return nfserr;
- if (svc_encode_result_payload(resp->rqstp, starting_len + 8, maxcount))
+ if (svc_encode_result_payload(resp->rqstp, starting_len, maxcount))
return nfserr_io;
- xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount));
-
- tmp = htonl(eof);
- write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4);
- tmp = htonl(maxcount);
- write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
-
- tmp = xdr_zero;
- pad = (maxcount&3) ? 4 - (maxcount&3) : 0;
- write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount,
- &tmp, pad);
- return 0;
+ xdr_truncate_encode(xdr, starting_len + xdr_align_size(maxcount));
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + maxcount, &zero,
+ xdr_pad_size(maxcount));
+ return nfs_ok;
}
static __be32
nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
+ bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags);
unsigned long maxcount;
struct xdr_stream *xdr = resp->xdr;
struct file *file;
@@ -3995,11 +3989,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
if (!p) {
- WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
+ WARN_ON_ONCE(splice_ok);
return nfserr_resource;
}
- if (resp->xdr->buf->page_len &&
- test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) {
+ if (resp->xdr->buf->page_len && splice_ok) {
WARN_ON_ONCE(1);
return nfserr_resource;
}
@@ -4008,31 +4001,30 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
maxcount = min_t(unsigned long, read->rd_length,
(xdr->buf->buflen - xdr->buf->len));
- if (file->f_op->splice_read &&
- test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
+ if (file->f_op->splice_read && splice_ok)
nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount);
else
nfserr = nfsd4_encode_readv(resp, read, file, maxcount);
-
- if (nfserr)
+ if (nfserr) {
xdr_truncate_encode(xdr, starting_len);
+ return nfserr;
+ }
- return nfserr;
+ p = xdr_encode_bool(p, read->rd_eof);
+ *p = cpu_to_be32(read->rd_length);
+ return nfs_ok;
}
static __be32
nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
{
- int maxcount;
- __be32 wire_count;
- int zero = 0;
+ __be32 *p, *maxcount_p, zero = xdr_zero;
struct xdr_stream *xdr = resp->xdr;
int length_offset = xdr->buf->len;
- int status;
- __be32 *p;
+ int maxcount, status;
- p = xdr_reserve_space(xdr, 4);
- if (!p)
+ maxcount_p = xdr_reserve_space(xdr, XDR_UNIT);
+ if (!maxcount_p)
return nfserr_resource;
maxcount = PAGE_SIZE;
@@ -4057,14 +4049,11 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
nfserr = nfserrno(status);
goto out_err;
}
-
- wire_count = htonl(maxcount);
- write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4);
- xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4));
- if (maxcount & 3)
- write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount,
- &zero, 4 - (maxcount&3));
- return 0;
+ *maxcount_p = cpu_to_be32(maxcount);
+ xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount));
+ write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero,
+ xdr_pad_size(maxcount));
+ return nfs_ok;
out_err:
xdr_truncate_encode(xdr, length_offset);
@@ -4715,13 +4704,13 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
__be32 *p;
nfserr = nfsd42_encode_write_res(resp, &copy->cp_res,
- !!copy->cp_synchronous);
+ nfsd4_copy_is_sync(copy));
if (nfserr)
return nfserr;
p = xdr_reserve_space(resp->xdr, 4 + 4);
*p++ = xdr_one; /* cr_consecutive */
- *p++ = cpu_to_be32(copy->cp_synchronous);
+ *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero;
return 0;
}
@@ -4919,7 +4908,8 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
*p++ = cpu_to_be32(1);
- return nfsd42_encode_nl4_server(resp, &cn->cpn_src);
+ nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src);
+ return nfserr;
}
static __be32
@@ -5373,8 +5363,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
so->so_replay.rp_buf, len);
}
status:
- /* Note that op->status is already in network byte order: */
- write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4);
+ *p = op->status;
}
/*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 0621c2faf242..917fa1892fd2 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -25,6 +25,7 @@
#include "state.h"
#include "netns.h"
#include "pnfs.h"
+#include "filecache.h"
/*
* We have a single directory with several nodes in it.
@@ -45,6 +46,7 @@ enum {
NFSD_Ports,
NFSD_MaxBlkSize,
NFSD_MaxConnections,
+ NFSD_Filecache,
NFSD_SupportedEnctypes,
/*
* The below MUST come last. Otherwise we leave a hole in nfsd_files[]
@@ -229,6 +231,13 @@ static const struct file_operations reply_cache_stats_operations = {
.release = single_release,
};
+static const struct file_operations filecache_ops = {
+ .open = nfsd_file_cache_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
/*----------------------------------------------------------------------------*/
/*
* payload - write methods
@@ -633,7 +642,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
}
/* Now write current state into reply buffer */
- len = 0;
sep = "";
remaining = SIMPLE_TRANSACTION_LIMIT;
for (num=2 ; num <= 4 ; num++) {
@@ -1371,6 +1379,7 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
[NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO},
+ [NFSD_Filecache] = {"filecache", &filecache_ops, S_IRUGO},
#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE)
[NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO},
#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
@@ -1475,14 +1484,7 @@ static __net_init int nfsd_init_net(struct net *net)
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_drc_error;
- nn->nfsd4_lease = 90; /* default lease time */
- nn->nfsd4_grace = 90;
- nn->somebody_reclaimed = false;
- nn->track_reclaim_completes = false;
- nn->clverifier_counter = prandom_u32();
- nn->clientid_base = prandom_u32();
- nn->clientid_counter = nn->clientid_base + 1;
- nn->s2s_cp_cl_id = nn->clientid_counter++;
+ nfsd4_init_leases_net(nn);
get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
seqlock_init(&nn->writeverf_lock);
@@ -1517,7 +1519,6 @@ static struct pernet_operations nfsd_net_ops = {
static int __init init_nfsd(void)
{
int retval;
- printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");
retval = nfsd4_init_slabs();
if (retval)
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 9a8b09afc173..57a468ed85c3 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -341,6 +341,8 @@ void nfsd_lockd_shutdown(void);
#define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */
#define NFSD_COURTESY_CLIENT_TIMEOUT (24 * 60 * 60) /* seconds */
+#define NFSD_CLIENT_MAX_TRIM_PER_RUN 128
+#define NFS4_CLIENTS_PER_GB 1024
/*
* The following attributes are currently not supported by the NFSv4 server:
@@ -496,12 +498,16 @@ extern void unregister_cld_notifier(void);
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
+
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
{
return 0;
}
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) {};
+
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index c29baa03dfaf..a5b71526cee0 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -331,8 +331,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
struct dentry *dentry;
__be32 error;
- dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));
-
if (!fhp->fh_dentry) {
error = nfsd_set_fh_dentry(rqstp, fhp);
if (error)
@@ -340,6 +338,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
}
dentry = fhp->fh_dentry;
exp = fhp->fh_export;
+
+ trace_nfsd_fh_verify(rqstp, fhp, type, access);
+
/*
* We still have to do all these permission checks, even when
* fh_dentry is already set:
@@ -548,7 +549,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
if (ref_fh == fhp)
fh_put(ref_fh);
- if (fhp->fh_locked || fhp->fh_dentry) {
+ if (fhp->fh_dentry) {
printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n",
dentry);
}
@@ -671,6 +672,25 @@ void fh_fill_post_attrs(struct svc_fh *fhp)
nfsd4_change_attribute(&fhp->fh_post_attr, inode);
}
+/**
+ * fh_fill_both_attrs - Fill pre-op and post-op attributes
+ * @fhp: file handle to be updated
+ *
+ * This is used when the directory wasn't changed, but wcc attributes
+ * are needed anyway.
+ */
+void fh_fill_both_attrs(struct svc_fh *fhp)
+{
+ fh_fill_post_attrs(fhp);
+ if (!fhp->fh_post_saved)
+ return;
+ fhp->fh_pre_change = fhp->fh_post_change;
+ fhp->fh_pre_mtime = fhp->fh_post_attr.mtime;
+ fhp->fh_pre_ctime = fhp->fh_post_attr.ctime;
+ fhp->fh_pre_size = fhp->fh_post_attr.size;
+ fhp->fh_pre_saved = true;
+}
+
/*
* Release a file handle.
*/
@@ -680,7 +700,6 @@ fh_put(struct svc_fh *fhp)
struct dentry * dentry = fhp->fh_dentry;
struct svc_export * exp = fhp->fh_export;
if (dentry) {
- fh_unlock(fhp);
fhp->fh_dentry = NULL;
dput(dentry);
fh_clear_pre_post_attrs(fhp);
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index fb9d358a267e..c3ae6414fc5c 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -81,7 +81,6 @@ typedef struct svc_fh {
struct dentry * fh_dentry; /* validated dentry */
struct svc_export * fh_export; /* export pointer */
- bool fh_locked; /* inode locked by us */
bool fh_want_write; /* remount protection taken */
bool fh_no_wcc; /* no wcc data needed */
bool fh_no_atomic_attr;
@@ -93,7 +92,7 @@ typedef struct svc_fh {
bool fh_post_saved; /* post-op attrs saved */
bool fh_pre_saved; /* pre-op attrs saved */
- /* Pre-op attributes saved during fh_lock */
+ /* Pre-op attributes saved when inode is locked */
__u64 fh_pre_size; /* size before operation */
struct timespec64 fh_pre_mtime; /* mtime before oper */
struct timespec64 fh_pre_ctime; /* ctime before oper */
@@ -103,7 +102,7 @@ typedef struct svc_fh {
*/
u64 fh_pre_change;
- /* Post-op attributes saved in fh_unlock */
+ /* Post-op attributes saved in fh_fill_post_attrs() */
struct kstat fh_post_attr; /* full attrs after operation */
u64 fh_post_change; /* nfsv4 change; see above */
} svc_fh;
@@ -223,8 +222,8 @@ void fh_put(struct svc_fh *);
static __inline__ struct svc_fh *
fh_copy(struct svc_fh *dst, struct svc_fh *src)
{
- WARN_ON(src->fh_dentry || src->fh_locked);
-
+ WARN_ON(src->fh_dentry);
+
*dst = *src;
return dst;
}
@@ -322,52 +321,5 @@ static inline u64 nfsd4_change_attribute(struct kstat *stat,
extern void fh_fill_pre_attrs(struct svc_fh *fhp);
extern void fh_fill_post_attrs(struct svc_fh *fhp);
-
-
-/*
- * Lock a file handle/inode
- * NOTE: both fh_lock and fh_unlock are done "by hand" in
- * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once
- * so, any changes here should be reflected there.
- */
-
-static inline void
-fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
-{
- struct dentry *dentry = fhp->fh_dentry;
- struct inode *inode;
-
- BUG_ON(!dentry);
-
- if (fhp->fh_locked) {
- printk(KERN_WARNING "fh_lock: %pd2 already locked!\n",
- dentry);
- return;
- }
-
- inode = d_inode(dentry);
- inode_lock_nested(inode, subclass);
- fh_fill_pre_attrs(fhp);
- fhp->fh_locked = true;
-}
-
-static inline void
-fh_lock(struct svc_fh *fhp)
-{
- fh_lock_nested(fhp, I_MUTEX_NORMAL);
-}
-
-/*
- * Unlock a file handle/inode
- */
-static inline void
-fh_unlock(struct svc_fh *fhp)
-{
- if (fhp->fh_locked) {
- fh_fill_post_attrs(fhp);
- inode_unlock(d_inode(fhp->fh_dentry));
- fhp->fh_locked = false;
- }
-}
-
+extern void fh_fill_both_attrs(struct svc_fh *fhp);
#endif /* _LINUX_NFSD_NFSFH_H */
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index fcdab8a8a41f..7381972f1677 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -51,6 +51,9 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
struct nfsd_sattrargs *argp = rqstp->rq_argp;
struct nfsd_attrstat *resp = rqstp->rq_resp;
struct iattr *iap = &argp->attrs;
+ struct nfsd_attrs attrs = {
+ .na_iattr = iap,
+ };
struct svc_fh *fhp;
dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n",
@@ -100,7 +103,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
}
}
- resp->status = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0);
+ resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0);
if (resp->status != nfs_ok)
goto out;
@@ -260,6 +263,9 @@ nfsd_proc_create(struct svc_rqst *rqstp)
svc_fh *dirfhp = &argp->fh;
svc_fh *newfhp = &resp->fh;
struct iattr *attr = &argp->attrs;
+ struct nfsd_attrs attrs = {
+ .na_iattr = attr,
+ };
struct inode *inode;
struct dentry *dchild;
int type, mode;
@@ -285,7 +291,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
goto done;
}
- fh_lock_nested(dirfhp, I_MUTEX_PARENT);
+ inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT);
dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len);
if (IS_ERR(dchild)) {
resp->status = nfserrno(PTR_ERR(dchild));
@@ -385,7 +391,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
if (!inode) {
/* File doesn't exist. Create it and set attrs */
resp->status = nfsd_create_locked(rqstp, dirfhp, argp->name,
- argp->len, attr, type, rdev,
+ argp->len, &attrs, type, rdev,
newfhp);
} else if (type == S_IFREG) {
dprintk("nfsd: existing %s, valid=%x, size=%ld\n",
@@ -396,13 +402,12 @@ nfsd_proc_create(struct svc_rqst *rqstp)
*/
attr->ia_valid &= ATTR_SIZE;
if (attr->ia_valid)
- resp->status = nfsd_setattr(rqstp, newfhp, attr, 0,
+ resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0,
(time64_t)0);
}
out_unlock:
- /* We don't really need to unlock, as fh_put does it. */
- fh_unlock(dirfhp);
+ inode_unlock(dirfhp->fh_dentry->d_inode);
fh_drop_write(dirfhp);
done:
fh_put(dirfhp);
@@ -472,6 +477,9 @@ nfsd_proc_symlink(struct svc_rqst *rqstp)
{
struct nfsd_symlinkargs *argp = rqstp->rq_argp;
struct nfsd_stat *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
struct svc_fh newfh;
if (argp->tlen > NFS_MAXPATHLEN) {
@@ -493,7 +501,7 @@ nfsd_proc_symlink(struct svc_rqst *rqstp)
fh_init(&newfh, NFS_FHSIZE);
resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen,
- argp->tname, &newfh);
+ argp->tname, &attrs, &newfh);
kfree(argp->tname);
fh_put(&argp->ffh);
@@ -511,6 +519,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp)
{
struct nfsd_createargs *argp = rqstp->rq_argp;
struct nfsd_diropres *resp = rqstp->rq_resp;
+ struct nfsd_attrs attrs = {
+ .na_iattr = &argp->attrs,
+ };
dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -522,7 +533,7 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp)
argp->attrs.ia_valid &= ~ATTR_SIZE;
fh_init(&resp->fh, NFS_FHSIZE);
resp->status = nfsd_create(rqstp, &argp->fh, argp->name, argp->len,
- &argp->attrs, S_IFDIR, 0, &resp->fh);
+ &attrs, S_IFDIR, 0, &resp->fh);
fh_put(&argp->fh);
if (resp->status != nfs_ok)
goto out;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f3d6313914ed..ae596dbf8667 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -703,7 +703,6 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name
extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
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,
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index a60ead3b227a..9ebd67d461f9 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -171,6 +171,52 @@ TRACE_EVENT(nfsd_compound_encode_err,
__entry->opnum, __entry->status)
);
+#define show_fs_file_type(x) \
+ __print_symbolic(x, \
+ { S_IFLNK, "LNK" }, \
+ { S_IFREG, "REG" }, \
+ { S_IFDIR, "DIR" }, \
+ { S_IFCHR, "CHR" }, \
+ { S_IFBLK, "BLK" }, \
+ { S_IFIFO, "FIFO" }, \
+ { S_IFSOCK, "SOCK" })
+
+TRACE_EVENT(nfsd_fh_verify,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ umode_t type,
+ int access
+ ),
+ TP_ARGS(rqstp, fhp, type, access),
+ TP_STRUCT__entry(
+ __field(unsigned int, netns_ino)
+ __sockaddr(server, rqstp->rq_xprt->xpt_remotelen)
+ __sockaddr(client, rqstp->rq_xprt->xpt_remotelen)
+ __field(u32, xid)
+ __field(u32, fh_hash)
+ __field(void *, inode)
+ __field(unsigned long, type)
+ __field(unsigned long, access)
+ ),
+ TP_fast_assign(
+ __entry->netns_ino = SVC_NET(rqstp)->ns.inum;
+ __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local,
+ rqstp->rq_xprt->xpt_locallen);
+ __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote,
+ rqstp->rq_xprt->xpt_remotelen);
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __entry->inode = d_inode(fhp->fh_dentry);
+ __entry->type = type;
+ __entry->access = access;
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x inode=%p type=%s access=%s",
+ __entry->xid, __entry->fh_hash, __entry->inode,
+ show_fs_file_type(__entry->type),
+ show_nfsd_may_flags(__entry->access)
+ )
+);
DECLARE_EVENT_CLASS(nfsd_fh_err_class,
TP_PROTO(struct svc_rqst *rqstp,
@@ -696,15 +742,12 @@ DEFINE_CLID_EVENT(confirmed_r);
__print_flags(val, "|", \
{ 1 << NFSD_FILE_HASHED, "HASHED" }, \
{ 1 << NFSD_FILE_PENDING, "PENDING" }, \
- { 1 << NFSD_FILE_BREAK_READ, "BREAK_READ" }, \
- { 1 << NFSD_FILE_BREAK_WRITE, "BREAK_WRITE" }, \
{ 1 << NFSD_FILE_REFERENCED, "REFERENCED"})
DECLARE_EVENT_CLASS(nfsd_file_class,
TP_PROTO(struct nfsd_file *nf),
TP_ARGS(nf),
TP_STRUCT__entry(
- __field(unsigned int, nf_hashval)
__field(void *, nf_inode)
__field(int, nf_ref)
__field(unsigned long, nf_flags)
@@ -712,15 +755,13 @@ DECLARE_EVENT_CLASS(nfsd_file_class,
__field(struct file *, nf_file)
),
TP_fast_assign(
- __entry->nf_hashval = nf->nf_hashval;
__entry->nf_inode = nf->nf_inode;
__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;
),
- TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p",
- __entry->nf_hashval,
+ TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p",
__entry->nf_inode,
__entry->nf_ref,
show_nf_flags(__entry->nf_flags),
@@ -733,34 +774,59 @@ DEFINE_EVENT(nfsd_file_class, name, \
TP_PROTO(struct nfsd_file *nf), \
TP_ARGS(nf))
-DEFINE_NFSD_FILE_EVENT(nfsd_file_alloc);
DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final);
DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash);
DEFINE_NFSD_FILE_EVENT(nfsd_file_put);
-DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_release_locked);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_dispose);
+
+TRACE_EVENT(nfsd_file_alloc,
+ TP_PROTO(
+ const struct nfsd_file *nf
+ ),
+ TP_ARGS(nf),
+ TP_STRUCT__entry(
+ __field(const void *, nf_inode)
+ __field(unsigned long, nf_flags)
+ __field(unsigned long, nf_may)
+ __field(unsigned int, nf_ref)
+ ),
+ TP_fast_assign(
+ __entry->nf_inode = nf->nf_inode;
+ __entry->nf_flags = nf->nf_flags;
+ __entry->nf_ref = refcount_read(&nf->nf_ref);
+ __entry->nf_may = nf->nf_may;
+ ),
+ TP_printk("inode=%p ref=%u flags=%s may=%s",
+ __entry->nf_inode, __entry->nf_ref,
+ show_nf_flags(__entry->nf_flags),
+ show_nfsd_may_flags(__entry->nf_may)
+ )
+);
TRACE_EVENT(nfsd_file_acquire,
- TP_PROTO(struct svc_rqst *rqstp, unsigned int hash,
- struct inode *inode, unsigned int may_flags,
- struct nfsd_file *nf, __be32 status),
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct inode *inode,
+ unsigned int may_flags,
+ const struct nfsd_file *nf,
+ __be32 status
+ ),
- TP_ARGS(rqstp, hash, inode, may_flags, nf, status),
+ TP_ARGS(rqstp, inode, may_flags, nf, status),
TP_STRUCT__entry(
__field(u32, xid)
- __field(unsigned int, hash)
- __field(void *, inode)
+ __field(const void *, inode)
__field(unsigned long, may_flags)
- __field(int, nf_ref)
+ __field(unsigned int, nf_ref)
__field(unsigned long, nf_flags)
__field(unsigned long, nf_may)
- __field(struct file *, nf_file)
+ __field(const void *, nf_file)
__field(u32, status)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqstp->rq_xid);
- __entry->hash = hash;
__entry->inode = inode;
__entry->may_flags = may_flags;
__entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0;
@@ -770,19 +836,117 @@ TRACE_EVENT(nfsd_file_acquire,
__entry->status = be32_to_cpu(status);
),
- TP_printk("xid=0x%x hash=0x%x inode=%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=%p status=%u",
- __entry->xid, __entry->hash, __entry->inode,
+ TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p status=%u",
+ __entry->xid, __entry->inode,
show_nfsd_may_flags(__entry->may_flags),
__entry->nf_ref, show_nf_flags(__entry->nf_flags),
show_nfsd_may_flags(__entry->nf_may),
- __entry->nf_file, __entry->status)
+ __entry->nf_file, __entry->status
+ )
+);
+
+TRACE_EVENT(nfsd_file_create,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ unsigned int may_flags,
+ const struct nfsd_file *nf
+ ),
+
+ TP_ARGS(rqstp, may_flags, nf),
+
+ TP_STRUCT__entry(
+ __field(const void *, nf_inode)
+ __field(const void *, nf_file)
+ __field(unsigned long, may_flags)
+ __field(unsigned long, nf_flags)
+ __field(unsigned long, nf_may)
+ __field(unsigned int, nf_ref)
+ __field(u32, xid)
+ ),
+
+ TP_fast_assign(
+ __entry->nf_inode = nf->nf_inode;
+ __entry->nf_file = nf->nf_file;
+ __entry->may_flags = may_flags;
+ __entry->nf_flags = nf->nf_flags;
+ __entry->nf_may = nf->nf_may;
+ __entry->nf_ref = refcount_read(&nf->nf_ref);
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ ),
+
+ TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
+ __entry->xid, __entry->nf_inode,
+ show_nfsd_may_flags(__entry->may_flags),
+ __entry->nf_ref, show_nf_flags(__entry->nf_flags),
+ show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
+ )
+);
+
+TRACE_EVENT(nfsd_file_insert_err,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct inode *inode,
+ unsigned int may_flags,
+ long error
+ ),
+ TP_ARGS(rqstp, inode, may_flags, error),
+ TP_STRUCT__entry(
+ __field(u32, xid)
+ __field(const void *, inode)
+ __field(unsigned long, may_flags)
+ __field(long, error)
+ ),
+ TP_fast_assign(
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->inode = inode;
+ __entry->may_flags = may_flags;
+ __entry->error = error;
+ ),
+ TP_printk("xid=0x%x inode=%p may_flags=%s error=%ld",
+ __entry->xid, __entry->inode,
+ show_nfsd_may_flags(__entry->may_flags),
+ __entry->error
+ )
+);
+
+TRACE_EVENT(nfsd_file_cons_err,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct inode *inode,
+ unsigned int may_flags,
+ const struct nfsd_file *nf
+ ),
+ TP_ARGS(rqstp, inode, may_flags, nf),
+ TP_STRUCT__entry(
+ __field(u32, xid)
+ __field(const void *, inode)
+ __field(unsigned long, may_flags)
+ __field(unsigned int, nf_ref)
+ __field(unsigned long, nf_flags)
+ __field(unsigned long, nf_may)
+ __field(const void *, nf_file)
+ ),
+ TP_fast_assign(
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->inode = inode;
+ __entry->may_flags = may_flags;
+ __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;
+ ),
+ TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
+ __entry->xid, __entry->inode,
+ show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref,
+ show_nf_flags(__entry->nf_flags),
+ show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
+ )
);
TRACE_EVENT(nfsd_file_open,
TP_PROTO(struct nfsd_file *nf, __be32 status),
TP_ARGS(nf, status),
TP_STRUCT__entry(
- __field(unsigned int, nf_hashval)
__field(void *, nf_inode) /* cannot be dereferenced */
__field(int, nf_ref)
__field(unsigned long, nf_flags)
@@ -790,15 +954,13 @@ TRACE_EVENT(nfsd_file_open,
__field(void *, nf_file) /* cannot be dereferenced */
),
TP_fast_assign(
- __entry->nf_hashval = nf->nf_hashval;
__entry->nf_inode = nf->nf_inode;
__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;
),
- TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p",
- __entry->nf_hashval,
+ TP_printk("inode=%p ref=%d flags=%s may=%s file=%p",
__entry->nf_inode,
__entry->nf_ref,
show_nf_flags(__entry->nf_flags),
@@ -807,30 +969,53 @@ TRACE_EVENT(nfsd_file_open,
)
DECLARE_EVENT_CLASS(nfsd_file_search_class,
- TP_PROTO(struct inode *inode, unsigned int hash, int found),
- TP_ARGS(inode, hash, found),
+ TP_PROTO(
+ const struct inode *inode,
+ unsigned int count
+ ),
+ TP_ARGS(inode, count),
TP_STRUCT__entry(
- __field(struct inode *, inode)
- __field(unsigned int, hash)
- __field(int, found)
+ __field(const struct inode *, inode)
+ __field(unsigned int, count)
),
TP_fast_assign(
__entry->inode = inode;
- __entry->hash = hash;
- __entry->found = found;
+ __entry->count = count;
),
- TP_printk("hash=0x%x inode=%p found=%d", __entry->hash,
- __entry->inode, __entry->found)
+ TP_printk("inode=%p count=%u",
+ __entry->inode, __entry->count)
);
#define DEFINE_NFSD_FILE_SEARCH_EVENT(name) \
DEFINE_EVENT(nfsd_file_search_class, name, \
- TP_PROTO(struct inode *inode, unsigned int hash, int found), \
- TP_ARGS(inode, hash, found))
+ TP_PROTO( \
+ const struct inode *inode, \
+ unsigned int count \
+ ), \
+ TP_ARGS(inode, count))
DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync);
DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode);
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_is_cached);
+
+TRACE_EVENT(nfsd_file_is_cached,
+ TP_PROTO(
+ const struct inode *inode,
+ int found
+ ),
+ TP_ARGS(inode, found),
+ TP_STRUCT__entry(
+ __field(const struct inode *, inode)
+ __field(int, found)
+ ),
+ TP_fast_assign(
+ __entry->inode = inode;
+ __entry->found = found;
+ ),
+ TP_printk("inode=%p is %scached",
+ __entry->inode,
+ __entry->found ? "" : "not "
+ )
+);
TRACE_EVENT(nfsd_file_fsnotify_handle_event,
TP_PROTO(struct inode *inode, u32 mask),
@@ -851,6 +1036,76 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
__entry->nlink, __entry->mode, __entry->mask)
);
+DECLARE_EVENT_CLASS(nfsd_file_gc_class,
+ TP_PROTO(
+ const struct nfsd_file *nf
+ ),
+ TP_ARGS(nf),
+ TP_STRUCT__entry(
+ __field(void *, nf_inode)
+ __field(void *, nf_file)
+ __field(int, nf_ref)
+ __field(unsigned long, nf_flags)
+ ),
+ TP_fast_assign(
+ __entry->nf_inode = nf->nf_inode;
+ __entry->nf_file = nf->nf_file;
+ __entry->nf_ref = refcount_read(&nf->nf_ref);
+ __entry->nf_flags = nf->nf_flags;
+ ),
+ TP_printk("inode=%p ref=%d nf_flags=%s nf_file=%p",
+ __entry->nf_inode, __entry->nf_ref,
+ show_nf_flags(__entry->nf_flags),
+ __entry->nf_file
+ )
+);
+
+#define DEFINE_NFSD_FILE_GC_EVENT(name) \
+DEFINE_EVENT(nfsd_file_gc_class, name, \
+ TP_PROTO( \
+ const struct nfsd_file *nf \
+ ), \
+ TP_ARGS(nf))
+
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add_disposed);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_hashed);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed);
+
+DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class,
+ TP_PROTO(
+ unsigned long removed,
+ unsigned long remaining
+ ),
+ TP_ARGS(removed, remaining),
+ TP_STRUCT__entry(
+ __field(unsigned long, removed)
+ __field(unsigned long, remaining)
+ ),
+ TP_fast_assign(
+ __entry->removed = removed;
+ __entry->remaining = remaining;
+ ),
+ TP_printk("%lu entries removed, %lu remaining",
+ __entry->removed, __entry->remaining)
+);
+
+#define DEFINE_NFSD_FILE_LRUWALK_EVENT(name) \
+DEFINE_EVENT(nfsd_file_lruwalk_class, name, \
+ TP_PROTO( \
+ unsigned long removed, \
+ unsigned long remaining \
+ ), \
+ TP_ARGS(removed, remaining))
+
+DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed);
+DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed);
+
#include "cache.h"
TRACE_DEFINE_ENUM(RC_DROPIT);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d79db56475d4..9f486b788ed0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -199,27 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out_nfserr;
}
} else {
- /*
- * In the nfsd4_open() case, this may be held across
- * subsequent open and delegation acquisition which may
- * need to take the child's i_mutex:
- */
- fh_lock_nested(fhp, I_MUTEX_PARENT);
- dentry = lookup_one_len(name, dparent, len);
+ dentry = lookup_one_len_unlocked(name, dparent, len);
host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
if (nfsd_mountpoint(dentry, exp)) {
- /*
- * We don't need the i_mutex after all. It's
- * still possible we could open this (regular
- * files can be mountpoints too), but the
- * i_mutex is just there to prevent renames of
- * something that we might be about to delegate,
- * and a mountpoint won't be renamed:
- */
- fh_unlock(fhp);
- if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
+ host_err = nfsd_cross_mnt(rqstp, &dentry, &exp);
+ if (host_err) {
dput(dentry);
goto out_nfserr;
}
@@ -234,7 +220,15 @@ out_nfserr:
return nfserrno(host_err);
}
-/*
+/**
+ * nfsd_lookup - look up a single path component for nfsd
+ *
+ * @rqstp: the request context
+ * @fhp: the file handle of the directory
+ * @name: the component name, or %NULL to look up parent
+ * @len: length of name to examine
+ * @resfh: pointer to pre-initialised filehandle to hold result.
+ *
* Look up one component of a pathname.
* N.B. After this call _both_ fhp and resfh need an fh_put
*
@@ -244,11 +238,11 @@ out_nfserr:
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
- * NeilBrown <neilb@cse.unsw.edu.au>
+ *
*/
__be32
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
- unsigned int len, struct svc_fh *resfh)
+ unsigned int len, struct svc_fh *resfh)
{
struct svc_export *exp;
struct dentry *dentry;
@@ -349,11 +343,13 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
* Set various file attributes. After this call fhp needs an fh_put.
*/
__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct nfsd_attrs *attr,
int check_guard, time64_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
+ struct iattr *iap = attr->na_iattr;
int accmode = NFSD_MAY_SATTR;
umode_t ftype = 0;
__be32 err;
@@ -420,7 +416,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
return err;
}
- fh_lock(fhp);
+ inode_lock(inode);
if (size_change) {
/*
* RFC5661, Section 18.30.4:
@@ -456,7 +452,19 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
host_err = notify_change(&init_user_ns, dentry, iap, NULL);
out_unlock:
- fh_unlock(fhp);
+ if (attr->na_seclabel && attr->na_seclabel->len)
+ attr->na_labelerr = security_inode_setsecctx(dentry,
+ attr->na_seclabel->data, attr->na_seclabel->len);
+ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl)
+ attr->na_aclerr = set_posix_acl(&init_user_ns,
+ inode, ACL_TYPE_ACCESS,
+ attr->na_pacl);
+ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) &&
+ !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode))
+ attr->na_aclerr = set_posix_acl(&init_user_ns,
+ inode, ACL_TYPE_DEFAULT,
+ attr->na_dpacl);
+ inode_unlock(inode);
if (size_change)
put_write_access(inode);
out:
@@ -494,32 +502,6 @@ int nfsd4_is_junction(struct dentry *dentry)
return 0;
return 1;
}
-#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct xdr_netobj *label)
-{
- __be32 error;
- int host_error;
- struct dentry *dentry;
-
- error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
- if (error)
- return error;
-
- dentry = fhp->fh_dentry;
-
- inode_lock(d_inode(dentry));
- host_error = security_inode_setsecctx(dentry, label->data, label->len);
- inode_unlock(d_inode(dentry));
- return nfserrno(host_error);
-}
-#else
-__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct xdr_netobj *label)
-{
- return nfserr_notsupp;
-}
-#endif
static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp)
{
@@ -1202,14 +1184,15 @@ out:
* @rqstp: RPC transaction being executed
* @fhp: NFS filehandle of parent directory
* @resfhp: NFS filehandle of new object
- * @iap: requested attributes of new object
+ * @attrs: requested attributes of new object
*
* Returns nfs_ok on success, or an nfsstat in network byte order.
*/
__be32
nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct svc_fh *resfhp, struct iattr *iap)
+ struct svc_fh *resfhp, struct nfsd_attrs *attrs)
{
+ struct iattr *iap = attrs->na_iattr;
__be32 status;
/*
@@ -1230,7 +1213,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
* if the attributes have not changed.
*/
if (iap->ia_valid)
- status = nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0);
+ status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0);
else
status = nfserrno(commit_metadata(resfhp));
@@ -1269,11 +1252,12 @@ nfsd_check_ignore_resizing(struct iattr *iap)
/* The parent directory should already be locked: */
__be32
nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
- char *fname, int flen, struct iattr *iap,
- int type, dev_t rdev, struct svc_fh *resfhp)
+ char *fname, int flen, struct nfsd_attrs *attrs,
+ int type, dev_t rdev, struct svc_fh *resfhp)
{
struct dentry *dentry, *dchild;
struct inode *dirp;
+ struct iattr *iap = attrs->na_iattr;
__be32 err;
int host_err;
@@ -1281,13 +1265,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
dirp = d_inode(dentry);
dchild = dget(resfhp->fh_dentry);
- if (!fhp->fh_locked) {
- WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n",
- dentry);
- err = nfserr_io;
- goto out;
- }
-
err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1347,7 +1324,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_err < 0)
goto out_nfserr;
- err = nfsd_create_setattr(rqstp, fhp, resfhp, iap);
+ err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
out:
dput(dchild);
@@ -1366,8 +1343,8 @@ out_nfserr:
*/
__be32
nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- char *fname, int flen, struct iattr *iap,
- int type, dev_t rdev, struct svc_fh *resfhp)
+ char *fname, int flen, struct nfsd_attrs *attrs,
+ int type, dev_t rdev, struct svc_fh *resfhp)
{
struct dentry *dentry, *dchild = NULL;
__be32 err;
@@ -1386,11 +1363,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (host_err)
return nfserrno(host_err);
- fh_lock_nested(fhp, I_MUTEX_PARENT);
+ inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
dchild = lookup_one_len(fname, dentry, flen);
host_err = PTR_ERR(dchild);
- if (IS_ERR(dchild))
- return nfserrno(host_err);
+ if (IS_ERR(dchild)) {
+ err = nfserrno(host_err);
+ goto out_unlock;
+ }
err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
/*
* We unconditionally drop our ref to dchild as fh_compose will have
@@ -1398,9 +1377,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
*/
dput(dchild);
if (err)
- return err;
- return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type,
- rdev, resfhp);
+ goto out_unlock;
+ fh_fill_pre_attrs(fhp);
+ err = nfsd_create_locked(rqstp, fhp, fname, flen, attrs, type,
+ rdev, resfhp);
+ fh_fill_post_attrs(fhp);
+out_unlock:
+ inode_unlock(dentry->d_inode);
+ return err;
}
/*
@@ -1441,15 +1425,25 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
return 0;
}
-/*
- * Create a symlink and look up its inode
+/**
+ * nfsd_symlink - Create a symlink and look up its inode
+ * @rqstp: RPC transaction being executed
+ * @fhp: NFS filehandle of parent directory
+ * @fname: filename of the new symlink
+ * @flen: length of @fname
+ * @path: content of the new symlink (NUL-terminated)
+ * @attrs: requested attributes of new object
+ * @resfhp: NFS filehandle of new object
+ *
* N.B. After this call _both_ fhp and resfhp need an fh_put
+ *
+ * Returns nfs_ok on success, or an nfsstat in network byte order.
*/
__be32
nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
- char *fname, int flen,
- char *path,
- struct svc_fh *resfhp)
+ char *fname, int flen,
+ char *path, struct nfsd_attrs *attrs,
+ struct svc_fh *resfhp)
{
struct dentry *dentry, *dnew;
__be32 err, cerr;
@@ -1467,33 +1461,35 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out;
host_err = fh_want_write(fhp);
- if (host_err)
- goto out_nfserr;
+ if (host_err) {
+ err = nfserrno(host_err);
+ goto out;
+ }
- fh_lock(fhp);
dentry = fhp->fh_dentry;
+ inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
dnew = lookup_one_len(fname, dentry, flen);
- host_err = PTR_ERR(dnew);
- if (IS_ERR(dnew))
- goto out_nfserr;
-
+ if (IS_ERR(dnew)) {
+ err = nfserrno(PTR_ERR(dnew));
+ inode_unlock(dentry->d_inode);
+ goto out_drop_write;
+ }
+ fh_fill_pre_attrs(fhp);
host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path);
err = nfserrno(host_err);
- fh_unlock(fhp);
+ cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
+ if (!err)
+ nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
+ fh_fill_post_attrs(fhp);
+ inode_unlock(dentry->d_inode);
if (!err)
err = nfserrno(commit_metadata(fhp));
-
- fh_drop_write(fhp);
-
- cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
dput(dnew);
if (err==0) err = cerr;
+out_drop_write:
+ fh_drop_write(fhp);
out:
return err;
-
-out_nfserr:
- err = nfserrno(host_err);
- goto out;
}
/*
@@ -1531,22 +1527,25 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
goto out;
}
- fh_lock_nested(ffhp, I_MUTEX_PARENT);
ddir = ffhp->fh_dentry;
dirp = d_inode(ddir);
+ inode_lock_nested(dirp, I_MUTEX_PARENT);
dnew = lookup_one_len(name, ddir, len);
- host_err = PTR_ERR(dnew);
- if (IS_ERR(dnew))
- goto out_nfserr;
+ if (IS_ERR(dnew)) {
+ err = nfserrno(PTR_ERR(dnew));
+ goto out_unlock;
+ }
dold = tfhp->fh_dentry;
err = nfserr_noent;
if (d_really_is_negative(dold))
goto out_dput;
+ fh_fill_pre_attrs(ffhp);
host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL);
- fh_unlock(ffhp);
+ fh_fill_post_attrs(ffhp);
+ inode_unlock(dirp);
if (!host_err) {
err = nfserrno(commit_metadata(ffhp));
if (!err)
@@ -1557,17 +1556,17 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
else
err = nfserrno(host_err);
}
-out_dput:
dput(dnew);
-out_unlock:
- fh_unlock(ffhp);
+out_drop_write:
fh_drop_write(tfhp);
out:
return err;
-out_nfserr:
- err = nfserrno(host_err);
- goto out_unlock;
+out_dput:
+ dput(dnew);
+out_unlock:
+ inode_unlock(dirp);
+ goto out_drop_write;
}
static void
@@ -1628,10 +1627,7 @@ retry:
goto out;
}
- /* cannot use fh_lock as we need deadlock protective ordering
- * so do it by hand */
trap = lock_rename(tdentry, fdentry);
- ffhp->fh_locked = tfhp->fh_locked = true;
fh_fill_pre_attrs(ffhp);
fh_fill_pre_attrs(tfhp);
@@ -1687,17 +1683,12 @@ retry:
dput(odentry);
out_nfserr:
err = nfserrno(host_err);
- /*
- * We cannot rely on fh_unlock on the two filehandles,
- * as that would do the wrong thing if the two directories
- * were the same, so again we do it by hand.
- */
+
if (!close_cached) {
fh_fill_post_attrs(ffhp);
fh_fill_post_attrs(tfhp);
}
unlock_rename(tdentry, fdentry);
- ffhp->fh_locked = tfhp->fh_locked = false;
fh_drop_write(ffhp);
/*
@@ -1741,19 +1732,19 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (host_err)
goto out_nfserr;
- fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = fhp->fh_dentry;
dirp = d_inode(dentry);
+ inode_lock_nested(dirp, I_MUTEX_PARENT);
rdentry = lookup_one_len(fname, dentry, flen);
host_err = PTR_ERR(rdentry);
if (IS_ERR(rdentry))
- goto out_drop_write;
+ goto out_unlock;
if (d_really_is_negative(rdentry)) {
dput(rdentry);
host_err = -ENOENT;
- goto out_drop_write;
+ goto out_unlock;
}
rinode = d_inode(rdentry);
ihold(rinode);
@@ -1761,6 +1752,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (!type)
type = d_inode(rdentry)->i_mode & S_IFMT;
+ fh_fill_pre_attrs(fhp);
if (type != S_IFDIR) {
if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
nfsd_close_cached_files(rdentry);
@@ -1768,8 +1760,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
} else {
host_err = vfs_rmdir(&init_user_ns, dirp, rdentry);
}
+ fh_fill_post_attrs(fhp);
- fh_unlock(fhp);
+ inode_unlock(dirp);
if (!host_err)
host_err = commit_metadata(fhp);
dput(rdentry);
@@ -1791,6 +1784,9 @@ out_nfserr:
}
out:
return err;
+out_unlock:
+ inode_unlock(dirp);
+ goto out_drop_write;
}
/*
@@ -2144,13 +2140,16 @@ out:
return err;
}
-/*
- * Removexattr and setxattr need to call fh_lock to both lock the inode
- * and set the change attribute. Since the top-level vfs_removexattr
- * and vfs_setxattr calls already do their own inode_lock calls, call
- * the _locked variant. Pass in a NULL pointer for delegated_inode,
- * and let the client deal with NFS4ERR_DELAY (same as with e.g.
- * setattr and remove).
+/**
+ * nfsd_removexattr - Remove an extended attribute
+ * @rqstp: RPC transaction being executed
+ * @fhp: NFS filehandle of object with xattr to remove
+ * @name: name of xattr to remove (NUL-terminate)
+ *
+ * Pass in a NULL pointer for delegated_inode, and let the client deal
+ * with NFS4ERR_DELAY (same as with e.g. setattr and remove).
+ *
+ * Returns nfs_ok on success, or an nfsstat in network byte order.
*/
__be32
nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
@@ -2166,12 +2165,14 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
if (ret)
return nfserrno(ret);
- fh_lock(fhp);
+ inode_lock(fhp->fh_dentry->d_inode);
+ fh_fill_pre_attrs(fhp);
ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry,
name, NULL);
- fh_unlock(fhp);
+ fh_fill_post_attrs(fhp);
+ inode_unlock(fhp->fh_dentry->d_inode);
fh_drop_write(fhp);
return nfsd_xattr_errno(ret);
@@ -2191,12 +2192,13 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
ret = fh_want_write(fhp);
if (ret)
return nfserrno(ret);
- fh_lock(fhp);
+ inode_lock(fhp->fh_dentry->d_inode);
+ fh_fill_pre_attrs(fhp);
ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf,
len, flags, NULL);
-
- fh_unlock(fhp);
+ fh_fill_post_attrs(fhp);
+ inode_unlock(fhp->fh_dentry->d_inode);
fh_drop_write(fhp);
return nfsd_xattr_errno(ret);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 26347d76f44a..c95cd414b4bb 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -6,6 +6,8 @@
#ifndef LINUX_NFSD_VFS_H
#define LINUX_NFSD_VFS_H
+#include <linux/fs.h>
+#include <linux/posix_acl.h>
#include "nfsfh.h"
#include "nfsd.h"
@@ -42,6 +44,22 @@ struct nfsd_file;
typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
/* nfsd/vfs.c */
+struct nfsd_attrs {
+ struct iattr *na_iattr; /* input */
+ struct xdr_netobj *na_seclabel; /* input */
+ struct posix_acl *na_pacl; /* input */
+ struct posix_acl *na_dpacl; /* input */
+
+ int na_labelerr; /* output */
+ int na_aclerr; /* output */
+};
+
+static inline void nfsd_attrs_free(struct nfsd_attrs *attrs)
+{
+ posix_acl_release(attrs->na_pacl);
+ posix_acl_release(attrs->na_dpacl);
+}
+
int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
struct svc_export **expp);
__be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *,
@@ -50,11 +68,9 @@ __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, time64_t);
+ struct nfsd_attrs *, 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 svc_rqst *rqstp,
@@ -63,14 +79,14 @@ __be32 nfsd4_clone_file_range(struct svc_rqst *rqstp,
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,
+ char *name, int len, struct nfsd_attrs *attrs,
int type, dev_t rdev, struct svc_fh *res);
__be32 nfsd_create(struct svc_rqst *, struct svc_fh *,
- char *name, int len, struct iattr *attrs,
+ char *name, int len, struct nfsd_attrs *attrs,
int type, dev_t rdev, struct svc_fh *res);
__be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
__be32 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct svc_fh *resfhp, struct iattr *iap);
+ struct svc_fh *resfhp, struct nfsd_attrs *iap);
__be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp,
u64 offset, u32 count, __be32 *verf);
#ifdef CONFIG_NFSD_V4
@@ -110,8 +126,9 @@ __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *,
char *, int *);
__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *,
- char *name, int len, char *path,
- struct svc_fh *res);
+ char *name, int len, char *path,
+ struct nfsd_attrs *attrs,
+ struct svc_fh *res);
__be32 nfsd_link(struct svc_rqst *, struct svc_fh *,
char *, int, struct svc_fh *);
ssize_t nfsd_copy_file_range(struct file *, u64,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 7b744011f2d3..96267258e629 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -279,6 +279,7 @@ struct nfsd4_open {
struct nfs4_clnt_odstate *op_odstate; /* used during processing */
struct nfs4_acl *op_acl;
struct xdr_netobj op_label;
+ struct svc_rqst *op_rqstp;
};
struct nfsd4_open_confirm {
@@ -302,9 +303,10 @@ struct nfsd4_read {
u32 rd_length; /* request */
int rd_vlen;
struct nfsd_file *rd_nf;
-
+
struct svc_rqst *rd_rqstp; /* response */
- struct svc_fh *rd_fhp; /* response */
+ struct svc_fh *rd_fhp; /* response */
+ u32 rd_eof; /* response */
};
struct nfsd4_readdir {
@@ -532,6 +534,13 @@ struct nfsd42_write_res {
stateid_t cb_stateid;
};
+struct nfsd4_cb_offload {
+ struct nfsd4_callback co_cb;
+ struct nfsd42_write_res co_res;
+ __be32 co_nfserr;
+ struct knfsd_fh co_fh;
+};
+
struct nfsd4_copy {
/* request */
stateid_t cp_src_stateid;
@@ -539,18 +548,16 @@ struct nfsd4_copy {
u64 cp_src_pos;
u64 cp_dst_pos;
u64 cp_count;
- struct nl4_server cp_src;
- bool cp_intra;
+ struct nl4_server *cp_src;
- /* both */
- u32 cp_synchronous;
+ unsigned long cp_flags;
+#define NFSD4_COPY_F_STOPPED (0)
+#define NFSD4_COPY_F_INTRA (1)
+#define NFSD4_COPY_F_SYNCHRONOUS (2)
+#define NFSD4_COPY_F_COMMITTED (3)
/* response */
struct nfsd42_write_res cp_res;
-
- /* for cb_offload */
- struct nfsd4_callback cp_cb;
- __be32 nfserr;
struct knfsd_fh fh;
struct nfs4_client *cp_clp;
@@ -563,14 +570,35 @@ struct nfsd4_copy {
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;
- bool committed;
};
+static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync)
+{
+ if (sync)
+ set_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+ else
+ clear_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+}
+
+static inline bool nfsd4_copy_is_sync(const struct nfsd4_copy *copy)
+{
+ return test_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+}
+
+static inline bool nfsd4_copy_is_async(const struct nfsd4_copy *copy)
+{
+ return !test_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+}
+
+static inline bool nfsd4_ssc_is_inter(const struct nfsd4_copy *copy)
+{
+ return !test_bit(NFSD4_COPY_F_INTRA, &copy->cp_flags);
+}
+
struct nfsd4_seek {
/* request */
stateid_t seek_stateid;
@@ -594,19 +622,20 @@ struct nfsd4_offload_status {
struct nfsd4_copy_notify {
/* request */
stateid_t cpn_src_stateid;
- struct nl4_server cpn_dst;
+ struct nl4_server *cpn_dst;
/* response */
stateid_t cpn_cnr_stateid;
u64 cpn_sec;
u32 cpn_nsec;
- struct nl4_server cpn_src;
+ struct nl4_server *cpn_src;
};
struct nfsd4_op {
u32 opnum;
- const struct nfsd4_operation * opdesc;
__be32 status;
+ const struct nfsd4_operation *opdesc;
+ struct nfs4_replay *replay;
union nfsd4_op_u {
struct nfsd4_access access;
struct nfsd4_close close;
@@ -670,7 +699,6 @@ struct nfsd4_op {
struct nfsd4_listxattrs listxattrs;
struct nfsd4_removexattr removexattr;
} u;
- struct nfs4_replay * replay;
};
bool nfsd4_cache_this_op(struct nfsd4_op *);
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index fcef192e5e45..70ce419e2709 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -292,6 +292,7 @@ void nlmsvc_locks_init_private(struct file_lock *, struct nlm_host *, pid_t);
__be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **,
struct nlm_lock *);
void nlm_release_file(struct nlm_file *);
+void nlmsvc_put_lockowner(struct nlm_lockowner *);
void nlmsvc_release_lockowner(struct nlm_lock *);
void nlmsvc_mark_resources(struct net *);
void nlmsvc_free_host_resources(struct nlm_host *);
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index 398f70093cd3..67e4a2c5500b 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -41,6 +41,8 @@ struct nlm_lock {
struct nfs_fh fh;
struct xdr_netobj oh;
u32 svid;
+ u64 lock_start;
+ u64 lock_len;
struct file_lock fl;
};
diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h
index 222ae8883e85..75843c00f326 100644
--- a/include/linux/nfs_ssc.h
+++ b/include/linux/nfs_ssc.h
@@ -64,7 +64,7 @@ struct nfsd4_ssc_umount_item {
refcount_t nsui_refcnt;
unsigned long nsui_expire;
struct vfsmount *nsui_vfsmount;
- char nsui_ipaddr[RPC_MAX_ADDRBUFLEN];
+ char nsui_ipaddr[RPC_MAX_ADDRBUFLEN + 1];
};
#endif
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5860f32e3958..986c8a17ca5e 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -419,8 +419,8 @@ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr)
*/
static inline __be32 *xdr_encode_bool(__be32 *p, u32 n)
{
- *p = n ? xdr_one : xdr_zero;
- return p++;
+ *p++ = n ? xdr_one : xdr_zero;
+ return p;
}
/**
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index b61d9c90fa26..5c48be033cc7 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1989,20 +1989,24 @@ TRACE_EVENT(svc_wake_up,
TRACE_EVENT(svc_alloc_arg_err,
TP_PROTO(
- unsigned int pages
+ unsigned int requested,
+ unsigned int allocated
),
- TP_ARGS(pages),
+ TP_ARGS(requested, allocated),
TP_STRUCT__entry(
- __field(unsigned int, pages)
+ __field(unsigned int, requested)
+ __field(unsigned int, allocated)
),
TP_fast_assign(
- __entry->pages = pages;
+ __entry->requested = requested;
+ __entry->allocated = allocated;
),
- TP_printk("pages=%u", __entry->pages)
+ TP_printk("requested=%u allocated=%u",
+ __entry->requested, __entry->allocated)
);
DECLARE_EVENT_CLASS(svc_deferred_event,
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 2c4dd7ca95b0..2106003645a7 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -691,7 +691,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
set_current_state(TASK_RUNNING);
return -EINTR;
}
- trace_svc_alloc_arg_err(pages);
+ trace_svc_alloc_arg_err(pages, ret);
memalloc_retry_wait(GFP_KERNEL);
}
rqstp->rq_page_end = &rqstp->rq_pages[pages];