summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorJ. Bruce Fields <bfields@redhat.com>2020-05-21 10:58:15 -0400
committerJ. Bruce Fields <bfields@redhat.com>2020-05-21 10:58:15 -0400
commit6670ee2ef219ac9e1c836a277dda0c949ad8b1ff (patch)
tree0eee3d97941caab0bc85f93a7653b0cfd4abf51b /fs
parent746c6237ece641da79df09abcf87bc29f6f9665b (diff)
parentf2453978a4f2ddb1938fa80e9bf0c9d6252bd5f8 (diff)
downloadlinux-stable-6670ee2ef219ac9e1c836a277dda0c949ad8b1ff.tar.gz
linux-stable-6670ee2ef219ac9e1c836a277dda0c949ad8b1ff.tar.bz2
linux-stable-6670ee2ef219ac9e1c836a277dda0c949ad8b1ff.zip
Merge branch 'nfsd-5.8' of git://linux-nfs.org/~cel/cel-2.6 into for-5.8-incoming
Highlights of this series: * Remove serialization of sending RPC/RDMA Replies * Convert the TCP socket send path to use xdr_buf::bvecs (pre-requisite for RPC-on-TLS) * Fix svcrdma backchannel sendto return code * Convert a number of dprintk call sites to use tracepoints * Fix the "suggest braces around empty body in an 'else' statement" warning
Diffstat (limited to 'fs')
-rw-r--r--fs/cachefiles/rdwr.c12
-rw-r--r--fs/ceph/caps.c3
-rw-r--r--fs/ceph/debugfs.c2
-rw-r--r--fs/ceph/mds_client.c8
-rw-r--r--fs/ceph/quota.c4
-rw-r--r--fs/cifs/cifssmb.c2
-rw-r--r--fs/cifs/file.c2
-rw-r--r--fs/cifs/inode.c2
-rw-r--r--fs/configfs/dir.c1
-rw-r--r--fs/coredump.c8
-rw-r--r--fs/eventpoll.c107
-rw-r--r--fs/exec.c4
-rw-r--r--fs/gfs2/bmap.c16
-rw-r--r--fs/gfs2/glock.c6
-rw-r--r--fs/gfs2/inode.c7
-rw-r--r--fs/gfs2/log.c11
-rw-r--r--fs/gfs2/lops.c19
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/quota.c13
-rw-r--r--fs/gfs2/quota.h3
-rw-r--r--fs/gfs2/super.c1
-rw-r--r--fs/gfs2/util.c10
-rw-r--r--fs/io_uring.c82
-rw-r--r--fs/nfs/fscache.c39
-rw-r--r--fs/nfs/mount_clnt.c3
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/nfs/pagelist.c5
-rw-r--r--fs/nfs/pnfs_nfs.c3
-rw-r--r--fs/nfs/super.c1
-rw-r--r--fs/nfs/write.c4
-rw-r--r--fs/nfsd/nfs4callback.c37
-rw-r--r--fs/nfsd/nfs4proc.c7
-rw-r--r--fs/nfsd/nfs4state.c63
-rw-r--r--fs/nfsd/nfscache.c57
-rw-r--r--fs/nfsd/nfsctl.c26
-rw-r--r--fs/nfsd/state.h7
-rw-r--r--fs/nfsd/trace.h345
-rw-r--r--fs/splice.c45
-rw-r--r--fs/vboxsf/super.c2
40 files changed, 656 insertions, 317 deletions
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 1dc97f2d6201..e7726f5f1241 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -60,9 +60,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
object = container_of(op->op.object, struct cachefiles_object, fscache);
spin_lock(&object->work_lock);
list_add_tail(&monitor->op_link, &op->to_do);
+ fscache_enqueue_retrieval(op);
spin_unlock(&object->work_lock);
- fscache_enqueue_retrieval(op);
fscache_put_retrieval(op);
return 0;
}
@@ -398,7 +398,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
struct inode *inode;
sector_t block;
unsigned shift;
- int ret;
+ int ret, ret2;
object = container_of(op->op.object,
struct cachefiles_object, fscache);
@@ -430,8 +430,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
block = page->index;
block <<= shift;
- ret = bmap(inode, &block);
- ASSERT(ret < 0);
+ ret2 = bmap(inode, &block);
+ ASSERT(ret2 == 0);
_debug("%llx -> %llx",
(unsigned long long) (page->index << shift),
@@ -739,8 +739,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
block = page->index;
block <<= shift;
- ret = bmap(inode, &block);
- ASSERT(!ret);
+ ret2 = bmap(inode, &block);
+ ASSERT(ret2 == 0);
_debug("%llx -> %llx",
(unsigned long long) (page->index << shift),
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 185db76300b3..5f3aa4d607de 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
ret = try_get_cap_refs(inode, need, want, 0, flags, got);
/* three special error codes */
- if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN)
+ if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE)
ret = 0;
return ret;
}
@@ -3746,6 +3746,7 @@ retry:
WARN_ON(1);
tsession = NULL;
target = -1;
+ mutex_lock(&session->s_mutex);
}
goto retry;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 481ac97b4d25..dcaed75de9e6 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
&congestion_kb_fops);
snprintf(name, sizeof(name), "../../bdi/%s",
- dev_name(fsc->sb->s_bdi->dev));
+ bdi_dev_name(fsc->sb->s_bdi));
fsc->debugfs_bdi =
debugfs_create_symlink("bdi",
fsc->client->debugfs_dir,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 486f91f9685b..7c63abf5bea9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session,
void *end = p + msg->front.iov_len;
struct ceph_mds_session_head *h;
u32 op;
- u64 seq;
- unsigned long features = 0;
+ u64 seq, features = 0;
int wake = 0;
bool blacklisted = false;
@@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session,
goto bad;
/* version >= 3, feature bits */
ceph_decode_32_safe(&p, end, len, bad);
- ceph_decode_need(&p, end, len, bad);
- memcpy(&features, p, min_t(size_t, len, sizeof(features)));
- p += len;
+ ceph_decode_64_safe(&p, end, features, bad);
+ p += len - sizeof(features);
}
mutex_lock(&mdsc->mutex);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index de56dee60540..19507e2fdb57 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
}
if (IS_ERR(in)) {
- pr_warn("Can't lookup inode %llx (err: %ld)\n",
- realm->ino, PTR_ERR(in));
+ dout("Can't lookup inode %llx (err: %ld)\n",
+ realm->ino, PTR_ERR(in));
qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
} else {
qri->timeout = 0;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 182b864b3075..5014a82391ff 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2152,8 +2152,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
}
}
+ kref_put(&wdata2->refcount, cifs_writedata_release);
if (rc) {
- kref_put(&wdata2->refcount, cifs_writedata_release);
if (is_retryable_error(rc))
continue;
i += nr_pages;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0b1528edebcf..75ddce8ef456 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4060,7 +4060,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
* than it negotiated since it will refuse the read
* then.
*/
- if ((tcon->ses) && !(tcon->ses->capabilities &
+ if (!(tcon->ses->capabilities &
tcon->ses->server->vals->cap_large_files)) {
current_read_size = min_t(uint,
current_read_size, CIFSMaxBufSize);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 390d2b15ef6e..5d2965a23730 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -730,7 +730,7 @@ static __u64 simple_hashstr(const char *str)
* cifs_backup_query_path_info - SMB1 fallback code to get ino
*
* Fallback code to get file metadata when we don't have access to
- * @full_path (EACCESS) and have backup creds.
+ * @full_path (EACCES) and have backup creds.
*
* @data will be set to search info result buffer
* @resp_buf will be set to cifs resp buf and needs to be freed with
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cf7b7e1d5bd7..cb733652ecca 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
spin_lock(&configfs_dirent_lock);
configfs_detach_rollback(dentry);
spin_unlock(&configfs_dirent_lock);
+ config_item_put(parent_item);
return -EINTR;
}
frag->frag_dead = true;
diff --git a/fs/coredump.c b/fs/coredump.c
index 408418e6aa13..478a0d810136 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo)
if (displaced)
put_files_struct(displaced);
if (!dump_interrupted()) {
+ /*
+ * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
+ * have this set to NULL.
+ */
+ if (!cprm.file) {
+ pr_info("Core dump to |%s disabled\n", cn.corename);
+ goto close_fail;
+ }
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);
file_end_write(cprm.file);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8c596641a72b..12eebcdea9c8 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi)
{
struct eventpoll *ep = epi->ep;
+ /* Fast preliminary check */
+ if (epi->next != EP_UNACTIVE_PTR)
+ return false;
+
/* Check that the same epi has not been just chained from another CPU */
if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
return false;
@@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
* chained in ep->ovflist and requeued later on.
*/
if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
- if (epi->next == EP_UNACTIVE_PTR &&
- chain_epi_lockless(epi))
+ if (chain_epi_lockless(epi))
+ ep_pm_stay_awake_rcu(epi);
+ } else if (!ep_is_linked(epi)) {
+ /* In the usual case, add event to ready list. */
+ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
ep_pm_stay_awake_rcu(epi);
- goto out_unlock;
- }
-
- /* If this file is already in the ready list we exit soon */
- if (!ep_is_linked(epi) &&
- list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) {
- ep_pm_stay_awake_rcu(epi);
}
/*
@@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
{
int res = 0, eavail, timed_out = 0;
u64 slack = 0;
- bool waiter = false;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
@@ -1867,55 +1866,75 @@ fetch_events:
*/
ep_reset_busy_poll_napi_id(ep);
- /*
- * We don't have any available event to return to the caller. We need
- * to sleep here, and we will be woken by ep_poll_callback() when events
- * become available.
- */
- if (!waiter) {
- waiter = true;
- init_waitqueue_entry(&wait, current);
+ do {
+ /*
+ * Internally init_wait() uses autoremove_wake_function(),
+ * thus wait entry is removed from the wait queue on each
+ * wakeup. Why it is important? In case of several waiters
+ * each new wakeup will hit the next waiter, giving it the
+ * chance to harvest new event. Otherwise wakeup can be
+ * lost. This is also good performance-wise, because on
+ * normal wakeup path no need to call __remove_wait_queue()
+ * explicitly, thus ep->lock is not taken, which halts the
+ * event delivery.
+ */
+ init_wait(&wait);
write_lock_irq(&ep->lock);
- __add_wait_queue_exclusive(&ep->wq, &wait);
- write_unlock_irq(&ep->lock);
- }
-
- for (;;) {
/*
- * We don't want to sleep if the ep_poll_callback() sends us
- * a wakeup in between. That's why we set the task state
- * to TASK_INTERRUPTIBLE before doing the checks.
+ * Barrierless variant, waitqueue_active() is called under
+ * the same lock on wakeup ep_poll_callback() side, so it
+ * is safe to avoid an explicit barrier.
*/
- set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_INTERRUPTIBLE);
+
/*
- * Always short-circuit for fatal signals to allow
- * threads to make a timely exit without the chance of
- * finding more events available and fetching
- * repeatedly.
+ * Do the final check under the lock. ep_scan_ready_list()
+ * plays with two lists (->rdllist and ->ovflist) and there
+ * is always a race when both lists are empty for short
+ * period of time although events are pending, so lock is
+ * important.
*/
- if (fatal_signal_pending(current)) {
- res = -EINTR;
- break;
+ eavail = ep_events_available(ep);
+ if (!eavail) {
+ if (signal_pending(current))
+ res = -EINTR;
+ else
+ __add_wait_queue_exclusive(&ep->wq, &wait);
}
+ write_unlock_irq(&ep->lock);
- eavail = ep_events_available(ep);
- if (eavail)
+ if (eavail || res)
break;
- if (signal_pending(current)) {
- res = -EINTR;
- break;
- }
if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) {
timed_out = 1;
break;
}
- }
+
+ /* We were woken up, thus go and try to harvest some events */
+ eavail = 1;
+
+ } while (0);
__set_current_state(TASK_RUNNING);
+ if (!list_empty_careful(&wait.entry)) {
+ write_lock_irq(&ep->lock);
+ __remove_wait_queue(&ep->wq, &wait);
+ write_unlock_irq(&ep->lock);
+ }
+
send_events:
+ if (fatal_signal_pending(current)) {
+ /*
+ * Always short-circuit for fatal signals to allow
+ * threads to make a timely exit without the chance of
+ * finding more events available and fetching
+ * repeatedly.
+ */
+ res = -EINTR;
+ }
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
@@ -1925,12 +1944,6 @@ send_events:
!(res = ep_send_events(ep, events, maxevents)) && !timed_out)
goto fetch_events;
- if (waiter) {
- write_lock_irq(&ep->lock);
- __remove_wait_queue(&ep->wq, &wait);
- write_unlock_irq(&ep->lock);
- }
-
return res;
}
diff --git a/fs/exec.c b/fs/exec.c
index 06b4c550af5d..2c465119affc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1317,6 +1317,8 @@ int flush_old_exec(struct linux_binprm * bprm)
*/
set_mm_exe_file(bprm->mm, bprm->file);
+ would_dump(bprm, bprm->file);
+
/*
* Release all of the old mmap stuff
*/
@@ -1876,8 +1878,6 @@ static int __do_execve_file(int fd, struct filename *filename,
if (retval < 0)
goto out;
- would_dump(bprm, bprm->file);
-
retval = exec_binprm(bprm);
if (retval < 0)
goto out;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 936a8ec6b48e..6306eaae378b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -528,10 +528,12 @@ lower_metapath:
/* Advance in metadata tree. */
(mp->mp_list[hgt])++;
- if (mp->mp_list[hgt] >= sdp->sd_inptrs) {
- if (!hgt)
+ if (hgt) {
+ if (mp->mp_list[hgt] >= sdp->sd_inptrs)
+ goto lower_metapath;
+ } else {
+ if (mp->mp_list[hgt] >= sdp->sd_diptrs)
break;
- goto lower_metapath;
}
fill_up_metapath:
@@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
ret = -ENOENT;
goto unlock;
} else {
- /* report a hole */
iomap->offset = pos;
iomap->length = length;
- goto do_alloc;
+ goto hole_found;
}
}
iomap->length = size;
@@ -933,8 +934,6 @@ unlock:
return ret;
do_alloc:
- iomap->addr = IOMAP_NULL_ADDR;
- iomap->type = IOMAP_HOLE;
if (flags & IOMAP_REPORT) {
if (pos >= size)
ret = -ENOENT;
@@ -956,6 +955,9 @@ do_alloc:
if (pos < size && height == ip->i_height)
ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
}
+hole_found:
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->type = IOMAP_HOLE;
goto out;
}
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 29f9b6684b74..bf70e3b14938 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock)
fs_err(sdp, "Error %d syncing glock \n", ret);
gfs2_dump_glock(NULL, gl, true);
}
- return;
+ goto skip_inval;
}
}
if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) {
@@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock)
clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
}
+skip_inval:
gfs2_glock_hold(gl);
/*
* Check for an error encountered since we called go_sync and go_inval.
@@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock)
goto out_unlock;
if (nonblock)
goto out_sched;
- smp_mb();
- if (atomic_read(&gl->gl_revokes) != 0)
- goto out_sched;
set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
gl->gl_target = gl->gl_demote_state;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 70b2d3a1e866..5acd3ce30759 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = finish_no_open(file, NULL);
}
gfs2_glock_dq_uninit(ghs);
- return error;
+ goto fail;
} else if (error != -ENOENT) {
goto fail_gunlock;
}
@@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = finish_open(file, dentry, gfs2_open_common);
}
gfs2_glock_dq_uninit(ghs);
+ gfs2_qa_put(ip);
gfs2_glock_dq_uninit(ghs + 1);
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
gfs2_glock_put(io_gl);
+ gfs2_qa_put(dip);
return error;
fail_gunlock3:
@@ -776,7 +778,6 @@ fail_gunlock2:
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
gfs2_glock_put(io_gl);
fail_free_inode:
- gfs2_qa_put(ip);
if (ip->i_gl) {
glock_clear_object(ip->i_gl, ip);
gfs2_glock_put(ip->i_gl);
@@ -1005,7 +1006,7 @@ out_gunlock:
out_child:
gfs2_glock_dq(ghs);
out_parent:
- gfs2_qa_put(ip);
+ gfs2_qa_put(dip);
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 3a75843ae580..0644e58c6191 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
struct buffer_head *bh = bd->bd_bh;
struct gfs2_glock *gl = bd->bd_gl;
+ sdp->sd_log_num_revoke++;
+ if (atomic_inc_return(&gl->gl_revokes) == 1)
+ gfs2_glock_hold(gl);
bh->b_private = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_remove_from_ail(bd); /* drops ref on bh */
bd->bd_bh = NULL;
- sdp->sd_log_num_revoke++;
- if (atomic_inc_return(&gl->gl_revokes) == 1)
- gfs2_glock_hold(gl);
set_bit(GLF_LFLUSH, &gl->gl_flags);
list_add(&bd->bd_list, &sdp->sd_log_revokes);
}
@@ -1131,6 +1131,10 @@ int gfs2_logd(void *data)
while (!kthread_should_stop()) {
+ if (gfs2_withdrawn(sdp)) {
+ msleep_interruptible(HZ);
+ continue;
+ }
/* Check for errors writing to the journal */
if (sdp->sd_log_error) {
gfs2_lm(sdp,
@@ -1139,6 +1143,7 @@ int gfs2_logd(void *data)
"prevent further damage.\n",
sdp->sd_fsname, sdp->sd_log_error);
gfs2_withdraw(sdp);
+ continue;
}
did_flush = false;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 5ea96757afc4..48b54ec1c793 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
struct super_block *sb = sdp->sd_vfs;
struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9);
+ bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
bio_set_dev(bio, sb->s_bdev);
bio->bi_end_io = end_io;
bio->bi_private = sdp;
@@ -509,7 +509,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
unsigned int bsize = sdp->sd_sb.sb_bsize, off;
unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
unsigned int shift = PAGE_SHIFT - bsize_shift;
- unsigned int readahead_blocks = BIO_MAX_PAGES << shift;
+ unsigned int max_bio_size = 2 * 1024 * 1024;
struct gfs2_journal_extent *je;
int sz, ret = 0;
struct bio *bio = NULL;
@@ -537,12 +537,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
off = 0;
}
- if (!bio || (bio_chained && !off)) {
+ if (!bio || (bio_chained && !off) ||
+ bio->bi_iter.bi_size >= max_bio_size) {
/* start new bio */
} else {
- sz = bio_add_page(bio, page, bsize, off);
- if (sz == bsize)
- goto block_added;
+ sector_t sector = dblock << sdp->sd_fsb2bb_shift;
+
+ if (bio_end_sector(bio) == sector) {
+ sz = bio_add_page(bio, page, bsize, off);
+ if (sz == bsize)
+ goto block_added;
+ }
if (off) {
unsigned int blocks =
(PAGE_SIZE - off) >> bsize_shift;
@@ -568,7 +573,7 @@ block_added:
off += bsize;
if (off == PAGE_SIZE)
page = NULL;
- if (blocks_submitted < blocks_read + readahead_blocks) {
+ if (blocks_submitted < 2 * max_bio_size >> bsize_shift) {
/* Keep at least one bio in flight */
continue;
}
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 4b72abcf83b2..9856cc2e0795 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
int num = 0;
if (unlikely(gfs2_withdrawn(sdp)) &&
- (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) {
+ (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) {
*bhp = NULL;
return -EIO;
}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index cc0c4b5800be..8259fef3f986 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
u32 x;
int error = 0;
- if (capable(CAP_SYS_RESOURCE) ||
- sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+ if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
return 0;
error = gfs2_quota_hold(ip, uid, gid);
@@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
int found;
if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
- goto out;
+ return;
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
struct gfs2_quota_data *qd;
@@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
qd_unlock(qda[x]);
}
-out:
gfs2_quota_unhold(ip);
}
@@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
return 0;
- if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
- return 0;
-
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
qd = ip->i_qadata->qa_qd[x];
@@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
if (ip->i_diskflags & GFS2_DIF_SYSTEM)
return;
- BUG_ON(ip->i_qadata->qa_ref <= 0);
+ if (gfs2_assert_withdraw(sdp, ip->i_qadata &&
+ ip->i_qadata->qa_ref > 0))
+ return;
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
qd = ip->i_qadata->qa_qd[x];
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 7f9ca8ef40fc..21ada332d555 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
int ret;
ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
- if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+ if (capable(CAP_SYS_RESOURCE) ||
+ sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (ret)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 37fc41632aa2..956fced0a8ec 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1404,7 +1404,6 @@ out:
if (ip->i_qadata)
gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);
gfs2_rs_delete(ip, NULL);
- gfs2_qa_put(ip);
gfs2_ordered_del_inode(ip);
clear_inode(inode);
gfs2_dir_hash_inval(ip);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 9b64d40ab379..aa087a5675af 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
if (!sb_rdonly(sdp->sd_vfs))
ret = gfs2_make_fs_ro(sdp);
+ if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
+ if (!ret)
+ ret = -EIO;
+ clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+ goto skip_recovery;
+ }
/*
* Drop the glock for our journal so another node can recover it.
*/
@@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE);
}
- if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
- clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
- goto skip_recovery;
- }
/*
* Dequeue the "live" glock, but keep a reference so it's never freed.
*/
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0b91b0631173..70ae7e840c85 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -680,8 +680,6 @@ struct io_op_def {
unsigned needs_mm : 1;
/* needs req->file assigned */
unsigned needs_file : 1;
- /* needs req->file assigned IFF fd is >= 0 */
- unsigned fd_non_neg : 1;
/* hash wq insertion if file is a regular file */
unsigned hash_reg_file : 1;
/* unbound wq insertion if file is a non-regular file */
@@ -784,8 +782,6 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
},
[IORING_OP_OPENAT] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
@@ -799,8 +795,6 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_STATX] = {
.needs_mm = 1,
- .needs_file = 1,
- .fd_non_neg = 1,
.needs_fs = 1,
.file_table = 1,
},
@@ -837,8 +831,6 @@ static const struct io_op_def io_op_defs[] = {
.buffer_select = 1,
},
[IORING_OP_OPENAT2] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
@@ -1402,10 +1394,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
for (i = 0; i < rb->to_free; i++) {
struct io_kiocb *req = rb->reqs[i];
- if (req->flags & REQ_F_FIXED_FILE) {
- req->file = NULL;
- percpu_ref_put(req->fixed_file_refs);
- }
if (req->flags & REQ_F_INFLIGHT)
inflight++;
__io_req_aux_free(req);
@@ -1678,7 +1666,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
return false;
- if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+ if (req->file || req->io)
rb->need_iter++;
rb->reqs[rb->to_free++] = req;
@@ -2775,16 +2763,19 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
- long ret;
+ long ret = 0;
if (force_nonblock)
return -EAGAIN;
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
- ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
- if (force_nonblock && ret == -EAGAIN)
- return -EAGAIN;
+
+ if (sp->len) {
+ ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+ }
io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -5368,15 +5359,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
io_steal_work(req, workptr);
}
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
- if (!io_op_defs[req->opcode].needs_file)
- return 0;
- if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
- return 0;
- return 1;
-}
-
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
int index)
{
@@ -5414,14 +5396,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
}
static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
- int fd, unsigned int flags)
+ int fd)
{
bool fixed;
- if (!io_req_needs_file(req, fd))
- return 0;
-
- fixed = (flags & IOSQE_FIXED_FILE);
+ fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
if (unlikely(!fixed && req->needs_fixed_file))
return -EBADF;
@@ -5798,7 +5777,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
struct io_submit_state *state, bool async)
{
unsigned int sqe_flags;
- int id, fd;
+ int id;
/*
* All io need record the previous position, if LINK vs DARIN,
@@ -5850,8 +5829,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
IOSQE_ASYNC | IOSQE_FIXED_FILE |
IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
- fd = READ_ONCE(sqe->fd);
- return io_req_set_file(state, req, fd, sqe_flags);
+ if (!io_op_defs[req->opcode].needs_file)
+ return 0;
+
+ return io_req_set_file(state, req, READ_ONCE(sqe->fd));
}
static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
@@ -7360,11 +7341,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
static void io_uring_cancel_files(struct io_ring_ctx *ctx,
struct files_struct *files)
{
- struct io_kiocb *req;
- DEFINE_WAIT(wait);
-
while (!list_empty_careful(&ctx->inflight_list)) {
- struct io_kiocb *cancel_req = NULL;
+ struct io_kiocb *cancel_req = NULL, *req;
+ DEFINE_WAIT(wait);
spin_lock_irq(&ctx->inflight_lock);
list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7404,6 +7383,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
*/
if (refcount_sub_and_test(2, &cancel_req->refs)) {
io_put_req(cancel_req);
+ finish_wait(&ctx->inflight_wait, &wait);
continue;
}
}
@@ -7411,8 +7391,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
io_put_req(cancel_req);
schedule();
+ finish_wait(&ctx->inflight_wait, &wait);
}
- finish_wait(&ctx->inflight_wait, &wait);
}
static int io_uring_flush(struct file *file, void *data)
@@ -7761,7 +7741,8 @@ err:
return ret;
}
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+ struct io_uring_params __user *params)
{
struct user_struct *user = NULL;
struct io_ring_ctx *ctx;
@@ -7853,6 +7834,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
p->cq_off.cqes = offsetof(struct io_rings, cqes);
+ p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+ IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+ IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+
+ if (copy_to_user(params, p, sizeof(*p))) {
+ ret = -EFAULT;
+ goto err;
+ }
/*
* Install ring fd as the very last thing, so we don't risk someone
* having closed it before we finish setup
@@ -7861,9 +7850,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
if (ret < 0)
goto err;
- p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
- IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
- IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
@@ -7879,7 +7865,6 @@ err:
static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
{
struct io_uring_params p;
- long ret;
int i;
if (copy_from_user(&p, params, sizeof(p)))
@@ -7894,14 +7879,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
return -EINVAL;
- ret = io_uring_create(entries, &p);
- if (ret < 0)
- return ret;
-
- if (copy_to_user(params, &p, sizeof(p)))
- return -EFAULT;
-
- return ret;
+ return io_uring_create(entries, &p, params);
}
SYSCALL_DEFINE2(io_uring_setup, u32, entries,
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 1abf126c2df4..a60df88efc40 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -118,8 +118,6 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
nfss->fscache_key = NULL;
nfss->fscache = NULL;
- if (!(nfss->options & NFS_OPTION_FSCACHE))
- return;
if (!uniq) {
uniq = "";
ulen = 1;
@@ -188,7 +186,8 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
/* create a cache index for looking up filehandles */
nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
&nfs_fscache_super_index_def,
- key, sizeof(*key) + ulen,
+ &key->key,
+ sizeof(key->key) + ulen,
NULL, 0,
nfss, 0, true);
dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
@@ -226,6 +225,19 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
}
}
+static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+ struct nfs_inode *nfsi)
+{
+ memset(auxdata, 0, sizeof(*auxdata));
+ auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+ if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+ auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+}
+
/*
* Initialise the per-inode cache cookie pointer for an NFS inode.
*/
@@ -239,14 +251,7 @@ void nfs_fscache_init_inode(struct inode *inode)
if (!(nfss->fscache && S_ISREG(inode->i_mode)))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
-
- if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
- auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
&nfs_fscache_inode_object_def,
@@ -266,11 +271,7 @@ void nfs_fscache_clear_inode(struct inode *inode)
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
fscache_relinquish_cookie(cookie, &auxdata, false);
nfsi->fscache = NULL;
}
@@ -310,11 +311,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
if (!fscache_cookie_valid(cookie))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
if (inode_is_open_for_write(inode)) {
dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 35c8cb2d7637..dda5c3e65d8d 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -30,6 +30,7 @@
#define encode_dirpath_sz (1 + XDR_QUADLEN(MNTPATHLEN))
#define MNT_status_sz (1)
#define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE)
+#define MNT_fhandlev3_sz XDR_QUADLEN(NFS3_FHSIZE)
#define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS)
/*
@@ -37,7 +38,7 @@
*/
#define MNT_enc_dirpath_sz encode_dirpath_sz
#define MNT_dec_mountres_sz (MNT_status_sz + MNT_fhandle_sz)
-#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandle_sz + \
+#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandlev3_sz + \
MNT_authflav3_sz)
/*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a0c1e653a935..9056f3dd380e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6347,7 +6347,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
.rpc_client = server->client,
.rpc_message = &msg,
.callback_ops = &nfs4_delegreturn_ops,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | RPC_TASK_TIMEOUT,
+ .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
};
int status = 0;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index ac93715c05a4..a8dc25ce48bb 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -734,9 +734,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
state = new;
state->owner = owner;
atomic_inc(&owner->so_count);
- list_add_rcu(&state->inode_states, &nfsi->open_states);
ihold(inode);
state->inode = inode;
+ list_add_rcu(&state->inode_states, &nfsi->open_states);
spin_unlock(&inode->i_lock);
/* Note: The reclaim code dictates that we add stateless
* and read-only stateids to the end of the list */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index f61f96603df7..6ca421cbe19c 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -752,7 +752,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
.callback_ops = call_ops,
.callback_data = hdr,
.workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+ .flags = RPC_TASK_ASYNC | flags,
};
hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
@@ -950,7 +950,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
hdr->cred,
NFS_PROTO(hdr->inode),
desc->pg_rpc_callops,
- desc->pg_ioflags, 0);
+ desc->pg_ioflags,
+ RPC_TASK_CRED_NOREF);
return ret;
}
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index e7ddbce48321..679767ac258d 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -536,7 +536,8 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
nfs_init_commit(data, NULL, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
NFS_PROTO(data->inode),
- data->mds_ops, how, 0);
+ data->mds_ops, how,
+ RPC_TASK_CRED_NOREF);
} else {
nfs_init_commit(data, NULL, data->lseg, cinfo);
initiate_commit(data, how);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index bdb6d0c2e755..7a70287f21a2 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1189,7 +1189,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
uniq = ctx->fscache_uniq;
ulen = strlen(ctx->fscache_uniq);
}
- return;
}
nfs_fscache_get_super_cookie(sb, uniq, ulen);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index df4b87c30ac9..1e767f779c49 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1695,7 +1695,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
.callback_ops = call_ops,
.callback_data = data,
.workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+ .flags = RPC_TASK_ASYNC | flags,
.priority = priority,
};
/* Set up the initial task struct. */
@@ -1813,7 +1813,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
nfs_init_commit(data, head, NULL, cinfo);
atomic_inc(&cinfo->mds->rpcs_out);
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
- data->mds_ops, how, 0);
+ data->mds_ops, how, RPC_TASK_CRED_NOREF);
}
/*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 5cf91322de0f..966ca75418c8 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -38,6 +38,7 @@
#include "nfsd.h"
#include "state.h"
#include "netns.h"
+#include "trace.h"
#include "xdr4cb.h"
#include "xdr4.h"
@@ -904,16 +905,20 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
if (clp->cl_minorversion == 0) {
if (!clp->cl_cred.cr_principal &&
- (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5))
+ (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) {
+ trace_nfsd_cb_setup_err(clp, -EINVAL);
return -EINVAL;
+ }
args.client_name = clp->cl_cred.cr_principal;
args.prognumber = conn->cb_prog;
args.protocol = XPRT_TRANSPORT_TCP;
args.authflavor = clp->cl_cred.cr_flavor;
clp->cl_cb_ident = conn->cb_ident;
} else {
- if (!conn->cb_xprt)
+ if (!conn->cb_xprt) {
+ trace_nfsd_cb_setup_err(clp, -EINVAL);
return -EINVAL;
+ }
clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
clp->cl_cb_session = ses;
args.bc_xprt = conn->cb_xprt;
@@ -925,32 +930,27 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
/* Create RPC client */
client = rpc_create(&args);
if (IS_ERR(client)) {
- dprintk("NFSD: couldn't create callback client: %ld\n",
- PTR_ERR(client));
+ trace_nfsd_cb_setup_err(clp, PTR_ERR(client));
return PTR_ERR(client);
}
cred = get_backchannel_cred(clp, client, ses);
if (!cred) {
+ trace_nfsd_cb_setup_err(clp, -ENOMEM);
rpc_shutdown_client(client);
return -ENOMEM;
}
clp->cl_cb_client = client;
clp->cl_cb_cred = cred;
+ trace_nfsd_cb_setup(clp);
return 0;
}
-static void warn_no_callback_path(struct nfs4_client *clp, int reason)
-{
- dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
- (int)clp->cl_name.len, clp->cl_name.data, reason);
-}
-
static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
{
if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
return;
clp->cl_cb_state = NFSD4_CB_DOWN;
- warn_no_callback_path(clp, reason);
+ trace_nfsd_cb_state(clp);
}
static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
@@ -958,17 +958,20 @@ static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
return;
clp->cl_cb_state = NFSD4_CB_FAULT;
- warn_no_callback_path(clp, reason);
+ trace_nfsd_cb_state(clp);
}
static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
{
struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);
+ trace_nfsd_cb_done(clp, task->tk_status);
if (task->tk_status)
nfsd4_mark_cb_down(clp, task->tk_status);
- else
+ else {
clp->cl_cb_state = NFSD4_CB_UP;
+ trace_nfsd_cb_state(clp);
+ }
}
static void nfsd4_cb_probe_release(void *calldata)
@@ -993,6 +996,7 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
void nfsd4_probe_callback(struct nfs4_client *clp)
{
clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+ trace_nfsd_cb_state(clp);
set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
nfsd4_run_cb(&clp->cl_cb_null);
}
@@ -1009,6 +1013,7 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
spin_lock(&clp->cl_lock);
memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn));
spin_unlock(&clp->cl_lock);
+ trace_nfsd_cb_state(clp);
}
/*
@@ -1165,8 +1170,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
struct nfsd4_callback *cb = calldata;
struct nfs4_client *clp = cb->cb_clp;
- dprintk("%s: minorversion=%d\n", __func__,
- clp->cl_minorversion);
+ trace_nfsd_cb_done(clp, task->tk_status);
if (!nfsd4_cb_sequence_done(task, cb))
return;
@@ -1271,6 +1275,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
* kill the old client:
*/
if (clp->cl_cb_client) {
+ trace_nfsd_cb_shutdown(clp);
rpc_shutdown_client(clp->cl_cb_client);
clp->cl_cb_client = NULL;
put_cred(clp->cl_cb_cred);
@@ -1314,6 +1319,8 @@ nfsd4_run_cb_work(struct work_struct *work)
struct rpc_clnt *clnt;
int flags;
+ trace_nfsd_cb_work(clp, cb->cb_msg.rpc_proc->p_name);
+
if (cb->cb_need_restart) {
cb->cb_need_restart = false;
} else {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a6d73aa51ce4..a09c35f0f6f0 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1155,7 +1155,7 @@ extern void nfs_sb_deactive(struct super_block *sb);
#define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys"
-/**
+/*
* Support one copy source server for now.
*/
static __be32
@@ -1245,10 +1245,9 @@ nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
mntput(ss_mnt);
}
-/**
- * nfsd4_setup_inter_ssc
- *
+/*
* Verify COPY destination stateid.
+ *
* Connect to the source server with NFSv4.1.
* Create the source struct file for nfsd_copy_range.
* Called with COPY cstate:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 31388046c6fe..bb3d2c32664a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -51,6 +51,7 @@
#include "netns.h"
#include "pnfs.h"
#include "filecache.h"
+#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -167,9 +168,6 @@ renew_client_locked(struct nfs4_client *clp)
return;
}
- dprintk("renewing client (clientid %08x/%08x)\n",
- clp->cl_clientid.cl_boot,
- clp->cl_clientid.cl_id);
list_move_tail(&clp->cl_lru, &nn->client_lru);
clp->cl_time = ktime_get_boottime_seconds();
}
@@ -1922,8 +1920,7 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
*/
if (clid->cl_boot == (u32)nn->boot_time)
return 0;
- dprintk("NFSD stale clientid (%08x/%08x) boot_time %08llx\n",
- clid->cl_boot, clid->cl_id, nn->boot_time);
+ trace_nfsd_clid_stale(clid);
return 1;
}
@@ -2872,14 +2869,12 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r
conn->cb_prog = se->se_callback_prog;
conn->cb_ident = se->se_callback_ident;
memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen);
+ trace_nfsd_cb_args(clp, conn);
return;
out_err:
conn->cb_addr.ss_family = AF_UNSPEC;
conn->cb_addrlen = 0;
- dprintk("NFSD: this client (clientid %08x/%08x) "
- "will not receive delegations\n",
- clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
-
+ trace_nfsd_cb_nodelegs(clp);
return;
}
@@ -3936,23 +3931,18 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (clp_used_exchangeid(conf))
goto out;
if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
- char addr_str[INET6_ADDRSTRLEN];
- rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
- sizeof(addr_str));
- dprintk("NFSD: setclientid: string in use by client "
- "at %s\n", addr_str);
+ trace_nfsd_clid_inuse_err(conf);
goto out;
}
}
unconf = find_unconfirmed_client_by_name(&clname, nn);
if (unconf)
unhash_client_locked(unconf);
+ /* We need to handle only case 1: probable callback update */
if (conf && same_verf(&conf->cl_verifier, &clverifier)) {
- /* case 1: probable callback update */
copy_clid(new, conf);
gen_confirm(new, nn);
- } else /* case 4 (new client) or cases 2, 3 (client reboot): */
- ;
+ }
new->cl_minorversion = 0;
gen_callback(new, setclid, rqstp);
add_to_unconfirmed(new);
@@ -4133,7 +4123,6 @@ out_free_openowner_slab:
out_free_client_slab:
kmem_cache_destroy(client_slab);
out:
- dprintk("nfsd4: out of memory while initializing nfsv4\n");
return -ENOMEM;
}
@@ -4565,6 +4554,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
struct nfs4_file *fp = dp->dl_stid.sc_file;
+ trace_nfsd_deleg_break(&dp->dl_stid.sc_stateid);
+
/*
* We don't want the locks code to timeout the lease for us;
* we'll remove it ourself if a delegation isn't returned
@@ -5089,8 +5080,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
- dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
- STATEID_VAL(&dp->dl_stid.sc_stateid));
+ trace_nfsd_deleg_open(&dp->dl_stid.sc_stateid);
open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
nfs4_put_stid(&dp->dl_stid);
return;
@@ -5207,9 +5197,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
nfs4_open_delegation(current_fh, open, stp);
nodeleg:
status = nfs_ok;
-
- dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
- STATEID_VAL(&stp->st_stid.sc_stateid));
+ trace_nfsd_deleg_none(&stp->st_stid.sc_stateid);
out:
/* 4.1 client trying to upgrade/downgrade delegation? */
if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
@@ -5263,8 +5251,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- dprintk("process_renew(%08x/%08x): starting\n",
- clid->cl_boot, clid->cl_id);
+ trace_nfsd_clid_renew(clid);
status = lookup_clientid(clid, cstate, nn, false);
if (status)
goto out;
@@ -5285,6 +5272,7 @@ nfsd4_end_grace(struct nfsd_net *nn)
if (nn->grace_ended)
return;
+ trace_nfsd_grace_complete(nn);
nn->grace_ended = true;
/*
* If the server goes down again right now, an NFSv4
@@ -5350,13 +5338,10 @@ nfs4_laundromat(struct nfsd_net *nn)
copy_stateid_t *cps_t;
int i;
- dprintk("NFSD: laundromat service - starting\n");
-
if (clients_still_reclaiming(nn)) {
new_timeo = 0;
goto out;
}
- dprintk("NFSD: end of grace period\n");
nfsd4_end_grace(nn);
INIT_LIST_HEAD(&reaplist);
@@ -5378,8 +5363,7 @@ nfs4_laundromat(struct nfsd_net *nn)
break;
}
if (mark_client_expired_locked(clp)) {
- dprintk("NFSD: client in use (clientid %08x)\n",
- clp->cl_clientid.cl_id);
+ trace_nfsd_clid_expired(&clp->cl_clientid);
continue;
}
list_add(&clp->cl_lru, &reaplist);
@@ -5387,8 +5371,7 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_unlock(&nn->client_lock);
list_for_each_safe(pos, next, &reaplist) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
- dprintk("NFSD: purging unused client (clientid %08x)\n",
- clp->cl_clientid.cl_id);
+ trace_nfsd_clid_purged(&clp->cl_clientid);
list_del_init(&clp->cl_lru);
expire_client(clp);
}
@@ -5478,7 +5461,6 @@ laundromat_main(struct work_struct *laundry)
laundromat_work);
t = nfs4_laundromat(nn);
- dprintk("NFSD: laundromat_main - sleeping for %lld seconds\n", t);
queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
}
@@ -6019,8 +6001,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
struct nfs4_stid *s;
struct nfs4_ol_stateid *stp = NULL;
- dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__,
- seqid, STATEID_VAL(stateid));
+ trace_nfsd_preprocess(seqid, stateid);
*stpp = NULL;
status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn);
@@ -6089,9 +6070,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
oo->oo_flags |= NFS4_OO_CONFIRMED;
nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
mutex_unlock(&stp->st_mutex);
- dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
- __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
-
+ trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid);
nfsd4_client_record_create(oo->oo_owner.so_client);
status = nfs_ok;
put_stateid:
@@ -7143,7 +7122,7 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash,
unsigned int strhashval;
struct nfs4_client_reclaim *crp;
- dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", name.len, name.data);
+ trace_nfsd_clid_reclaim(nn, name.len, name.data);
crp = alloc_reclaim();
if (crp) {
strhashval = clientstr_hashval(name);
@@ -7193,7 +7172,7 @@ nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn)
unsigned int strhashval;
struct nfs4_client_reclaim *crp = NULL;
- dprintk("NFSD: nfs4_find_reclaim_client for name %.*s\n", name.len, name.data);
+ trace_nfsd_clid_find(nn, name.len, name.data);
strhashval = clientstr_hashval(name);
list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) {
@@ -7757,6 +7736,9 @@ nfsd_recall_delegations(struct list_head *reaplist)
list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) {
list_del_init(&dp->dl_recall_lru);
clp = dp->dl_stid.sc_client;
+
+ trace_nfsd_deleg_recall(&dp->dl_stid.sc_stateid);
+
/*
* We skipped all entries that had a zero dl_time before,
* so we can now reset the dl_time back to 0. If a delegation
@@ -7939,6 +7921,7 @@ nfs4_state_start_net(struct net *net)
goto skip_grace;
printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n",
nn->nfsd4_grace, net->ns.inum);
+ trace_nfsd_grace_start(nn);
queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
return 0;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 96352ab7bd81..945d2f5e760e 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -20,8 +20,7 @@
#include "nfsd.h"
#include "cache.h"
-
-#define NFSDDBG_FACILITY NFSDDBG_REPCACHE
+#include "trace.h"
/*
* We use this value to determine the number of hash buckets from the max
@@ -323,8 +322,10 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key,
const struct svc_cacherep *rp, struct nfsd_net *nn)
{
if (key->c_key.k_xid == rp->c_key.k_xid &&
- key->c_key.k_csum != rp->c_key.k_csum)
+ key->c_key.k_csum != rp->c_key.k_csum) {
++nn->payload_misses;
+ trace_nfsd_drc_mismatch(nn, key, rp);
+ }
return memcmp(&key->c_key, &rp->c_key, sizeof(key->c_key));
}
@@ -377,15 +378,22 @@ out:
return ret;
}
-/*
+/**
+ * nfsd_cache_lookup - Find an entry in the duplicate reply cache
+ * @rqstp: Incoming Call to find
+ *
* Try to find an entry matching the current call in the cache. When none
* is found, we try to grab the oldest expired entry off the LRU list. If
* a suitable one isn't there, then drop the cache_lock and allocate a
* new one, then search again in case one got inserted while this thread
* didn't hold the lock.
+ *
+ * Return values:
+ * %RC_DOIT: Process the request normally
+ * %RC_REPLY: Reply from cache
+ * %RC_DROPIT: Do not process the request further
*/
-int
-nfsd_cache_lookup(struct svc_rqst *rqstp)
+int nfsd_cache_lookup(struct svc_rqst *rqstp)
{
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct svc_cacherep *rp, *found;
@@ -399,7 +407,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
rqstp->rq_cacherep = NULL;
if (type == RC_NOCACHE) {
nfsdstats.rcnocache++;
- return rtn;
+ goto out;
}
csum = nfsd_cache_csum(rqstp);
@@ -409,10 +417,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
* preallocate an entry.
*/
rp = nfsd_reply_cache_alloc(rqstp, csum, nn);
- if (!rp) {
- dprintk("nfsd: unable to allocate DRC entry!\n");
- return rtn;
- }
+ if (!rp)
+ goto out;
spin_lock(&b->cache_lock);
found = nfsd_cache_insert(b, rp, nn);
@@ -431,8 +437,10 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
/* go ahead and prune the cache */
prune_bucket(b, nn);
- out:
+
+out_unlock:
spin_unlock(&b->cache_lock);
+out:
return rtn;
found_entry:
@@ -442,13 +450,13 @@ found_entry:
/* Request being processed */
if (rp->c_state == RC_INPROG)
- goto out;
+ goto out_trace;
/* From the hall of fame of impractical attacks:
* Is this a user who tries to snoop on the cache? */
rtn = RC_DOIT;
if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure)
- goto out;
+ goto out_trace;
/* Compose RPC reply header */
switch (rp->c_type) {
@@ -460,7 +468,7 @@ found_entry:
break;
case RC_REPLBUFF:
if (!nfsd_cache_append(rqstp, &rp->c_replvec))
- goto out; /* should not happen */
+ goto out_unlock; /* should not happen */
rtn = RC_REPLY;
break;
default:
@@ -468,13 +476,19 @@ found_entry:
nfsd_reply_cache_free_locked(b, rp, nn);
}
- goto out;
+out_trace:
+ trace_nfsd_drc_found(nn, rqstp, rtn);
+ goto out_unlock;
}
-/*
- * Update a cache entry. This is called from nfsd_dispatch when
- * the procedure has been executed and the complete reply is in
- * rqstp->rq_res.
+/**
+ * nfsd_cache_update - Update an entry in the duplicate reply cache.
+ * @rqstp: svc_rqst with a finished Reply
+ * @cachetype: which cache to update
+ * @statp: Reply's status code
+ *
+ * This is called from nfsd_dispatch when the procedure has been
+ * executed and the complete reply is in rqstp->rq_res.
*
* We're copying around data here rather than swapping buffers because
* the toplevel loop requires max-sized buffers, which would be a waste
@@ -487,8 +501,7 @@ found_entry:
* nfsd failed to encode a reply that otherwise would have been cached.
* In this case, nfsd_cache_update is called with statp == NULL.
*/
-void
-nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
+void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct svc_cacherep *rp = rqstp->rq_cacherep;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3bb2db947d29..b48eac3bb72b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -238,7 +238,7 @@ static inline struct net *netns(struct file *file)
return file_inode(file)->i_sb->s_fs_info;
}
-/**
+/*
* write_unlock_ip - Release all locks used by a client
*
* Experimental.
@@ -277,7 +277,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
return nlmsvc_unlock_all_by_ip(sap);
}
-/**
+/*
* write_unlock_fs - Release all locks on a local file system
*
* Experimental.
@@ -327,7 +327,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size)
return error;
}
-/**
+/*
* write_filehandle - Get a variable-length NFS file handle by path
*
* On input, the buffer contains a '\n'-terminated C string comprised of
@@ -402,7 +402,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
return mesg - buf;
}
-/**
+/*
* write_threads - Start NFSD, or report the current number of running threads
*
* Input:
@@ -452,7 +452,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv);
}
-/**
+/*
* write_pool_threads - Set or report the current number of threads per pool
*
* Input:
@@ -661,7 +661,7 @@ out:
return tlen + len;
}
-/**
+/*
* write_versions - Set or report the available NFS protocol versions
*
* Input:
@@ -811,7 +811,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size,
return -EINVAL;
}
-/**
+/*
* write_ports - Pass a socket file descriptor or transport name to listen on
*
* Input:
@@ -867,7 +867,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
int nfsd_max_blksize;
-/**
+/*
* write_maxblksize - Set or report the current NFS blksize
*
* Input:
@@ -917,7 +917,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
nfsd_max_blksize);
}
-/**
+/*
* write_maxconn - Set or report the current max number of connections
*
* Input:
@@ -998,7 +998,7 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
return rv;
}
-/**
+/*
* write_leasetime - Set or report the current NFSv4 lease time
*
* Input:
@@ -1025,7 +1025,7 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}
-/**
+/*
* write_gracetime - Set or report current NFSv4 grace period time
*
* As above, but sets the time of the NFSv4 grace period.
@@ -1069,7 +1069,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
nfs4_recoverydir());
}
-/**
+/*
* write_recoverydir - Set or report the pathname of the recovery directory
*
* Input:
@@ -1101,7 +1101,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
return rv;
}
-/**
+/*
* write_v4_end_grace - release grace period for nfsd's v4.x lock manager
*
* Input:
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 68d3f30ee760..3b408532a5dc 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -64,13 +64,6 @@ typedef struct {
refcount_t sc_count;
} copy_stateid_t;
-#define STATEID_FMT "(%08x/%08x/%08x/%08x)"
-#define STATEID_VAL(s) \
- (s)->si_opaque.so_clid.cl_boot, \
- (s)->si_opaque.so_clid.cl_id, \
- (s)->si_opaque.so_id, \
- (s)->si_generation
-
struct nfsd4_callback {
struct nfs4_client *cb_clp;
struct rpc_message cb_msg;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 78c574251c60..1861db1bdc67 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -277,6 +277,7 @@ DECLARE_EVENT_CLASS(nfsd_stateid_class,
DEFINE_EVENT(nfsd_stateid_class, nfsd_##name, \
TP_PROTO(stateid_t *stp), \
TP_ARGS(stp))
+
DEFINE_STATEID_EVENT(layoutstate_alloc);
DEFINE_STATEID_EVENT(layoutstate_unhash);
DEFINE_STATEID_EVENT(layoutstate_free);
@@ -288,6 +289,138 @@ DEFINE_STATEID_EVENT(layout_recall_done);
DEFINE_STATEID_EVENT(layout_recall_fail);
DEFINE_STATEID_EVENT(layout_recall_release);
+DEFINE_STATEID_EVENT(deleg_open);
+DEFINE_STATEID_EVENT(deleg_none);
+DEFINE_STATEID_EVENT(deleg_break);
+DEFINE_STATEID_EVENT(deleg_recall);
+
+DECLARE_EVENT_CLASS(nfsd_stateseqid_class,
+ TP_PROTO(u32 seqid, const stateid_t *stp),
+ TP_ARGS(seqid, stp),
+ TP_STRUCT__entry(
+ __field(u32, seqid)
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __field(u32, si_id)
+ __field(u32, si_generation)
+ ),
+ TP_fast_assign(
+ __entry->seqid = seqid;
+ __entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+ __entry->cl_id = stp->si_opaque.so_clid.cl_id;
+ __entry->si_id = stp->si_opaque.so_id;
+ __entry->si_generation = stp->si_generation;
+ ),
+ TP_printk("seqid=%u client %08x:%08x stateid %08x:%08x",
+ __entry->seqid, __entry->cl_boot, __entry->cl_id,
+ __entry->si_id, __entry->si_generation)
+)
+
+#define DEFINE_STATESEQID_EVENT(name) \
+DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \
+ TP_PROTO(u32 seqid, const stateid_t *stp), \
+ TP_ARGS(seqid, stp))
+
+DEFINE_STATESEQID_EVENT(preprocess);
+DEFINE_STATESEQID_EVENT(open_confirm);
+
+DECLARE_EVENT_CLASS(nfsd_clientid_class,
+ TP_PROTO(const clientid_t *clid),
+ TP_ARGS(clid),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clid->cl_boot;
+ __entry->cl_id = clid->cl_id;
+ ),
+ TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id)
+)
+
+#define DEFINE_CLIENTID_EVENT(name) \
+DEFINE_EVENT(nfsd_clientid_class, nfsd_clid_##name, \
+ TP_PROTO(const clientid_t *clid), \
+ TP_ARGS(clid))
+
+DEFINE_CLIENTID_EVENT(expired);
+DEFINE_CLIENTID_EVENT(purged);
+DEFINE_CLIENTID_EVENT(renew);
+DEFINE_CLIENTID_EVENT(stale);
+
+DECLARE_EVENT_CLASS(nfsd_net_class,
+ TP_PROTO(const struct nfsd_net *nn),
+ TP_ARGS(nn),
+ TP_STRUCT__entry(
+ __field(unsigned long long, boot_time)
+ ),
+ TP_fast_assign(
+ __entry->boot_time = nn->boot_time;
+ ),
+ TP_printk("boot_time=%16llx", __entry->boot_time)
+)
+
+#define DEFINE_NET_EVENT(name) \
+DEFINE_EVENT(nfsd_net_class, nfsd_##name, \
+ TP_PROTO(const struct nfsd_net *nn), \
+ TP_ARGS(nn))
+
+DEFINE_NET_EVENT(grace_start);
+DEFINE_NET_EVENT(grace_complete);
+
+DECLARE_EVENT_CLASS(nfsd_clid_class,
+ TP_PROTO(const struct nfsd_net *nn,
+ unsigned int namelen,
+ const unsigned char *namedata),
+ TP_ARGS(nn, namelen, namedata),
+ TP_STRUCT__entry(
+ __field(unsigned long long, boot_time)
+ __field(unsigned int, namelen)
+ __dynamic_array(unsigned char, name, namelen)
+ ),
+ TP_fast_assign(
+ __entry->boot_time = nn->boot_time;
+ __entry->namelen = namelen;
+ memcpy(__get_dynamic_array(name), namedata, namelen);
+ ),
+ TP_printk("boot_time=%16llx nfs4_clientid=%.*s",
+ __entry->boot_time, __entry->namelen, __get_str(name))
+)
+
+#define DEFINE_CLID_EVENT(name) \
+DEFINE_EVENT(nfsd_clid_class, nfsd_clid_##name, \
+ TP_PROTO(const struct nfsd_net *nn, \
+ unsigned int namelen, \
+ const unsigned char *namedata), \
+ TP_ARGS(nn, namelen, namedata))
+
+DEFINE_CLID_EVENT(find);
+DEFINE_CLID_EVENT(reclaim);
+
+TRACE_EVENT(nfsd_clid_inuse_err,
+ TP_PROTO(const struct nfs4_client *clp),
+ TP_ARGS(clp),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ __field(unsigned int, namelen)
+ __dynamic_array(unsigned char, name, clp->cl_name.len)
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ memcpy(__entry->addr, &clp->cl_addr,
+ sizeof(struct sockaddr_in6));
+ __entry->namelen = clp->cl_name.len;
+ memcpy(__get_dynamic_array(name), clp->cl_name.data,
+ clp->cl_name.len);
+ ),
+ TP_printk("nfs4_clientid %.*s already in use by %pISpc, client %08x:%08x",
+ __entry->namelen, __get_str(name), __entry->addr,
+ __entry->cl_boot, __entry->cl_id)
+)
+
TRACE_DEFINE_ENUM(NFSD_FILE_HASHED);
TRACE_DEFINE_ENUM(NFSD_FILE_PENDING);
TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ);
@@ -432,6 +565,218 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
__entry->nlink, __entry->mode, __entry->mask)
);
+#include "cache.h"
+
+TRACE_DEFINE_ENUM(RC_DROPIT);
+TRACE_DEFINE_ENUM(RC_REPLY);
+TRACE_DEFINE_ENUM(RC_DOIT);
+
+#define show_drc_retval(x) \
+ __print_symbolic(x, \
+ { RC_DROPIT, "DROPIT" }, \
+ { RC_REPLY, "REPLY" }, \
+ { RC_DOIT, "DOIT" })
+
+TRACE_EVENT(nfsd_drc_found,
+ TP_PROTO(
+ const struct nfsd_net *nn,
+ const struct svc_rqst *rqstp,
+ int result
+ ),
+ TP_ARGS(nn, rqstp, result),
+ TP_STRUCT__entry(
+ __field(unsigned long long, boot_time)
+ __field(unsigned long, result)
+ __field(u32, xid)
+ ),
+ TP_fast_assign(
+ __entry->boot_time = nn->boot_time;
+ __entry->result = result;
+ __entry->xid = be32_to_cpu(rqstp->rq_xid);
+ ),
+ TP_printk("boot_time=%16llx xid=0x%08x result=%s",
+ __entry->boot_time, __entry->xid,
+ show_drc_retval(__entry->result))
+
+);
+
+TRACE_EVENT(nfsd_drc_mismatch,
+ TP_PROTO(
+ const struct nfsd_net *nn,
+ const struct svc_cacherep *key,
+ const struct svc_cacherep *rp
+ ),
+ TP_ARGS(nn, key, rp),
+ TP_STRUCT__entry(
+ __field(unsigned long long, boot_time)
+ __field(u32, xid)
+ __field(u32, cached)
+ __field(u32, ingress)
+ ),
+ TP_fast_assign(
+ __entry->boot_time = nn->boot_time;
+ __entry->xid = be32_to_cpu(key->c_key.k_xid);
+ __entry->cached = (__force u32)key->c_key.k_csum;
+ __entry->ingress = (__force u32)rp->c_key.k_csum;
+ ),
+ TP_printk("boot_time=%16llx xid=0x%08x cached-csum=0x%08x ingress-csum=0x%08x",
+ __entry->boot_time, __entry->xid, __entry->cached,
+ __entry->ingress)
+);
+
+TRACE_EVENT(nfsd_cb_args,
+ TP_PROTO(
+ const struct nfs4_client *clp,
+ const struct nfs4_cb_conn *conn
+ ),
+ TP_ARGS(clp, conn),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __field(u32, prog)
+ __field(u32, ident)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ __entry->prog = conn->cb_prog;
+ __entry->ident = conn->cb_ident;
+ memcpy(__entry->addr, &conn->cb_addr,
+ sizeof(struct sockaddr_in6));
+ ),
+ TP_printk("client %08x:%08x callback addr=%pISpc prog=%u ident=%u",
+ __entry->cl_boot, __entry->cl_id,
+ __entry->addr, __entry->prog, __entry->ident)
+);
+
+TRACE_EVENT(nfsd_cb_nodelegs,
+ TP_PROTO(const struct nfs4_client *clp),
+ TP_ARGS(clp),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ ),
+ TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id)
+)
+
+TRACE_DEFINE_ENUM(NFSD4_CB_UP);
+TRACE_DEFINE_ENUM(NFSD4_CB_UNKNOWN);
+TRACE_DEFINE_ENUM(NFSD4_CB_DOWN);
+TRACE_DEFINE_ENUM(NFSD4_CB_FAULT);
+
+#define show_cb_state(val) \
+ __print_symbolic(val, \
+ { NFSD4_CB_UP, "UP" }, \
+ { NFSD4_CB_UNKNOWN, "UNKNOWN" }, \
+ { NFSD4_CB_DOWN, "DOWN" }, \
+ { NFSD4_CB_FAULT, "FAULT"})
+
+DECLARE_EVENT_CLASS(nfsd_cb_class,
+ TP_PROTO(const struct nfs4_client *clp),
+ TP_ARGS(clp),
+ TP_STRUCT__entry(
+ __field(unsigned long, state)
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ ),
+ TP_fast_assign(
+ __entry->state = clp->cl_cb_state;
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr,
+ sizeof(struct sockaddr_in6));
+ ),
+ TP_printk("addr=%pISpc client %08x:%08x state=%s",
+ __entry->addr, __entry->cl_boot, __entry->cl_id,
+ show_cb_state(__entry->state))
+);
+
+#define DEFINE_NFSD_CB_EVENT(name) \
+DEFINE_EVENT(nfsd_cb_class, nfsd_cb_##name, \
+ TP_PROTO(const struct nfs4_client *clp), \
+ TP_ARGS(clp))
+
+DEFINE_NFSD_CB_EVENT(setup);
+DEFINE_NFSD_CB_EVENT(state);
+DEFINE_NFSD_CB_EVENT(shutdown);
+
+TRACE_EVENT(nfsd_cb_setup_err,
+ TP_PROTO(
+ const struct nfs4_client *clp,
+ long error
+ ),
+ TP_ARGS(clp, error),
+ TP_STRUCT__entry(
+ __field(long, error)
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ ),
+ TP_fast_assign(
+ __entry->error = error;
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr,
+ sizeof(struct sockaddr_in6));
+ ),
+ TP_printk("addr=%pISpc client %08x:%08x error=%ld",
+ __entry->addr, __entry->cl_boot, __entry->cl_id, __entry->error)
+);
+
+TRACE_EVENT(nfsd_cb_work,
+ TP_PROTO(
+ const struct nfs4_client *clp,
+ const char *procedure
+ ),
+ TP_ARGS(clp, procedure),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __string(procedure, procedure)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ __assign_str(procedure, procedure)
+ memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr,
+ sizeof(struct sockaddr_in6));
+ ),
+ TP_printk("addr=%pISpc client %08x:%08x procedure=%s",
+ __entry->addr, __entry->cl_boot, __entry->cl_id,
+ __get_str(procedure))
+);
+
+TRACE_EVENT(nfsd_cb_done,
+ TP_PROTO(
+ const struct nfs4_client *clp,
+ int status
+ ),
+ TP_ARGS(clp, status),
+ TP_STRUCT__entry(
+ __field(u32, cl_boot)
+ __field(u32, cl_id)
+ __field(int, status)
+ __array(unsigned char, addr, sizeof(struct sockaddr_in6))
+ ),
+ TP_fast_assign(
+ __entry->cl_boot = clp->cl_clientid.cl_boot;
+ __entry->cl_id = clp->cl_clientid.cl_id;
+ __entry->status = status;
+ memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr,
+ sizeof(struct sockaddr_in6));
+ ),
+ TP_printk("addr=%pISpc client %08x:%08x status=%d",
+ __entry->addr, __entry->cl_boot, __entry->cl_id,
+ __entry->status)
+);
+
#endif /* _NFSD_TRACE_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/splice.c b/fs/splice.c
index 4735defc46ee..fd0a1e7e5959 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in,
loff_t offset;
long ret;
+ if (unlikely(!(in->f_mode & FMODE_READ) ||
+ !(out->f_mode & FMODE_WRITE)))
+ return -EBADF;
+
ipipe = get_pipe_info(in);
opipe = get_pipe_info(out);
@@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
if (off_in || off_out)
return -ESPIPE;
- if (!(in->f_mode & FMODE_READ))
- return -EBADF;
-
- if (!(out->f_mode & FMODE_WRITE))
- return -EBADF;
-
/* Splicing to self would be fun, but... */
if (ipipe == opipe)
return -EINVAL;
@@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
offset = out->f_pos;
}
- if (unlikely(!(out->f_mode & FMODE_WRITE)))
- return -EBADF;
-
if (unlikely(out->f_flags & O_APPEND))
return -EINVAL;
@@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
error = -EBADF;
in = fdget(fd_in);
if (in.file) {
- if (in.file->f_mode & FMODE_READ) {
- out = fdget(fd_out);
- if (out.file) {
- if (out.file->f_mode & FMODE_WRITE)
- error = do_splice(in.file, off_in,
- out.file, off_out,
- len, flags);
- fdput(out);
- }
+ out = fdget(fd_out);
+ if (out.file) {
+ error = do_splice(in.file, off_in, out.file, off_out,
+ len, flags);
+ fdput(out);
}
fdput(in);
}
@@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len,
struct pipe_inode_info *opipe = get_pipe_info(out);
int ret = -EINVAL;
+ if (unlikely(!(in->f_mode & FMODE_READ) ||
+ !(out->f_mode & FMODE_WRITE)))
+ return -EBADF;
+
/*
* Duplicate the contents of ipipe to opipe without actually
* copying the data.
@@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
{
- struct fd in;
+ struct fd in, out;
int error;
if (unlikely(flags & ~SPLICE_F_ALL))
@@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
error = -EBADF;
in = fdget(fdin);
if (in.file) {
- if (in.file->f_mode & FMODE_READ) {
- struct fd out = fdget(fdout);
- if (out.file) {
- if (out.file->f_mode & FMODE_WRITE)
- error = do_tee(in.file, out.file,
- len, flags);
- fdput(out);
- }
+ out = fdget(fdout);
+ if (out.file) {
+ error = do_tee(in.file, out.file, len, flags);
+ fdput(out);
}
fdput(in);
}
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 675e26989376..8fe03b4a0d2b 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
goto fail_free;
}
- err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id);
+ err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id);
if (err)
goto fail_free;