aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorBenjamin Herrenschmidt <benh@kernel.crashing.org>2008-07-22 17:12:37 +1000
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2008-07-22 17:12:37 +1000
commit8725f25acc656c1522d48a6746055099efdaca4c (patch)
treee241424fa58178ed6c2a95a4eb931ea83dbea33c /fs
parentc69cccc95fe4b90dde5fe33e6a3b77880b534fa4 (diff)
parent93ded9b8fd42abe2c3607097963d8de6ad9117eb (diff)
Merge commit 'origin/master'
Manually fixed up: drivers/net/fs_enet/fs_enet-main.c
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig8
-rw-r--r--fs/compat_ioctl.c114
-rw-r--r--fs/configfs/configfs_internal.h4
-rw-r--r--fs/configfs/dir.c159
-rw-r--r--fs/configfs/inode.c2
-rw-r--r--fs/configfs/symlink.c16
-rw-r--r--fs/dlm/config.c8
-rw-r--r--fs/lockd/svc.c33
-rw-r--r--fs/lockd/svc4proc.c7
-rw-r--r--fs/lockd/svclock.c33
-rw-r--r--fs/lockd/svcproc.c7
-rw-r--r--fs/lockd/svcsubs.c32
-rw-r--r--fs/nfsd/lockd.c2
-rw-r--r--fs/nfsd/nfs2acl.c7
-rw-r--r--fs/nfsd/nfs3acl.c5
-rw-r--r--fs/nfsd/nfs3proc.c8
-rw-r--r--fs/nfsd/nfs4proc.c76
-rw-r--r--fs/nfsd/nfs4state.c49
-rw-r--r--fs/nfsd/nfs4xdr.c392
-rw-r--r--fs/nfsd/nfsctl.c118
-rw-r--r--fs/nfsd/nfsfh.c31
-rw-r--r--fs/nfsd/nfsproc.c9
-rw-r--r--fs/nfsd/nfssvc.c148
-rw-r--r--fs/nfsd/vfs.c140
-rw-r--r--fs/ocfs2/aops.c13
-rw-r--r--fs/ocfs2/cluster/heartbeat.c10
-rw-r--r--fs/ocfs2/cluster/netdebug.c8
-rw-r--r--fs/ocfs2/cluster/nodemanager.c16
-rw-r--r--fs/ocfs2/dlmglue.c122
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/ocfs2/journal.c2
-rw-r--r--fs/ocfs2/localalloc.c2
-rw-r--r--fs/ocfs2/ocfs2.h12
-rw-r--r--fs/ocfs2/ocfs2_fs.h2
-rw-r--r--fs/ocfs2/stack_user.c19
-rw-r--r--fs/ocfs2/super.c6
-rw-r--r--fs/proc/proc_net.c32
-rw-r--r--fs/proc/proc_tty.c48
38 files changed, 945 insertions, 757 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 17216ba99c8..37db79a2ff9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -470,6 +470,14 @@ config OCFS2_FS_USERSPACE_CLUSTER
It is safe to say Y, as the clustering method is run-time
selectable.
+config OCFS2_FS_STATS
+ bool "OCFS2 statistics"
+ depends on OCFS2_FS
+ default y
+ help
+ This option allows some fs statistics to be captured. Enabling
+ this option may increase the memory consumption.
+
config OCFS2_DEBUG_MASKLOG
bool "OCFS2 logging support"
depends on OCFS2_FS
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index c54eaab71a1..7b3a03c7c6a 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -58,7 +58,6 @@
#include <linux/syscalls.h>
#include <linux/i2c.h>
#include <linux/i2c-dev.h>
-#include <linux/wireless.h>
#include <linux/atalk.h>
#include <linux/loop.h>
@@ -1759,64 +1758,6 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, unsigned long a
return sys_ioctl(fd, cmd, (unsigned long)tdata);
}
-struct compat_iw_point {
- compat_caddr_t pointer;
- __u16 length;
- __u16 flags;
-};
-
-static int do_wireless_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
-{
- struct iwreq __user *iwr;
- struct iwreq __user *iwr_u;
- struct iw_point __user *iwp;
- struct compat_iw_point __user *iwp_u;
- compat_caddr_t pointer_u;
- void __user *pointer;
- __u16 length, flags;
- int ret;
-
- iwr_u = compat_ptr(arg);
- iwp_u = (struct compat_iw_point __user *) &iwr_u->u.data;
- iwr = compat_alloc_user_space(sizeof(*iwr));
- if (iwr == NULL)
- return -ENOMEM;
-
- iwp = &iwr->u.data;
-
- if (!access_ok(VERIFY_WRITE, iwr, sizeof(*iwr)))
- return -EFAULT;
-
- if (__copy_in_user(&iwr->ifr_ifrn.ifrn_name[0],
- &iwr_u->ifr_ifrn.ifrn_name[0],
- sizeof(iwr->ifr_ifrn.ifrn_name)))
- return -EFAULT;
-
- if (__get_user(pointer_u, &iwp_u->pointer) ||
- __get_user(length, &iwp_u->length) ||
- __get_user(flags, &iwp_u->flags))
- return -EFAULT;
-
- if (__put_user(compat_ptr(pointer_u), &iwp->pointer) ||
- __put_user(length, &iwp->length) ||
- __put_user(flags, &iwp->flags))
- return -EFAULT;
-
- ret = sys_ioctl(fd, cmd, (unsigned long) iwr);
-
- if (__get_user(pointer, &iwp->pointer) ||
- __get_user(length, &iwp->length) ||
- __get_user(flags, &iwp->flags))
- return -EFAULT;
-
- if (__put_user(ptr_to_compat(pointer), &iwp_u->pointer) ||
- __put_user(length, &iwp_u->length) ||
- __put_user(flags, &iwp_u->flags))
- return -EFAULT;
-
- return ret;
-}
-
/* Since old style bridge ioctl's endup using SIOCDEVPRIVATE
* for some operations; this forces use of the newer bridge-utils that
* use compatiable ioctls
@@ -2405,6 +2346,7 @@ COMPATIBLE_IOCTL(HCIGETDEVLIST)
COMPATIBLE_IOCTL(HCIGETDEVINFO)
COMPATIBLE_IOCTL(HCIGETCONNLIST)
COMPATIBLE_IOCTL(HCIGETCONNINFO)
+COMPATIBLE_IOCTL(HCIGETAUTHINFO)
COMPATIBLE_IOCTL(HCISETRAW)
COMPATIBLE_IOCTL(HCISETSCAN)
COMPATIBLE_IOCTL(HCISETAUTH)
@@ -2501,36 +2443,6 @@ COMPATIBLE_IOCTL(I2C_TENBIT)
COMPATIBLE_IOCTL(I2C_PEC)
COMPATIBLE_IOCTL(I2C_RETRIES)
COMPATIBLE_IOCTL(I2C_TIMEOUT)
-/* wireless */
-COMPATIBLE_IOCTL(SIOCSIWCOMMIT)
-COMPATIBLE_IOCTL(SIOCGIWNAME)
-COMPATIBLE_IOCTL(SIOCSIWNWID)
-COMPATIBLE_IOCTL(SIOCGIWNWID)
-COMPATIBLE_IOCTL(SIOCSIWFREQ)
-COMPATIBLE_IOCTL(SIOCGIWFREQ)
-COMPATIBLE_IOCTL(SIOCSIWMODE)
-COMPATIBLE_IOCTL(SIOCGIWMODE)
-COMPATIBLE_IOCTL(SIOCSIWSENS)
-COMPATIBLE_IOCTL(SIOCGIWSENS)
-COMPATIBLE_IOCTL(SIOCSIWRANGE)
-COMPATIBLE_IOCTL(SIOCSIWPRIV)
-COMPATIBLE_IOCTL(SIOCSIWSTATS)
-COMPATIBLE_IOCTL(SIOCSIWAP)
-COMPATIBLE_IOCTL(SIOCGIWAP)
-COMPATIBLE_IOCTL(SIOCSIWRATE)
-COMPATIBLE_IOCTL(SIOCGIWRATE)
-COMPATIBLE_IOCTL(SIOCSIWRTS)
-COMPATIBLE_IOCTL(SIOCGIWRTS)
-COMPATIBLE_IOCTL(SIOCSIWFRAG)
-COMPATIBLE_IOCTL(SIOCGIWFRAG)
-COMPATIBLE_IOCTL(SIOCSIWTXPOW)
-COMPATIBLE_IOCTL(SIOCGIWTXPOW)
-COMPATIBLE_IOCTL(SIOCSIWRETRY)
-COMPATIBLE_IOCTL(SIOCGIWRETRY)
-COMPATIBLE_IOCTL(SIOCSIWPOWER)
-COMPATIBLE_IOCTL(SIOCGIWPOWER)
-COMPATIBLE_IOCTL(SIOCSIWAUTH)
-COMPATIBLE_IOCTL(SIOCGIWAUTH)
/* hiddev */
COMPATIBLE_IOCTL(HIDIOCGVERSION)
COMPATIBLE_IOCTL(HIDIOCAPPLICATION)
@@ -2761,29 +2673,7 @@ COMPATIBLE_IOCTL(USBDEVFS_IOCTL32)
HANDLE_IOCTL(I2C_FUNCS, w_long)
HANDLE_IOCTL(I2C_RDWR, do_i2c_rdwr_ioctl)
HANDLE_IOCTL(I2C_SMBUS, do_i2c_smbus_ioctl)
-/* wireless */
-HANDLE_IOCTL(SIOCGIWRANGE, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWPRIV, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWSTATS, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWSPY, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWSPY, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWTHRSPY, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWTHRSPY, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWMLME, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWAPLIST, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWSCAN, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWSCAN, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWESSID, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWESSID, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWNICKN, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWNICKN, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWENCODE, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWENCODE, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWGENIE, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWGENIE, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWENCODEEXT, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCGIWENCODEEXT, do_wireless_ioctl)
-HANDLE_IOCTL(SIOCSIWPMKSA, do_wireless_ioctl)
+/* bridge */
HANDLE_IOCTL(SIOCSIFBR, old_bridge_ioctl)
HANDLE_IOCTL(SIOCGIFBR, old_bridge_ioctl)
/* Not implemented in the native kernel */
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index cca98609aa7..da015c12e3e 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/spinlock.h>
struct configfs_dirent {
atomic_t s_count;
@@ -47,8 +48,11 @@ struct configfs_dirent {
#define CONFIGFS_USET_DIR 0x0040
#define CONFIGFS_USET_DEFAULT 0x0080
#define CONFIGFS_USET_DROPPING 0x0100
+#define CONFIGFS_USET_IN_MKDIR 0x0200
#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR)
+extern spinlock_t configfs_dirent_lock;
+
extern struct vfsmount * configfs_mount;
extern struct kmem_cache *configfs_dir_cachep;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index a48dc7dd876..179589be063 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -30,11 +30,25 @@
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/err.h>
#include <linux/configfs.h>
#include "configfs_internal.h"
DECLARE_RWSEM(configfs_rename_sem);
+/*
+ * Protects mutations of configfs_dirent linkage together with proper i_mutex
+ * Also protects mutations of symlinks linkage to target configfs_dirent
+ * Mutators of configfs_dirent linkage must *both* have the proper inode locked
+ * and configfs_dirent_lock locked, in that order.
+ * This allows one to safely traverse configfs_dirent trees and symlinks without
+ * having to lock inodes.
+ *
+ * Protects setting of CONFIGFS_USET_DROPPING: checking the flag
+ * unlocked is not reliable unless in detach_groups() called from
+ * rmdir()/unregister() and from configfs_attach_group()
+ */
+DEFINE_SPINLOCK(configfs_dirent_lock);
static void configfs_d_iput(struct dentry * dentry,
struct inode * inode)
@@ -74,13 +88,20 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare
sd = kmem_cache_zalloc(configfs_dir_cachep, GFP_KERNEL);
if (!sd)
- return NULL;
+ return ERR_PTR(-ENOMEM);
atomic_set(&sd->s_count, 1);
INIT_LIST_HEAD(&sd->s_links);
INIT_LIST_HEAD(&sd->s_children);
- list_add(&sd->s_sibling, &parent_sd->s_children);
sd->s_element = element;
+ spin_lock(&configfs_dirent_lock);
+ if (parent_sd->s_type & CONFIGFS_USET_DROPPING) {
+ spin_unlock(&configfs_dirent_lock);
+ kmem_cache_free(configfs_dir_cachep, sd);
+ return ERR_PTR(-ENOENT);
+ }
+ list_add(&sd->s_sibling, &parent_sd->s_children);
+ spin_unlock(&configfs_dirent_lock);
return sd;
}
@@ -118,8 +139,8 @@ int configfs_make_dirent(struct configfs_dirent * parent_sd,
struct configfs_dirent * sd;
sd = configfs_new_dirent(parent_sd, element);
- if (!sd)
- return -ENOMEM;
+ if (IS_ERR(sd))
+ return PTR_ERR(sd);
sd->s_mode = mode;
sd->s_type = type;
@@ -173,7 +194,9 @@ static int create_dir(struct config_item * k, struct dentry * p,
} else {
struct configfs_dirent *sd = d->d_fsdata;
if (sd) {
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
}
}
@@ -224,7 +247,9 @@ int configfs_create_link(struct configfs_symlink *sl,
else {
struct configfs_dirent *sd = dentry->d_fsdata;
if (sd) {
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
}
}
@@ -238,7 +263,9 @@ static void remove_dir(struct dentry * d)
struct configfs_dirent * sd;
sd = d->d_fsdata;
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
if (d->d_inode)
simple_rmdir(parent->d_inode,d);
@@ -331,13 +358,13 @@ static struct dentry * configfs_lookup(struct inode *dir,
/*
* Only subdirectories count here. Files (CONFIGFS_NOT_PINNED) are
- * attributes and are removed by rmdir(). We recurse, taking i_mutex
- * on all children that are candidates for default detach. If the
- * result is clean, then configfs_detach_group() will handle dropping
- * i_mutex. If there is an error, the caller will clean up the i_mutex
- * holders via configfs_detach_rollback().
+ * attributes and are removed by rmdir(). We recurse, setting
+ * CONFIGFS_USET_DROPPING on all children that are candidates for
+ * default detach.
+ * If there is an error, the caller will reset the flags via
+ * configfs_detach_rollback().
*/
-static int configfs_detach_prep(struct dentry *dentry)
+static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex)
{
struct configfs_dirent *parent_sd = dentry->d_fsdata;
struct configfs_dirent *sd;
@@ -352,15 +379,20 @@ static int configfs_detach_prep(struct dentry *dentry)
if (sd->s_type & CONFIGFS_NOT_PINNED)
continue;
if (sd->s_type & CONFIGFS_USET_DEFAULT) {
- mutex_lock(&sd->s_dentry->d_inode->i_mutex);
- /* Mark that we've taken i_mutex */
+ /* Abort if racing with mkdir() */
+ if (sd->s_type & CONFIGFS_USET_IN_MKDIR) {
+ if (wait_mutex)
+ *wait_mutex = &sd->s_dentry->d_inode->i_mutex;
+ return -EAGAIN;
+ }
+ /* Mark that we're trying to drop the group */
sd->s_type |= CONFIGFS_USET_DROPPING;
/*
* Yup, recursive. If there's a problem, blame
* deep nesting of default_groups
*/
- ret = configfs_detach_prep(sd->s_dentry);
+ ret = configfs_detach_prep(sd->s_dentry, wait_mutex);
if (!ret)
continue;
} else
@@ -374,7 +406,7 @@ out:
}
/*
- * Walk the tree, dropping i_mutex wherever CONFIGFS_USET_DROPPING is
+ * Walk the tree, resetting CONFIGFS_USET_DROPPING wherever it was
* set.
*/
static void configfs_detach_rollback(struct dentry *dentry)
@@ -385,11 +417,7 @@ static void configfs_detach_rollback(struct dentry *dentry)
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
if (sd->s_type & CONFIGFS_USET_DEFAULT) {
configfs_detach_rollback(sd->s_dentry);
-
- if (sd->s_type & CONFIGFS_USET_DROPPING) {
- sd->s_type &= ~CONFIGFS_USET_DROPPING;
- mutex_unlock(&sd->s_dentry->d_inode->i_mutex);
- }
+ sd->s_type &= ~CONFIGFS_USET_DROPPING;
}
}
}
@@ -410,7 +438,9 @@ static void detach_attrs(struct config_item * item)
list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) {
if (!sd->s_element || !(sd->s_type & CONFIGFS_NOT_PINNED))
continue;
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_drop_dentry(sd, dentry);
configfs_put(sd);
}
@@ -466,16 +496,12 @@ static void detach_groups(struct config_group *group)
child = sd->s_dentry;
+ mutex_lock(&child->d_inode->i_mutex);
+
configfs_detach_group(sd->s_element);
child->d_inode->i_flags |= S_DEAD;
- /*
- * From rmdir/unregister, a configfs_detach_prep() pass
- * has taken our i_mutex for us. Drop it.
- * From mkdir/register cleanup, there is no sem held.
- */
- if (sd->s_type & CONFIGFS_USET_DROPPING)
- mutex_unlock(&child->d_inode->i_mutex);
+ mutex_unlock(&child->d_inode->i_mutex);
d_delete(child);
dput(child);
@@ -1001,9 +1027,10 @@ EXPORT_SYMBOL(configfs_undepend_item);
static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
- int ret, module_got = 0;
- struct config_group *group;
- struct config_item *item;
+ int ret = 0;
+ int module_got = 0;
+ struct config_group *group = NULL;
+ struct config_item *item = NULL;
struct config_item *parent_item;
struct configfs_subsystem *subsys;
struct configfs_dirent *sd;
@@ -1044,28 +1071,32 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name);
mutex_lock(&subsys->su_mutex);
- group = NULL;
- item = NULL;
if (type->ct_group_ops->make_group) {
group = type->ct_group_ops->make_group(to_config_group(parent_item), name);
- if (group) {
+ if (!group)
+ group = ERR_PTR(-ENOMEM);
+ if (!IS_ERR(group)) {
link_group(to_config_group(parent_item), group);
item = &group->cg_item;
- }
+ } else
+ ret = PTR_ERR(group);
} else {
item = type->ct_group_ops->make_item(to_config_group(parent_item), name);
- if (item)
+ if (!item)
+ item = ERR_PTR(-ENOMEM);
+ if (!IS_ERR(item))
link_obj(parent_item, item);
+ else
+ ret = PTR_ERR(item);
}
mutex_unlock(&subsys->su_mutex);
kfree(name);
- if (!item) {
+ if (ret) {
/*
* If item == NULL, then link_obj() was never called.
* There are no extra references to clean up.
*/
- ret = -ENOMEM;
goto out_put;
}
@@ -1093,11 +1124,26 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
*/
module_got = 1;
+ /*
+ * Make racing rmdir() fail if it did not tag parent with
+ * CONFIGFS_USET_DROPPING
+ * Note: if CONFIGFS_USET_DROPPING is already set, attach_group() will
+ * fail and let rmdir() terminate correctly
+ */
+ spin_lock(&configfs_dirent_lock);
+ /* This will make configfs_detach_prep() fail */
+ sd->s_type |= CONFIGFS_USET_IN_MKDIR;
+ spin_unlock(&configfs_dirent_lock);
+
if (group)
ret = configfs_attach_group(parent_item, item, dentry);
else
ret = configfs_attach_item(parent_item, item, dentry);
+ spin_lock(&configfs_dirent_lock);
+ sd->s_type &= ~CONFIGFS_USET_IN_MKDIR;
+ spin_unlock(&configfs_dirent_lock);
+
out_unlink:
if (ret) {
/* Tear down everything we built up */
@@ -1161,12 +1207,27 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
return -EINVAL;
}
- ret = configfs_detach_prep(dentry);
- if (ret) {
- configfs_detach_rollback(dentry);
- config_item_put(parent_item);
- return ret;
- }
+ spin_lock(&configfs_dirent_lock);
+ do {
+ struct mutex *wait_mutex;
+
+ ret = configfs_detach_prep(dentry, &wait_mutex);
+ if (ret) {
+ configfs_detach_rollback(dentry);
+ spin_unlock(&configfs_dirent_lock);
+ if (ret != -EAGAIN) {
+ config_item_put(parent_item);
+ return ret;
+ }
+
+ /* Wait until the racing operation terminates */
+ mutex_lock(wait_mutex);
+ mutex_unlock(wait_mutex);
+
+ spin_lock(&configfs_dirent_lock);
+ }
+ } while (ret == -EAGAIN);
+ spin_unlock(&configfs_dirent_lock);
/* Get a working ref for the duration of this function */
item = configfs_get_config_item(dentry);
@@ -1258,7 +1319,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
file->private_data = configfs_new_dirent(parent_sd, NULL);
mutex_unlock(&dentry->d_inode->i_mutex);
- return file->private_data ? 0 : -ENOMEM;
+ return IS_ERR(file->private_data) ? PTR_ERR(file->private_data) : 0;
}
@@ -1268,7 +1329,9 @@ static int configfs_dir_close(struct inode *inode, struct file *file)
struct configfs_dirent * cursor = file->private_data;
mutex_lock(&dentry->d_inode->i_mutex);
+ spin_lock(&configfs_dirent_lock);
list_del_init(&cursor->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
mutex_unlock(&dentry->d_inode->i_mutex);
release_configfs_dirent(cursor);
@@ -1308,7 +1371,9 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
/* fallthrough */
default:
if (filp->f_pos == 2) {
+ spin_lock(&configfs_dirent_lock);
list_move(q, &parent_sd->s_children);
+ spin_unlock(&configfs_dirent_lock);
}
for (p=q->next; p!= &parent_sd->s_children; p=p->next) {
struct configfs_dirent *next;
@@ -1331,7 +1396,9 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
dt_type(next)) < 0)
return 0;
+ spin_lock(&configfs_dirent_lock);
list_move(q, p);
+ spin_unlock(&configfs_dirent_lock);
p = q;
filp->f_pos++;
}
@@ -1362,6 +1429,7 @@ static loff_t configfs_dir_lseek(struct file * file, loff_t offset, int origin)
struct list_head *p;
loff_t n = file->f_pos - 2;
+ spin_lock(&configfs_dirent_lock);
list_del(&cursor->s_sibling);
p = sd->s_children.next;
while (n && p != &sd->s_children) {
@@ -1373,6 +1441,7 @@ static loff_t configfs_dir_lseek(struct file * file, loff_t offset, int origin)
p = p->next;
}
list_add_tail(&cursor->s_sibling, p);
+ spin_unlock(&configfs_dirent_lock);
}
}
mutex_unlock(&dentry->d_inode->i_mutex);
@@ -1448,9 +1517,11 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
I_MUTEX_PARENT);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
- if (configfs_detach_prep(dentry)) {
+ spin_lock(&configfs_dirent_lock);
+ if (configfs_detach_prep(dentry, NULL)) {
printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n");
}
+ spin_unlock(&configfs_dirent_lock);
configfs_detach_group(&group->cg_item);
dentry->d_inode->i_flags |= S_DEAD;
mutex_unlock(&dentry->d_inode->i_mutex);
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index b9a1d810346..4803ccc9448 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -247,7 +247,9 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
if (!sd->s_element)
continue;
if (!strcmp(configfs_get_name(sd), name)) {
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_drop_dentry(sd, dir);
configfs_put(sd);
break;
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 2a731ef5f30..0004d18c40a 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -77,12 +77,15 @@ static int create_link(struct config_item *parent_item,
sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
if (sl) {
sl->sl_target = config_item_get(item);
- /* FIXME: needs a lock, I'd bet */
+ spin_lock(&configfs_dirent_lock);
list_add(&sl->sl_list, &target_sd->s_links);
+ spin_unlock(&configfs_dirent_lock);
ret = configfs_create_link(sl, parent_item->ci_dentry,
dentry);
if (ret) {
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sl->sl_list);
+ spin_unlock(&configfs_dirent_lock);
config_item_put(item);
kfree(sl);
}
@@ -137,8 +140,12 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
goto out_put;
ret = type->ct_item_ops->allow_link(parent_item, target_item);
- if (!ret)
+ if (!ret) {
ret = create_link(parent_item, target_item, dentry);
+ if (ret && type->ct_item_ops->drop_link)
+ type->ct_item_ops->drop_link(parent_item,
+ target_item);
+ }
config_item_put(target_item);
path_put(&nd.path);
@@ -169,7 +176,9 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry)
parent_item = configfs_get_config_item(dentry->d_parent);
type = parent_item->ci_type;
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sd->s_sibling);
+ spin_unlock(&configfs_dirent_lock);
configfs_drop_dentry(sd, dentry->d_parent);
dput(dentry);
configfs_put(sd);
@@ -184,8 +193,9 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry)
type->ct_item_ops->drop_link(parent_item,
sl->sl_target);
- /* FIXME: Needs lock */
+ spin_lock(&configfs_dirent_lock);
list_del_init(&sl->sl_list);
+ spin_unlock(&configfs_dirent_lock);
/* Put reference from create_link() */
config_item_put(sl->sl_target);
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index eac23bd288b..c4e7d721bd8 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -438,7 +438,7 @@ static struct config_group *make_cluster(struct config_group *g,
kfree(gps);
kfree(sps);
kfree(cms);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
static void drop_cluster(struct config_group *g, struct config_item *i)
@@ -495,7 +495,7 @@ static struct config_group *make_space(struct config_group *g, const char *name)
kfree(sp);
kfree(gps);
kfree(nds);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
static void drop_space(struct config_group *g, struct config_item *i)
@@ -528,7 +528,7 @@ static struct config_item *make_comm(struct config_group *g, const char *name)
cm = kzalloc(sizeof(struct comm), GFP_KERNEL);
if (!cm)
- return NULL;
+ return ERR_PTR(-ENOMEM);
config_item_init_type_name(&cm->item, name, &comm_type);
cm->nodeid = -1;
@@ -561,7 +561,7 @@ static struct config_item *make_node(struct config_group *g, const char *name)
nd = kzalloc(sizeof(struct node), GFP_KERNEL);
if (!nd)
- return NULL;
+ return ERR_PTR(-ENOMEM);
config_item_init_type_name(&nd->item, name, &node_type);
nd->nodeid = -1;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 2169af4d545..5bd9bf0fa9d 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -50,7 +50,7 @@ EXPORT_SYMBOL(nlmsvc_ops);
static DEFINE_MUTEX(nlmsvc_mutex);
static unsigned int nlmsvc_users;
static struct task_struct *nlmsvc_task;
-static struct svc_serv *nlmsvc_serv;
+static struct svc_rqst *nlmsvc_rqst;
int nlmsvc_grace_period;
unsigned long nlmsvc_timeout;
@@ -194,20 +194,11 @@ lockd(void *vrqstp)
svc_process(rqstp);
}
-
flush_signals(current);
if (nlmsvc_ops)
nlmsvc_invalidate_all();
nlm_shutdown_hosts();
-
unlock_kernel();
-
- nlmsvc_task = NULL;
- nlmsvc_serv = NULL;
-
- /* Exit the RPC thread */
- svc_exit_thread(rqstp);
-
return 0;
}
@@ -254,16 +245,15 @@ int
lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
{
struct svc_serv *serv;
- struct svc_rqst *rqstp;
int error = 0;
mutex_lock(&nlmsvc_mutex);
/*
* Check whether we're already up and running.
*/
- if (nlmsvc_serv) {
+ if (nlmsvc_rqst) {
if (proto)
- error = make_socks(nlmsvc_serv, proto);
+ error = make_socks(nlmsvc_rqst->rq_server, proto);
goto out;
}
@@ -288,9 +278,10 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
/*
* Create the kernel thread and wait for it to start.
*/
- rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
- if (IS_ERR(rqstp)) {
- error = PTR_ERR(rqstp);
+ nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
+ if (IS_ERR(nlmsvc_rqst)) {
+ error = PTR_ERR(nlmsvc_rqst);
+ nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: svc_rqst allocation failed, error=%d\n",
error);
@@ -298,16 +289,15 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
}
svc_sock_update_bufs(serv);
- nlmsvc_serv = rqstp->rq_server;
- nlmsvc_task = kthread_run(lockd, rqstp, serv->sv_name);
+ nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name);
if (IS_ERR(nlmsvc_task)) {
error = PTR_ERR(nlmsvc_task);
+ svc_exit_thread(nlmsvc_rqst);
nlmsvc_task = NULL;
- nlmsvc_serv = NULL;
+ nlmsvc_rqst = NULL;
printk(KERN_WARNING
"lockd_up: kthread_run failed, error=%d\n", error);
- svc_exit_thread(rqstp);
goto destroy_and_out;
}
@@ -346,6 +336,9 @@ lockd_down(void)
BUG();
}
kthread_stop(nlmsvc_task);
+ svc_exit_thread(nlmsvc_rqst);
+ nlmsvc_task = NULL;
+ nlmsvc_rqst = NULL;
out:
mutex_unlock(&nlmsvc_mutex);
}
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 2e27176ff42..39944463933 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -58,8 +58,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
return 0;
no_locks:
- if (host)
- nlm_release_host(host);
+ nlm_release_host(host);
if (error)
return error;
return nlm_lck_denied_nolocks;
@@ -100,7 +99,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now check for conflicting locks */
- resp->status = nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie);
+ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie);
if (resp->status == nlm_drop_reply)
rc = rpc_drop_reply;
else
@@ -146,7 +145,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
#endif
/* Now try to lock the file */
- resp->status = nlmsvc_lock(rqstp, file, &argp->lock,
+ resp->status = nlmsvc_lock(rqstp, file, host, &argp->lock,
argp->block, &argp->cookie);
if (resp->status == nlm_drop_reply)
rc = rpc_drop_reply;
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 56a08ab9a4c..821b9acdfb6 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -129,9 +129,9 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock)
static inline int nlm_cookie_match(struct nlm_cookie *a, struct nlm_cookie *b)
{
- if(a->len != b->len)
+ if (a->len != b->len)
return 0;
- if(memcmp(a->data,b->data,a->len))
+ if (memcmp(a->data, b->data, a->len))
return 0;
return 1;
}
@@ -180,6 +180,7 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
struct nlm_block *block;
struct nlm_rqst *call = NULL;
+ nlm_get_host(host);
call = nlm_alloc_call(host);
if (call == NULL)
return NULL;
@@ -358,10 +359,10 @@ nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
*/
__be32
nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
- struct nlm_lock *lock, int wait, struct nlm_cookie *cookie)
+ struct nlm_host *host, struct nlm_lock *lock, int wait,
+ struct nlm_cookie *cookie)
{
struct nlm_block *block = NULL;
- struct nlm_host *host;
int error;
__be32 ret;
@@ -373,11 +374,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
(long long)lock->fl.fl_end,
wait);
- /* Create host handle for callback */
- host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
- if (host == NULL)
- return nlm_lck_denied_nolocks;
-
/* Lock file against concurrent access */
mutex_lock(&file->f_mutex);
/* Get existing block (in case client is busy-waiting)
@@ -385,8 +381,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
*/
block = nlmsvc_lookup_block(file, lock);
if (block == NULL) {
- block = nlmsvc_create_block(rqstp, nlm_get_host(host), file,
- lock, cookie);
+ block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
ret = nlm_lck_denied_nolocks;
if (block == NULL)
goto out;
@@ -417,7 +412,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
lock->fl.fl_flags &= ~FL_SLEEP;
dprintk("lockd: vfs_lock_file returned %d\n", error);
- switch(error) {
+ switch (error) {
case 0:
ret = nlm_granted;
goto out;
@@ -450,7 +445,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
out:
mutex_unlock(&file->f_mutex);
nlmsvc_release_block(block);
- nlm_release_host(host);
dprintk("lockd: nlmsvc_lock returned %u\n", ret);
return ret;
}
@@ -460,8 +454,8 @@ out:
*/
__be32
nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
- struct nlm_lock *lock, struct nlm_lock *conflock,
- struct nlm_cookie *cookie)
+ struct nlm_host *host, struct nlm_lock *lock,
+ struct nlm_lock *conflock, struct nlm_cookie *cookie)
{
struct nlm_block *block = NULL;
int error;
@@ -479,16 +473,9 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
if (block == NULL) {
struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
- struct nlm_host *host;
if (conf == NULL)
return nlm_granted;
- /* Create host handle for callback */
- host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
- if (host == NULL) {
- kfree(conf);
- return nlm_lck_denied_nolocks;
- }
block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
if (block == NULL) {
kfree(conf);
@@ -897,7 +884,7 @@ nlmsvc_retry_blocked(void)
if (block->b_when == NLM_NEVER)
break;
- if (time_after(block->b_when,jiffies)) {
+ if (time_after(block->b_when, jiffies)) {
timeout = block->b_when - jiffies;
break;
}
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index ce6952b50a7..76019d2ff72 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -87,8 +87,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
return 0;
no_locks:
- if (host)
- nlm_release_host(host);
+ nlm_release_host(host);
if (error)
return error;
return nlm_lck_denied_nolocks;
@@ -129,7 +128,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now check for conflicting locks */
- resp->status = cast_status(nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie));
+ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie));
if (resp->status == nlm_drop_reply)
rc = rpc_drop_reply;
else
@@ -176,7 +175,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
#endif
/* Now try to lock the file */
- resp->status = cast_status(nlmsvc_lock(rqstp, file, &argp->lock,
+ resp->status = cast_status(nlmsvc_lock(rqstp, file, host, &argp->lock,
argp->block, &argp->cookie));
if (resp->status == nlm_drop_reply)
rc = rpc_drop_reply;
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index d1c48b539df..198b4e55b37 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -373,13 +373,16 @@ nlmsvc_free_host_resources(struct nlm_host *host)
}
}
-/*
- * Remove all locks held for clients
+/**
+ * nlmsvc_invalidate_all - remove all locks held for clients
+ *
+ * Release all locks held by NFS clients.
+ *
*/
void
nlmsvc_invalidate_all(void)
{
- /* Release all locks held by NFS clients.
+ /*
* Previously, the code would call
* nlmsvc_free_host_resources for each client in
* turn, which is about as inefficient as it gets.
@@ -396,6 +399,12 @@ nlmsvc_match_sb(void *datap, struct nlm_file *file)
return sb == file->f_file->f_path.mnt->mnt_sb;
}
+/**
+ * nlmsvc_unlock_all_by_sb - release locks held on this file system
+ * @sb: super block
+ *
+ * Release all locks held by clients accessing this file system.
+ */
int
nlmsvc_unlock_all_by_sb(struct super_block *sb)
{
@@ -409,17 +418,22 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb);
static int
nlmsvc_match_ip(void *datap, struct nlm_host *host)
{
- __be32 *server_addr = datap;
-
- return host->h_saddr.sin_addr.s_addr == *server_addr;
+ return nlm_cmp_addr(&host->h_saddr, datap);
}
+/**
+ * nlmsvc_unlock_all_by_ip - release local locks by IP address
+ * @server_addr: server's IP address as seen by clients
+ *
+ * Release all locks held by clients accessing this host
+ * via the passed in IP address.
+ */
int
-nlmsvc_unlock_all_by_ip(__be32 server_addr)
+nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr)
{
int ret;
- ret = nlm_traverse_files(&server_addr, nlmsvc_match_ip, NULL);
- return ret ? -EIO : 0;
+ ret = nlm_traverse_files(server_addr, nlmsvc_match_ip, NULL);
+ return ret ? -EIO : 0;
}
EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_ip);
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 9e4a568a501..6b6225ac492 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp)
fh.fh_export = NULL;
exp_readlock();
- nfserr = nfsd_open(rqstp, &fh, S_IFREG, MAY_LOCK, filp);
+ nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp);
fh_put(&fh);
rqstp->rq_client = NULL;
exp_readunlock();
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1c3b7654e96..4e3219e8411 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -40,7 +40,8 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
dprintk("nfsd: GETACL(2acl) %s\n", SVCFH_fmt(&argp->fh));
fh = fh_copy(&resp->fh, &argp->fh);
- if ((nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP)))
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ if (nfserr)
RETURN_STATUS(nfserr);
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
@@ -107,7 +108,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
dprintk("nfsd: SETACL(2acl) %s\n", SVCFH_fmt(&argp->fh));
fh = fh_copy(&resp->fh, &argp->fh);
- nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
@@ -134,7 +135,7 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- return fh_verify(rqstp, &resp->fh, 0, MAY_NOP);
+ return fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
}
/*
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index b647f2f872d..9981dbb377a 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -36,7 +36,8 @@ static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
__be32 nfserr = 0;
fh = fh_copy(&resp->fh, &argp->fh);
- if ((nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP)))
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ if (nfserr)
RETURN_STATUS(nfserr);
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
@@ -101,7 +102,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
__be32 nfserr = 0;
fh = fh_copy(&resp->fh, &argp->fh);
- nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index c721a1e6e9d..4d617ea28cf 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -63,7 +63,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp,
SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
if (nfserr)
RETURN_STATUS(nfserr);
@@ -242,7 +242,7 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
attr = &argp->attrs;
/* Get the directory inode */
- nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, MAY_CREATE);
+ nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_CREATE);
if (nfserr)
RETURN_STATUS(nfserr);
@@ -558,7 +558,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp,
resp->f_maxfilesize = ~(u32) 0;
resp->f_properties = NFS3_FSF_DEFAULT;
- nfserr = fh_verify(rqstp, &argp->fh, 0, MAY_NOP);
+ nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP);
/* Check special features of the file system. May request
* different read/write sizes for file systems known to have
@@ -597,7 +597,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp,
resp->p_case_insensitive = 0;
resp->p_case_preserving = 1;
- nfserr = fh_verify(rqstp, &argp->fh, 0, MAY_NOP);
+ nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP);
if (nfserr == 0) {
struct super_block *sb = argp->fh.fh_dentry->d_inode->i_sb;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index c309c881bd4..eef1629806f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -71,11 +71,11 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
return nfserr_inval;
if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
- accmode |= MAY_READ;
+ accmode |= NFSD_MAY_READ;
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
- accmode |= (MAY_WRITE | MAY_TRUNC);
+ accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
- accmode |= MAY_WRITE;
+ accmode |= NFSD_MAY_WRITE;
status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
@@ -126,7 +126,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
&resfh.fh_handle.fh_base, resfh.fh_handle.fh_size);
if (!created)
- status = do_open_permission(rqstp, current_fh, open, MAY_NOP);
+ status = do_open_permission(rqstp, current_fh, open,
+ NFSD_MAY_NOP);
out:
fh_put(&resfh);
@@ -157,7 +158,8 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
(open->op_iattr.ia_size == 0);
- status = do_open_permission(rqstp, current_fh, open, MAY_OWNER_OVERRIDE);
+ status = do_open_permission(rqstp, current_fh, open,
+ NFSD_MAY_OWNER_OVERRIDE);
return status;
}
@@ -186,7 +188,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
cstate->current_fh.fh_handle.fh_size = rp->rp_openfh_len;
memcpy(&cstate->current_fh.fh_handle.fh_base, rp->rp_openfh,
rp->rp_openfh_len);
- status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP);
+ status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
dprintk("nfsd4_open: replay failed"
" restoring previous filehandle\n");
@@ -285,7 +287,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
putfh->pf_fhlen);
- return fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP);
+ return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
}
static __be32
@@ -363,7 +365,8 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fh_init(&resfh, NFS4_FHSIZE);
- status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, MAY_CREATE);
+ status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
+ NFSD_MAY_CREATE);
if (status == nfserr_symlink)
status = nfserr_notdir;
if (status)
@@ -445,7 +448,7 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
__be32 status;
- status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP);
+ status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
return status;
@@ -730,7 +733,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
int count;
__be32 status;
- status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP);
+ status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
return status;
@@ -843,10 +846,13 @@ struct nfsd4_operation {
#define ALLOWED_WITHOUT_FH 1
/* GETATTR and ops not listed as returning NFS4ERR_MOVED: */
#define ALLOWED_ON_ABSENT_FS 2
+ char *op_name;
};
static struct nfsd4_operation nfsd4_ops[];
+static inline char *nfsd4_op_name(unsigned opnum);
+
/*
* COMPOUND call.
*/
@@ -888,7 +894,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
while (!status && resp->opcnt < args->opcnt) {
op = &args->ops[resp->opcnt++];
- dprintk("nfsv4 compound op #%d: %d\n", resp->opcnt, op->opnum);
+ dprintk("nfsv4 compound op #%d/%d: %d (%s)\n",
+ resp->opcnt, args->opcnt, op->opnum,
+ nfsd4_op_name(op->opnum));
/*
* The XDR decode routines may have pre-set op->status;
@@ -952,126 +960,170 @@ encode_op:
out:
nfsd4_release_compoundargs(args);
cstate_free(cstate);
+ dprintk("nfsv4 compound returned %d\n", ntohl(status));
return status;
}
static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
[OP_ACCESS] = {
.op_func = (nfsd4op_func)nfsd4_access,
+ .op_name = "OP_ACCESS",
},
[OP_CLOSE] = {
.op_func = (nfsd4op_func)nfsd4_close,
+ .op_name = "OP_CLOSE",
},
[OP_COMMIT] = {
.op_func = (nfsd4op_func)nfsd4_commit,
+ .op_name = "OP_COMMIT",
},
[OP_CREATE] = {
.op_func = (nfsd4op_func)nfsd4_create,
+ .op_name = "OP_CREATE",
},
[OP_DELEGRETURN] = {
.op_func = (nfsd4op_func)nfsd4_delegreturn,
+ .op_name = "OP_DELEGRETURN",
},
[OP_GETATTR] = {
.op_func = (nfsd4op_func)nfsd4_getattr,
.op_flags = ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_GETATTR",
},
[OP_GETFH] = {
.op_func = (nfsd4op_func)nfsd4_getfh,
+ .op_name = "OP_GETFH",
},
[OP_LINK] = {
.op_func = (nfsd4op_func)nfsd4_link,
+ .op_name = "OP_LINK",
},
[OP_LOCK] = {
.op_func = (nfsd4op_func)nfsd4_lock,
+ .op_name = "OP_LOCK",
},
[OP_LOCKT] = {
.op_func = (nfsd4op_func)nfsd4_lockt,
+ .op_name = "OP_LOCKT",
},
[OP_LOCKU] = {
.op_func = (nfsd4op_func)nfsd4_locku,
+ .op_name = "OP_LOCKU",
},
[OP_LOOKUP] = {
.op_func = (nfsd4op_func)nfsd4_lookup,
+ .op_name = "OP_LOOKUP",
},
[OP_LOOKUPP] = {
.op_func = (nfsd4op_func)nfsd4_lookupp,
+ .op_name = "OP_LOOKUPP",
},
[OP_NVERIFY] = {
.op_func = (nfsd4op_func)nfsd4_nverify,
+ .op_name = "OP_NVERIFY",
},
[OP_OPEN] = {
.op_func = (nfsd4op_func)nfsd4_open,
+ .op_name = "OP_OPEN",
},
[OP_OPEN_CONFIRM] = {
.op_func = (nfsd4op_func)nfsd4_open_confirm,
+ .op_name = "OP_OPEN_CONFIRM",
},
[OP_OPEN_DOWNGRADE] = {
.op_func = (nfsd4op_func)nfsd4_open_downgrade,
+ .op_name = "OP_OPEN_DOWNGRADE",
},
[OP_PUTFH] = {
.op_func = (nfsd4op_func)nfsd4_putfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_PUTFH",
},
[OP_PUTPUBFH] = {
- /* unsupported; just for future reference: */
+ /* unsupported, just for future reference: */
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_PUTPUBFH",
},
[OP_PUTROOTFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_PUTROOTFH",
},
[OP_READ] = {
.op_func = (nfsd4op_func)nfsd4_read,
+ .op_name = "OP_READ",
},
[OP_READDIR] = {
.op_func = (nfsd4op_func)nfsd4_readdir,
+ .op_name = "OP_READDIR",
},
[OP_READLINK] = {
.op_func = (nfsd4op_func)nfsd4_readlink,
+ .op_name = "OP_READLINK",
},
[OP_REMOVE] = {
.op_func = (nfsd4op_func)nfsd4_remove,
+ .op_name = "OP_REMOVE",
},
[OP_RENAME] = {
+ .op_name = "OP_RENAME",
.op_func = (nfsd4op_func)nfsd4_rename,
},
[OP_RENEW] = {
.op_func = (nfsd4op_func)nfsd4_renew,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_RENEW",
},
[OP_RESTOREFH] = {
.op_func = (nfsd4op_func)nfsd4_restorefh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_RESTOREFH",
},
[OP_SAVEFH] = {
.op_func = (nfsd4op_func)nfsd4_savefh,
+ .op_name = "OP_SAVEFH",
},
[OP_SECINFO] = {
.op_func = (nfsd4op_func)nfsd4_secinfo,
+ .op_name = "OP_SECINFO",
},
[OP_SETATTR] = {
.op_func = (nfsd4op_func)nfsd4_setattr,
+ .op_name = "OP_SETATTR",
},
[OP_SETCLIENTID] = {
.op_func = (nfsd4op_func)nfsd4_setclientid,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_SETCLIENTID",
},
[OP_SETCLIENTID_CONFIRM] = {
.op_func = (nfsd4op_func)nfsd4_setclientid_confirm,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_SETCLIENTID_CONFIRM",
},
[OP_VERIFY] = {
.op_func = (nfsd4op_func)nfsd4_verify,
+ .op_name = "OP_VERIFY",
},
[OP_WRITE] = {
.op_func = (nfsd4op_func)nfsd4_write,
+ .op_name = "OP_WRITE",
},
[OP_RELEASE_LOCKOWNER] = {
.op_func = (nfsd4op_func)nfsd4_release_lockowner,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+ .op_name = "OP_RELEASE_LOCKOWNER",
},
};
+static inline char *
+nfsd4_op_name(unsigned opnum)
+{
+ if (opnum < ARRAY_SIZE(nfsd4_ops))
+ return nfsd4_ops[opnum].op_name;
+ return "unknown_operation";
+}
+
#define nfs4svc_decode_voidargs NULL
#define nfs4svc_release_void NULL
#define nfsd4_voidres nfsd4_voidargs
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 8799b870818..1578d7a2667 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1173,6 +1173,24 @@ static inline int deny_valid(u32 x)
return x <= NFS4_SHARE_DENY_BOTH;
}
+/*
+ * We store the NONE, READ, WRITE, and BOTH bits separately in the
+ * st_{access,deny}_bmap field of the stateid, in order to track not
+ * only what share bits are currently in force, but also what
+ * combinations of share bits previous opens have used. This allows us
+ * to enforce the recommendation of rfc 3530 14.2.19 that the server
+ * return an error if the client attempt to downgrade to a combination
+ * of share bits not explicable by closing some of its previous opens.
+ *
+ * XXX: This enforcement is actually incomplete, since we don't keep
+ * track of access/deny bit combinations; so, e.g., we allow:
+ *
+ * OPEN allow read, deny write
+ * OPEN allow both, deny none
+ * DOWNGRADE allow read, deny none
+ *
+ * which we should reject.
+ */
static void
set_access(unsigned int *access, unsigned long bmap) {
int i;
@@ -1570,6 +1588,10 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta
int err = get_write_access(inode);
if (err)
return nfserrno(err);
+ err = mnt_want_write(cur_fh->fh_export->ex_path.mnt);
+ if (err)
+ return nfserrno(err);
+ file_take_write(filp);
}
status = nfsd4_truncate(rqstp, cur_fh, open);
if (status) {
@@ -1579,8 +1601,8 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta
}
/* remember the open */
filp->f_mode |= open->op_share_access;
- set_bit(open->op_share_access, &stp->st_access_bmap);
- set_bit(open->op_share_deny, &stp->st_deny_bmap);
+ __set_bit(open->op_share_access, &stp->st_access_bmap);
+ __set_bit(open->op_share_deny, &stp->st_deny_bmap);
return nfs_ok;
}
@@ -1722,9 +1744,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
/* Stateid was not found, this is a new OPEN */
int flags = 0;
if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
- flags |= MAY_READ;
+ flags |= NFSD_MAY_READ;
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
- flags |= MAY_WRITE;
+ flags |= NFSD_MAY_WRITE;
status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags);
if (status)
goto out;
@@ -2610,7 +2632,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_inval;
if ((status = fh_verify(rqstp, &cstate->current_fh,
- S_IFREG, MAY_LOCK))) {
+ S_IFREG, NFSD_MAY_LOCK))) {
dprintk("NFSD: nfsd4_lock: permission denied!\n");
return status;
}
@@ -3249,12 +3271,14 @@ nfs4_state_shutdown(void)
nfs4_unlock_state();
}
+/*
+ * user_recovery_dirname is protected by the nfsd_mutex since it's only
+ * accessed when nfsd is starting.
+ */
static void
nfs4_set_recdir(char *recdir)
{
- nfs4_lock_state();
strcpy(user_recovery_dirname, recdir);
- nfs4_unlock_state();
}
/*
@@ -3278,6 +3302,12 @@ nfs4_reset_recoverydir(char *recdir)
return status;
}
+char *
+nfs4_recoverydir(void)
+{
+ return user_recovery_dirname;
+}
+
/*
* Called when leasetime is changed.
*
@@ -3286,11 +3316,12 @@ nfs4_reset_recoverydir(char *recdir)
* we start to register any changes in lease time. If the administrator
* really wants to change the lease time *now*, they can go ahead and bring
* nfsd down and then back up again after changing the lease time.
+ *
+ * user_lease_time is protected by nfsd_mutex since it's only really accessed
+ * when nfsd is starting
*/
void
nfs4_reset_lease(time_t leasetime)
{
- lock_kernel();
user_lease_time = leasetime;
- unlock_kernel();
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c513bbdf2d3..14ba4d9b285 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -986,10 +986,74 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel
}
static __be32
+nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
+{
+ return nfs_ok;
+}
+
+static __be32
+nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p)
+{
+ return nfserr_opnotsupp;
+}
+
+typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *);
+
+static nfsd4_dec nfsd4_dec_ops[] = {
+ [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access,
+ [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close,
+ [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit,
+ [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create,
+ [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn,
+ [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr,
+ [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_LINK] = (nfsd4_dec)nfsd4_decode_link,
+ [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock,
+ [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt,
+ [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku,
+ [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup,
+ [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify,
+ [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open,
+ [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm,
+ [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade,
+ [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh,
+ [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_notsupp,
+ [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_READ] = (nfsd4_dec)nfsd4_decode_read,
+ [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir,
+ [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove,
+ [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename,
+ [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew,
+ [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop,
+ [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo,
+ [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr,
+ [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid,
+ [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm,
+ [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify,
+ [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write,
+ [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner,
+};
+
+struct nfsd4_minorversion_ops {
+ nfsd4_dec *decoders;
+ int nops;
+};
+
+static struct nfsd4_minorversion_ops nfsd4_minorversion[] = {
+ [0] = { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) },
+};
+
+static __be32
nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
{
DECODE_HEAD;
struct nfsd4_op *op;
+ struct nfsd4_minorversion_ops *ops;
int i;
/*
@@ -1019,6 +1083,10 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
}
}
+ if (argp->minorversion >= ARRAY_SIZE(nfsd4_minorversion))
+ argp->opcnt = 0;
+
+ ops = &nfsd4_minorversion[argp->minorversion];
for (i = 0; i < argp->opcnt; i++) {
op = &argp->ops[i];
op->replay = NULL;
@@ -1056,120 +1124,11 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
}
op->opnum = ntohl(*argp->p++);
- switch (op->opnum) {
- case 2: /* Reserved operation */
- op->opnum = OP_ILLEGAL;
- if (argp->minorversion == 0)
- op->status = nfserr_op_illegal;
- else
- op->status = nfserr_minor_vers_mismatch;
- break;
- case OP_ACCESS:
- op->status = nfsd4_decode_access(argp, &op->u.access);
- break;
- case OP_CLOSE:
- op->status = nfsd4_decode_close(argp, &op->u.close);
- break;
- case OP_COMMIT:
- op->status = nfsd4_decode_commit(argp, &op->u.commit);
- break;
- case OP_CREATE:
- op->status = nfsd4_decode_create(argp, &op->u.create);
- break;
- case OP_DELEGRETURN:
- op->status = nfsd4_decode_delegreturn(argp, &op->u.delegreturn);
- break;
- case OP_GETATTR:
- op->status = nfsd4_decode_getattr(argp, &op->u.getattr);
- break;
- case OP_GETFH:
- op->status = nfs_ok;
- break;
- case OP_LINK:
- op->status = nfsd4_decode_link(argp, &op->u.link);
- break;
- case OP_LOCK:
- op->status = nfsd4_decode_lock(argp, &op->u.lock);
- break;
- case OP_LOCKT:
- op->status = nfsd4_decode_lockt(argp, &op->u.lockt);
- break;
- case OP_LOCKU:
- op->status = nfsd4_decode_locku(argp, &op->u.locku);
- break;
- case OP_LOOKUP:
- op->status = nfsd4_decode_lookup(argp, &op->u.lookup);
- break;
- case OP_LOOKUPP:
- op->status = nfs_ok;
- break;
- case OP_NVERIFY:
- op->status = nfsd4_decode_verify(argp, &op->u.nverify);
- break;
- case OP_OPEN:
- op->status = nfsd4_decode_open(argp, &op->u.open);
- break;
- case OP_OPEN_CONFIRM:
- op->status = nfsd4_decode_open_confirm(argp, &op->u.open_confirm);
- break;
- case OP_OPEN_DOWNGRADE:
- op->status = nfsd4_decode_open_downgrade(argp, &op->u.open_downgrade);
- break;
- case OP_PUTFH:
- op->status = nfsd4_decode_putfh(argp, &op->u.putfh);
- break;
- case OP_PUTROOTFH:
- op->status = nfs_ok;
- break;
- case OP_READ:
- op->status = nfsd4_decode_read(argp, &op->u.read);
- break;
- case OP_READDIR:
- op->status = nfsd4_decode_readdir(argp, &op->u.readdir);
- break;
- case OP_READLINK:
- op->status = nfs_ok;
- break;
- case OP_REMOVE:
- op->status = nfsd4_decode_remove(argp, &op->u.remove);
- break;
- case OP_RENAME:
- op->status = nfsd4_decode_rename(argp, &op->u.rename);
- break;
- case OP_RESTOREFH:
- op->status = nfs_ok;
- break;
- case OP_RENEW:
- op->status = nfsd4_decode_renew(argp, &op->u.renew);
- break;
- case OP_SAVEFH:
- op->status = nfs_ok;
- break;
- case OP_SECINFO:
- op->status = nfsd4_decode_secinfo(argp, &op->u.secinfo);
- break;
- case OP_SETATTR:
- op->status = nfsd4_decode_setattr(argp, &op->u.setattr);
- break;
- case OP_SETCLIENTID:
- op->status = nfsd4_decode_setclientid(argp, &op->u.setclientid);
- break;
- case OP_SETCLIENTID_CONFIRM:
- op->status = nfsd4_decode_setclientid_confirm(argp, &op->u.setclientid_confirm);
- break;
- case OP_VERIFY:
- op->status = nfsd4_decode_verify(argp, &op->u.verify);
- break;
- case OP_WRITE:
- op->status = nfsd4_decode_write(argp, &op->u.write);
- break;
- case OP_RELEASE_LOCKOWNER:
- op->status = nfsd4_decode_release_lockowner(argp, &op->u.release_lockowner);
- break;
- default:
+ if (op->opnum >= OP_ACCESS && op->opnum < ops->nops)
+ op->status = ops->decoders[op->opnum](argp, &op->u);
+ else {
op->opnum = OP_ILLEGAL;
op->status = nfserr_op_illegal;
- break;
}
if (op->status) {
@@ -1201,11 +1160,11 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
*p++ = htonl((u32)((n) >> 32)); \
*p++ = htonl((u32)(n)); \
} while (0)
-#define WRITEMEM(ptr,nbytes) do { \
+#define WRITEMEM(ptr,nbytes) do { if (nbytes > 0) { \
*(p + XDR_QUADLEN(nbytes) -1) = 0; \
memcpy(p, ptr, nbytes); \
p += XDR_QUADLEN(nbytes); \
-} while (0)
+}} while (0)
#define WRITECINFO(c) do { \
*p++ = htonl(c.atomic); \
*p++ = htonl(c.before_ctime_sec); \
@@ -1991,7 +1950,7 @@ fail:
return -EINVAL;
}
-static void
+static __be32
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
ENCODE_HEAD;
@@ -2002,9 +1961,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
WRITE32(access->ac_resp_access);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
{
ENCODE_SEQID_OP_HEAD;
@@ -2016,10 +1976,11 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
ADJUST_ARGS();
}
ENCODE_SEQID_OP_TAIL(close->cl_stateowner);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
ENCODE_HEAD;
@@ -2029,9 +1990,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
WRITEMEM(commit->co_verf.data, 8);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
ENCODE_HEAD;
@@ -2044,6 +2006,7 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
WRITE32(create->cr_bmval[1]);
ADJUST_ARGS();
}
+ return nfserr;
}
static __be32
@@ -2064,9 +2027,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
return nfserr;
}
-static void
-nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp)
+static __be32
+nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp)
{
+ struct svc_fh *fhp = *fhpp;
unsigned int len;
ENCODE_HEAD;
@@ -2077,6 +2041,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
WRITEMEM(&fhp->fh_handle.fh_base, len);
ADJUST_ARGS();
}
+ return nfserr;
}
/*
@@ -2104,7 +2069,7 @@ nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denie
ADJUST_ARGS();
}
-static void
+static __be32
nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
{
ENCODE_SEQID_OP_HEAD;
@@ -2118,16 +2083,18 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo
nfsd4_encode_lock_denied(resp, &lock->lk_denied);
ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
{
if (nfserr == nfserr_denied)
nfsd4_encode_lock_denied(resp, &lockt->lt_denied);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
{
ENCODE_SEQID_OP_HEAD;
@@ -2140,10 +2107,11 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
}
ENCODE_SEQID_OP_TAIL(locku->lu_stateowner);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
ENCODE_HEAD;
@@ -2153,10 +2121,11 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
WRITECINFO(link->li_cinfo);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
ENCODE_SEQID_OP_HEAD;
@@ -2219,9 +2188,10 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
/* XXX save filehandle here */
out:
ENCODE_SEQID_OP_TAIL(open->op_stateowner);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
{
ENCODE_SEQID_OP_HEAD;
@@ -2234,9 +2204,10 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct
}
ENCODE_SEQID_OP_TAIL(oc->oc_stateowner);
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
{
ENCODE_SEQID_OP_HEAD;
@@ -2249,6 +2220,7 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struc
}
ENCODE_SEQID_OP_TAIL(od->od_stateowner);
+ return nfserr;
}
static __be32
@@ -2443,7 +2415,7 @@ err_no_verf:
return nfserr;
}
-static void
+static __be32
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
ENCODE_HEAD;
@@ -2453,9 +2425,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
WRITECINFO(remove->rm_cinfo);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
ENCODE_HEAD;
@@ -2466,9 +2439,10 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
WRITECINFO(rename->rn_tinfo);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo *secinfo)
{
@@ -2532,13 +2506,14 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
out:
if (exp)
exp_put(exp);
+ return nfserr;
}
/*
* The SETATTR encode routine is special -- it always encodes a bitmap,
* regardless of the error status.
*/
-static void
+static __be32
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
ENCODE_HEAD;
@@ -2555,9 +2530,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
WRITE32(setattr->sa_bmval[1]);
}
ADJUST_ARGS();
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
ENCODE_HEAD;
@@ -2574,9 +2550,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
WRITE32(0);
ADJUST_ARGS();
}
+ return nfserr;
}
-static void
+static __be32
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
ENCODE_HEAD;
@@ -2588,8 +2565,56 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
WRITEMEM(write->wr_verifier.data, 8);
ADJUST_ARGS();
}
+ return nfserr;
}
+static __be32
+nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
+{
+ return nfserr;
+}
+
+typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *);
+
+static nfsd4_enc nfsd4_enc_ops[] = {
+ [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access,
+ [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close,
+ [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit,
+ [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create,
+ [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr,
+ [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh,
+ [OP_LINK] = (nfsd4_enc)nfsd4_encode_link,
+ [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock,
+ [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt,
+ [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku,
+ [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open,
+ [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm,
+ [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade,
+ [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_READ] = (nfsd4_enc)nfsd4_encode_read,
+ [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir,
+ [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink,
+ [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove,
+ [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename,
+ [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo,
+ [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr,
+ [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid,
+ [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write,
+ [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop,
+};
+
void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
@@ -2601,101 +2626,12 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
statp = p++; /* to be backfilled at the end */
ADJUST_ARGS();
- switch (op->opnum) {
- case OP_ACCESS:
- nfsd4_encode_access(resp, op->status, &op->u.access);
- break;
- case OP_CLOSE:
- nfsd4_encode_close(resp, op->status, &op->u.close);
- break;
- case OP_COMMIT:
- nfsd4_encode_commit(resp, op->status, &op->u.commit);
- break;
- case OP_CREATE:
- nfsd4_encode_create(resp, op->status, &op->u.create);
- break;
- case OP_DELEGRETURN:
- break;
- case OP_GETATTR:
- op->status = nfsd4_encode_getattr(resp, op->status, &op->u.getattr);
- break;
- case OP_GETFH:
- nfsd4_encode_getfh(resp, op->status, op->u.getfh);
- break;
- case OP_LINK:
- nfsd4_encode_link(resp, op->status, &op->u.link);
- break;
- case OP_LOCK:
- nfsd4_encode_lock(resp, op->status, &op->u.lock);
- break;
- case OP_LOCKT:
- nfsd4_encode_lockt(resp, op->status, &op->u.lockt);
- break;
- case OP_LOCKU:
- nfsd4_encode_locku(resp, op->status, &op->u.locku);
- break;
- case OP_LOOKUP:
- break;
- case OP_LOOKUPP:
- break;
- case OP_NVERIFY:
- break;
- case OP_OPEN:
- nfsd4_encode_open(resp, op->status, &op->u.open);
- break;
- case OP_OPEN_CONFIRM:
- nfsd4_encode_open_confirm(resp, op->status, &op->u.open_confirm);
- break;
- case OP_OPEN_DOWNGRADE:
- nfsd4_encode_open_downgrade(resp, op->status, &op->u.open_downgrade);
- break;
- case OP_PUTFH:
- break;
- case OP_PUTROOTFH:
- break;
- case OP_READ:
- op->status = nfsd4_encode_read(resp, op->status, &op->u.read);
- break;
- case OP_READDIR:
- op->status = nfsd4_encode_readdir(resp, op->status, &op->u.readdir);
- break;
- case OP_READLINK:
- op->status = nfsd4_encode_readlink(resp, op->status, &op->u.readlink);
- break;
- case OP_REMOVE:
- nfsd4_encode_remove(resp, op->status, &op->u.remove);
- break;
- case OP_RENAME:
- nfsd4_encode_rename(resp, op->status, &op->u.rename);
- break;
- case OP_RENEW:
- break;
- case OP_RESTOREFH:
- break;
- case OP_SAVEFH:
- break;
- case OP_SECINFO:
- nfsd4_encode_secinfo(resp, op->status, &op->u.secinfo);
- break;
- case OP_SETATTR:
- nfsd4_encode_setattr(resp, op->status, &op->u.setattr);
- break;
- case OP_SETCLIENTID:
- nfsd4_encode_setclientid(resp, op->status, &op->u.setclientid);
- break;
- case OP_SETCLIENTID_CONFIRM:
- break;
- case OP_VERIFY:
- break;
- case OP_WRITE:
- nfsd4_encode_write(resp, op->status, &op->u.write);
- break;
- case OP_RELEASE_LOCKOWNER:
- break;
- default:
- break;
- }
-
+ if (op->opnum == OP_ILLEGAL)
+ goto status;
+ BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) ||
+ !nfsd4_enc_ops[op->opnum]);
+ op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u);
+status:
/*
* Note: We write the status directly, instead of using WRITE32(),
* since it is already in network byte order.
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 5ac00c4fee9..1955a2702e6 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -310,9 +310,12 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
{
- __be32 server_ip;
- char *fo_path, c;
+ struct sockaddr_in sin = {
+ .sin_family = AF_INET,
+ };
int b1, b2, b3, b4;
+ char c;
+ char *fo_path;
/* sanity check */
if (size == 0)
@@ -326,11 +329,13 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
return -EINVAL;
/* get ipv4 address */
- if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4)
+ if (sscanf(fo_path, NIPQUAD_FMT "%c", &b1, &b2, &b3, &b4, &c) != 4)
return -EINVAL;
- server_ip = htonl((((((b1<<8)|b2)<<8)|b3)<<8)|b4);
+ if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255)
+ return -EINVAL;
+ sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4);
- return nlmsvc_unlock_all_by_ip(server_ip);
+ return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin);
}
static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size)
@@ -450,22 +455,26 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
int i;
int rv;
int len;
- int npools = nfsd_nrpools();
+ int npools;
int *nthreads;
+ mutex_lock(&nfsd_mutex);
+ npools = nfsd_nrpools();
if (npools == 0) {
/*
* NFS is shut down. The admin can start it by
* writing to the threads file but NOT the pool_threads
* file, sorry. Report zero threads.
*/
+ mutex_unlock(&nfsd_mutex);
strcpy(buf, "0\n");
return strlen(buf);
}
nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL);
+ rv = -ENOMEM;
if (nthreads == NULL)
- return -ENOMEM;
+ goto out_free;
if (size > 0) {
for (i = 0; i < npools; i++) {
@@ -496,14 +505,16 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
mesg += len;
}
+ mutex_unlock(&nfsd_mutex);
return (mesg-buf);
out_free:
kfree(nthreads);
+ mutex_unlock(&nfsd_mutex);
return rv;
}
-static ssize_t write_versions(struct file *file, char *buf, size_t size)
+static ssize_t __write_versions(struct file *file, char *buf, size_t size)
{
/*
* Format:
@@ -566,14 +577,23 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size)
return len;
}
-static ssize_t write_ports(struct file *file, char *buf, size_t size)
+static ssize_t write_versions(struct file *file, char *buf, size_t size)
+{
+ ssize_t rv;
+
+ mutex_lock(&nfsd_mutex);
+ rv = __write_versions(file, buf, size);
+ mutex_unlock(&nfsd_mutex);
+ return rv;
+}
+
+static ssize_t __write_ports(struct file *file, char *buf, size_t size)
{
if (size == 0) {
int len = 0;
- lock_kernel();
+
if (nfsd_serv)
len = svc_xprt_names(nfsd_serv, buf, 0);
- unlock_kernel();
return len;
}
/* Either a single 'fd' number is written, in which
@@ -603,9 +623,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
/* Decrease the count, but don't shutdown the
* the service
*/
- lock_kernel();
nfsd_serv->sv_nrthreads--;
- unlock_kernel();
}
return err < 0 ? err : 0;
}
@@ -614,10 +632,8 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
int len = 0;
if (!toclose)
return -ENOMEM;
- lock_kernel();
if (nfsd_serv)
len = svc_sock_names(buf, nfsd_serv, toclose);
- unlock_kernel();
if (len >= 0)
lockd_down();
kfree(toclose);
@@ -655,7 +671,6 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) {
if (port == 0)
return -EINVAL;
- lock_kernel();
if (nfsd_serv) {
xprt = svc_find_xprt(nfsd_serv, transport,
AF_UNSPEC, port);
@@ -666,13 +681,23 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
} else
err = -ENOTCONN;
}
- unlock_kernel();
return err < 0 ? err : 0;
}
}
return -EINVAL;
}
+static ssize_t write_ports(struct file *file, char *buf, size_t size)
+{
+ ssize_t rv;
+
+ mutex_lock(&nfsd_mutex);
+ rv = __write_ports(file, buf, size);
+ mutex_unlock(&nfsd_mutex);
+ return rv;
+}
+
+
int nfsd_max_blksize;
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
@@ -691,13 +716,13 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
if (bsize > NFSSVC_MAXBLKSIZE)
bsize = NFSSVC_MAXBLKSIZE;
bsize &= ~(1024-1);
- lock_kernel();
+ mutex_lock(&nfsd_mutex);
if (nfsd_serv && nfsd_serv->sv_nrthreads) {
- unlock_kernel();
+ mutex_unlock(&nfsd_mutex);
return -EBUSY;
}
nfsd_max_blksize = bsize;
- unlock_kernel();
+ mutex_unlock(&nfsd_mutex);
}
return sprintf(buf, "%d\n", nfsd_max_blksize);
}
@@ -705,16 +730,17 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
#ifdef CONFIG_NFSD_V4
extern time_t nfs4_leasetime(void);
-static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
+static ssize_t __write_leasetime(struct file *file, char *buf, size_t size)
{
/* if size > 10 seconds, call
* nfs4_reset_lease() then write out the new lease (seconds) as reply
*/
char *mesg = buf;
- int rv;
+ int rv, lease;
if (size > 0) {
- int lease;
+ if (nfsd_serv)
+ return -EBUSY;
rv = get_int(&mesg, &lease);
if (rv)
return rv;
@@ -726,24 +752,52 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
return strlen(buf);
}
-static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
+static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
+{
+ ssize_t rv;
+
+ mutex_lock(&nfsd_mutex);
+ rv = __write_leasetime(file, buf, size);
+ mutex_unlock(&nfsd_mutex);
+ return rv;
+}
+
+extern char *nfs4_recoverydir(void);
+
+static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
char *recdir;
int len, status;
- if (size == 0 || size > PATH_MAX || buf[size-1] != '\n')
- return -EINVAL;
- buf[size-1] = 0;
+ if (size > 0) {
+ if (nfsd_serv)
+ return -EBUSY;
+ if (size > PATH_MAX || buf[size-1] != '\n')
+ return -EINVAL;
+ buf[size-1] = 0;
- recdir = mesg;
- len = qword_get(&mesg, recdir, size);
- if (len <= 0)
- return -EINVAL;
+ recdir = mesg;
+ len = qword_get(&mesg, recdir, size);
+ if (len <= 0)
+ return -EINVAL;
- status = nfs4_reset_recoverydir(recdir);
+ status = nfs4_reset_recoverydir(recdir);
+ }
+ sprintf(buf, "%s\n", nfs4_recoverydir());
return strlen(buf);
}
+
+static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
+{
+ ssize_t rv;
+
+ mutex_lock(&nfsd_mutex);
+ rv = __write_recoverydir(file, buf, size);
+ mutex_unlock(&nfsd_mutex);
+ return rv;
+}
+
#endif
/*----------------------------------------------------------------------------*/
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 100ae564116..f45451eb1e3 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -176,9 +176,24 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
if (IS_ERR(exp))
return nfserrno(PTR_ERR(exp));
- error = nfsd_setuser_and_check_port(rqstp, exp);
- if (error)
- goto out;
+ if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
+ /* Elevate privileges so that the lack of 'r' or 'x'
+ * permission on some parent directory will
+ * not stop exportfs_decode_fh from being able
+ * to reconnect a directory into the dentry cache.
+ * The same problem can affect "SUBTREECHECK" exports,
+ * but as nfsd_acceptable depends on correct
+ * access control settings being in effect, we cannot
+ * fix that case easily.
+ */
+ current->cap_effective =
+ cap_raise_nfsd_set(current->cap_effective,
+ current->cap_permitted);
+ } else {
+ error = nfsd_setuser_and_check_port(rqstp, exp);
+ if (error)
+ goto out;
+ }
/*
* Look up the dentry using the NFS file handle.
@@ -215,6 +230,14 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
goto out;
}
+ if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
+ error = nfsd_setuser_and_check_port(rqstp, exp);
+ if (error) {
+ dput(dentry);
+ goto out;
+ }
+ }
+
if (S_ISDIR(dentry->d_inode->i_mode) &&
(dentry->d_flags & DCACHE_DISCONNECTED)) {
printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
@@ -279,7 +302,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
if (error)
goto out;
- if (!(access & MAY_LOCK)) {
+ if (!(access & NFSD_MAY_LOCK)) {
/*
* pseudoflavor restrictions are not enforced on NLM,
* which clients virtually always use auth_sys for,
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 6cfc96a1248..0766f95d236 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -65,7 +65,7 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp,
dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
return nfsd_return_attrs(nfserr, resp);
}
@@ -215,11 +215,11 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
SVCFH_fmt(dirfhp), argp->len, argp->name);
/* First verify the parent file handle */
- nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, MAY_EXEC);
+ nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC);
if (nfserr)
goto done; /* must fh_put dirfhp even on error */
- /* Check for MAY_WRITE in nfsd_create if necessary */
+ /* Check for NFSD_MAY_WRITE in nfsd_create if necessary */
nfserr = nfserr_acces;
if (!argp->len)
@@ -281,7 +281,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
nfserr = nfsd_permission(rqstp,
newfhp->fh_export,
newfhp->fh_dentry,
- MAY_WRITE|MAY_LOCAL_ACCESS);
+ NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS);
if (nfserr && nfserr != nfserr_rofs)
goto out_unlock;
}
@@ -614,6 +614,7 @@ nfserrno (int errno)
#endif
{ nfserr_stale, -ESTALE },
{ nfserr_jukebox, -ETIMEDOUT },
+ { nfserr_jukebox, -ERESTARTSYS },
{ nfserr_dropit, -EAGAIN },
{ nfserr_dropit, -ENOMEM },
{ nfserr_badname, -ESRCH },
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 941041f4b13..80292ff5e92 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -21,6 +21,7 @@
#include <linux/smp_lock.h>
#include <linux/freezer.h>
#include <linux/fs_struct.h>
+#include <linux/kthread.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/stats.h>
@@ -36,28 +37,38 @@
#define NFSDDBG_FACILITY NFSDDBG_SVC
-/* these signals will be delivered to an nfsd thread
- * when handling a request
- */
-#define ALLOWED_SIGS (sigmask(SIGKILL))
-/* these signals will be delivered to an nfsd thread
- * when not handling a request. i.e. when waiting
- */
-#define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT))
-/* if the last thread dies with SIGHUP, then the exports table is
- * left unchanged ( like 2.4-{0-9} ). Any other signal will clear
- * the exports table (like 2.2).
- */
-#define SIG_NOCLEAN SIGHUP
-
extern struct svc_program nfsd_program;
-static void nfsd(struct svc_rqst *rqstp);
+static int nfsd(void *vrqstp);
struct timeval nfssvc_boot;
- struct svc_serv *nfsd_serv;
static atomic_t nfsd_busy;
static unsigned long nfsd_last_call;
static DEFINE_SPINLOCK(nfsd_call_lock);
+/*
+ * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members
+ * of the svc_serv struct. In particular, ->sv_nrthreads but also to some
+ * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
+ *
+ * If (out side the lock) nfsd_serv is non-NULL, then it must point to a
+ * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
+ * of nfsd threads must exist and each must listed in ->sp_all_threads in each
+ * entry of ->sv_pools[].
+ *
+ * Transitions of the thread count between zero and non-zero are of particular
+ * interest since the svc_serv needs to be created and initialized at that
+ * point, or freed.
+ *
+ * Finally, the nfsd_mutex also protects some of the global variables that are
+ * accessed when nfsd starts and that are settable via the write_* routines in
+ * nfsctl.c. In particular:
+ *
+ * user_recovery_dirname
+ * user_lease_time
+ * nfsd_versions
+ */
+DEFINE_MUTEX(nfsd_mutex);
+struct svc_serv *nfsd_serv;
+
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
static struct svc_stat nfsd_acl_svcstats;
static struct svc_version * nfsd_acl_version[] = {
@@ -145,13 +156,14 @@ int nfsd_vers(int vers, enum vers_op change)
int nfsd_nrthreads(void)
{
- if (nfsd_serv == NULL)
- return 0;
- else
- return nfsd_serv->sv_nrthreads;
+ int rv = 0;
+ mutex_lock(&nfsd_mutex);
+ if (nfsd_serv)
+ rv = nfsd_serv->sv_nrthreads;
+ mutex_unlock(&nfsd_mutex);
+ return rv;
}
-static int killsig; /* signal that was used to kill last nfsd */
static void nfsd_last_thread(struct svc_serv *serv)
{
/* When last nfsd thread exits we need to do some clean-up */
@@ -162,11 +174,9 @@ static void nfsd_last_thread(struct svc_serv *serv)
nfsd_racache_shutdown();
nfs4_state_shutdown();
- printk(KERN_WARNING "nfsd: last server has exited\n");
- if (killsig != SIG_NOCLEAN) {
- printk(KERN_WARNING "nfsd: unexporting all filesystems\n");
- nfsd_export_flush();
- }
+ printk(KERN_WARNING "nfsd: last server has exited, flushing export "
+ "cache\n");
+ nfsd_export_flush();
}
void nfsd_reset_versions(void)
@@ -190,13 +200,14 @@ void nfsd_reset_versions(void)
}
}
+
int nfsd_create_serv(void)
{
int err = 0;
- lock_kernel();
+
+ WARN_ON(!mutex_is_locked(&nfsd_mutex));
if (nfsd_serv) {
svc_get(nfsd_serv);
- unlock_kernel();
return 0;
}
if (nfsd_max_blksize == 0) {
@@ -217,13 +228,11 @@ int nfsd_create_serv(void)
}
atomic_set(&nfsd_busy, 0);
- nfsd_serv = svc_create_pooled(&nfsd_program,
- nfsd_max_blksize,
- nfsd_last_thread,
- nfsd, SIG_NOCLEAN, THIS_MODULE);
+ nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+ nfsd_last_thread, nfsd, THIS_MODULE);
if (nfsd_serv == NULL)
err = -ENOMEM;
- unlock_kernel();
+
do_gettimeofday(&nfssvc_boot); /* record boot time */
return err;
}
@@ -282,6 +291,8 @@ int nfsd_set_nrthreads(int n, int *nthreads)
int tot = 0;
int err = 0;
+ WARN_ON(!mutex_is_locked(&nfsd_mutex));
+
if (nfsd_serv == NULL || n <= 0)
return 0;
@@ -316,7 +327,6 @@ int nfsd_set_nrthreads(int n, int *nthreads)
nthreads[0] = 1;
/* apply the new numbers */
- lock_kernel();
svc_get(nfsd_serv);
for (i = 0; i < n; i++) {
err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i],
@@ -325,7 +335,6 @@ int nfsd_set_nrthreads(int n, int *nthreads)
break;
}
svc_destroy(nfsd_serv);
- unlock_kernel();
return err;
}
@@ -334,8 +343,8 @@ int
nfsd_svc(unsigned short port, int nrservs)
{
int error;
-
- lock_kernel();
+
+ mutex_lock(&nfsd_mutex);
dprintk("nfsd: creating service\n");
error = -EINVAL;
if (nrservs <= 0)
@@ -363,7 +372,7 @@ nfsd_svc(unsigned short port, int nrservs)
failure:
svc_destroy(nfsd_serv); /* Release server */
out:
- unlock_kernel();
+ mutex_unlock(&nfsd_mutex);
return error;
}
@@ -391,18 +400,17 @@ update_thread_usage(int busy_threads)
/*
* This is the NFS server kernel thread
*/
-static void
-nfsd(struct svc_rqst *rqstp)
+static int
+nfsd(void *vrqstp)
{
+ struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
struct fs_struct *fsp;
- int err;
- sigset_t shutdown_mask, allowed_mask;
+ int err, preverr = 0;
/* Lock module and set up kernel thread */
- lock_kernel();
- daemonize("nfsd");
+ mutex_lock(&nfsd_mutex);
- /* After daemonize() this kernel thread shares current->fs
+ /* At this point, the thread shares current->fs
* with the init process. We need to create files with a
* umask of 0 instead of init's umask. */
fsp = copy_fs_struct(current->fs);
@@ -414,14 +422,17 @@ nfsd(struct svc_rqst *rqstp)
current->fs = fsp;
current->fs->umask = 0;
- siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS);
- siginitsetinv(&allowed_mask, ALLOWED_SIGS);
+ /*
+ * thread is spawned with all signals set to SIG_IGN, re-enable
+ * the ones that will bring down the thread
+ */
+ allow_signal(SIGKILL);
+ allow_signal(SIGHUP);
+ allow_signal(SIGINT);
+ allow_signal(SIGQUIT);
nfsdstats.th_cnt++;
-
- rqstp->rq_task = current;
-
- unlock_kernel();
+ mutex_unlock(&nfsd_mutex);
/*
* We want less throttling in balance_dirty_pages() so that nfs to
@@ -435,26 +446,30 @@ nfsd(struct svc_rqst *rqstp)
* The main request loop
*/
for (;;) {
- /* Block all but the shutdown signals */
- sigprocmask(SIG_SETMASK, &shutdown_mask, NULL);
-
/*
* Find a socket with data available and call its
* recvfrom routine.
*/
while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN)
;
- if (err < 0)
+ if (err == -EINTR)
break;
+ else if (err < 0) {
+ if (err != preverr) {
+ printk(KERN_WARNING "%s: unexpected error "
+ "from svc_recv (%d)\n", __func__, -err);
+ preverr = err;
+ }
+ schedule_timeout_uninterruptible(HZ);
+ continue;
+ }
+
update_thread_usage(atomic_read(&nfsd_busy));
atomic_inc(&nfsd_busy);
/* Lock the export hash tables for reading. */
exp_readlock();
- /* Process request with signals blocked. */
- sigprocmask(SIG_SETMASK, &allowed_mask, NULL);
-
svc_process(rqstp);
/* Unlock export hash tables */
@@ -463,22 +478,10 @@ nfsd(struct svc_rqst *rqstp)
atomic_dec(&nfsd_busy);
}
- if (err != -EINTR) {
- printk(KERN_WARNING "nfsd: terminating on error %d\n", -err);
- } else {
- unsigned int signo;
-
- for (signo = 1; signo <= _NSIG; signo++)
- if (sigismember(&current->pending.signal, signo) &&
- !sigismember(&current->blocked, signo))
- break;
- killsig = signo;
- }
/* Clear signals before calling svc_exit_thread() */
flush_signals(current);
- lock_kernel();
-
+ mutex_lock(&nfsd_mutex);
nfsdstats.th_cnt --;
out:
@@ -486,8 +489,9 @@ out:
svc_exit_thread(rqstp);
/* Release module */
- unlock_kernel();
+ mutex_unlock(&nfsd_mutex);
module_put_and_exit(0);
+ return 0;
}
static __be32 map_new_errors(u32 vers, __be32 nfserr)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a3a291f771f..0f4481e0502 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -144,7 +144,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
/* Obtain dentry and export. */
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
if (err)
return err;
@@ -262,14 +262,14 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
{
struct dentry *dentry;
struct inode *inode;
- int accmode = MAY_SATTR;
+ int accmode = NFSD_MAY_SATTR;
int ftype = 0;
__be32 err;
int host_err;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
- accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
+ accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
@@ -331,7 +331,8 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
*/
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
- err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
+ err = nfsd_permission(rqstp, fhp->fh_export, dentry,
+ NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
@@ -462,7 +463,7 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int flags = 0;
/* Get inode */
- error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR);
+ error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
if (error)
return error;
@@ -563,20 +564,20 @@ struct accessmap {
int how;
};
static struct accessmap nfs3_regaccess[] = {
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_EXECUTE, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_TRUNC },
- { NFS3_ACCESS_EXTEND, MAY_WRITE },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_TRUNC },
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE },
{ 0, 0 }
};
static struct accessmap nfs3_diraccess[] = {
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_LOOKUP, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_EXEC|MAY_WRITE|MAY_TRUNC },
- { NFS3_ACCESS_EXTEND, MAY_EXEC|MAY_WRITE },
- { NFS3_ACCESS_DELETE, MAY_REMOVE },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_LOOKUP, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC},
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_EXEC|NFSD_MAY_WRITE },
+ { NFS3_ACCESS_DELETE, NFSD_MAY_REMOVE },
{ 0, 0 }
};
@@ -589,10 +590,10 @@ static struct accessmap nfs3_anyaccess[] = {
* mainly at mode bits, and we make sure to ignore read-only
* filesystem checks
*/
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_EXECUTE, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_LOCAL_ACCESS },
- { NFS3_ACCESS_EXTEND, MAY_WRITE|MAY_LOCAL_ACCESS },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
{ 0, 0 }
};
@@ -606,7 +607,7 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
u32 query, result = 0, sresult = 0;
__be32 error;
- error = fh_verify(rqstp, fhp, 0, MAY_NOP);
+ error = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (error)
goto out;
@@ -678,7 +679,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
* in case a chmod has now revoked permission.
*/
- err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
+ err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
@@ -689,7 +690,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
- if (IS_APPEND(inode) && (access & MAY_WRITE))
+ if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
goto out;
/*
* We must ignore files (but only files) which might have mandatory
@@ -706,14 +707,14 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
* Check to see if there are any leases on this file.
* This may block while leases are broken.
*/
- host_err = break_lease(inode, O_NONBLOCK | ((access & MAY_WRITE) ? FMODE_WRITE : 0));
+ host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0));
if (host_err == -EWOULDBLOCK)
host_err = -ETIMEDOUT;
if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
- if (access & MAY_WRITE) {
- if (access & MAY_READ)
+ if (access & NFSD_MAY_WRITE) {
+ if (access & NFSD_MAY_READ)
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
@@ -1069,12 +1070,12 @@ nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (file) {
err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
- MAY_READ|MAY_OWNER_OVERRIDE);
+ NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
} else {
- err = nfsd_open(rqstp, fhp, S_IFREG, MAY_READ, &file);
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
if (err)
goto out;
err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
@@ -1098,13 +1099,13 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (file) {
err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
- MAY_WRITE|MAY_OWNER_OVERRIDE);
+ NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
stablep);
} else {
- err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file);
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
if (err)
goto out;
@@ -1136,7 +1137,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
if ((u64)count > ~(u64)offset)
return nfserr_inval;
- if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0)
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
+ if (err)
return err;
if (EX_ISSYNC(fhp->fh_export)) {
if (file->f_op && file->f_op->fsync) {
@@ -1197,7 +1199,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1248,36 +1250,34 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
iap->ia_mode = 0;
iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
+ err = nfserr_inval;
+ if (!S_ISREG(type) && !S_ISDIR(type) && !special_file(type)) {
+ printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",
+ type);
+ goto out;
+ }
+
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
+
/*
* Get the dir op function pointer.
*/
err = 0;
switch (type) {
case S_IFREG:
- host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
- if (host_err)
- goto out_nfserr;
host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
break;
case S_IFDIR:
- host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
- if (host_err)
- goto out_nfserr;
host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
break;
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
- host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
- if (host_err)
- goto out_nfserr;
host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
break;
- default:
- printk("nfsd: bad file type %o in nfsd_create\n", type);
- host_err = -EINVAL;
- goto out_nfserr;
}
if (host_err < 0) {
mnt_drop_write(fhp->fh_export->ex_path.mnt);
@@ -1289,7 +1289,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
write_inode_now(dchild->d_inode, 1);
}
-
err2 = nfsd_create_setattr(rqstp, resfhp, iap);
if (err2)
err = err2;
@@ -1334,7 +1333,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out;
if (!(iap->ia_valid & ATTR_MODE))
iap->ia_mode = 0;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1471,7 +1470,7 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
__be32 err;
int host_err;
- err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP);
+ err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP);
if (err)
goto out;
@@ -1526,7 +1525,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
fh_lock(fhp);
@@ -1591,10 +1590,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
__be32 err;
int host_err;
- err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
- err = fh_verify(rqstp, tfhp, -S_IFDIR, MAY_NOP);
+ err = fh_verify(rqstp, tfhp, -S_IFDIR, NFSD_MAY_NOP);
if (err)
goto out;
@@ -1661,10 +1660,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
__be32 err;
int host_err;
- err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_REMOVE);
+ err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
goto out;
- err = fh_verify(rqstp, tfhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, tfhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1768,7 +1767,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
err = nfserr_acces;
if (!flen || isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_REMOVE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
goto out;
@@ -1834,7 +1833,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
struct file *file;
loff_t offset = *offsetp;
- err = nfsd_open(rqstp, fhp, S_IFDIR, MAY_READ, &file);
+ err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
if (err)
goto out;
@@ -1875,7 +1874,7 @@ out:
__be32
nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat)
{
- __be32 err = fh_verify(rqstp, fhp, 0, MAY_NOP);
+ __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (!err && vfs_statfs(fhp->fh_dentry,stat))
err = nfserr_io;
return err;
@@ -1896,18 +1895,18 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
struct inode *inode = dentry->d_inode;
int err;
- if (acc == MAY_NOP)
+ if (acc == NFSD_MAY_NOP)
return 0;
#if 0
dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n",
acc,
- (acc & MAY_READ)? " read" : "",
- (acc & MAY_WRITE)? " write" : "",
- (acc & MAY_EXEC)? " exec" : "",
- (acc & MAY_SATTR)? " sattr" : "",
- (acc & MAY_TRUNC)? " trunc" : "",
- (acc & MAY_LOCK)? " lock" : "",
- (acc & MAY_OWNER_OVERRIDE)? " owneroverride" : "",
+ (acc & NFSD_MAY_READ)? " read" : "",
+ (acc & NFSD_MAY_WRITE)? " write" : "",
+ (acc & NFSD_MAY_EXEC)? " exec" : "",
+ (acc & NFSD_MAY_SATTR)? " sattr" : "",
+ (acc & NFSD_MAY_TRUNC)? " trunc" : "",
+ (acc & NFSD_MAY_LOCK)? " lock" : "",
+ (acc & NFSD_MAY_OWNER_OVERRIDE)? " owneroverride" : "",
inode->i_mode,
IS_IMMUTABLE(inode)? " immut" : "",
IS_APPEND(inode)? " append" : "",
@@ -1920,18 +1919,18 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
* system. But if it is IRIX doing check on write-access for a
* device special file, we ignore rofs.
*/
- if (!(acc & MAY_LOCAL_ACCESS))
- if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) {
+ if (!(acc & NFSD_MAY_LOCAL_ACCESS))
+ if (acc & (NFSD_MAY_WRITE | NFSD_MAY_SATTR | NFSD_MAY_TRUNC)) {
if (exp_rdonly(rqstp, exp) ||
__mnt_is_readonly(exp->ex_path.mnt))
return nfserr_rofs;
- if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
+ if (/* (acc & NFSD_MAY_WRITE) && */ IS_IMMUTABLE(inode))
return nfserr_perm;
}
- if ((acc & MAY_TRUNC) && IS_APPEND(inode))
+ if ((acc & NFSD_MAY_TRUNC) && IS_APPEND(inode))
return nfserr_perm;
- if (acc & MAY_LOCK) {
+ if (acc & NFSD_MAY_LOCK) {
/* If we cannot rely on authentication in NLM requests,
* just allow locks, otherwise require read permission, or
* ownership
@@ -1939,7 +1938,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
if (exp->ex_flags & NFSEXP_NOAUTHNLM)
return 0;
else
- acc = MAY_READ | MAY_OWNER_OVERRIDE;
+ acc = NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE;
}
/*
* The file owner always gets access permission for accesses that
@@ -1955,15 +1954,16 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
* We must trust the client to do permission checking - using "ACCESS"
* with NFSv3.
*/
- if ((acc & MAY_OWNER_OVERRIDE) &&
+ if ((acc & NFSD_MAY_OWNER_OVERRIDE) &&
inode->i_uid == current->fsuid)
return 0;
+ /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL);
/* Allow read access to binaries even when mode 111 */
if (err == -EACCES && S_ISREG(inode->i_mode) &&
- acc == (MAY_READ | MAY_OWNER_OVERRIDE))
+ acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
err = permission(inode, MAY_EXEC, NULL);
return err? nfserrno(err) : 0;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 17964c0505a..1db080135c6 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -174,10 +174,17 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
* need to use BH_New is when we're extending i_size on a file
* system which doesn't support holes, in which case BH_New
* allows block_prepare_write() to zero.
+ *
+ * If we see this on a sparse file system, then a truncate has
+ * raced us and removed the cluster. In this case, we clear
+ * the buffers dirty and uptodate bits and let the buffer code
+ * ignore it as a hole.
*/
- mlog_bug_on_msg(create && p_blkno == 0 && ocfs2_sparse_alloc(osb),
- "ino %lu, iblock %llu\n", inode->i_ino,
- (unsigned long long)iblock);
+ if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
+ clear_buffer_dirty(bh_result);
+ clear_buffer_uptodate(bh_result);
+ goto bail;
+ }
/* Treat the unwritten extent as a hole for zeroing purposes. */
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f02ccb34604..7dce1612553 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1493,24 +1493,18 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g
const char *name)
{
struct o2hb_region *reg = NULL;
- struct config_item *ret = NULL;
reg = kzalloc(sizeof(struct o2hb_region), GFP_KERNEL);
if (reg == NULL)
- goto out; /* ENOMEM */
+ return ERR_PTR(-ENOMEM);
config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
- ret = &reg->hr_item;
-
spin_lock(&o2hb_live_lock);
list_add_tail(&reg->hr_all_item, &o2hb_all_regions);
spin_unlock(&o2hb_live_lock);
-out:
- if (ret == NULL)
- kfree(reg);
- return ret;
+ return &reg->hr_item;
}
static void o2hb_heartbeat_group_drop_item(struct config_group *group,
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 7bf3c0ea7bd..d8bfa0eb41b 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -146,8 +146,10 @@ static int nst_seq_show(struct seq_file *seq, void *v)
nst->st_task->comm, nst->st_node,
nst->st_sc, nst->st_id, nst->st_msg_type,
nst->st_msg_key,
- nst->st_sock_time.tv_sec, nst->st_sock_time.tv_usec,
- nst->st_send_time.tv_sec, nst->st_send_time.tv_usec,
+ nst->st_sock_time.tv_sec,
+ (unsigned long)nst->st_sock_time.tv_usec,
+ nst->st_send_time.tv_sec,
+ (unsigned long)nst->st_send_time.tv_usec,
nst->st_status_time.tv_sec,
nst->st_status_time.tv_usec);
}
@@ -274,7 +276,7 @@ static void *sc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
return sc; /* unused, just needs to be null when done */
}
-#define TV_SEC_USEC(TV) TV.tv_sec, TV.tv_usec
+#define TV_SEC_USEC(TV) TV.tv_sec, (unsigned long)TV.tv_usec
static int sc_seq_show(struct seq_file *seq, void *v)
{
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index cfdb08b484e..816a3f61330 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -648,26 +648,19 @@ static struct config_item *o2nm_node_group_make_item(struct config_group *group,
const char *name)
{
struct o2nm_node *node = NULL;
- struct config_item *ret = NULL;
if (strlen(name) > O2NM_MAX_NAME_LEN)
- goto out; /* ENAMETOOLONG */
+ return ERR_PTR(-ENAMETOOLONG);
node = kzalloc(sizeof(struct o2nm_node), GFP_KERNEL);
if (node == NULL)
- goto out; /* ENOMEM */
+ return ERR_PTR(-ENOMEM);
strcpy(node->nd_name, name); /* use item.ci_namebuf instead? */
config_item_init_type_name(&node->nd_item, name, &o2nm_node_type);
spin_lock_init(&node->nd_lock);
- ret = &node->nd_item;
-
-out:
- if (ret == NULL)
- kfree(node);
-
- return ret;
+ return &node->nd_item;
}
static void o2nm_node_group_drop_item(struct config_group *group,
@@ -762,7 +755,7 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
/* this runs under the parent dir's i_mutex; there can be only
* one caller in here at a time */
if (o2nm_single_cluster)
- goto out; /* ENOSPC */
+ return ERR_PTR(-ENOSPC);
cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL);
ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL);
@@ -795,6 +788,7 @@ out:
kfree(ns);
o2hb_free_hb_set(o2hb_group);
kfree(defs);
+ ret = ERR_PTR(-ENOMEM);
}
return ret;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 80e20d9f278..eae3d643a5e 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -31,6 +31,7 @@
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/time.h>
#define MLOG_MASK_PREFIX ML_DLM_GLUE
#include <cluster/masklog.h>
@@ -59,6 +60,9 @@ struct ocfs2_mask_waiter {
struct completion mw_complete;
unsigned long mw_mask;
unsigned long mw_goal;
+#ifdef CONFIG_OCFS2_FS_STATS
+ unsigned long long mw_lock_start;
+#endif
};
static struct ocfs2_super *ocfs2_get_dentry_osb(struct ocfs2_lock_res *lockres);
@@ -366,6 +370,75 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res)
spin_unlock(&ocfs2_dlm_tracking_lock);
}
+#ifdef CONFIG_OCFS2_FS_STATS
+static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+ res->l_lock_num_prmode = 0;
+ res->l_lock_num_prmode_failed = 0;
+ res->l_lock_total_prmode = 0;
+ res->l_lock_max_prmode = 0;
+ res->l_lock_num_exmode = 0;
+ res->l_lock_num_exmode_failed = 0;
+ res->l_lock_total_exmode = 0;
+ res->l_lock_max_exmode = 0;
+ res->l_lock_refresh = 0;
+}
+
+static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
+ struct ocfs2_mask_waiter *mw, int ret)
+{
+ unsigned long long *num, *sum;
+ unsigned int *max, *failed;
+ struct timespec ts = current_kernel_time();
+ unsigned long long time = timespec_to_ns(&ts) - mw->mw_lock_start;
+
+ if (level == LKM_PRMODE) {
+ num = &res->l_lock_num_prmode;
+ sum = &res->l_lock_total_prmode;
+ max = &res->l_lock_max_prmode;
+ failed = &res->l_lock_num_prmode_failed;
+ } else if (level == LKM_EXMODE) {
+ num = &res->l_lock_num_exmode;
+ sum = &res->l_lock_total_exmode;
+ max = &res->l_lock_max_exmode;
+ failed = &res->l_lock_num_exmode_failed;
+ } else
+ return;
+
+ (*num)++;
+ (*sum) += time;
+ if (time > *max)
+ *max = time;
+ if (ret)
+ (*failed)++;
+}
+
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+ lockres->l_lock_refresh++;
+}
+
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+ struct timespec ts = current_kernel_time();
+ mw->mw_lock_start = timespec_to_ns(&ts);
+}
+#else
+static inline void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+}
+static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
+ int level, struct ocfs2_mask_waiter *mw, int ret)
+{
+}
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+}
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+}
+#endif
+
static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
struct ocfs2_lock_res *res,
enum ocfs2_lock_type type,
@@ -385,6 +458,8 @@ static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
res->l_flags = OCFS2_LOCK_INITIALIZED;
ocfs2_add_lockres_tracking(res, osb->osb_dlm_debug);
+
+ ocfs2_init_lock_stats(res);
}
void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
@@ -1048,6 +1123,7 @@ static void ocfs2_init_mask_waiter(struct ocfs2_mask_waiter *mw)
{
INIT_LIST_HEAD(&mw->mw_item);
init_completion(&mw->mw_complete);
+ ocfs2_init_start_time(mw);
}
static int ocfs2_wait_for_mask(struct ocfs2_mask_waiter *mw)
@@ -1254,6 +1330,7 @@ out:
goto again;
mlog_errno(ret);
}
+ ocfs2_update_lock_stats(lockres, level, &mw, ret);
mlog_exit(ret);
return ret;
@@ -1983,6 +2060,7 @@ static int ocfs2_inode_lock_update(struct inode *inode,
le32_to_cpu(fe->i_flags));
ocfs2_refresh_inode(inode, fe);
+ ocfs2_track_lock_refresh(lockres);
}
status = 0;
@@ -2267,6 +2345,7 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
if (status < 0)
mlog_errno(status);
+ ocfs2_track_lock_refresh(lockres);
}
bail:
mlog_exit(status);
@@ -2461,7 +2540,7 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
}
/* So that debugfs.ocfs2 can determine which format is being used */
-#define OCFS2_DLM_DEBUG_STR_VERSION 1
+#define OCFS2_DLM_DEBUG_STR_VERSION 2
static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
{
int i;
@@ -2502,6 +2581,47 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
for(i = 0; i < DLM_LVB_LEN; i++)
seq_printf(m, "0x%x\t", lvb[i]);
+#ifdef CONFIG_OCFS2_FS_STATS
+# define lock_num_prmode(_l) (_l)->l_lock_num_prmode
+# define lock_num_exmode(_l) (_l)->l_lock_num_exmode
+# define lock_num_prmode_failed(_l) (_l)->l_lock_num_prmode_failed
+# define lock_num_exmode_failed(_l) (_l)->l_lock_num_exmode_failed
+# define lock_total_prmode(_l) (_l)->l_lock_total_prmode
+# define lock_total_exmode(_l) (_l)->l_lock_total_exmode
+# define lock_max_prmode(_l) (_l)->l_lock_max_prmode
+# define lock_max_exmode(_l) (_l)->l_lock_max_exmode
+# define lock_refresh(_l) (_l)->l_lock_refresh
+#else
+# define lock_num_prmode(_l) (0ULL)
+# define lock_num_exmode(_l) (0ULL)
+# define lock_num_prmode_failed(_l) (0)
+# define lock_num_exmode_failed(_l) (0)
+# define lock_total_prmode(_l) (0ULL)
+# define lock_total_exmode(_l) (0ULL)
+# define lock_max_prmode(_l) (0)
+# define lock_max_exmode(_l) (0)
+# define lock_refresh(_l) (0)
+#endif
+ /* The following seq_print was added in version 2 of this output */
+ seq_printf(m, "%llu\t"
+ "%llu\t"
+ "%u\t"
+ "%u\t"
+ "%llu\t"
+ "%llu\t"
+ "%u\t"
+ "%u\t"
+ "%u\t",
+ lock_num_prmode(lockres),
+ lock_num_exmode(lockres),
+ lock_num_prmode_failed(lockres),
+ lock_num_exmode_failed(lockres),
+ lock_total_prmode(lockres),
+ lock_total_exmode(lockres),
+ lock_max_prmode(lockres),
+ lock_max_exmode(lockres),
+ lock_refresh(lockres));
+
/* End the line */
seq_printf(m, "\n");
return 0;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 57e0d30cde9..e8514e8b6ce 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2202,7 +2202,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
if (ret == -EINVAL)
- mlog(ML_ERROR, "generic_file_aio_read returned -EINVAL\n");
+ mlog(0, "generic_file_aio_read returned -EINVAL\n");
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 9698338adc3..a8c19cb3cfd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -329,7 +329,7 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
mlog(0, "Trying to extend transaction by %d blocks\n", nblocks);
-#ifdef OCFS2_DEBUG_FS
+#ifdef CONFIG_OCFS2_DEBUG_FS
status = 1;
#else
status = journal_extend(handle, nblocks);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index be774bdc8b3..28e492e4ec8 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -498,7 +498,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
-#ifdef OCFS2_DEBUG_FS
+#ifdef CONFIG_OCFS2_DEBUG_FS
if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
ocfs2_local_alloc_count_bits(alloc)) {
ocfs2_error(osb->sb, "local alloc inode %llu says it has "
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 31692379c17..1cb814be8ef 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -132,6 +132,18 @@ struct ocfs2_lock_res {
wait_queue_head_t l_event;
struct list_head l_debug_list;
+
+#ifdef CONFIG_OCFS2_FS_STATS
+ unsigned long long l_lock_num_prmode; /* PR acquires */
+ unsigned long long l_lock_num_exmode; /* EX acquires */
+ unsigned int l_lock_num_prmode_failed; /* Failed PR gets */
+ unsigned int l_lock_num_exmode_failed; /* Failed EX gets */
+ unsigned long long l_lock_total_prmode; /* Tot wait for PR */
+ unsigned long long l_lock_total_exmode; /* Tot wait for EX */
+ unsigned int l_lock_max_prmode; /* Max wait for PR */
+ unsigned int l_lock_max_exmode; /* Max wait for EX */
+ unsigned int l_lock_refresh; /* Disk refreshes */
+#endif
};
struct ocfs2_dlm_debug {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 52c42666515..3f194517762 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -901,7 +901,7 @@ static inline int ocfs2_sprintf_system_inode_name(char *buf, int len,
* list has a copy per slot.
*/
if (type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE)
- chars = snprintf(buf, len,
+ chars = snprintf(buf, len, "%s",
ocfs2_system_inodes[type].si_name);
else
chars = snprintf(buf, len,
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index bd7e0f3acfc..353fc35c674 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -550,26 +550,17 @@ static ssize_t ocfs2_control_read(struct file *file,
size_t count,
loff_t *ppos)
{
- char *proto_string = OCFS2_CONTROL_PROTO;
- size_t to_write = 0;
-
- if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
- return 0;
-
- to_write = OCFS2_CONTROL_PROTO_LEN - *ppos;
- if (to_write > count)
- to_write = count;
- if (copy_to_user(buf, proto_string + *ppos, to_write))
- return -EFAULT;
+ ssize_t ret;
- *ppos += to_write;
+ ret = simple_read_from_buffer(buf, count, ppos,
+ OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN);
/* Have we read the whole protocol list? */
- if (*ppos >= OCFS2_CONTROL_PROTO_LEN)
+ if (ret > 0 && *ppos >= OCFS2_CONTROL_PROTO_LEN)
ocfs2_control_set_handshake_state(file,
OCFS2_CONTROL_HANDSHAKE_READ);
- return to_write;
+ return ret;
}
static int ocfs2_control_release(struct inode *inode, struct file *file)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index df63ba20ae9..ccecfe5094f 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1703,7 +1703,11 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
local = ocfs2_mount_local(osb);
/* will play back anything left in the journal. */
- ocfs2_journal_load(osb->journal, local);
+ status = ocfs2_journal_load(osb->journal, local);
+ if (status < 0) {
+ mlog(ML_ERROR, "ocfs2 journal load failed! %d\n", status);
+ goto finally;
+ }
if (dirty) {
/* recover my local alloc if we didn't unmount cleanly. */
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 83f357b30d7..b224a28e0c1 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -51,6 +51,30 @@ int seq_open_net(struct inode *ino, struct file *f,
}
EXPORT_SYMBOL_GPL(seq_open_net);
+int single_open_net(struct inode *inode, struct file *file,
+ int (*show)(struct seq_file *, void *))
+{
+ int err;
+ struct net *net;
+
+ err = -ENXIO;
+ net = get_proc_net(inode);
+ if (net == NULL)
+ goto err_net;
+
+ err = single_open(file, show, net);
+ if (err < 0)
+ goto err_open;
+
+ return 0;
+
+err_open:
+ put_net(net);
+err_net:
+ return err;
+}
+EXPORT_SYMBOL_GPL(single_open_net);
+
int seq_release_net(struct inode *ino, struct file *f)
{
struct seq_file *seq;
@@ -63,6 +87,14 @@ int seq_release_net(struct inode *ino, struct file *f)
}
EXPORT_SYMBOL_GPL(seq_release_net);
+int single_release_net(struct inode *ino, struct file *f)
+{
+ struct seq_file *seq = f->private_data;
+ put_net(seq->private);
+ return single_release(ino, f);
+}
+EXPORT_SYMBOL_GPL(single_release_net);
+
static struct net *get_proc_task_net(struct inode *dir)
{
struct task_struct *task;
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index 21f490f5d65..d153946d6d1 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -136,54 +136,6 @@ static const struct file_operations proc_tty_drivers_operations = {
.release = seq_release,
};
-static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
-{
- return (*pos < NR_LDISCS) ? pos : NULL;
-}
-
-static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
-{
- (*pos)++;
- return (*pos < NR_LDISCS) ? pos : NULL;
-}
-
-static void tty_ldiscs_seq_stop(struct seq_file *m, void *v)
-{
-}
-
-static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
-{
- int i = *(loff_t *)v;
- struct tty_ldisc *ld;
-
- ld = tty_ldisc_get(i);
- if (ld == NULL)
- return 0;
- seq_printf(m, "%-10s %2d\n", ld->name ? ld->name : "???", i);
- tty_ldisc_put(i);
- return 0;
-}
-
-static const struct seq_operations tty_ldiscs_seq_ops = {
- .start = tty_ldiscs_seq_start,
- .next = tty_ldiscs_seq_next,
- .stop = tty_ldiscs_seq_stop,
- .show = tty_ldiscs_seq_show,
-};
-
-static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tty_ldiscs_seq_ops);
-}
-
-static const struct file_operations tty_ldiscs_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_tty_ldiscs_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* This function is called by tty_register_driver() to handle
* registering the driver's /proc handler into /proc/tty/driver/<foo>