summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig10
-rw-r--r--fs/dlm/dir.c7
-rw-r--r--fs/dlm/lockspace.c17
-rw-r--r--fs/dlm/lowcomms.c22
-rw-r--r--fs/dlm/lowcomms.h3
-rw-r--r--fs/dlm/member.c19
-rw-r--r--fs/dlm/requestqueue.c2
-rw-r--r--fs/eventfd.c3
-rw-r--r--fs/exofs/common.h6
-rw-r--r--fs/exofs/inode.c8
-rw-r--r--fs/exofs/osd.c26
-rw-r--r--fs/fuse/Makefile1
-rw-r--r--fs/fuse/cuse.c610
-rw-r--r--fs/fuse/dev.c15
-rw-r--r--fs/fuse/dir.c33
-rw-r--r--fs/fuse/file.c346
-rw-r--r--fs/fuse/fuse_i.h47
-rw-r--r--fs/fuse/inode.c118
-rw-r--r--fs/gfs2/Makefile1
-rw-r--r--fs/gfs2/bmap.c3
-rw-r--r--fs/gfs2/glock.c12
-rw-r--r--fs/gfs2/log.c9
-rw-r--r--fs/gfs2/lops.c3
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/gfs2/rgrp.c11
-rw-r--r--fs/gfs2/super.c4
-rw-r--r--fs/gfs2/trace_gfs2.h407
-rw-r--r--fs/partitions/check.c42
28 files changed, 1476 insertions, 311 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 9f7270f36b2..525da2e8f73 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -62,6 +62,16 @@ source "fs/autofs/Kconfig"
source "fs/autofs4/Kconfig"
source "fs/fuse/Kconfig"
+config CUSE
+ tristate "Character device in Userpace support"
+ depends on FUSE_FS
+ help
+ This FUSE extension allows character devices to be
+ implemented in userspace.
+
+ If you want to develop or use userspace character device
+ based on CUSE, answer Y or M.
+
config GENERIC_ACL
bool
select FS_POSIX_ACL
diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 858fba14aaa..c4dfa1dcc86 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -49,7 +49,8 @@ static struct dlm_direntry *get_free_de(struct dlm_ls *ls, int len)
spin_unlock(&ls->ls_recover_list_lock);
if (!found)
- de = kzalloc(sizeof(struct dlm_direntry) + len, GFP_KERNEL);
+ de = kzalloc(sizeof(struct dlm_direntry) + len,
+ ls->ls_allocation);
return de;
}
@@ -211,7 +212,7 @@ int dlm_recover_directory(struct dlm_ls *ls)
dlm_dir_clear(ls);
- last_name = kmalloc(DLM_RESNAME_MAXLEN, GFP_KERNEL);
+ last_name = kmalloc(DLM_RESNAME_MAXLEN, ls->ls_allocation);
if (!last_name)
goto out;
@@ -322,7 +323,7 @@ static int get_entry(struct dlm_ls *ls, int nodeid, char *name,
if (namelen > DLM_RESNAME_MAXLEN)
return -EINVAL;
- de = kzalloc(sizeof(struct dlm_direntry) + namelen, GFP_KERNEL);
+ de = kzalloc(sizeof(struct dlm_direntry) + namelen, ls->ls_allocation);
if (!de)
return -ENOMEM;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index cd8e2df3c29..d489fcc8671 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -384,7 +384,7 @@ static void threads_stop(void)
dlm_astd_stop();
}
-static int new_lockspace(char *name, int namelen, void **lockspace,
+static int new_lockspace(const char *name, int namelen, void **lockspace,
uint32_t flags, int lvblen)
{
struct dlm_ls *ls;
@@ -419,16 +419,14 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
break;
}
ls->ls_create_count++;
- module_put(THIS_MODULE);
- error = 1; /* not an error, return 0 */
+ *lockspace = ls;
+ error = 1;
break;
}
spin_unlock(&lslist_lock);
- if (error < 0)
- goto out;
if (error)
- goto ret_zero;
+ goto out;
error = -ENOMEM;
@@ -583,7 +581,6 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
dlm_create_debug_file(ls);
log_debug(ls, "join complete");
- ret_zero:
*lockspace = ls;
return 0;
@@ -614,7 +611,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
return error;
}
-int dlm_new_lockspace(char *name, int namelen, void **lockspace,
+int dlm_new_lockspace(const char *name, int namelen, void **lockspace,
uint32_t flags, int lvblen)
{
int error = 0;
@@ -628,7 +625,9 @@ int dlm_new_lockspace(char *name, int namelen, void **lockspace,
error = new_lockspace(name, namelen, lockspace, flags, lvblen);
if (!error)
ls_count++;
- else if (!ls_count)
+ if (error > 0)
+ error = 0;
+ if (!ls_count)
threads_stop();
out:
mutex_unlock(&ls_lock);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 609108a8326..cdb580a9c7a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -309,6 +309,20 @@ static void lowcomms_state_change(struct sock *sk)
lowcomms_write_space(sk);
}
+int dlm_lowcomms_connect_node(int nodeid)
+{
+ struct connection *con;
+
+ if (nodeid == dlm_our_nodeid())
+ return 0;
+
+ con = nodeid2con(nodeid, GFP_NOFS);
+ if (!con)
+ return -ENOMEM;
+ lowcomms_connect_sock(con);
+ return 0;
+}
+
/* Make a socket active */
static int add_sock(struct socket *sock, struct connection *con)
{
@@ -486,7 +500,7 @@ static void process_sctp_notification(struct connection *con,
return;
}
- new_con = nodeid2con(nodeid, GFP_KERNEL);
+ new_con = nodeid2con(nodeid, GFP_NOFS);
if (!new_con)
return;
@@ -722,7 +736,7 @@ static int tcp_accept_from_sock(struct connection *con)
* the same time and the connections cross on the wire.
* In this case we store the incoming one in "othercon"
*/
- newcon = nodeid2con(nodeid, GFP_KERNEL);
+ newcon = nodeid2con(nodeid, GFP_NOFS);
if (!newcon) {
result = -ENOMEM;
goto accept_err;
@@ -732,7 +746,7 @@ static int tcp_accept_from_sock(struct connection *con)
struct connection *othercon = newcon->othercon;
if (!othercon) {
- othercon = kmem_cache_zalloc(con_cache, GFP_KERNEL);
+ othercon = kmem_cache_zalloc(con_cache, GFP_NOFS);
if (!othercon) {
log_print("failed to allocate incoming socket");
mutex_unlock(&newcon->sock_mutex);
@@ -1421,7 +1435,7 @@ static int work_start(void)
static void stop_conn(struct connection *con)
{
con->flags |= 0x0F;
- if (con->sock)
+ if (con->sock && con->sock->sk)
con->sock->sk->sk_user_data = NULL;
}
diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h
index a9a9618c0d3..1311e642628 100644
--- a/fs/dlm/lowcomms.h
+++ b/fs/dlm/lowcomms.h
@@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -19,6 +19,7 @@ void dlm_lowcomms_stop(void);
int dlm_lowcomms_close(int nodeid);
void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc);
void dlm_lowcomms_commit_buffer(void *mh);
+int dlm_lowcomms_connect_node(int nodeid);
#endif /* __LOWCOMMS_DOT_H__ */
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 26133f05ae3..b128775913b 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -1,7 +1,7 @@
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2009 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -17,6 +17,7 @@
#include "recover.h"
#include "rcom.h"
#include "config.h"
+#include "lowcomms.h"
static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
{
@@ -45,9 +46,9 @@ static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
static int dlm_add_member(struct dlm_ls *ls, int nodeid)
{
struct dlm_member *memb;
- int w;
+ int w, error;
- memb = kzalloc(sizeof(struct dlm_member), GFP_KERNEL);
+ memb = kzalloc(sizeof(struct dlm_member), ls->ls_allocation);
if (!memb)
return -ENOMEM;
@@ -57,6 +58,12 @@ static int dlm_add_member(struct dlm_ls *ls, int nodeid)
return w;
}
+ error = dlm_lowcomms_connect_node(nodeid);
+ if (error < 0) {
+ kfree(memb);
+ return error;
+ }
+
memb->nodeid = nodeid;
memb->weight = w;
add_ordered_member(ls, memb);
@@ -136,7 +143,7 @@ static void make_member_array(struct dlm_ls *ls)
ls->ls_total_weight = total;
- array = kmalloc(sizeof(int) * total, GFP_KERNEL);
+ array = kmalloc(sizeof(int) * total, ls->ls_allocation);
if (!array)
return;
@@ -219,7 +226,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
continue;
log_debug(ls, "new nodeid %d is a re-added member", rv->new[i]);
- memb = kzalloc(sizeof(struct dlm_member), GFP_KERNEL);
+ memb = kzalloc(sizeof(struct dlm_member), ls->ls_allocation);
if (!memb)
return -ENOMEM;
memb->nodeid = rv->new[i];
@@ -334,7 +341,7 @@ int dlm_ls_start(struct dlm_ls *ls)
int *ids = NULL, *new = NULL;
int error, ids_count = 0, new_count = 0;
- rv = kzalloc(sizeof(struct dlm_recover), GFP_KERNEL);
+ rv = kzalloc(sizeof(struct dlm_recover), ls->ls_allocation);
if (!rv)
return -ENOMEM;
diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c
index daa4183fbb8..7a2307c0891 100644
--- a/fs/dlm/requestqueue.c
+++ b/fs/dlm/requestqueue.c
@@ -35,7 +35,7 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
struct rq_entry *e;
int length = ms->m_header.h_length - sizeof(struct dlm_message);
- e = kmalloc(sizeof(struct rq_entry) + length, GFP_KERNEL);
+ e = kmalloc(sizeof(struct rq_entry) + length, ls->ls_allocation);
if (!e) {
log_print("dlm_add_requestqueue: out of memory len %d", length);
return;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 2a701d593d3..3f0e1974abd 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -16,6 +16,7 @@
#include <linux/anon_inodes.h>
#include <linux/eventfd.h>
#include <linux/syscalls.h>
+#include <linux/module.h>
struct eventfd_ctx {
wait_queue_head_t wqh;
@@ -56,6 +57,7 @@ int eventfd_signal(struct file *file, int n)
return n;
}
+EXPORT_SYMBOL_GPL(eventfd_signal);
static int eventfd_release(struct inode *inode, struct file *file)
{
@@ -197,6 +199,7 @@ struct file *eventfd_fget(int fd)
return file;
}
+EXPORT_SYMBOL_GPL(eventfd_fget);
SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
{
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
index b1512c4bb8c..24667eedc02 100644
--- a/fs/exofs/common.h
+++ b/fs/exofs/common.h
@@ -175,10 +175,4 @@ int exofs_async_op(struct osd_request *or,
int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr);
-int osd_req_read_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
-
-int osd_req_write_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
-
#endif /*ifndef __EXOFS_COM_H__*/
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index ba8d9fab469..77d0a295eb1 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -59,10 +59,9 @@ static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
struct inode *inode)
{
struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
- struct request_queue *req_q = sbi->s_dev->scsi_device->request_queue;
pcol->sbi = sbi;
- pcol->req_q = req_q;
+ pcol->req_q = osd_request_queue(sbi->s_dev);
pcol->inode = inode;
pcol->expected_pages = expected_pages;
@@ -266,7 +265,7 @@ static int read_exec(struct page_collect *pcol, bool is_sync)
goto err;
}
- osd_req_read(or, &obj, pcol->bio, i_start);
+ osd_req_read(or, &obj, i_start, pcol->bio, pcol->length);
if (is_sync) {
exofs_sync_op(or, pcol->sbi->s_timeout, oi->i_cred);
@@ -522,7 +521,8 @@ static int write_exec(struct page_collect *pcol)
*pcol_copy = *pcol;
- osd_req_write(or, &obj, pcol_copy->bio, i_start);
+ pcol_copy->bio->bi_rw |= (1 << BIO_RW); /* FIXME: bio_set_dir() */
+ osd_req_write(or, &obj, i_start, pcol_copy->bio, pcol_copy->length);
ret = exofs_async_op(or, writepages_done, pcol_copy, oi->i_cred);
if (unlikely(ret)) {
EXOFS_ERR("write_exec: exofs_async_op() Faild\n");
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
index 06ca92672eb..b3d2ccb87aa 100644
--- a/fs/exofs/osd.c
+++ b/fs/exofs/osd.c
@@ -125,29 +125,3 @@ int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
return -EIO;
}
-
-int osd_req_read_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
-{
- struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
- struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
-
- if (!bio)
- return -ENOMEM;
-
- osd_req_read(or, obj, bio, offset);
- return 0;
-}
-
-int osd_req_write_kern(struct osd_request *or,
- const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
-{
- struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
- struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
-
- if (!bio)
- return -ENOMEM;
-
- osd_req_write(or, obj, bio, offset);
- return 0;
-}
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 72437065f6a..e95eeb445e5 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -3,5 +3,6 @@
#
obj-$(CONFIG_FUSE_FS) += fuse.o
+obj-$(CONFIG_CUSE) += cuse.o
fuse-objs := dev.o dir.o file.o inode.o control.o
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
new file mode 100644
index 00000000000..de792dcf327
--- /dev/null
+++ b/fs/fuse/cuse.c
@@ -0,0 +1,610 @@
+/*
+ * CUSE: Character device in Userspace
+ *
+ * Copyright (C) 2008-2009 SUSE Linux Products GmbH
+ * Copyright (C) 2008-2009 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * CUSE enables character devices to be implemented from userland much
+ * like FUSE allows filesystems. On initialization /dev/cuse is
+ * created. By opening the file and replying to the CUSE_INIT request
+ * userland CUSE server can create a character device. After that the
+ * operation is very similar to FUSE.
+ *
+ * A CUSE instance involves the following objects.
+ *
+ * cuse_conn : contains fuse_conn and serves as bonding structure
+ * channel : file handle connected to the userland CUSE server
+ * cdev : the implemented character device
+ * dev : generic device for cdev
+ *
+ * Note that 'channel' is what 'dev' is in FUSE. As CUSE deals with
+ * devices, it's called 'channel' to reduce confusion.
+ *
+ * channel determines when the character device dies. When channel is
+ * closed, everything begins to destruct. The cuse_conn is taken off
+ * the lookup table preventing further access from cdev, cdev and
+ * generic device are removed and the base reference of cuse_conn is
+ * put.
+ *
+ * On each open, the matching cuse_conn is looked up and if found an
+ * additional reference is taken which is released when the file is
+ * closed.
+ */
+
+#include <linux/fuse.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/kdev_t.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/magic.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+
+#include "fuse_i.h"
+
+#define CUSE_CONNTBL_LEN 64
+
+struct cuse_conn {
+ struct list_head list; /* linked on cuse_conntbl */
+ struct fuse_conn fc; /* fuse connection */
+ struct cdev *cdev; /* associated character device */
+ struct device *dev; /* device representing @cdev */
+
+ /* init parameters, set once during initialization */
+ bool unrestricted_ioctl;
+};
+
+static DEFINE_SPINLOCK(cuse_lock); /* protects cuse_conntbl */
+static struct list_head cuse_conntbl[CUSE_CONNTBL_LEN];
+static struct class *cuse_class;
+
+static struct cuse_conn *fc_to_cc(struct fuse_conn *fc)
+{
+ return container_of(fc, struct cuse_conn, fc);
+}
+
+static struct list_head *cuse_conntbl_head(dev_t devt)
+{
+ return &cuse_conntbl[(MAJOR(devt) + MINOR(devt)) % CUSE_CONNTBL_LEN];
+}
+
+
+/**************************************************************************
+ * CUSE frontend operations
+ *
+ * These are file operations for the character device.
+ *
+ * On open, CUSE opens a file from the FUSE mnt and stores it to
+ * private_data of the open file. All other ops call FUSE ops on the
+ * FUSE file.
+ */
+
+static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ loff_t pos = 0;
+
+ return fuse_direct_io(file, buf, count, &pos, 0);
+}
+
+static ssize_t cuse_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ loff_t pos = 0;
+ /*
+ * No locking or generic_write_checks(), the server is
+ * responsible for locking and sanity checks.
+ */
+ return fuse_direct_io(file, buf, count, &pos, 1);
+}
+
+static int cuse_open(struct inode *inode, struct file *file)
+{
+ dev_t devt = inode->i_cdev->dev;
+ struct cuse_conn *cc = NULL, *pos;
+ int rc;
+
+ /* look up and get the connection */
+ spin_lock(&cuse_lock);
+ list_for_each_entry(pos, cuse_conntbl_head(devt), list)
+ if (pos->dev->devt == devt) {
+ fuse_conn_get(&pos->fc);
+ cc = pos;
+ break;
+ }
+ spin_unlock(&cuse_lock);
+
+ /* dead? */
+ if (!cc)
+ return -ENODEV;
+
+ /*
+ * Generic permission check is already done against the chrdev
+ * file, proceed to open.
+ */
+ rc = fuse_do_open(&cc->fc, 0, file, 0);
+ if (rc)
+ fuse_conn_put(&cc->fc);
+ return rc;
+}
+
+static int cuse_release(struct inode *inode, struct file *file)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
+
+ fuse_sync_release(ff, file->f_flags);
+ fuse_conn_put(fc);
+
+ return 0;
+}
+
+static long cuse_file_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct fuse_file *ff = file->private_data;
+ struct cuse_conn *cc = fc_to_cc(ff->fc);
+ unsigned int flags = 0;
+
+ if (cc->unrestricted_ioctl)
+ flags |= FUSE_IOCTL_UNRESTRICTED;
+
+ return fuse_do_ioctl(file, cmd, arg, flags);
+}
+
+static long cuse_file_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct fuse_file *ff = file->private_data;
+ struct cuse_conn *cc = fc_to_cc(ff->fc);
+ unsigned int flags = FUSE_IOCTL_COMPAT;
+
+ if (cc->unrestricted_ioctl)
+ flags |= FUSE_IOCTL_UNRESTRICTED;
+
+ return fuse_do_ioctl(file, cmd, arg, flags);
+}
+
+static const struct file_operations cuse_frontend_fops = {
+ .owner = THIS_MODULE,
+ .read = cuse_read,
+ .write = cuse_write,
+ .open = cuse_open,
+ .release = cuse_release,
+ .unlocked_ioctl = cuse_file_ioctl,
+ .compat_ioctl = cuse_file_compat_ioctl,
+ .poll = fuse_file_poll,
+};
+
+
+/**************************************************************************
+ * CUSE channel initialization and destruction
+ */
+
+struct cuse_devinfo {
+ const char *name;
+};
+
+/**
+ * cuse_parse_one - parse one key=value pair
+ * @pp: i/o parameter for the current position
+ * @end: points to one past the end of the packed string
+ * @keyp: out parameter for key
+ * @valp: out parameter for value
+ *
+ * *@pp points to packed strings - "key0=val0\0key1=val1\0" which ends
+ * at @end - 1. This function parses one pair and set *@keyp to the
+ * start of the key and *@valp to the start of the value. Note that
+ * the original string is modified such that the key string is
+ * terminated with '\0'. *@pp is updated to point to the next string.
+ *
+ * RETURNS:
+ * 1 on successful parse, 0 on EOF, -errno on failure.
+ */
+static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp)
+{
+ char *p = *pp;
+ char *key, *val;
+
+ while (p < end && *p == '\0')
+ p++;
+ if (p == end)
+ return 0;
+
+ if (end[-1] != '\0') {
+ printk(KERN_ERR "CUSE: info not properly terminated\n");
+ return -EINVAL;
+ }
+
+ key = val = p;
+ p += strlen(p);
+
+ if (valp) {
+ strsep(&val, "=");
+ if (!val)
+ val = key + strlen(key);
+ key = strstrip(key);
+ val = strstrip(val);
+ } else
+ key = strstrip(key);
+
+ if (!strlen(key)) {
+ printk(KERN_ERR "CUSE: zero length info key specified\n");
+ return -EINVAL;
+ }
+
+ *pp = p;
+ *keyp = key;
+ if (valp)
+ *valp = val;
+
+ return 1;
+}
+
+/**
+ * cuse_parse_dev_info - parse device info
+ * @p: device info string
+ * @len: length of device info string
+ * @devinfo: out parameter for parsed device info
+ *
+ * Parse @p to extract device info and store it into @devinfo. String
+ * pointed to by @p is modified by parsing and @devinfo points into
+ * them, so @p shouldn't be freed while @devinfo is in use.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo)
+{
+ char *end = p + len;
+ char *key, *val;
+ int rc;
+
+ while (true) {
+ rc = cuse_parse_one(&p, end, &key, &val);
+ if (rc < 0)
+ return rc;
+ if (!rc)
+ break;
+ if (strcmp(key, "DEVNAME") == 0)
+ devinfo->name = val;
+ else
+ printk(KERN_WARNING "CUSE: unknown device info \"%s\"\n",
+ key);
+ }
+
+ if (!devinfo->name || !strlen(devinfo->name)) {
+ printk(KERN_ERR "CUSE: DEVNAME unspecified\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void cuse_gendev_release(struct device *dev)
+{
+ kfree(dev);
+}
+
+/**
+ * cuse_process_init_reply - finish initializing CUSE channel
+ *
+ * This function creates the character device and sets up all the
+ * required data structures for it. Please read the comment at the
+ * top of this file for high level overview.
+ */
+static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
+{
+ struct cuse_conn *cc = fc_to_cc(fc);
+ struct cuse_init_out *arg = &req->misc.cuse_init_out;
+ struct page *page = req->pages[0];
+ struct cuse_devinfo devinfo = { };
+ struct device *dev;
+ struct cdev *cdev;
+ dev_t devt;
+ int rc;
+
+ if (req->out.h.error ||
+ arg->major != FUSE_KERNEL_VERSION || arg->minor < 11) {
+ goto err;
+ }
+
+ fc->minor = arg->minor;
+ fc->max_read = max_t(unsigned, arg->max_read, 4096);
+ fc->max_write = max_t(unsigned, arg->max_write, 4096);
+
+ /* parse init reply */
+ cc->unrestricted_ioctl = arg->flags & CUSE_UNRESTRICTED_IOCTL;
+
+ rc = cuse_parse_devinfo(page_address(page), req->out.args[1].size,
+ &devinfo);
+ if (rc)
+ goto err;
+
+ /* determine and reserve devt */
+ devt = MKDEV(arg->dev_major, arg->dev_minor);
+ if (!MAJOR(devt))
+ rc = alloc_chrdev_region(&devt, MINOR(devt), 1, devinfo.name);
+ else
+ rc = register_chrdev_region(devt, 1, devinfo.name);
+ if (rc) {
+ printk(KERN_ERR "CUSE: failed to register chrdev region\n");
+ goto err;
+ }
+
+ /* devt determined, create device */
+ rc = -ENOMEM;
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ goto err_region;
+
+ device_initialize(dev);
+ dev_set_uevent_suppress(dev, 1);
+ dev->class = cuse_class;
+ dev->devt = devt;
+ dev->release = cuse_gendev_release;
+ dev_set_drvdata(dev, cc);
+ dev_set_name(dev, "%s", devinfo.name);
+
+ rc = device_add(dev);
+ if (rc)
+ goto err_device;
+
+ /* register cdev */
+ rc = -ENOMEM;
+ cdev = cdev_alloc();
+ if (!cdev)
+ goto err_device;
+
+ cdev->owner = THIS_MODULE;
+ cdev->ops = &cuse_frontend_fops;
+
+ rc = cdev_add(cdev, devt, 1);
+ if (rc)
+ goto err_cdev;
+
+ cc->dev = dev;
+ cc->cdev = cdev;
+
+ /* make the device available */
+ spin_lock(&cuse_lock);
+ list_add(&cc->list, cuse_conntbl_head(devt));
+ spin_unlock(&cuse_lock);
+
+ /* announce device availability */
+ dev_set_uevent_suppress(dev, 0);
+ kobject_uevent(&dev->kobj, KOBJ_ADD);
+out:
+ __free_page(page);
+ return;
+
+err_cdev:
+ cdev_del(cdev);
+err_device:
+ put_device(dev);
+err_region:
+ unregister_chrdev_region(devt, 1);
+err:
+ fc->conn_error = 1;
+ goto out;
+}
+
+static int cuse_send_init(struct cuse_conn *cc)
+{
+ int rc;
+ struct fuse_req *req;
+ struct page *page;
+ struct fuse_conn *fc = &cc->fc;
+ struct cuse_init_in *arg;
+
+ BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
+
+ req = fuse_get_req(fc);
+ if (IS_ERR(req)) {
+ rc = PTR_ERR(req);
+ goto err;
+ }
+
+ rc = -ENOMEM;
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page)
+ goto err_put_req;
+
+ arg = &req->misc.cuse_init_in;
+ arg->major = FUSE_KERNEL_VERSION;
+ arg->minor = FUSE_KERNEL_MINOR_VERSION;
+ arg->flags |= CUSE_UNRESTRICTED_IOCTL;
+ req->in.h.opcode = CUSE_INIT;
+ req->in.numargs = 1;
+ req->in.args[0].size = sizeof(struct cuse_init_in);
+ req->in.args[0].value = arg;
+ req->out.numargs = 2;
+ req->out.args[0].size = sizeof(struct cuse_init_out);
+ req->out.args[0].value = &req->misc.cuse_init_out;
+ req->out.args[1].size = CUSE_INIT_INFO_MAX;
+ req->out.argvar = 1;
+ req->out.argpages = 1;
+ req->pages[0] = page;
+ req->num_pages = 1;
+ req->end = cuse_process_init_reply;
+ fuse_request_send_background(fc, req);
+
+ return 0;
+
+err_put_req:
+ fuse_put_request(fc, req);
+err:
+ return rc;
+}
+
+static void cuse_fc_release(struct fuse_conn *fc)
+{
+ struct cuse_conn *cc = fc_to_cc(fc);
+ kfree(cc);
+}
+
+/**
+ * cuse_channel_open - open method for /dev/cuse
+ * @inode: inode for /dev/cuse
+ * @file: file struct being opened
+ *
+ * Userland CUSE server can create a CUSE device by opening /dev/cuse
+ * and replying to the initilaization request kernel sends. This
+ * function is responsible for handling CUSE device initialization.
+ * Because the fd opened by this function is used during
+ * initialization, this function only creates cuse_conn and sends
+ * init. The rest is delegated to a kthread.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int cuse_channel_open(struct inode *inode, struct file *file)
+{
+ struct cuse_conn *cc;
+ int rc;
+
+ /* set up cuse_conn */
+ cc = kzalloc(sizeof(*cc), GFP_KERNEL);
+ if (!cc)
+ return -ENOMEM;
+
+ fuse_conn_init(&cc->fc);
+
+ INIT_LIST_HEAD(&cc->list);
+ cc->fc.release = cuse_fc_release;
+
+ cc->fc.connected = 1;
+ cc->fc.blocked = 0;
+ rc = cuse_send_init(cc);
+ if (rc) {
+ fuse_conn_put(&cc->fc);
+ return rc;
+ }
+ file->private_data = &cc->fc; /* channel owns base reference to cc */
+
+ return 0;
+}
+
+/**
+ * cuse_channel_release - release method for /dev/cuse
+ * @inode: inode for /dev/cuse
+ * @file: file struct being closed
+ *
+ * Disconnect the channel, deregister CUSE device and initiate
+ * destruction by putting the default reference.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int cuse_channel_release(struct inode *inode, struct file *file)
+{
+ struct cuse_conn *cc = fc_to_cc(file->private_data);
+ int rc;
+
+ /* remove from the conntbl, no more access from this point on */
+ spin_lock(&cuse_lock);
+ list_del_init(&cc->list);
+ spin_unlock(&cuse_lock);
+
+ /* remove device */
+ if (cc->dev)
+ device_unregister(cc->dev);
+ if (cc->cdev) {
+ unregister_chrdev_region(cc->cdev->dev, 1);
+ cdev_del(cc->cdev);
+ }
+
+ /* kill connection and shutdown channel */
+ fuse_conn_kill(&cc->fc);
+ rc = fuse_dev_release(inode, file); /* puts the base reference */
+
+ return rc;
+}
+
+static struct file_operations cuse_channel_fops; /* initialized during init */
+
+
+/**************************************************************************
+ * Misc stuff and module initializatiion
+ *
+ * CUSE exports the same set of attributes to sysfs as fusectl.
+ */
+
+static ssize_t cuse_class_waiting_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cuse_conn *cc = dev_get_drvdata(dev);
+
+ return sprintf(buf, "%d\n", atomic_read(&cc->fc.num_waiting));
+}
+
+static ssize_t cuse_class_abort_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cuse_conn *cc = dev_get_drvdata(dev);
+
+ fuse_abort_conn(&cc->fc);
+ return count;
+}
+
+static struct device_attribute cuse_class_dev_attrs[] = {
+ __ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL),
+ __ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store),
+ { }
+};
+
+static struct miscdevice cuse_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "cuse",
+ .fops = &cuse_channel_fops,
+};
+
+static int __init cuse_init(void)
+{
+ int i, rc;
+
+ /* init conntbl */
+ for (i = 0; i < CUSE_CONNTBL_LEN; i++)
+ INIT_LIST_HEAD(&cuse_conntbl[i]);
+
+ /* inherit and extend fuse_dev_operations */
+ cuse_channel_fops = fuse_dev_operations;
+ cuse_channel_fops.owner = THIS_MODULE;
+ cuse_channel_fops.open = cuse_channel_open;
+ cuse_channel_fops.release = cuse_channel_release;
+
+ cuse_class = class_create(THIS_MODULE, "cuse");
+ if (IS_ERR(cuse_class))
+ return PTR_ERR(cuse_class);
+
+ cuse_class->dev_attrs = cuse_class_dev_attrs;
+
+ rc = misc_register(&cuse_miscdev);
+ if (rc) {
+ class_destroy(cuse_class);
+ return rc;
+ }
+
+ return 0;
+}
+
+static void __exit cuse_exit(void)
+{
+ misc_deregister(&cuse_miscdev);
+ class_destroy(cuse_class);
+}
+
+module_init(cuse_init);
+module_exit(cuse_exit);
+
+MODULE_AUTHOR("Tejun Heo <tj@kernel.org>");
+MODULE_DESCRIPTION("Character device in Userspace");
+MODULE_LICENSE("GPL");
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ba76b68c52f..8fed2ed12f3 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -46,6 +46,7 @@ struct fuse_req *fuse_request_alloc(void)
fuse_request_init(req);
return req;
}
+EXPORT_SYMBOL_GPL(fuse_request_alloc);
struct fuse_req *fuse_request_alloc_nofs(void)
{
@@ -124,6 +125,7 @@ struct fuse_req *fuse_get_req(struct fuse_conn *fc)
atomic_dec(&fc->num_waiting);
return ERR_PTR(err);
}
+EXPORT_SYMBOL_GPL(fuse_get_req);
/*
* Return request in fuse_file->reserved_req. However that may
@@ -208,6 +210,7 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
fuse_request_free(req);
}
}
+EXPORT_SYMBOL_GPL(fuse_put_request);
static unsigned len_args(unsigned numargs, struct fuse_arg *args)
{
@@ -282,7 +285,7 @@ __releases(&fc->lock)
wake_up_all(&fc->blocked_waitq);
}
if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
- fc->connected) {
+ fc->connected && fc->bdi_initialized) {
clear_bdi_congested(&fc->bdi, READ);
clear_bdi_congested(&fc->bdi, WRITE);
}
@@ -400,6 +403,7 @@ void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
}
spin_unlock(&fc->lock);
}
+EXPORT_SYMBOL_GPL(fuse_request_send);
static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
struct fuse_req *req)
@@ -408,7 +412,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
fc->num_background++;
if (fc->num_background == FUSE_MAX_BACKGROUND)
fc->blocked = 1;
- if (fc->num_background == FUSE_CONGESTION_THRESHOLD) {
+ if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
+ fc->bdi_initialized) {
set_bdi_congested(&fc->bdi, READ);
set_bdi_congested(&fc->bdi, WRITE);
}
@@ -439,6 +444,7 @@ void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
req->isreply = 1;
fuse_request_send_nowait(fc, req);
}
+EXPORT_SYMBOL_GPL(fuse_request_send_background);
/*
* Called under fc->lock
@@ -1105,8 +1111,9 @@ void fuse_abort_conn(struct fuse_conn *fc)
}
spin_unlock(&fc->lock);
}
+EXPORT_SYMBOL_GPL(fuse_abort_conn);
-static int fuse_dev_release(struct inode *inode, struct file *file)
+int fuse_dev_release(struct inode *inode, struct file *file)
{
struct fuse_conn *fc = fuse_get_conn(file);
if (fc) {
@@ -1120,6 +1127,7 @@ static int fuse_dev_release(struct inode *inode, struct file *file)
return 0;
}
+EXPORT_SYMBOL_GPL(fuse_dev_release);
static int fuse_dev_fasync(int fd, struct file *file, int on)
{
@@ -1142,6 +1150,7 @@ const struct file_operations fuse_dev_operations = {
.release = fuse_dev_release,
.fasync = fuse_dev_fasync,
};
+EXPORT_SYMBOL_GPL(fuse_dev_operations);
static struct miscdevice fuse_miscdevice = {
.minor = FUSE_MINOR,
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 8b8eebc5614..b3089a083d3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -362,19 +362,6 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
}
/*
- * Synchronous release for the case when something goes wrong in CREATE_OPEN
- */
-static void fuse_sync_release(struct fuse_conn *fc, struct fuse_file *ff,
- u64 nodeid, int flags)
-{
- fuse_release_fill(ff, nodeid, flags, FUSE_RELEASE);
- ff->reserved_req->force = 1;
- fuse_request_send(fc, ff->reserved_req);
- fuse_put_request(fc, ff->reserved_req);
- kfree(ff);
-}
-
-/*
* Atomic create+open operation
*
* If the filesystem doesn't support this, then fall back to separate
@@ -445,12 +432,14 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
goto out_free_ff;
fuse_put_request(fc, req);
+ ff->fh = outopen.fh;
+ ff->nodeid = outentry.nodeid;
+ ff->open_flags = outopen.open_flags;
inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
&outentry.attr, entry_attr_timeout(&outentry), 0);
if (!inode) {
flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
- ff->fh = outopen.fh;
- fuse_sync_release(fc, ff, outentry.nodeid, flags);
+ fuse_sync_release(ff, flags);
fuse_send_forget(fc, forget_req, outentry.nodeid, 1);
return -ENOMEM;
}
@@ -460,11 +449,11 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
fuse_invalidate_attr(dir);
file = lookup_instantiate_filp(nd, entry, generic_file_open);
if (IS_ERR(file)) {
- ff->fh = outopen.fh;
- fuse_sync_release(fc, ff, outentry.nodeid, flags);
+ fuse_sync_release(ff, flags);
return PTR_ERR(file);
}
- fuse_finish_open(inode, file, ff, &outopen);
+ file->private_data = fuse_file_get(ff);
+ fuse_finish_open(inode, file);
return 0;
out_free_ff:
@@ -1035,7 +1024,7 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir)
req->out.argpages = 1;
req->num_pages = 1;
req->pages[0] = page;
- fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR);
+ fuse_read_fill(req, file, file->f_pos, PAGE_SIZE, FUSE_READDIR);
fuse_request_send(fc, req);
nbytes = req->out.args[0].size;
err = req->out.h.error;
@@ -1101,12 +1090,14 @@ static void fuse_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
static int fuse_dir_open(struct inode *inode, struct file *file)
{
- return fuse_open_common(inode, file, 1);
+ return fuse_open_common(inode, file, true);
}
static int fuse_dir_release(struct inode *inode, struct file *file)
{
- return fuse_release_common(inode, file, 1);
+ fuse_release_common(file, FUSE_RELEASEDIR);
+
+ return 0;
}
static int fuse_dir_fsync(struct file *file, struct dentry *de, int datasync)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 06f30e96567..fce6ce694fd 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -12,13 +12,13 @@
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/module.h>
static const struct file_operations fuse_direct_io_file_operations;
-static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
- struct fuse_open_out *outargp)
+static int fuse_send_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
+ int opcode, struct fuse_open_out *outargp)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_open_in inarg;
struct fuse_req *req;
int err;
@@ -31,8 +31,8 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
if (!fc->atomic_o_trunc)
inarg.flags &= ~O_TRUNC;
- req->in.h.opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;
- req->in.h.nodeid = get_node_id(inode);
+ req->in.h.opcode = opcode;
+ req->in.h.nodeid = nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
@@ -49,22 +49,27 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir,
struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
{
struct fuse_file *ff;
+
ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
- if (ff) {
- ff->reserved_req = fuse_request_alloc();
- if (!ff->reserved_req) {
- kfree(ff);
- return NULL;
- } else {
- INIT_LIST_HEAD(&ff->write_entry);
- atomic_set(&ff->count, 0);
- spin_lock(&fc->lock);
- ff->kh = ++fc->khctr;
- spin_unlock(&fc->lock);
- }
- RB_CLEAR_NODE(&ff->polled_node);
- init_waitqueue_head(&ff->poll_wait);
+ if (unlikely(!ff))
+ return NULL;
+
+ ff->fc = fc;
+ ff->reserved_req = fuse_request_alloc();
+ if (unlikely(!ff->reserved_req)) {
+ kfree(ff);
+ return NULL;
}
+
+ INIT_LIST_HEAD(&ff->write_entry);
+ atomic_set(&ff->count, 0);
+ RB_CLEAR_NODE(&ff->polled_node);
+ init_waitqueue_head(&ff->poll_wait);
+
+ spin_lock(&fc->lock);
+ ff->kh = ++fc->khctr;
+ spin_unlock(&fc->lock);
+
return ff;
}
@@ -74,7 +79,7 @@ void fuse_file_free(struct fuse_file *ff)
kfree(ff);
}
-static struct fuse_file *fuse_file_get(struct fuse_file *ff)
+struct fuse_file *fuse_file_get(struct fuse_file *ff)
{
atomic_inc(&ff->count);
return ff;
@@ -82,40 +87,65 @@ static struct fuse_file *fuse_file_get(struct fuse_file *ff)
static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
{
- dput(req->misc.release.dentry);
- mntput(req->misc.release.vfsmount);
+ path_put(&req->misc.release.path);
}
static void fuse_file_put(struct fuse_file *ff)
{
if (atomic_dec_and_test(&ff->count)) {
struct fuse_req *req = ff->reserved_req;
- struct inode *inode = req->misc.release.dentry->d_inode;
- struct fuse_conn *fc = get_fuse_conn(inode);
+
req->end = fuse_release_end;
- fuse_request_send_background(fc, req);
+ fuse_request_send_background(ff->fc, req);
kfree(ff);
}
}
-void fuse_finish_open(struct inode *inode, struct file *file,
- struct fuse_file *ff, struct fuse_open_out *outarg)
+int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
+ bool isdir)
{
- if (outarg->open_flags & FOPEN_DIRECT_IO)
+ struct fuse_open_out outarg;
+ struct fuse_file *ff;
+ int err;
+ int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;
+
+ ff = fuse_file_alloc(fc);
+ if (!ff)
+ return -ENOMEM;
+
+ err = fuse_send_open(fc, nodeid, file, opcode, &outarg);
+ if (err) {
+ fuse_file_free(ff);
+ return err;
+ }
+
+ if (isdir)
+ outarg.open_flags &= ~FOPEN_DIRECT_IO;
+
+ ff->fh = outarg.fh;
+ ff->nodeid = nodeid;
+ ff->open_flags = outarg.open_flags;
+ file->private_data = fuse_file_get(ff);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fuse_do_open);
+
+void fuse_finish_open(struct inode *inode, struct file *file)
+{
+ struct fuse_file *ff = file->private_data;
+
+ if (ff->open_flags & FOPEN_DIRECT_IO)
file->f_op = &fuse_direct_io_file_operations;
- if (!(outarg->open_flags & FOPEN_KEEP_CACHE))
+ if (!(ff->open_flags & FOPEN_KEEP_CACHE))
invalidate_inode_pages2(inode->i_mapping);
- if (outarg->open_flags & FOPEN_NONSEEKABLE)
+ if (ff->open_flags & FOPEN_NONSEEKABLE)
nonseekable_open(inode, file);
- ff->fh = outarg->fh;
- file->private_data = fuse_file_get(ff);
}
-int fuse_open_common(struct inode *inode, struct file *file, int isdir)
+int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
{
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_open_out outarg;
- struct fuse_file *ff;
int err;
/* VFS checks this, but only _after_ ->open() */
@@ -126,78 +156,85 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir)
if (err)
return err;
- ff = fuse_file_alloc(fc);
- if (!ff)
- return -ENOMEM;
-
- err = fuse_send_open(inode, file, isdir, &outarg);
+ err = fuse_do_open(fc, get_node_id(inode), file, isdir);
if (err)
- fuse_file_free(ff);
- else {
- if (isdir)
- outarg.open_flags &= ~FOPEN_DIRECT_IO;
- fuse_finish_open(inode, file, ff, &outarg);
- }
+ return err;
- return err;
+ fuse_finish_open(inode, file);
+
+ return 0;
}
-void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode)
+static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode)
{
+ struct fuse_conn *fc = ff->fc;
struct fuse_req *req = ff->reserved_req;
struct fuse_release_in *inarg = &req->misc.release.in;
+ spin_lock(&fc->lock);
+ list_del(&ff->write_entry);
+ if (!RB_EMPTY_NODE(&ff->polled_node))
+ rb_erase(&ff->polled_node, &fc->polled_files);
+ spin_unlock(&fc->lock);
+
+ wake_up_interruptible_sync(&ff->poll_wait);
+
inarg->fh = ff->fh;
inarg->flags = flags;
req->in.h.opcode = opcode;
- req->in.h.nodeid = nodeid;
+ req->in.h.nodeid = ff->nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(struct fuse_release_in);
req->in.args[0].value = inarg;
}
-int fuse_release_common(struct inode *inode, struct file *file, int isdir)
+void fuse_release_common(struct file *file, int opcode)
{
- struct fuse_file *ff = file->private_data;
- if (ff) {
- struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_req *req = ff->reserved_req;
-
- fuse_release_fill(ff, get_node_id(inode), file->f_flags,
- isdir ? FUSE_RELEASEDIR : FUSE_RELEASE);
+ struct fuse_file *ff;
+ struct fuse_req *req;
- /* Hold vfsmount and dentry until release is finished */
- req->misc.release.vfsmount = mntget(file->f_path.mnt);
- req->misc.release.dentry = dget(file->f_path.dentry);
+ ff = file->private_data;
+ if (unlikely(!ff))
+ return;
- spin_lock(&fc->lock);
- list_del(&ff->write_entry);
- if (!RB_EMPTY_NODE(&ff->polled_node))
- rb_erase(&ff->polled_node, &fc->polled_files);
- spin_unlock(&fc->lock);
+ req = ff->reserved_req;
+ fuse_prepare_release(ff, file->f_flags, opcode);
- wake_up_interruptible_sync(&ff->poll_wait);
- /*
- * Normally this will send the RELEASE request,
- * however if some asynchronous READ or WRITE requests
- * are outstanding, the sending will be delayed
- */
- fuse_file_put(ff);
- }
+ /* Hold vfsmount and dentry until release is finished */
+ path_get(&file->f_path);
+ req->misc.release.path = file->f_path;
- /* Return value is ignored by VFS */
- return 0;
+ /*
+ * Normally this will send the RELEASE request, however if
+ * some asynchronous READ or WRITE requests are outstanding,
+ * the sending will be delayed.
+ */
+ fuse_file_put(ff);
}
static int fuse_open(struct inode *inode, struct file *file)
{
- return fuse_open_common(inode, file, 0);
+ return fuse_open_common(inode, file, false);
}
static int fuse_release(struct inode *inode, struct file *file)
{
- return fuse_release_common(inode, file, 0);
+ fuse_release_common(file, FUSE_RELEASE);
+
+ /* return value is ignored by VFS */
+ return 0;
+}
+
+void fuse_sync_release(struct fuse_file *ff, int flags)
+{
+ WARN_ON(atomic_read(&ff->count) > 1);
+ fuse_prepare_release(ff, flags, FUSE_RELEASE);
+ ff->reserved_req->force = 1;
+ fuse_request_send(ff->fc, ff->reserved_req);
+ fuse_put_request(ff->fc, ff->reserved_req);
+ kfree(ff);
}
+EXPORT_SYMBOL_GPL(fuse_sync_release);
/*
* Scramble the ID space with XTEA, so that the value of the files_struct
@@ -371,8 +408,8 @@ static int fuse_fsync(struct file *file, struct dentry *de, int datasync)
return fuse_fsync_common(file, de, datasync, 0);
}
-void fuse_read_fill(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count, int opcode)
+void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
+ size_t count, int opcode)
{
struct fuse_read_in *inarg = &req->misc.read.in;
struct fuse_file *ff = file->private_data;
@@ -382,7 +419,7 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
inarg->size = count;
inarg->flags = file->f_flags;
req->in.h.opcode = opcode;
- req->in.h.nodeid = get_node_id(inode);
+ req->in.h.nodeid = ff->nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(struct fuse_read_in);
req->in.args[0].value = inarg;
@@ -392,12 +429,12 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
}
static size_t fuse_send_read(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count,
- fl_owner_t owner)
+ loff_t pos, size_t count, fl_owner_t owner)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
- fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ fuse_read_fill(req, file, pos, count, FUSE_READ);
if (owner != NULL) {
struct fuse_read_in *inarg = &req->misc.read.in;
@@ -455,7 +492,7 @@ static int fuse_readpage(struct file *file, struct page *page)
req->out.argpages = 1;
req->num_pages = 1;
req->pages[0] = page;
- num_read = fuse_send_read(req, file, inode, pos, count, NULL);
+ num_read = fuse_send_read(req, file, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
@@ -504,19 +541,18 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
fuse_file_put(req->ff);
}
-static void fuse_send_readpages(struct fuse_req *req, struct file *file,
- struct inode *inode)
+static void fuse_send_readpages(struct fuse_req *req, struct file *file)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
loff_t pos = page_offset(req->pages[0]);
size_t count = req->num_pages << PAGE_CACHE_SHIFT;
req->out.argpages = 1;
req->out.page_zeroing = 1;
- fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
+ fuse_read_fill(req, file, pos, count, FUSE_READ);
req->misc.read.attr_ver = fuse_get_attr_version(fc);
if (fc->async_read) {
- struct fuse_file *ff = file->private_data;
req->ff = fuse_file_get(ff);
req->end = fuse_readpages_end;
fuse_request_send_background(fc, req);
@@ -546,7 +582,7 @@ static int fuse_readpages_fill(void *_data, struct page *page)
(req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
(req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read ||
req->pages[req->num_pages - 1]->index + 1 != page->index)) {
- fuse_send_readpages(req, data->file, inode);
+ fuse_send_readpages(req, data->file);
data->req = req = fuse_get_req(fc);
if (IS_ERR(req)) {
unlock_page(page);
@@ -580,7 +616,7 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
if (!err) {
if (data.req->num_pages)
- fuse_send_readpages(data.req, file, inode);
+ fuse_send_readpages(data.req, file);
else
fuse_put_request(fc, data.req);
}
@@ -607,24 +643,19 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
return generic_file_aio_read(iocb, iov, nr_segs, pos);
}
-static void fuse_write_fill(struct fuse_req *req, struct file *file,
- struct fuse_file *ff, struct inode *inode,
- loff_t pos, size_t count, int writepage)
+static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff,
+ loff_t pos, size_t count)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_write_in *inarg = &req->misc.write.in;
struct fuse_write_out *outarg = &req->misc.write.out;
- memset(inarg, 0, sizeof(struct fuse_write_in));
inarg->fh = ff->fh;
inarg->offset = pos;
inarg->size = count;
- inarg->write_flags = writepage ? FUSE_WRITE_CACHE : 0;
- inarg->flags = file ? file->f_flags : 0;
req->in.h.opcode = FUSE_WRITE;
- req->in.h.nodeid = get_node_id(inode);
+ req->in.h.nodeid = ff->nodeid;
req->in.numargs = 2;
- if (fc->minor < 9)
+ if (ff->fc->minor < 9)
req->in.args[0].size = FUSE_COMPAT_WRITE_IN_SIZE;
else
req->in.args[0].size = sizeof(struct fuse_write_in);
@@ -636,13 +667,15 @@ static void fuse_write_fill(struct fuse_req *req, struct file *file,
}
static size_t fuse_send_write(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count,
- fl_owner_t owner)
+ loff_t pos, size_t count, fl_owner_t owner)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
- fuse_write_fill(req, file, file->private_data, inode, pos, count, 0);
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
+ struct fuse_write_in *inarg = &req->misc.write.in;
+
+ fuse_write_fill(req, ff, pos, count);
+ inarg->flags = file->f_flags;
if (owner != NULL) {
- struct fuse_write_in *inarg = &req->misc.write.in;
inarg->write_flags |= FUSE_WRITE_LOCKOWNER;
inarg->lock_owner = fuse_lock_owner_id(fc, owner);
}
@@ -700,7 +733,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode,
req->num_pages = 1;
req->pages[0] = page;
req->page_offset = offset;
- nres = fuse_send_write(req, file, inode, pos, count, NULL);
+ nres = fuse_send_write(req, file, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
if (!err && !nres)
@@ -741,7 +774,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
for (i = 0; i < req->num_pages; i++)
fuse_wait_on_page_writeback(inode, req->pages[i]->index);
- res = fuse_send_write(req, file, inode, pos, count, NULL);
+ res = fuse_send_write(req, file, pos, count, NULL);
offset = req->page_offset;
count = res;
@@ -979,25 +1012,23 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
return 0;
}
-static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos, int write)
+ssize_t fuse_direct_io(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos, int write)
{
- struct inode *inode = file->f_path.dentry->d_inode;
- struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
size_t nmax = write ? fc->max_write : fc->max_read;
loff_t pos = *ppos;
ssize_t res = 0;
struct fuse_req *req;
- if (is_bad_inode(inode))
- return -EIO;
-
req = fuse_get_req(fc);
if (IS_ERR(req))
return PTR_ERR(req);
while (count) {
size_t nres;
+ fl_owner_t owner = current->files;
size_t nbytes = min(count, nmax);
int err = fuse_get_user_pages(req, buf, &nbytes, write);
if (err) {
@@ -1006,11 +1037,10 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
}
if (write)
- nres = fuse_send_write(req, file, inode, pos, nbytes,
- current->files);
+ nres = fuse_send_write(req, file, pos, nbytes, owner);
else
- nres = fuse_send_read(req, file, inode, pos, nbytes,
- current->files);
+ nres = fuse_send_read(req, file, pos, nbytes, owner);
+
fuse_release_user_pages(req, !write);
if (req->out.h.error) {
if (!res)
@@ -1034,20 +1064,27 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
}
}
fuse_put_request(fc, req);
- if (res > 0) {
- if (write)
- fuse_write_update_size(inode, pos);
+ if (res > 0)
*ppos = pos;
- }
- fuse_invalidate_attr(inode);
return res;
}
+EXPORT_SYMBOL_GPL(fuse_direct_io);
static ssize_t fuse_direct_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
- return fuse_direct_io(file, buf, count, ppos, 0);
+ ssize_t res;
+ struct inode *inode = file->f_path.dentry->d_inode;
+
+ if (is_bad_inode(inode))
+ return -EIO;
+
+ res = fuse_direct_io(file, buf, count, ppos, 0);
+
+ fuse_invalidate_attr(inode);
+
+ return res;
}
static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
@@ -1055,12 +1092,22 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
{
struct inode *inode = file->f_path.dentry->d_inode;
ssize_t res;
+
+ if (is_bad_inode(inode))
+ return -EIO;
+
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
res = generic_write_checks(file, ppos, &count, 0);
- if (!res)
+ if (!res) {
res = fuse_direct_io(file, buf, count, ppos, 1);
+ if (res > 0)
+ fuse_write_update_size(inode, *ppos);
+ }
mutex_unlock(&inode->i_mutex);
+
+ fuse_invalidate_attr(inode);
+
return res;
}
@@ -1177,9 +1224,10 @@ static int fuse_writepage_locked(struct page *page)
req->ff = fuse_file_get(ff);
spin_unlock(&fc->lock);
- fuse_write_fill(req, NULL, ff, inode, page_offset(page), 0, 1);
+ fuse_write_fill(req, ff, page_offset(page), 0);
copy_highpage(tmp_page, page);
+ req->misc.write.in.write_flags |= FUSE_WRITE_CACHE;
req->in.argpages = 1;
req->num_pages = 1;
req->pages[0] = tmp_page;
@@ -1603,12 +1651,11 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
* limits ioctl data transfers to well-formed ioctls and is the forced
* behavior for all FUSE servers.
*/
-static long fuse_file_do_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg, unsigned int flags)
+long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
+ unsigned int flags)
{
- struct inode *inode = file->f_dentry->d_inode;
struct fuse_file *ff = file->private_data;
- struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_conn *fc = ff->fc;
struct fuse_ioctl_in inarg = {
.fh = ff->fh,
.cmd = cmd,
@@ -1627,13 +1674,6 @@ static long fuse_file_do_ioctl(struct file *file, unsigned int cmd,
/* assume all the iovs returned by client always fits in a page */
BUILD_BUG_ON(sizeof(struct iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
- if (!fuse_allow_task(fc, current))
- return -EACCES;
-
- err = -EIO;
- if (is_bad_inode(inode))
- goto out;
-
err = -ENOMEM;
pages = kzalloc(sizeof(pages[0]) * FUSE_MAX_PAGES_PER_REQ, GFP_KERNEL);
iov_page = alloc_page(GFP_KERNEL);
@@ -1694,7 +1734,7 @@ static long fuse_file_do_ioctl(struct file *file, unsigned int cmd,
/* okay, let's send it to the client */
req->in.h.opcode = FUSE_IOCTL;
- req->in.h.nodeid = get_node_id(inode);
+ req->in.h.nodeid = ff->nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
@@ -1777,17 +1817,33 @@ static long fuse_file_do_ioctl(struct file *file, unsigned int cmd,
return err ? err : outarg.result;
}
+EXPORT_SYMBOL_GPL(fuse_do_ioctl);
+
+static long fuse_file_ioctl_common(struct file *file, unsigned int cmd,
+ unsigned long arg, unsigned int flags)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (!fuse_allow_task(fc, current))
+ return -EACCES;
+
+ if (is_bad_inode(inode))
+ return -EIO;
+
+ return fuse_do_ioctl(file, cmd, arg, flags);
+}
static long fuse_file_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- return fuse_file_do_ioctl(file, cmd, arg, 0);
+ return fuse_file_ioctl_common(file, cmd, arg, 0);
}
static long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- return fuse_file_do_ioctl(file, cmd, arg, FUSE_IOCTL_COMPAT);
+ return fuse_file_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT);
}
/*
@@ -1841,11 +1897,10 @@ static void fuse_register_polled_file(struct fuse_conn *fc,
spin_unlock(&fc->lock);
}
-static unsigned fuse_file_poll(struct file *file, poll_table *wait)
+unsigned fuse_file_poll(struct file *file, poll_table *wait)
{
- struct inode *inode = file->f_dentry->d_inode;
struct fuse_file *ff = file->private_data;
- struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_conn *fc = ff->fc;
struct fuse_poll_in inarg = { .fh = ff->fh, .kh = ff->kh };
struct fuse_poll_out outarg;
struct fuse_req *req;
@@ -1870,7 +1925,7 @@ static unsigned fuse_file_poll(struct file *file, poll_table *wait)
return PTR_ERR(req);
req->in.h.opcode = FUSE_POLL;
- req->in.h.nodeid = get_node_id(inode);
+ req->in.h.nodeid = ff->nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
@@ -1889,6 +1944,7 @@ static unsigned fuse_file_poll(struct file *file, poll_table *wait)
}
return POLLERR;
}
+EXPORT_SYMBOL_GPL(fuse_file_poll);
/*
* This is called from fuse_handle_notify() on FUSE_NOTIFY_POLL and
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6fc5aedaa0d..aaf2f9ff970 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -97,8 +97,13 @@ struct fuse_inode {
struct list_head writepages;
};
+struct fuse_conn;
+
/** FUSE specific file data */
struct fuse_file {
+ /** Fuse connection for this file */
+ struct fuse_conn *fc;
+
/** Request reserved for flush and release */
struct fuse_req *reserved_req;
@@ -108,9 +113,15 @@ struct fuse_file {
/** File handle used by userspace */
u64 fh;
+ /** Node id of this file */
+ u64 nodeid;
+
/** Refcount */
atomic_t count;
+ /** FOPEN_* flags returned by open */
+ u32 open_flags;
+
/** Entry on inode's write_files list */
struct list_head write_entry;
@@ -185,8 +196,6 @@ enum fuse_req_state {
FUSE_REQ_FINISHED
};
-struct fuse_conn;
-
/**
* A request to the client
*/
@@ -248,11 +257,12 @@ struct fuse_req {
struct fuse_forget_in forget_in;
struct {
struct fuse_release_in in;
- struct vfsmount *vfsmount;
- struct dentry *dentry;
+ struct path path;
} release;
struct fuse_init_in init_in;
struct fuse_init_out init_out;
+ struct cuse_init_in cuse_init_in;
+ struct cuse_init_out cuse_init_out;
struct {
struct fuse_read_in in;
u64 attr_ver;
@@ -386,6 +396,9 @@ struct fuse_conn {
/** Filesystem supports NFS exporting. Only set in INIT */
unsigned export_support:1;
+ /** Set if bdi is valid */
+ unsigned bdi_initialized:1;
+
/*
* The following bitfields are only for optimization purposes
* and hence races in setting them will not cause malfunction
@@ -515,25 +528,24 @@ void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req,
* Initialize READ or READDIR request
*/
void fuse_read_fill(struct fuse_req *req, struct file *file,
- struct inode *inode, loff_t pos, size_t count, int opcode);
+ loff_t pos, size_t count, int opcode);
/**
* Send OPEN or OPENDIR request
*/
-int fuse_open_common(struct inode *inode, struct file *file, int isdir);
+int fuse_open_common(struct inode *inode, struct file *file, bool isdir);
struct fuse_file *fuse_file_alloc(struct fuse_conn *fc);
+struct fuse_file *fuse_file_get(struct fuse_file *ff);
void fuse_file_free(struct fuse_file *ff);
-void fuse_finish_open(struct inode *inode, struct file *file,
- struct fuse_file *ff, struct fuse_open_out *outarg);
+void fuse_finish_open(struct inode *inode, struct file *file);
-/** Fill in ff->reserved_req with a RELEASE request */
-void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode);
+void fuse_sync_release(struct fuse_file *ff, int flags);
/**
* Send RELEASE or RELEASEDIR request
*/
-int fuse_release_common(struct inode *inode, struct file *file, int isdir);
+void fuse_release_common(struct file *file, int opcode);
/**
* Send FSYNC or FSYNCDIR request
@@ -652,10 +664,12 @@ void fuse_invalidate_entry_cache(struct dentry *entry);
*/
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);
+void fuse_conn_kill(struct fuse_conn *fc);
+
/**
* Initialize fuse_conn
*/
-int fuse_conn_init(struct fuse_conn *fc, struct super_block *sb);
+void fuse_conn_init(struct fuse_conn *fc);
/**
* Release reference to fuse_conn
@@ -694,4 +708,13 @@ void fuse_release_nowrite(struct inode *inode);
u64 fuse_get_attr_version(struct fuse_conn *fc);
+int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
+ bool isdir);
+ssize_t fuse_direct_io(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos, int write);
+long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
+ unsigned int flags);
+unsigned fuse_file_poll(struct file *file, poll_table *wait);
+int fuse_dev_release(struct inode *inode, struct file *file);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 91f7c85f1ff..f0df55a5292 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -277,11 +277,14 @@ static void fuse_send_destroy(struct fuse_conn *fc)
}
}
-static void fuse_put_super(struct super_block *sb)
+static void fuse_bdi_destroy(struct fuse_conn *fc)
{
- struct fuse_conn *fc = get_fuse_conn_super(sb);
+ if (fc->bdi_initialized)
+ bdi_destroy(&fc->bdi);
+}
- fuse_send_destroy(fc);
+void fuse_conn_kill(struct fuse_conn *fc)
+{
spin_lock(&fc->lock);
fc->connected = 0;
fc->blocked = 0;
@@ -295,7 +298,16 @@ static void fuse_put_super(struct super_block *sb)
list_del(&fc->entry);
fuse_ctl_remove_conn(fc);
mutex_unlock(&fuse_mutex);
- bdi_destroy(&fc->bdi);
+ fuse_bdi_destroy(fc);
+}
+EXPORT_SYMBOL_GPL(fuse_conn_kill);
+
+static void fuse_put_super(struct super_block *sb)
+{
+ struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+ fuse_send_destroy(fc);
+ fuse_conn_kill(fc);
fuse_conn_put(fc);
}
@@ -466,10 +478,8 @@ static int fuse_show_options(struct seq_file *m, struct vfsmount *mnt)
return 0;
}
-int fuse_conn_init(struct fuse_conn *fc, struct super_block *sb)
+void fuse_conn_init(struct fuse_conn *fc)
{
- int err;
-
memset(fc, 0, sizeof(*fc));
spin_lock_init(&fc->lock);
mutex_init(&fc->inst_mutex);
@@ -484,49 +494,12 @@ int fuse_conn_init(struct fuse_conn *fc, struct super_block *sb)
INIT_LIST_HEAD(&fc->bg_queue);
INIT_LIST_HEAD(&fc->entry);
atomic_set(&fc->num_waiting, 0);
- fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- fc->bdi.unplug_io_fn = default_unplug_io_fn;
- /* fuse does it's own writeback accounting */
- fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
fc->khctr = 0;
fc->polled_files = RB_ROOT;
- fc->dev = sb->s_dev;
- err = bdi_init(&fc->bdi);
- if (err)
- goto error_mutex_destroy;
- if (sb->s_bdev) {
- err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
- MAJOR(fc->dev), MINOR(fc->dev));
- } else {
- err = bdi_register_dev(&fc->bdi, fc->dev);
- }
- if (err)
- goto error_bdi_destroy;
- /*
- * For a single fuse filesystem use max 1% of dirty +
- * writeback threshold.
- *
- * This gives about 1M of write buffer for memory maps on a
- * machine with 1G and 10% dirty_ratio, which should be more
- * than enough.
- *
- * Privileged users can raise it by writing to
- *
- * /sys/class/bdi/<bdi>/max_ratio
- */
- bdi_set_max_ratio(&fc->bdi, 1);
fc->reqctr = 0;
fc->blocked = 1;
fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
-
- return 0;
-
- error_bdi_destroy:
- bdi_destroy(&fc->bdi);
- error_mutex_destroy:
- mutex_destroy(&fc->inst_mutex);
- return err;
}
EXPORT_SYMBOL_GPL(fuse_conn_init);
@@ -539,12 +512,14 @@ void fuse_conn_put(struct fuse_conn *fc)
fc->release(fc);
}
}
+EXPORT_SYMBOL_GPL(fuse_conn_put);
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
{
atomic_inc(&fc->count);
return fc;
}
+EXPORT_SYMBOL_GPL(fuse_conn_get);
static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
{
@@ -797,6 +772,48 @@ static void fuse_free_conn(struct fuse_conn *fc)
kfree(fc);
}
+static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
+{
+ int err;
+
+ fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ fc->bdi.unplug_io_fn = default_unplug_io_fn;
+ /* fuse does it's own writeback accounting */
+ fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB;
+
+ err = bdi_init(&fc->bdi);
+ if (err)
+ return err;
+
+ fc->bdi_initialized = 1;
+
+ if (sb->s_bdev) {
+ err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
+ MAJOR(fc->dev), MINOR(fc->dev));
+ } else {
+ err = bdi_register_dev(&fc->bdi, fc->dev);
+ }
+
+ if (err)
+ return err;
+
+ /*
+ * For a single fuse filesystem use max 1% of dirty +
+ * writeback threshold.
+ *
+ * This gives about 1M of write buffer for memory maps on a
+ * machine with 1G and 10% dirty_ratio, which should be more
+ * than enough.
+ *
+ * Privileged users can raise it by writing to
+ *
+ * /sys/class/bdi/<bdi>/max_ratio
+ */
+ bdi_set_max_ratio(&fc->bdi, 1);
+
+ return 0;
+}
+
static int fuse_fill_super(struct super_block *sb, void *data, int silent)
{
struct fuse_conn *fc;
@@ -843,11 +860,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
if (!fc)
goto err_fput;
- err = fuse_conn_init(fc, sb);
- if (err) {
- kfree(fc);
- goto err_fput;
- }
+ fuse_conn_init(fc);
+
+ fc->dev = sb->s_dev;
+ err = fuse_bdi_init(fc, sb);
+ if (err)
+ goto err_put_conn;
fc->release = fuse_free_conn;
fc->flags = d.flags;
@@ -911,7 +929,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
err_put_root:
dput(root_dentry);
err_put_conn:
- bdi_destroy(&fc->bdi);
+ fuse_bdi_destroy(fc);
fuse_conn_put(fc);
err_fput:
fput(file);
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index d53a9bea1c2..3da2f1f4f73 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,3 +1,4 @@
+EXTRA_CFLAGS := -I$(src)
obj-$(CONFIG_GFS2_FS) += gfs2.o
gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
glops.o inode.o log.o lops.o main.o meta_io.o \
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 329763530dc..6d47379e794 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -25,6 +25,7 @@
#include "trans.h"
#include "dir.h"
#include "util.h"
+#include "trace_gfs2.h"
/* This doesn't need to be that large as max 64 bit pointers in a 4k
* block is 512, so __u16 is fine for that. It saves stack space to
@@ -589,6 +590,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
clear_buffer_mapped(bh_map);
clear_buffer_new(bh_map);
clear_buffer_boundary(bh_map);
+ trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
if (gfs2_is_dir(ip)) {
bsize = sdp->sd_jbsize;
arr = sdp->sd_jheightsize;
@@ -623,6 +625,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
ret = 0;
out:
release_metapath(&mp);
+ trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
bmap_unlock(ip, create);
return ret;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2bf62bcc518..297421c0427 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -39,6 +39,8 @@
#include "super.h"
#include "util.h"
#include "bmap.h"
+#define CREATE_TRACE_POINTS
+#include "trace_gfs2.h"
struct gfs2_gl_hash_bucket {
struct hlist_head hb_list;
@@ -155,7 +157,7 @@ static void glock_free(struct gfs2_glock *gl)
if (aspace)
gfs2_aspace_put(aspace);
-
+ trace_gfs2_glock_put(gl);
sdp->sd_lockstruct.ls_ops->lm_put_lock(gfs2_glock_cachep, gl);
}
@@ -317,14 +319,17 @@ restart:
return 2;
gh->gh_error = ret;
list_del_init(&gh->gh_list);
+ trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
+ trace_gfs2_promote(gh, 1);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
+ trace_gfs2_promote(gh, 0);
gfs2_holder_wake(gh);
continue;
}
@@ -354,6 +359,7 @@ static inline void do_error(struct gfs2_glock *gl, const int ret)
else
continue;
list_del_init(&gh->gh_list);
+ trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
}
}
@@ -422,6 +428,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
int rv;
spin_lock(&gl->gl_spin);
+ trace_gfs2_glock_state_change(gl, state);
state_change(gl, state);
gh = find_first_waiter(gl);
@@ -851,6 +858,7 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
gl->gl_demote_state != state) {
gl->gl_demote_state = LM_ST_UNLOCKED;
}
+ trace_gfs2_demote_rq(gl);
}
/**
@@ -936,6 +944,7 @@ fail:
goto do_cancel;
return;
}
+ trace_gfs2_glock_queue(gh, 1);
list_add_tail(&gh->gh_list, insert_pt);
do_cancel:
gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
@@ -1032,6 +1041,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
!test_bit(GLF_DEMOTE, &gl->gl_flags))
fast_path = 1;
}
+ trace_gfs2_glock_queue(gh, 0);
spin_unlock(&gl->gl_spin);
if (likely(fast_path))
return;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f2e449c595b..13c6237c5f6 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -28,6 +28,7 @@
#include "meta_io.h"
#include "util.h"
#include "dir.h"
+#include "trace_gfs2.h"
#define PULL 1
@@ -313,6 +314,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
gfs2_log_lock(sdp);
}
atomic_sub(blks, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, -blks);
gfs2_log_unlock(sdp);
mutex_unlock(&sdp->sd_log_reserve_mutex);
@@ -333,6 +335,7 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
gfs2_log_lock(sdp);
atomic_add(blks, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, blks);
gfs2_assert_withdraw(sdp,
atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
@@ -558,6 +561,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
gfs2_log_lock(sdp);
atomic_add(dist, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, dist);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
gfs2_log_unlock(sdp);
@@ -715,6 +719,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
up_write(&sdp->sd_log_flush_lock);
return;
}
+ trace_gfs2_log_flush(sdp, 1);
ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ai->ai_ail1_list);
@@ -746,6 +751,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
gfs2_log_lock(sdp);
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+ trace_gfs2_log_blocks(sdp, -1);
gfs2_log_unlock(sdp);
log_write_header(sdp, 0, PULL);
}
@@ -763,7 +769,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
ai = NULL;
}
gfs2_log_unlock(sdp);
-
+ trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
kfree(ai);
@@ -787,6 +793,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
atomic_add(unused, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, unused);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 00315f50fa4..9969ff062c5 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -27,6 +27,7 @@
#include "rgrp.h"
#include "trans.h"
#include "util.h"
+#include "trace_gfs2.h"
/**
* gfs2_pin - Pin a buffer in memory
@@ -53,6 +54,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
if (bd->bd_ail)
list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
get_bh(bh);
+ trace_gfs2_pin(bd, 1);
}
/**
@@ -89,6 +91,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
bd->bd_ail = ai;
list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+ trace_gfs2_pin(bd, 0);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index cc34f271b3e..7bc3c45cd67 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -33,6 +33,7 @@
#include "log.h"
#include "quota.h"
#include "dir.h"
+#include "trace_gfs2.h"
#define DO 0
#define UNDO 1
@@ -775,6 +776,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
/* Map the extents for this journal's blocks */
map_journal_extents(sdp);
}
+ trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free));
if (sdp->sd_lockstruct.ls_first) {
unsigned int x;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index de3239731db..daa4ae341a2 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -29,6 +29,7 @@
#include "util.h"
#include "log.h"
#include "inode.h"
+#include "trace_gfs2.h"
#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)
@@ -1519,7 +1520,7 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone -= *n;
spin_unlock(&sdp->sd_rindex_spin);
-
+ trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED);
*bn = block;
return 0;
@@ -1571,7 +1572,7 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone--;
spin_unlock(&sdp->sd_rindex_spin);
-
+ trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
return block;
}
@@ -1591,7 +1592,7 @@ void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
-
+ trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
@@ -1619,7 +1620,7 @@ void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
-
+ trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
@@ -1642,6 +1643,7 @@ void gfs2_unlink_di(struct inode *inode)
rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED);
if (!rgd)
return;
+ trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED);
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_trans_add_rg(rgd);
@@ -1673,6 +1675,7 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
{
gfs2_free_uninit_di(rgd, ip->i_no_addr);
+ trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE);
gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid);
gfs2_meta_wipe(ip, ip->i_no_addr, 1);
}
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index c8930b31cdf..0a680133647 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -719,8 +719,6 @@ static void gfs2_put_super(struct super_block *sb)
int error;
struct gfs2_jdesc *jd;
- lock_kernel();
-
/* Unfreeze the filesystem, if we need to */
mutex_lock(&sdp->sd_freeze_lock);
@@ -787,8 +785,6 @@ restart:
/* At this point, we're through participating in the lockspace */
gfs2_sys_fs_del(sdp);
-
- unlock_kernel();
}
/**
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
new file mode 100644
index 00000000000..98d6ef1c1dc
--- /dev/null
+++ b/fs/gfs2/trace_gfs2.h
@@ -0,0 +1,407 @@
+#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GFS2_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gfs2
+#define TRACE_INCLUDE_FILE trace_gfs2
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/dlmconstants.h>
+#include <linux/gfs2_ondisk.h>
+#include "incore.h"
+#include "glock.h"
+
+#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn }
+#define glock_trace_name(x) __print_symbolic(x, \
+ dlm_state_name(IV), \
+ dlm_state_name(NL), \
+ dlm_state_name(CR), \
+ dlm_state_name(CW), \
+ dlm_state_name(PR), \
+ dlm_state_name(PW), \
+ dlm_state_name(EX))
+
+#define block_state_name(x) __print_symbolic(x, \
+ { GFS2_BLKST_FREE, "free" }, \
+ { GFS2_BLKST_USED, "used" }, \
+ { GFS2_BLKST_DINODE, "dinode" }, \
+ { GFS2_BLKST_UNLINKED, "unlinked" })
+
+#define show_glock_flags(flags) __print_flags(flags, "", \
+ {(1UL << GLF_LOCK), "l" }, \
+ {(1UL << GLF_DEMOTE), "D" }, \
+ {(1UL << GLF_PENDING_DEMOTE), "d" }, \
+ {(1UL << GLF_DEMOTE_IN_PROGRESS), "p" }, \
+ {(1UL << GLF_DIRTY), "y" }, \
+ {(1UL << GLF_LFLUSH), "f" }, \
+ {(1UL << GLF_INVALIDATE_IN_PROGRESS), "i" }, \
+ {(1UL << GLF_REPLY_PENDING), "r" }, \
+ {(1UL << GLF_INITIAL), "I" }, \
+ {(1UL << GLF_FROZEN), "F" })
+
+#ifndef NUMPTY
+#define NUMPTY
+static inline u8 glock_trace_state(unsigned int state)
+{
+ switch(state) {
+ case LM_ST_SHARED:
+ return DLM_LOCK_PR;
+ case LM_ST_DEFERRED:
+ return DLM_LOCK_CW;
+ case LM_ST_EXCLUSIVE:
+ return DLM_LOCK_EX;
+ }
+ return DLM_LOCK_NL;
+}
+#endif
+
+/* Section 1 - Locking
+ *
+ * Objectives:
+ * Latency: Remote demote request to state change
+ * Latency: Local lock request to state change
+ * Latency: State change to lock grant
+ * Correctness: Ordering of local lock state vs. I/O requests
+ * Correctness: Responses to remote demote requests
+ */
+
+/* General glock state change (DLM lock request completes) */
+TRACE_EVENT(gfs2_glock_state_change,
+
+ TP_PROTO(const struct gfs2_glock *gl, unsigned int new_state),
+
+ TP_ARGS(gl, new_state),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( u8, cur_state )
+ __field( u8, new_state )
+ __field( u8, dmt_state )
+ __field( u8, tgt_state )
+ __field( unsigned long, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gl->gl_sbd->sd_vfs->s_dev;
+ __entry->glnum = gl->gl_name.ln_number;
+ __entry->gltype = gl->gl_name.ln_type;
+ __entry->cur_state = glock_trace_state(gl->gl_state);
+ __entry->new_state = glock_trace_state(new_state);
+ __entry->tgt_state = glock_trace_state(gl->gl_target);
+ __entry->dmt_state = glock_trace_state(gl->gl_demote_state);
+ __entry->flags = gl->gl_flags;
+ ),
+
+ TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+ (unsigned long long)__entry->glnum,
+ glock_trace_name(__entry->cur_state),
+ glock_trace_name(__entry->new_state),
+ glock_trace_name(__entry->tgt_state),
+ glock_trace_name(__entry->dmt_state),
+ show_glock_flags(__entry->flags))
+);
+
+/* State change -> unlocked, glock is being deallocated */
+TRACE_EVENT(gfs2_glock_put,
+
+ TP_PROTO(const struct gfs2_glock *gl),
+
+ TP_ARGS(gl),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( u8, cur_state )
+ __field( unsigned long, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gl->gl_sbd->sd_vfs->s_dev;
+ __entry->gltype = gl->gl_name.ln_type;
+ __entry->glnum = gl->gl_name.ln_number;
+ __entry->cur_state = glock_trace_state(gl->gl_state);
+ __entry->flags = gl->gl_flags;
+ ),
+
+ TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->gltype, (unsigned long long)__entry->glnum,
+ glock_trace_name(__entry->cur_state),
+ glock_trace_name(DLM_LOCK_IV),
+ show_glock_flags(__entry->flags))
+
+);
+
+/* Callback (local or remote) requesting lock demotion */
+TRACE_EVENT(gfs2_demote_rq,
+
+ TP_PROTO(const struct gfs2_glock *gl),
+
+ TP_ARGS(gl),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( u8, cur_state )
+ __field( u8, dmt_state )
+ __field( unsigned long, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gl->gl_sbd->sd_vfs->s_dev;
+ __entry->gltype = gl->gl_name.ln_type;
+ __entry->glnum = gl->gl_name.ln_number;
+ __entry->cur_state = glock_trace_state(gl->gl_state);
+ __entry->dmt_state = glock_trace_state(gl->gl_demote_state);
+ __entry->flags = gl->gl_flags;
+ ),
+
+ TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+ (unsigned long long)__entry->glnum,
+ glock_trace_name(__entry->cur_state),
+ glock_trace_name(__entry->dmt_state),
+ show_glock_flags(__entry->flags))
+
+);
+
+/* Promotion/grant of a glock */
+TRACE_EVENT(gfs2_promote,
+
+ TP_PROTO(const struct gfs2_holder *gh, int first),
+
+ TP_ARGS(gh, first),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( int, first )
+ __field( u8, state )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+ __entry->glnum = gh->gh_gl->gl_name.ln_number;
+ __entry->gltype = gh->gh_gl->gl_name.ln_type;
+ __entry->first = first;
+ __entry->state = glock_trace_state(gh->gh_state);
+ ),
+
+ TP_printk("%u,%u glock %u:%llu promote %s %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+ (unsigned long long)__entry->glnum,
+ __entry->first ? "first": "other",
+ glock_trace_name(__entry->state))
+);
+
+/* Queue/dequeue a lock request */
+TRACE_EVENT(gfs2_glock_queue,
+
+ TP_PROTO(const struct gfs2_holder *gh, int queue),
+
+ TP_ARGS(gh, queue),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, glnum )
+ __field( u32, gltype )
+ __field( int, queue )
+ __field( u8, state )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+ __entry->glnum = gh->gh_gl->gl_name.ln_number;
+ __entry->gltype = gh->gh_gl->gl_name.ln_type;
+ __entry->queue = queue;
+ __entry->state = glock_trace_state(gh->gh_state);
+ ),
+
+ TP_printk("%u,%u glock %u:%llu %squeue %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+ (unsigned long long)__entry->glnum,
+ __entry->queue ? "" : "de",
+ glock_trace_name(__entry->state))
+);
+
+/* Section 2 - Log/journal
+ *
+ * Objectives:
+ * Latency: Log flush time
+ * Correctness: pin/unpin vs. disk I/O ordering
+ * Performance: Log usage stats
+ */
+
+/* Pin/unpin a block in the log */
+TRACE_EVENT(gfs2_pin,
+
+ TP_PROTO(const struct gfs2_bufdata *bd, int pin),
+
+ TP_ARGS(bd, pin),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( int, pin )
+ __field( u32, len )
+ __field( sector_t, block )
+ __field( u64, ino )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bd->bd_gl->gl_sbd->sd_vfs->s_dev;
+ __entry->pin = pin;
+ __entry->len = bd->bd_bh->b_size;
+ __entry->block = bd->bd_bh->b_blocknr;
+ __entry->ino = bd->bd_gl->gl_name.ln_number;
+ ),
+
+ TP_printk("%u,%u log %s %llu/%lu inode %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->pin ? "pin" : "unpin",
+ (unsigned long long)__entry->block,
+ (unsigned long)__entry->len,
+ (unsigned long long)__entry->ino)
+);
+
+/* Flushing the log */
+TRACE_EVENT(gfs2_log_flush,
+
+ TP_PROTO(const struct gfs2_sbd *sdp, int start),
+
+ TP_ARGS(sdp, start),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( int, start )
+ __field( u64, log_seq )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sdp->sd_vfs->s_dev;
+ __entry->start = start;
+ __entry->log_seq = sdp->sd_log_sequence;
+ ),
+
+ TP_printk("%u,%u log flush %s %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->start ? "start" : "end",
+ (unsigned long long)__entry->log_seq)
+);
+
+/* Reserving/releasing blocks in the log */
+TRACE_EVENT(gfs2_log_blocks,
+
+ TP_PROTO(const struct gfs2_sbd *sdp, int blocks),
+
+ TP_ARGS(sdp, blocks),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( int, blocks )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sdp->sd_vfs->s_dev;
+ __entry->blocks = blocks;
+ ),
+
+ TP_printk("%u,%u log reserve %d", MAJOR(__entry->dev),
+ MINOR(__entry->dev), __entry->blocks)
+);
+
+/* Section 3 - bmap
+ *
+ * Objectives:
+ * Latency: Bmap request time
+ * Performance: Block allocator tracing
+ * Correctness: Test of disard generation vs. blocks allocated
+ */
+
+/* Map an extent of blocks, possibly a new allocation */
+TRACE_EVENT(gfs2_bmap,
+
+ TP_PROTO(const struct gfs2_inode *ip, const struct buffer_head *bh,
+ sector_t lblock, int create, int errno),
+
+ TP_ARGS(ip, bh, lblock, create, errno),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, lblock )
+ __field( sector_t, pblock )
+ __field( u64, inum )
+ __field( unsigned long, state )
+ __field( u32, len )
+ __field( int, create )
+ __field( int, errno )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = ip->i_gl->gl_sbd->sd_vfs->s_dev;
+ __entry->lblock = lblock;
+ __entry->pblock = buffer_mapped(bh) ? bh->b_blocknr : 0;
+ __entry->inum = ip->i_no_addr;
+ __entry->state = bh->b_state;
+ __entry->len = bh->b_size;
+ __entry->create = create;
+ __entry->errno = errno;
+ ),
+
+ TP_printk("%u,%u bmap %llu map %llu/%lu to %llu flags:%08lx %s %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->inum,
+ (unsigned long long)__entry->lblock,
+ (unsigned long)__entry->len,
+ (unsigned long long)__entry->pblock,
+ __entry->state, __entry->create ? "create " : "nocreate",
+ __entry->errno)
+);
+
+/* Keep track of blocks as they are allocated/freed */
+TRACE_EVENT(gfs2_block_alloc,
+
+ TP_PROTO(const struct gfs2_inode *ip, u64 block, unsigned len,
+ u8 block_state),
+
+ TP_ARGS(ip, block, len, block_state),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( u64, start )
+ __field( u64, inum )
+ __field( u32, len )
+ __field( u8, block_state )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = ip->i_gl->gl_sbd->sd_vfs->s_dev;
+ __entry->start = block;
+ __entry->inum = ip->i_no_addr;
+ __entry->len = len;
+ __entry->block_state = block_state;
+ ),
+
+ TP_printk("%u,%u bmap %llu alloc %llu/%lu %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->inum,
+ (unsigned long long)__entry->start,
+ (unsigned long)__entry->len,
+ block_state_name(__entry->block_state))
+);
+
+#endif /* _TRACE_GFS2_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
+
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 0af36085eb2..1a9c7878f86 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -556,27 +556,49 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
/* add partitions */
for (p = 1; p < state->limit; p++) {
- sector_t size = state->parts[p].size;
- sector_t from = state->parts[p].from;
+ sector_t size, from;
+try_scan:
+ size = state->parts[p].size;
if (!size)
continue;
+
+ from = state->parts[p].from;
if (from >= get_capacity(disk)) {
printk(KERN_WARNING
"%s: p%d ignored, start %llu is behind the end of the disk\n",
disk->disk_name, p, (unsigned long long) from);
continue;
}
+
if (from + size > get_capacity(disk)) {
- /*
- * we can not ignore partitions of broken tables
- * created by for example camera firmware, but we
- * limit them to the end of the disk to avoid
- * creating invalid block devices
- */
+ struct block_device_operations *bdops = disk->fops;
+ unsigned long long capacity;
+
printk(KERN_WARNING
- "%s: p%d size %llu limited to end of disk\n",
+ "%s: p%d size %llu exceeds device capacity, ",
disk->disk_name, p, (unsigned long long) size);
- size = get_capacity(disk) - from;
+
+ if (bdops->set_capacity &&
+ (disk->flags & GENHD_FL_NATIVE_CAPACITY) == 0) {
+ printk(KERN_CONT "enabling native capacity\n");
+ capacity = bdops->set_capacity(disk, ~0ULL);
+ disk->flags |= GENHD_FL_NATIVE_CAPACITY;
+ if (capacity > get_capacity(disk)) {
+ set_capacity(disk, capacity);
+ check_disk_size_change(disk, bdev);
+ bdev->bd_invalidated = 0;
+ }
+ goto try_scan;
+ } else {
+ /*
+ * we can not ignore partitions of broken tables
+ * created by for example camera firmware, but
+ * we limit them to the end of the disk to avoid
+ * creating invalid block devices
+ */
+ printk(KERN_CONT "limited to end of disk\n");
+ size = get_capacity(disk) - from;
+ }
}
part = add_partition(disk, p, from, size,
state->parts[p].flags);