1
linux/fs/9p/vfs_dir.c

316 lines
6.9 KiB
C
Raw Normal View History

/*
* linux/fs/9p/vfs_dir.c
*
* This file contains vfs directory ops for the 9P2000 protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/idr.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 01:04:11 -07:00
#include <linux/slab.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include "v9fs.h"
#include "v9fs_vfs.h"
#include "fid.h"
/**
* struct p9_rdir - readdir accounting
* @mutex: mutex protecting readdir
* @head: start offset of current dirread buffer
* @tail: end offset of current dirread buffer
* @buf: dirread buffer
*
* private structure for keeping track of readdir
* allocated on demand
*/
struct p9_rdir {
struct mutex mutex;
int head;
int tail;
uint8_t *buf;
};
/**
* dt_type - return file type
* @mistat: mistat structure
*
*/
static inline int dt_type(struct p9_wstat *mistat)
{
unsigned long perm = mistat->mode;
int rettype = DT_REG;
if (perm & P9_DMDIR)
rettype = DT_DIR;
if (perm & P9_DMSYMLINK)
rettype = DT_LNK;
return rettype;
}
static void p9stat_init(struct p9_wstat *stbuf)
{
stbuf->name = NULL;
stbuf->uid = NULL;
stbuf->gid = NULL;
stbuf->muid = NULL;
stbuf->extension = NULL;
}
/**
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
* v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir
* @filp: opened file structure
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
* @buflen: Length in bytes of buffer to allocate
*
*/
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
static int v9fs_alloc_rdir_buf(struct file *filp, int buflen)
{
struct p9_rdir *rdir;
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
struct p9_fid *fid;
int err = 0;
fid = filp->private_data;
if (!fid->rdir) {
rdir = kmalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
if (rdir == NULL) {
err = -ENOMEM;
goto exit;
}
spin_lock(&filp->f_dentry->d_lock);
if (!fid->rdir) {
rdir->buf = (uint8_t *)rdir + sizeof(struct p9_rdir);
mutex_init(&rdir->mutex);
rdir->head = rdir->tail = 0;
fid->rdir = (void *) rdir;
rdir = NULL;
}
spin_unlock(&filp->f_dentry->d_lock);
kfree(rdir);
}
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
exit:
return err;
}
/**
* v9fs_dir_readdir - read a directory
* @filp: opened file structure
* @dirent: directory structure ???
* @filldir: function to populate directory structure ???
*
*/
static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
int over;
struct p9_wstat st;
int err = 0;
struct p9_fid *fid;
int buflen;
int reclen = 0;
struct p9_rdir *rdir;
P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
fid = filp->private_data;
buflen = fid->clnt->msize - P9_IOHDRSZ;
err = v9fs_alloc_rdir_buf(filp, buflen);
if (err)
goto exit;
rdir = (struct p9_rdir *) fid->rdir;
err = mutex_lock_interruptible(&rdir->mutex);
if (err)
return err;
while (err == 0) {
if (rdir->tail == rdir->head) {
err = v9fs_file_readn(filp, rdir->buf, NULL,
buflen, filp->f_pos);
if (err <= 0)
goto unlock_and_exit;
rdir->head = 0;
rdir->tail = err;
}
while (rdir->head < rdir->tail) {
p9stat_init(&st);
err = p9stat_read(rdir->buf + rdir->head,
rdir->tail - rdir->head, &st,
fid->clnt->proto_version);
if (err) {
P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err);
err = -EIO;
p9stat_free(&st);
goto unlock_and_exit;
}
reclen = st.size+2;
over = filldir(dirent, st.name, strlen(st.name),
filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
p9stat_free(&st);
if (over) {
err = 0;
goto unlock_and_exit;
}
rdir->head += reclen;
filp->f_pos += reclen;
}
}
unlock_and_exit:
mutex_unlock(&rdir->mutex);
exit:
return err;
}
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
/**
* v9fs_dir_readdir_dotl - read a directory
* @filp: opened file structure
* @dirent: buffer to fill dirent structures
* @filldir: function to populate dirent structures
*
*/
static int v9fs_dir_readdir_dotl(struct file *filp, void *dirent,
filldir_t filldir)
{
int over;
int err = 0;
struct p9_fid *fid;
int buflen;
struct p9_rdir *rdir;
struct p9_dirent curdirent;
u64 oldoffset = 0;
P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
fid = filp->private_data;
buflen = fid->clnt->msize - P9_READDIRHDRSZ;
err = v9fs_alloc_rdir_buf(filp, buflen);
if (err)
goto exit;
rdir = (struct p9_rdir *) fid->rdir;
err = mutex_lock_interruptible(&rdir->mutex);
if (err)
return err;
while (err == 0) {
if (rdir->tail == rdir->head) {
err = p9_client_readdir(fid, rdir->buf, buflen,
filp->f_pos);
if (err <= 0)
goto unlock_and_exit;
rdir->head = 0;
rdir->tail = err;
}
while (rdir->head < rdir->tail) {
err = p9dirent_read(rdir->buf + rdir->head,
buflen - rdir->head, &curdirent,
fid->clnt->proto_version);
if (err < 0) {
P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err);
err = -EIO;
goto unlock_and_exit;
}
/* d_off in dirent structure tracks the offset into
* the next dirent in the dir. However, filldir()
* expects offset into the current dirent. Hence
* while calling filldir send the offset from the
* previous dirent structure.
*/
over = filldir(dirent, curdirent.d_name,
strlen(curdirent.d_name),
oldoffset, v9fs_qid2ino(&curdirent.qid),
curdirent.d_type);
oldoffset = curdirent.d_off;
if (over) {
err = 0;
goto unlock_and_exit;
}
filp->f_pos = curdirent.d_off;
rdir->head += err;
}
}
unlock_and_exit:
mutex_unlock(&rdir->mutex);
exit:
return err;
}
/**
* v9fs_dir_release - close a directory
* @inode: inode of the directory
* @filp: file pointer to a directory
*
*/
int v9fs_dir_release(struct inode *inode, struct file *filp)
{
struct p9_fid *fid;
fid = filp->private_data;
P9_DPRINTK(P9_DEBUG_VFS,
"inode: %p filp: %p fid: %d\n", inode, filp, fid->fid);
filemap_write_and_wait(inode->i_mapping);
p9_client_clunk(fid);
return 0;
}
const struct file_operations v9fs_dir_operations = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
.readdir = v9fs_dir_readdir,
.open = v9fs_file_open,
.release = v9fs_dir_release,
};
const struct file_operations v9fs_dir_operations_dotl = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 06:41:26 -07:00
.readdir = v9fs_dir_readdir_dotl,
.open = v9fs_file_open,
.release = v9fs_dir_release,
};