mirror_zfs/module/zfs/zpl_inode.c

413 lines
8.7 KiB
C
Raw Normal View History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2011, Lawrence Livermore National Security, LLC.
*/
#include <sys/zfs_vfsops.h>
#include <sys/zfs_vnops.h>
#include <sys/vfs.h>
#include <sys/zpl.h>
static struct dentry *
zpl_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
cred_t *cr = CRED();
struct inode *ip;
int error;
crhold(cr);
error = -zfs_lookup(dir, dname(dentry), &ip, 0, cr, NULL, NULL);
ASSERT3S(error, <=, 0);
crfree(cr);
if (error) {
if (error == -ENOENT)
return d_splice_alias(NULL, dentry);
else
return ERR_PTR(error);
}
return d_splice_alias(ip, dentry);
}
static void
zpl_vap_init(vattr_t *vap, struct inode *dir, struct dentry *dentry,
mode_t mode, cred_t *cr)
{
vap->va_mask = ATTR_MODE;
vap->va_mode = mode;
vap->va_dentry = dentry;
vap->va_uid = crgetfsuid(cr);
if (dir && dir->i_mode & S_ISGID) {
vap->va_gid = dir->i_gid;
if (S_ISDIR(mode))
vap->va_mode |= S_ISGID;
} else {
vap->va_gid = crgetfsgid(cr);
}
}
static int
zpl_create(struct inode *dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
cred_t *cr = CRED();
struct inode *ip;
vattr_t *vap;
int error;
crhold(cr);
vap = kmem_zalloc(sizeof(vattr_t), KM_SLEEP);
zpl_vap_init(vap, dir, dentry, mode, cr);
error = -zfs_create(dir, (char *)dentry->d_name.name,
vap, 0, mode, &ip, cr, 0, NULL);
kmem_free(vap, sizeof(vattr_t));
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static int
zpl_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
{
cred_t *cr = CRED();
struct inode *ip;
vattr_t *vap;
int error;
/*
* We currently expect Linux to supply rdev=0 for all sockets
* and fifos, but we want to know if this behavior ever changes.
*/
if (S_ISSOCK(mode) || S_ISFIFO(mode))
ASSERT(rdev == 0);
crhold(cr);
vap = kmem_zalloc(sizeof(vattr_t), KM_SLEEP);
zpl_vap_init(vap, dir, dentry, mode, cr);
vap->va_rdev = rdev;
error = -zfs_create(dir, (char *)dentry->d_name.name,
vap, 0, mode, &ip, cr, 0, NULL);
kmem_free(vap, sizeof(vattr_t));
crfree(cr);
ASSERT3S(error, <=, 0);
return (-error);
}
static int
zpl_unlink(struct inode *dir, struct dentry *dentry)
{
cred_t *cr = CRED();
int error;
crhold(cr);
error = -zfs_remove(dir, dname(dentry), cr);
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static int
zpl_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
cred_t *cr = CRED();
vattr_t *vap;
struct inode *ip;
int error;
crhold(cr);
vap = kmem_zalloc(sizeof(vattr_t), KM_SLEEP);
zpl_vap_init(vap, dir, dentry, mode | S_IFDIR, cr);
error = -zfs_mkdir(dir, dname(dentry), vap, &ip, cr, 0, NULL);
kmem_free(vap, sizeof(vattr_t));
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static int
zpl_rmdir(struct inode * dir, struct dentry *dentry)
{
cred_t *cr = CRED();
int error;
crhold(cr);
error = -zfs_rmdir(dir, dname(dentry), NULL, cr, 0);
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static int
zpl_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
int error;
Improve fstat(2) performance There is at most a factor of 3x performance improvement to be had by using the Linux generic_fillattr() helper. However, to use it safely we need to ensure the values in a cached inode are kept rigerously up to date. Unfortunately, this isn't the case for the blksize, blocks, and atime fields. At the moment the authoritative values are still stored in the znode. This patch introduces an optimized zfs_getattr_fast() call. The idea is to use the up to date values from the inode and the blksize, block, and atime fields from the znode. At some latter date we should be able to strictly use the inode values and further improve performance. The remaining overhead in the zfs_getattr_fast() call can be attributed to having to take the znode mutex. This overhead is unavoidable until the inode is kept strictly up to date. The the careful reader will notice the we do not use the customary ZFS_ENTER()/ZFS_EXIT() macros. These macro's are designed to ensure the filesystem is not torn down in the middle of an operation. However, in this case the VFS is holding a reference on the active inode so we know this is impossible. =================== Performance Tests ======================== This test calls the fstat(2) system call 10,000,000 times on an open file description in a tight loop. The test results show the zfs stat(2) performance is now only 22% slower than ext4. This is a 2.5x improvement and there is a clear long term plan to get to parity with ext4. filesystem | test-1 test-2 test-3 | average | times-ext4 --------------+-------------------------+---------+----------- ext4 | 7.785s 7.899s 7.284s | 7.656s | 1.000x zfs-0.6.0-rc4 | 24.052s 22.531s 23.857s | 23.480s | 3.066x zfs-faststat | 9.224s 9.398s 9.485s | 9.369s | 1.223x The second test is to run 'du' of a copy of the /usr tree which contains 110514 files. The test is run multiple times both using both a cold cache (/proc/sys/vm/drop_caches) and a hot cache. As expected this change signigicantly improved the zfs hot cache performance and doesn't quite bring zfs to parity with ext4. A little surprisingly the zfs cold cache performance is better than ext4. This can probably be attributed to the zfs allocation policy of co-locating all the meta data on disk which minimizes seek times. By default the ext4 allocator will spread the data over the entire disk only co-locating each directory. filesystem | cold | hot --------------+---------+-------- ext4 | 13.318s | 1.040s zfs-0.6.0-rc4 | 4.982s | 1.762s zfs-faststat | 4.933s | 1.345s
2011-07-10 02:44:16 +04:00
error = -zfs_getattr_fast(dentry->d_inode, stat);
ASSERT3S(error, <=, 0);
return (error);
}
static int
Drop HAVE_XVATTR macros When I began work on the Posix layer it immediately became clear to me that to integrate cleanly with the Linux VFS certain Solaris specific things would have to go. One of these things was to elimate as many Solaris specific types from the ZPL layer as possible. They would be replaced with their Linux equivalents. This would not only be good for performance, but for the general readability and health of the code. The Solaris and Linux VFS are different beasts and should be treated as such. Most of the code remains common for constructing transactions and such, but there are subtle and important differenced which need to be repsected. This policy went quite for for certain types such as the vnode_t, and it initially seemed to be working out well for the vattr_t. There was a relatively small amount of related xvattr_t code I was forced to comment out with HAVE_XVATTR. But it didn't look that hard to come back soon and replace it all with a native Linux type. However, after going doing this path with xvattr some distance it clear that this code was woven in the ZPL more deeply than I thought. In particular its hooks went very deep in to the ZPL replay code and replacing it would not be as easy as I originally thought. Rather than continue persuing replacing and removing this code I've taken a step back and reevaluted things. This commit reverts many of my previous commits which removed xvattr related code. It restores much of the code to its original upstream state and now relies on improved xvattr_t support in the zfs package itself. The result of this is that much of the code which I had commented out, which accidentally broke things like replay, is now back in place and working. However, there may be a small performance impact for getattr/setattr operations because they now require a translation from native Linux to Solaris types. For now that's a price I'm willing to pay. Once everything is completely functional we can revisting the issue of removing the vattr_t/xvattr_t types. Closes #111
2011-03-01 23:24:09 +03:00
zpl_setattr(struct dentry *dentry, struct iattr *ia)
{
cred_t *cr = CRED();
Drop HAVE_XVATTR macros When I began work on the Posix layer it immediately became clear to me that to integrate cleanly with the Linux VFS certain Solaris specific things would have to go. One of these things was to elimate as many Solaris specific types from the ZPL layer as possible. They would be replaced with their Linux equivalents. This would not only be good for performance, but for the general readability and health of the code. The Solaris and Linux VFS are different beasts and should be treated as such. Most of the code remains common for constructing transactions and such, but there are subtle and important differenced which need to be repsected. This policy went quite for for certain types such as the vnode_t, and it initially seemed to be working out well for the vattr_t. There was a relatively small amount of related xvattr_t code I was forced to comment out with HAVE_XVATTR. But it didn't look that hard to come back soon and replace it all with a native Linux type. However, after going doing this path with xvattr some distance it clear that this code was woven in the ZPL more deeply than I thought. In particular its hooks went very deep in to the ZPL replay code and replacing it would not be as easy as I originally thought. Rather than continue persuing replacing and removing this code I've taken a step back and reevaluted things. This commit reverts many of my previous commits which removed xvattr related code. It restores much of the code to its original upstream state and now relies on improved xvattr_t support in the zfs package itself. The result of this is that much of the code which I had commented out, which accidentally broke things like replay, is now back in place and working. However, there may be a small performance impact for getattr/setattr operations because they now require a translation from native Linux to Solaris types. For now that's a price I'm willing to pay. Once everything is completely functional we can revisting the issue of removing the vattr_t/xvattr_t types. Closes #111
2011-03-01 23:24:09 +03:00
vattr_t *vap;
int error;
Drop HAVE_XVATTR macros When I began work on the Posix layer it immediately became clear to me that to integrate cleanly with the Linux VFS certain Solaris specific things would have to go. One of these things was to elimate as many Solaris specific types from the ZPL layer as possible. They would be replaced with their Linux equivalents. This would not only be good for performance, but for the general readability and health of the code. The Solaris and Linux VFS are different beasts and should be treated as such. Most of the code remains common for constructing transactions and such, but there are subtle and important differenced which need to be repsected. This policy went quite for for certain types such as the vnode_t, and it initially seemed to be working out well for the vattr_t. There was a relatively small amount of related xvattr_t code I was forced to comment out with HAVE_XVATTR. But it didn't look that hard to come back soon and replace it all with a native Linux type. However, after going doing this path with xvattr some distance it clear that this code was woven in the ZPL more deeply than I thought. In particular its hooks went very deep in to the ZPL replay code and replacing it would not be as easy as I originally thought. Rather than continue persuing replacing and removing this code I've taken a step back and reevaluted things. This commit reverts many of my previous commits which removed xvattr related code. It restores much of the code to its original upstream state and now relies on improved xvattr_t support in the zfs package itself. The result of this is that much of the code which I had commented out, which accidentally broke things like replay, is now back in place and working. However, there may be a small performance impact for getattr/setattr operations because they now require a translation from native Linux to Solaris types. For now that's a price I'm willing to pay. Once everything is completely functional we can revisting the issue of removing the vattr_t/xvattr_t types. Closes #111
2011-03-01 23:24:09 +03:00
error = inode_change_ok(dentry->d_inode, ia);
if (error)
return (error);
crhold(cr);
Drop HAVE_XVATTR macros When I began work on the Posix layer it immediately became clear to me that to integrate cleanly with the Linux VFS certain Solaris specific things would have to go. One of these things was to elimate as many Solaris specific types from the ZPL layer as possible. They would be replaced with their Linux equivalents. This would not only be good for performance, but for the general readability and health of the code. The Solaris and Linux VFS are different beasts and should be treated as such. Most of the code remains common for constructing transactions and such, but there are subtle and important differenced which need to be repsected. This policy went quite for for certain types such as the vnode_t, and it initially seemed to be working out well for the vattr_t. There was a relatively small amount of related xvattr_t code I was forced to comment out with HAVE_XVATTR. But it didn't look that hard to come back soon and replace it all with a native Linux type. However, after going doing this path with xvattr some distance it clear that this code was woven in the ZPL more deeply than I thought. In particular its hooks went very deep in to the ZPL replay code and replacing it would not be as easy as I originally thought. Rather than continue persuing replacing and removing this code I've taken a step back and reevaluted things. This commit reverts many of my previous commits which removed xvattr related code. It restores much of the code to its original upstream state and now relies on improved xvattr_t support in the zfs package itself. The result of this is that much of the code which I had commented out, which accidentally broke things like replay, is now back in place and working. However, there may be a small performance impact for getattr/setattr operations because they now require a translation from native Linux to Solaris types. For now that's a price I'm willing to pay. Once everything is completely functional we can revisting the issue of removing the vattr_t/xvattr_t types. Closes #111
2011-03-01 23:24:09 +03:00
vap = kmem_zalloc(sizeof(vattr_t), KM_SLEEP);
vap->va_mask = ia->ia_valid & ATTR_IATTR_MASK;
vap->va_mode = ia->ia_mode;
vap->va_uid = ia->ia_uid;
vap->va_gid = ia->ia_gid;
vap->va_size = ia->ia_size;
vap->va_atime = ia->ia_atime;
vap->va_mtime = ia->ia_mtime;
vap->va_ctime = ia->ia_ctime;
error = -zfs_setattr(dentry->d_inode, vap, 0, cr);
kmem_free(vap, sizeof(vattr_t));
crfree(cr);
ASSERT3S(error, <=, 0);
Drop HAVE_XVATTR macros When I began work on the Posix layer it immediately became clear to me that to integrate cleanly with the Linux VFS certain Solaris specific things would have to go. One of these things was to elimate as many Solaris specific types from the ZPL layer as possible. They would be replaced with their Linux equivalents. This would not only be good for performance, but for the general readability and health of the code. The Solaris and Linux VFS are different beasts and should be treated as such. Most of the code remains common for constructing transactions and such, but there are subtle and important differenced which need to be repsected. This policy went quite for for certain types such as the vnode_t, and it initially seemed to be working out well for the vattr_t. There was a relatively small amount of related xvattr_t code I was forced to comment out with HAVE_XVATTR. But it didn't look that hard to come back soon and replace it all with a native Linux type. However, after going doing this path with xvattr some distance it clear that this code was woven in the ZPL more deeply than I thought. In particular its hooks went very deep in to the ZPL replay code and replacing it would not be as easy as I originally thought. Rather than continue persuing replacing and removing this code I've taken a step back and reevaluted things. This commit reverts many of my previous commits which removed xvattr related code. It restores much of the code to its original upstream state and now relies on improved xvattr_t support in the zfs package itself. The result of this is that much of the code which I had commented out, which accidentally broke things like replay, is now back in place and working. However, there may be a small performance impact for getattr/setattr operations because they now require a translation from native Linux to Solaris types. For now that's a price I'm willing to pay. Once everything is completely functional we can revisting the issue of removing the vattr_t/xvattr_t types. Closes #111
2011-03-01 23:24:09 +03:00
return (error);
}
static int
zpl_rename(struct inode *sdip, struct dentry *sdentry,
struct inode *tdip, struct dentry *tdentry)
{
cred_t *cr = CRED();
int error;
crhold(cr);
error = -zfs_rename(sdip, dname(sdentry), tdip, dname(tdentry), cr, 0);
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static int
zpl_symlink(struct inode *dir, struct dentry *dentry, const char *name)
{
cred_t *cr = CRED();
vattr_t *vap;
struct inode *ip;
int error;
crhold(cr);
vap = kmem_zalloc(sizeof(vattr_t), KM_SLEEP);
zpl_vap_init(vap, dir, dentry, S_IFLNK | S_IRWXUGO, cr);
error = -zfs_symlink(dir, dname(dentry), vap, (char *)name, &ip, cr, 0);
kmem_free(vap, sizeof(vattr_t));
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static void *
zpl_follow_link(struct dentry *dentry, struct nameidata *nd)
{
cred_t *cr = CRED();
struct inode *ip = dentry->d_inode;
struct iovec iov;
uio_t uio;
char *link;
int error;
crhold(cr);
iov.iov_len = MAXPATHLEN;
iov.iov_base = link = kmem_zalloc(MAXPATHLEN, KM_SLEEP);
uio.uio_iov = &iov;
uio.uio_iovcnt = 1;
uio.uio_resid = (MAXPATHLEN - 1);
uio.uio_segflg = UIO_SYSSPACE;
error = -zfs_readlink(ip, &uio, cr);
if (error) {
kmem_free(link, MAXPATHLEN);
nd_set_link(nd, ERR_PTR(error));
} else {
nd_set_link(nd, link);
}
crfree(cr);
return (NULL);
}
static void
zpl_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr)
{
char *link;
link = nd_get_link(nd);
if (!IS_ERR(link))
kmem_free(link, MAXPATHLEN);
}
static int
zpl_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
cred_t *cr = CRED();
struct inode *ip = old_dentry->d_inode;
int error;
if (ip->i_nlink >= ZFS_LINK_MAX)
return -EMLINK;
crhold(cr);
ip->i_ctime = CURRENT_TIME_SEC;
igrab(ip); /* Use ihold() if available */
error = -zfs_link(dir, ip, dname(dentry), cr);
if (error) {
iput(ip);
goto out;
}
d_instantiate(dentry, ip);
out:
crfree(cr);
ASSERT3S(error, <=, 0);
return (error);
}
static void
zpl_truncate_range(struct inode* ip, loff_t start, loff_t end)
{
cred_t *cr = CRED();
flock64_t bf;
ASSERT3S(start, <=, end);
/*
* zfs_freesp() will interpret (len == 0) as meaning "truncate until
* the end of the file". We don't want that.
*/
if (start == end)
return;
crhold(cr);
bf.l_type = F_WRLCK;
bf.l_whence = 0;
bf.l_start = start;
bf.l_len = end - start;
bf.l_pid = 0;
zfs_space(ip, F_FREESP, &bf, FWRITE, start, cr);
crfree(cr);
}
#ifdef HAVE_INODE_FALLOCATE
static long
zpl_fallocate(struct inode *ip, int mode, loff_t offset, loff_t len)
{
return zpl_fallocate_common(ip, mode, offset, len);
}
#endif /* HAVE_INODE_FALLOCATE */
const struct inode_operations zpl_inode_operations = {
.create = zpl_create,
.link = zpl_link,
.unlink = zpl_unlink,
.symlink = zpl_symlink,
.mkdir = zpl_mkdir,
.rmdir = zpl_rmdir,
.mknod = zpl_mknod,
.rename = zpl_rename,
.setattr = zpl_setattr,
.getattr = zpl_getattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = zpl_xattr_list,
.truncate_range = zpl_truncate_range,
#ifdef HAVE_INODE_FALLOCATE
.fallocate = zpl_fallocate,
#endif /* HAVE_INODE_FALLOCATE */
};
const struct inode_operations zpl_dir_inode_operations = {
.create = zpl_create,
.lookup = zpl_lookup,
.link = zpl_link,
.unlink = zpl_unlink,
.symlink = zpl_symlink,
.mkdir = zpl_mkdir,
.rmdir = zpl_rmdir,
.mknod = zpl_mknod,
.rename = zpl_rename,
.setattr = zpl_setattr,
.getattr = zpl_getattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = zpl_xattr_list,
};
const struct inode_operations zpl_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = zpl_follow_link,
.put_link = zpl_put_link,
.setattr = zpl_setattr,
.getattr = zpl_getattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = zpl_xattr_list,
};
const struct inode_operations zpl_special_inode_operations = {
.setattr = zpl_setattr,
.getattr = zpl_getattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = zpl_xattr_list,
};