linux/fs/coda/inode.c

326 lines
6.9 KiB
C
Raw Normal View History

/*
* Super block/filesystem wide operations
*
* Copyright (C) 1996 Peter J. Braam <braam@maths.ox.ac.uk> and
* Michael Callahan <callahan@maths.ox.ac.uk>
*
* Rewritten for Linux 2.1. Peter Braam <braam@cs.cmu.edu>
* Copyright (C) Carnegie Mellon University
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/file.h>
#include <linux/vfs.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 11:04:11 +03:00
#include <linux/slab.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/coda.h>
#include <linux/coda_linux.h>
#include <linux/coda_psdev.h>
#include <linux/coda_fs_i.h>
#include <linux/coda_cache.h>
#include "coda_int.h"
/* VFS super_block ops */
static void coda_evict_inode(struct inode *);
static void coda_put_super(struct super_block *);
static int coda_statfs(struct dentry *dentry, struct kstatfs *buf);
static struct kmem_cache * coda_inode_cachep;
static struct inode *coda_alloc_inode(struct super_block *sb)
{
struct coda_inode_info *ei;
ei = (struct coda_inode_info *)kmem_cache_alloc(coda_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
memset(&ei->c_fid, 0, sizeof(struct CodaFid));
ei->c_flags = 0;
ei->c_uid = 0;
ei->c_cached_perm = 0;
spin_lock_init(&ei->c_lock);
return &ei->vfs_inode;
}
static void coda_destroy_inode(struct inode *inode)
{
kmem_cache_free(coda_inode_cachep, ITOC(inode));
}
static void init_once(void *foo)
{
struct coda_inode_info *ei = (struct coda_inode_info *) foo;
inode_init_once(&ei->vfs_inode);
}
int coda_init_inodecache(void)
{
coda_inode_cachep = kmem_cache_create("coda_inode_cache",
sizeof(struct coda_inode_info),
[PATCH] cpuset memory spread: slab cache filesystems Mark file system inode and similar slab caches subject to SLAB_MEM_SPREAD memory spreading. If a slab cache is marked SLAB_MEM_SPREAD, then anytime that a task that's in a cpuset with the 'memory_spread_slab' option enabled goes to allocate from such a slab cache, the allocations are spread evenly over all the memory nodes (task->mems_allowed) allowed to that task, instead of favoring allocation on the node local to the current cpu. The following inode and similar caches are marked SLAB_MEM_SPREAD: file cache ==== ===== fs/adfs/super.c adfs_inode_cache fs/affs/super.c affs_inode_cache fs/befs/linuxvfs.c befs_inode_cache fs/bfs/inode.c bfs_inode_cache fs/block_dev.c bdev_cache fs/cifs/cifsfs.c cifs_inode_cache fs/coda/inode.c coda_inode_cache fs/dquot.c dquot fs/efs/super.c efs_inode_cache fs/ext2/super.c ext2_inode_cache fs/ext2/xattr.c (fs/mbcache.c) ext2_xattr fs/ext3/super.c ext3_inode_cache fs/ext3/xattr.c (fs/mbcache.c) ext3_xattr fs/fat/cache.c fat_cache fs/fat/inode.c fat_inode_cache fs/freevxfs/vxfs_super.c vxfs_inode fs/hpfs/super.c hpfs_inode_cache fs/isofs/inode.c isofs_inode_cache fs/jffs/inode-v23.c jffs_fm fs/jffs2/super.c jffs2_i fs/jfs/super.c jfs_ip fs/minix/inode.c minix_inode_cache fs/ncpfs/inode.c ncp_inode_cache fs/nfs/direct.c nfs_direct_cache fs/nfs/inode.c nfs_inode_cache fs/ntfs/super.c ntfs_big_inode_cache_name fs/ntfs/super.c ntfs_inode_cache fs/ocfs2/dlm/dlmfs.c dlmfs_inode_cache fs/ocfs2/super.c ocfs2_inode_cache fs/proc/inode.c proc_inode_cache fs/qnx4/inode.c qnx4_inode_cache fs/reiserfs/super.c reiser_inode_cache fs/romfs/inode.c romfs_inode_cache fs/smbfs/inode.c smb_inode_cache fs/sysv/inode.c sysv_inode_cache fs/udf/super.c udf_inode_cache fs/ufs/super.c ufs_inode_cache net/socket.c sock_inode_cache net/sunrpc/rpc_pipe.c rpc_inode_cache The choice of which slab caches to so mark was quite simple. I marked those already marked SLAB_RECLAIM_ACCOUNT, except for fs/xfs, dentry_cache, inode_cache, and buffer_head, which were marked in a previous patch. Even though SLAB_RECLAIM_ACCOUNT is for a different purpose, it marks the same potentially large file system i/o related slab caches as we need for memory spreading. Given that the rule now becomes "wherever you would have used a SLAB_RECLAIM_ACCOUNT slab cache flag before (usually the inode cache), use the SLAB_MEM_SPREAD flag too", this should be easy enough to maintain. Future file system writers will just copy one of the existing file system slab cache setups and tend to get it right without thinking. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 14:16:05 +03:00
0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
init_once);
if (coda_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
void coda_destroy_inodecache(void)
{
kmem_cache_destroy(coda_inode_cachep);
}
static int coda_remount(struct super_block *sb, int *flags, char *data)
{
*flags |= MS_NOATIME;
return 0;
}
/* exported operations */
static const struct super_operations coda_super_operations =
{
.alloc_inode = coda_alloc_inode,
.destroy_inode = coda_destroy_inode,
.evict_inode = coda_evict_inode,
.put_super = coda_put_super,
.statfs = coda_statfs,
.remount_fs = coda_remount,
};
static int get_device_index(struct coda_mount_data *data)
{
struct file *file;
struct inode *inode;
int idx;
if(data == NULL) {
printk("coda_read_super: Bad mount data\n");
return -1;
}
if(data->version != CODA_MOUNT_VERSION) {
printk("coda_read_super: Bad mount version\n");
return -1;
}
file = fget(data->fd);
inode = NULL;
if(file)
inode = file->f_path.dentry->d_inode;
if(!inode || !S_ISCHR(inode->i_mode) ||
imajor(inode) != CODA_PSDEV_MAJOR) {
if(file)
fput(file);
printk("coda_read_super: Bad file\n");
return -1;
}
idx = iminor(inode);
fput(file);
if(idx < 0 || idx >= MAX_CODADEVS) {
printk("coda_read_super: Bad minor number\n");
return -1;
}
return idx;
}
static int coda_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *root = NULL;
struct venus_comm *vc = NULL;
struct CodaFid fid;
int error;
int idx;
lock_kernel();
idx = get_device_index((struct coda_mount_data *) data);
/* Ignore errors in data, for backward compatibility */
if(idx == -1)
idx = 0;
printk(KERN_INFO "coda_read_super: device index: %i\n", idx);
vc = &coda_comms[idx];
if (!vc->vc_inuse) {
printk("coda_read_super: No pseudo device\n");
unlock_kernel();
return -EINVAL;
}
if ( vc->vc_sb ) {
printk("coda_read_super: Device already mounted\n");
unlock_kernel();
return -EBUSY;
}
error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY);
if (error)
goto bdi_err;
vc->vc_sb = sb;
sb->s_fs_info = vc;
sb->s_flags |= MS_NOATIME;
sb->s_blocksize = 4096; /* XXXXX what do we put here?? */
sb->s_blocksize_bits = 12;
sb->s_magic = CODA_SUPER_MAGIC;
sb->s_op = &coda_super_operations;
sb->s_bdi = &vc->bdi;
/* get root fid from Venus: this needs the root inode */
error = venus_rootfid(sb, &fid);
if ( error ) {
printk("coda_read_super: coda_get_rootfid failed with %d\n",
error);
goto error;
}
printk("coda_read_super: rootfid is %s\n", coda_f2s(&fid));
/* make root inode */
error = coda_cnode_make(&root, &fid, sb);
if ( error || !root ) {
printk("Failure of coda_cnode_make for root: error %d\n", error);
goto error;
}
printk("coda_read_super: rootinode is %ld dev %s\n",
root->i_ino, root->i_sb->s_id);
sb->s_root = d_alloc_root(root);
if (!sb->s_root)
goto error;
unlock_kernel();
return 0;
error:
bdi_destroy(&vc->bdi);
bdi_err:
if (root)
iput(root);
if (vc)
vc->vc_sb = NULL;
unlock_kernel();
return -EINVAL;
}
static void coda_put_super(struct super_block *sb)
{
bdi_destroy(&coda_vcp(sb)->bdi);
coda_vcp(sb)->vc_sb = NULL;
sb->s_fs_info = NULL;
printk("Coda: Bye bye.\n");
}
static void coda_evict_inode(struct inode *inode)
{
truncate_inode_pages(&inode->i_data, 0);
end_writeback(inode);
coda_cache_clear_inode(inode);
}
int coda_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
int err = coda_revalidate_inode(dentry);
if (!err)
generic_fillattr(dentry->d_inode, stat);
return err;
}
int coda_setattr(struct dentry *de, struct iattr *iattr)
{
struct inode *inode = de->d_inode;
struct coda_vattr vattr;
int error;
lock_kernel();
memset(&vattr, 0, sizeof(vattr));
inode->i_ctime = CURRENT_TIME_SEC;
coda_iattr_to_vattr(iattr, &vattr);
vattr.va_type = C_VNON; /* cannot set type */
/* Venus is responsible for truncating the container-file!!! */
error = venus_setattr(inode->i_sb, coda_i2f(inode), &vattr);
if ( !error ) {
coda_vattr_to_iattr(inode, &vattr);
coda_cache_clear_inode(inode);
}
unlock_kernel();
return error;
}
const struct inode_operations coda_file_inode_operations = {
.permission = coda_permission,
.getattr = coda_getattr,
.setattr = coda_setattr,
};
static int coda_statfs(struct dentry *dentry, struct kstatfs *buf)
{
int error;
lock_kernel();
error = venus_statfs(dentry, buf);
unlock_kernel();
if (error) {
/* fake something like AFS does */
buf->f_blocks = 9000000;
buf->f_bfree = 9000000;
buf->f_bavail = 9000000;
buf->f_files = 9000000;
buf->f_ffree = 9000000;
}
/* and fill in the rest */
buf->f_type = CODA_SUPER_MAGIC;
buf->f_bsize = 4096;
buf->f_namelen = CODA_MAXNAMLEN;
return 0;
}
/* init_coda: used by filesystems.c to register coda */
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
static int coda_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
return get_sb_nodev(fs_type, flags, data, coda_fill_super, mnt);
}
struct file_system_type coda_fs_type = {
.owner = THIS_MODULE,
.name = "coda",
.get_sb = coda_get_sb,
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
};