OpenCloudOS-Kernel/fs/coda/dir.c

580 lines
14 KiB
C
Raw Normal View History

/*
* Directory operations for Coda filesystem
* Original version: (C) 1996 P. Braam and M. Callahan
* Rewritten for Linux 2.1. (C) 1997 Carnegie Mellon University
*
* Carnegie Mellon encourages users to contribute improvements to
* the Coda project. Contact Peter Braam (coda@cs.cmu.edu).
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/time.h>
#include <linux/fs.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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/spinlock.h>
#include <linux/namei.h>
#include <linux/uaccess.h>
#include <linux/coda.h>
#include <linux/coda_psdev.h>
#include "coda_linux.h"
#include "coda_cache.h"
#include "coda_int.h"
/* same as fs/bad_inode.c */
static int coda_return_EIO(void)
{
return -EIO;
}
#define CODA_EIO_ERROR ((void *) (coda_return_EIO))
/* inode operations for directories */
/* access routines: lookup, readlink, permission */
static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags)
{
struct super_block *sb = dir->i_sb;
const char *name = entry->d_name.name;
size_t length = entry->d_name.len;
struct inode *inode;
int type = 0;
if (length > CODA_MAXNAMLEN) {
pr_err("name too long: lookup, %s (%*s)\n",
coda_i2s(dir), (int)length, name);
return ERR_PTR(-ENAMETOOLONG);
}
/* control object, create inode on the fly */
if (is_root_inode(dir) && coda_iscontrol(name, length)) {
inode = coda_cnode_makectl(sb);
type = CODA_NOCACHE;
} else {
struct CodaFid fid = { { 0, } };
int error = venus_lookup(sb, coda_i2f(dir), name, length,
&type, &fid);
inode = !error ? coda_cnode_make(&fid, sb) : ERR_PTR(error);
}
if (!IS_ERR(inode) && (type & CODA_NOCACHE))
coda_flag_inode(inode, C_VATTR | C_PURGE);
if (inode == ERR_PTR(-ENOENT))
inode = NULL;
return d_splice_alias(inode, entry);
}
int coda_permission(struct inode *inode, int mask)
{
int error;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (!mask)
return 0;
if ((mask & MAY_EXEC) && !execute_ok(inode))
return -EACCES;
if (coda_cache_check(inode, mask))
return 0;
error = venus_access(inode->i_sb, coda_i2f(inode), mask);
if (!error)
coda_cache_enter(inode, mask);
return error;
}
static inline void coda_dir_update_mtime(struct inode *dir)
{
#ifdef REQUERY_VENUS_FOR_MTIME
/* invalidate the directory cnode's attributes so we refetch the
* attributes from venus next time the inode is referenced */
coda_flag_inode(dir, C_VATTR);
#else
/* optimistically we can also act as if our nose bleeds. The
* granularity of the mtime is coarse anyways so we might actually be
* right most of the time. Note: we only do this for directories. */
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
#endif
}
/* we have to wrap inc_nlink/drop_nlink because sometimes userspace uses a
* trick to fool GNU find's optimizations. If we can't be sure of the link
* (because of volume mount points) we set i_nlink to 1 which forces find
* to consider every child as a possible directory. We should also never
* see an increment or decrement for deleted directories where i_nlink == 0 */
static inline void coda_dir_inc_nlink(struct inode *dir)
{
if (dir->i_nlink >= 2)
inc_nlink(dir);
}
static inline void coda_dir_drop_nlink(struct inode *dir)
{
if (dir->i_nlink > 2)
drop_nlink(dir);
}
/* creation routines: create, mknod, mkdir, link, symlink */
static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl)
{
int error;
const char *name=de->d_name.name;
int length=de->d_name.len;
struct inode *inode;
struct CodaFid newfid;
struct coda_vattr attrs;
if (is_root_inode(dir) && coda_iscontrol(name, length))
return -EPERM;
error = venus_create(dir->i_sb, coda_i2f(dir), name, length,
0, mode, &newfid, &attrs);
if (error)
goto err_out;
inode = coda_iget(dir->i_sb, &newfid, &attrs);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto err_out;
}
/* invalidate the directory cnode's attributes */
coda_dir_update_mtime(dir);
d_instantiate(de, inode);
return 0;
err_out:
d_drop(de);
return error;
}
static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode)
{
struct inode *inode;
struct coda_vattr attrs;
const char *name = de->d_name.name;
int len = de->d_name.len;
int error;
struct CodaFid newfid;
if (is_root_inode(dir) && coda_iscontrol(name, len))
return -EPERM;
attrs.va_mode = mode;
error = venus_mkdir(dir->i_sb, coda_i2f(dir),
name, len, &newfid, &attrs);
if (error)
goto err_out;
inode = coda_iget(dir->i_sb, &newfid, &attrs);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto err_out;
}
/* invalidate the directory cnode's attributes */
coda_dir_inc_nlink(dir);
coda_dir_update_mtime(dir);
d_instantiate(de, inode);
return 0;
err_out:
d_drop(de);
return error;
}
/* try to make de an entry in dir_inodde linked to source_de */
static int coda_link(struct dentry *source_de, struct inode *dir_inode,
struct dentry *de)
{
struct inode *inode = source_de->d_inode;
const char * name = de->d_name.name;
int len = de->d_name.len;
int error;
if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
return -EPERM;
error = venus_link(dir_inode->i_sb, coda_i2f(inode),
coda_i2f(dir_inode), (const char *)name, len);
if (error) {
d_drop(de);
return error;
}
coda_dir_update_mtime(dir_inode);
ihold(inode);
d_instantiate(de, inode);
inc_nlink(inode);
return 0;
}
static int coda_symlink(struct inode *dir_inode, struct dentry *de,
const char *symname)
{
const char *name = de->d_name.name;
int len = de->d_name.len;
int symlen;
int error;
if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
return -EPERM;
symlen = strlen(symname);
if (symlen > CODA_MAXPATHLEN)
return -ENAMETOOLONG;
/*
* This entry is now negative. Since we do not create
* an inode for the entry we have to drop it.
*/
d_drop(de);
error = venus_symlink(dir_inode->i_sb, coda_i2f(dir_inode), name, len,
symname, symlen);
/* mtime is no good anymore */
if (!error)
coda_dir_update_mtime(dir_inode);
return error;
}
/* destruction routines: unlink, rmdir */
static int coda_unlink(struct inode *dir, struct dentry *de)
{
int error;
const char *name = de->d_name.name;
int len = de->d_name.len;
error = venus_remove(dir->i_sb, coda_i2f(dir), name, len);
if (error)
return error;
coda_dir_update_mtime(dir);
drop_nlink(de->d_inode);
return 0;
}
static int coda_rmdir(struct inode *dir, struct dentry *de)
{
const char *name = de->d_name.name;
int len = de->d_name.len;
int error;
error = venus_rmdir(dir->i_sb, coda_i2f(dir), name, len);
if (!error) {
/* VFS may delete the child */
if (de->d_inode)
clear_nlink(de->d_inode);
/* fix the link count of the parent */
coda_dir_drop_nlink(dir);
coda_dir_update_mtime(dir);
}
return error;
}
/* rename */
static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
const char *old_name = old_dentry->d_name.name;
const char *new_name = new_dentry->d_name.name;
int old_length = old_dentry->d_name.len;
int new_length = new_dentry->d_name.len;
int error;
error = venus_rename(old_dir->i_sb, coda_i2f(old_dir),
coda_i2f(new_dir), old_length, new_length,
(const char *) old_name, (const char *)new_name);
if (!error) {
if (new_dentry->d_inode) {
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 20:02:35 +08:00
if (d_is_dir(new_dentry)) {
coda_dir_drop_nlink(old_dir);
coda_dir_inc_nlink(new_dir);
}
coda_dir_update_mtime(old_dir);
coda_dir_update_mtime(new_dir);
coda_flag_inode(new_dentry->d_inode, C_VATTR);
} else {
coda_flag_inode(old_dir, C_VATTR);
coda_flag_inode(new_dir, C_VATTR);
}
}
return error;
}
static inline unsigned int CDT2DT(unsigned char cdt)
{
unsigned int dt;
switch(cdt) {
case CDT_UNKNOWN: dt = DT_UNKNOWN; break;
case CDT_FIFO: dt = DT_FIFO; break;
case CDT_CHR: dt = DT_CHR; break;
case CDT_DIR: dt = DT_DIR; break;
case CDT_BLK: dt = DT_BLK; break;
case CDT_REG: dt = DT_REG; break;
case CDT_LNK: dt = DT_LNK; break;
case CDT_SOCK: dt = DT_SOCK; break;
case CDT_WHT: dt = DT_WHT; break;
default: dt = DT_UNKNOWN; break;
}
return dt;
}
/* support routines */
static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx)
{
struct coda_file_info *cfi;
struct coda_inode_info *cii;
struct file *host_file;
struct venus_dirent *vdir;
unsigned long vdir_size = offsetof(struct venus_dirent, d_name);
unsigned int type;
struct qstr name;
ino_t ino;
int ret;
cfi = CODA_FTOC(coda_file);
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
cii = ITOC(file_inode(coda_file));
vdir = kmalloc(sizeof(*vdir), GFP_KERNEL);
if (!vdir) return -ENOMEM;
if (!dir_emit_dots(coda_file, ctx))
goto out;
while (1) {
/* read entries from the directory file */
ret = kernel_read(host_file, ctx->pos - 2, (char *)vdir,
sizeof(*vdir));
if (ret < 0) {
pr_err("%s: read dir %s failed %d\n",
__func__, coda_f2s(&cii->c_fid), ret);
break;
}
if (ret == 0) break; /* end of directory file reached */
/* catch truncated reads */
if (ret < vdir_size || ret < vdir_size + vdir->d_namlen) {
pr_err("%s: short read on %s\n",
__func__, coda_f2s(&cii->c_fid));
ret = -EBADF;
break;
}
/* validate whether the directory file actually makes sense */
if (vdir->d_reclen < vdir_size + vdir->d_namlen) {
pr_err("%s: invalid dir %s\n",
__func__, coda_f2s(&cii->c_fid));
ret = -EBADF;
break;
}
name.len = vdir->d_namlen;
name.name = vdir->d_name;
/* Make sure we skip '.' and '..', we already got those */
if (name.name[0] == '.' && (name.len == 1 ||
(name.name[1] == '.' && name.len == 2)))
vdir->d_fileno = name.len = 0;
/* skip null entries */
if (vdir->d_fileno && name.len) {
ino = vdir->d_fileno;
type = CDT2DT(vdir->d_type);
if (!dir_emit(ctx, name.name, name.len, ino, type))
break;
}
/* we'll always have progress because d_reclen is unsigned and
* we've already established it is non-zero. */
ctx->pos += vdir->d_reclen;
}
out:
kfree(vdir);
return 0;
}
/* file operations for directories */
static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
{
struct coda_file_info *cfi;
struct file *host_file;
int ret;
cfi = CODA_FTOC(coda_file);
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
if (host_file->f_op->iterate) {
struct inode *host_inode = file_inode(host_file);
mutex_lock(&host_inode->i_mutex);
ret = -ENOENT;
if (!IS_DEADDIR(host_inode)) {
ret = host_file->f_op->iterate(host_file, ctx);
file_accessed(host_file);
}
mutex_unlock(&host_inode->i_mutex);
return ret;
}
/* Venus: we must read Venus dirents from a file */
return coda_venus_readdir(coda_file, ctx);
}
/* called when a cache lookup succeeds */
static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
{
struct inode *inode;
struct coda_inode_info *cii;
if (flags & LOOKUP_RCU)
return -ECHILD;
inode = de->d_inode;
if (!inode || is_root_inode(inode))
goto out;
if (is_bad_inode(inode))
goto bad;
cii = ITOC(de->d_inode);
if (!(cii->c_flags & (C_PURGE | C_FLUSH)))
goto out;
shrink_dcache_parent(de);
/* propagate for a flush */
if (cii->c_flags & C_FLUSH)
coda_flag_inode_children(inode, C_FLUSH);
if (d_count(de) > 1)
/* pretend it's valid, but don't change the flags */
goto out;
/* clear the flags. */
spin_lock(&cii->c_lock);
cii->c_flags &= ~(C_VATTR | C_PURGE | C_FLUSH);
spin_unlock(&cii->c_lock);
bad:
return 0;
out:
return 1;
}
/*
* This is the callback from dput() when d_count is going to 0.
* We use this to unhash dentries with bad inodes.
*/
static int coda_dentry_delete(const struct dentry * dentry)
{
int flags;
if (!dentry->d_inode)
return 0;
flags = (ITOC(dentry->d_inode)->c_flags) & C_PURGE;
if (is_bad_inode(dentry->d_inode) || flags) {
return 1;
}
return 0;
}
/*
* This is called when we want to check if the inode has
* changed on the server. Coda makes this easy since the
* cache manager Venus issues a downcall to the kernel when this
* happens
*/
int coda_revalidate_inode(struct inode *inode)
{
struct coda_vattr attr;
int error;
int old_mode;
ino_t old_ino;
struct coda_inode_info *cii = ITOC(inode);
if (!cii->c_flags)
return 0;
if (cii->c_flags & (C_VATTR | C_PURGE | C_FLUSH)) {
error = venus_getattr(inode->i_sb, &(cii->c_fid), &attr);
if (error)
return -EIO;
/* this inode may be lost if:
- it's ino changed
- type changes must be permitted for repair and
missing mount points.
*/
old_mode = inode->i_mode;
old_ino = inode->i_ino;
coda_vattr_to_iattr(inode, &attr);
if ((old_mode & S_IFMT) != (inode->i_mode & S_IFMT)) {
pr_warn("inode %ld, fid %s changed type!\n",
inode->i_ino, coda_f2s(&(cii->c_fid)));
}
/* the following can happen when a local fid is replaced
with a global one, here we lose and declare the inode bad */
if (inode->i_ino != old_ino)
return -EIO;
coda_flag_inode_children(inode, C_FLUSH);
spin_lock(&cii->c_lock);
cii->c_flags &= ~(C_VATTR | C_PURGE | C_FLUSH);
spin_unlock(&cii->c_lock);
}
return 0;
}
const struct dentry_operations coda_dentry_operations = {
.d_revalidate = coda_dentry_revalidate,
.d_delete = coda_dentry_delete,
};
const struct inode_operations coda_dir_inode_operations = {
.create = coda_create,
.lookup = coda_lookup,
.link = coda_link,
.unlink = coda_unlink,
.symlink = coda_symlink,
.mkdir = coda_mkdir,
.rmdir = coda_rmdir,
.mknod = CODA_EIO_ERROR,
.rename = coda_rename,
.permission = coda_permission,
.getattr = coda_getattr,
.setattr = coda_setattr,
};
const struct file_operations coda_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.iterate = coda_readdir,
.open = coda_open,
.release = coda_release,
.fsync = coda_fsync,
};