#include <linux/stat.h>
#include <linux/module.h>
#include <linux/mount.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/idr.h>
#include <linux/namei.h>
#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
#include <asm/uaccess.h>
-static ssize_t proc_file_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos);
-static ssize_t proc_file_write(struct file *file, const char __user *buffer,
- size_t count, loff_t *ppos);
-static loff_t proc_file_lseek(struct file *, loff_t, int);
+#include "internal.h"
-int proc_match(int len, const char *name, struct proc_dir_entry *de)
+DEFINE_SPINLOCK(proc_subdir_lock);
+
+static int proc_match(int len, const char *name, struct proc_dir_entry *de)
{
if (de->namelen != len)
return 0;
return !memcmp(name, de->name, len);
}
-static struct file_operations proc_file_operations = {
- .llseek = proc_file_lseek,
- .read = proc_file_read,
- .write = proc_file_write,
-};
-
/* buffer size is one page but our output routines use some slack for overruns */
#define PROC_BLOCK_SIZE (PAGE_SIZE - 1024)
static ssize_t
-proc_file_read(struct file *file, char __user *buf, size_t nbytes,
+__proc_file_read(struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos)
{
- struct inode * inode = file->f_dentry->d_inode;
+ struct inode * inode = file->f_path.dentry->d_inode;
char *page;
ssize_t retval=0;
int eof=0;
ssize_t n, count;
char *start;
struct proc_dir_entry * dp;
+ unsigned long long pos;
+
+ /*
+ * Gaah, please just use "seq_file" instead. The legacy /proc
+ * interfaces cut loff_t down to off_t for reads, and ignore
+ * the offset entirely for writes..
+ */
+ pos = *ppos;
+ if (pos > MAX_NON_LFS)
+ return 0;
+ if (nbytes > MAX_NON_LFS - pos)
+ nbytes = MAX_NON_LFS - pos;
dp = PDE(inode);
- if (!(page = (char*) __get_free_page(GFP_KERNEL)))
+ if (!(page = (char*) __get_free_page(GFP_TEMPORARY)))
return -ENOMEM;
while ((nbytes > 0) && !eof) {
count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
start = NULL;
- if (dp->get_info) {
- /* Handle old net routines */
- n = dp->get_info(page, &start, *ppos, count);
- if (n < count)
- eof = 1;
- } else if (dp->read_proc) {
+ if (dp->read_proc) {
/*
* How to be a proc read function
* ------------------------------
}
static ssize_t
+proc_file_read(struct file *file, char __user *buf, size_t nbytes,
+ loff_t *ppos)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ spin_unlock(&pde->pde_unload_lock);
+
+ rv = __proc_file_read(file, buf, nbytes, ppos);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static ssize_t
proc_file_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
- struct inode *inode = file->f_dentry->d_inode;
- struct proc_dir_entry * dp;
-
- dp = PDE(inode);
-
- if (!dp->write_proc)
- return -EIO;
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+
+ if (pde->write_proc) {
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ spin_unlock(&pde->pde_unload_lock);
- /* FIXME: does this routine need ppos? probably... */
- return dp->write_proc(file, buffer, count, dp->data);
+ /* FIXME: does this routine need ppos? probably... */
+ rv = pde->write_proc(file, buffer, count, pde->data);
+ pde_users_dec(pde);
+ }
+ return rv;
}
static loff_t
proc_file_lseek(struct file *file, loff_t offset, int orig)
{
- lock_kernel();
-
- switch (orig) {
- case 0:
- if (offset < 0)
- goto out;
- file->f_pos = offset;
- unlock_kernel();
- return(file->f_pos);
- case 1:
- if (offset + file->f_pos < 0)
- goto out;
- file->f_pos += offset;
- unlock_kernel();
- return(file->f_pos);
- case 2:
- goto out;
- default:
- goto out;
- }
-
-out:
- unlock_kernel();
- return -EINVAL;
+ loff_t retval = -EINVAL;
+ switch (orig) {
+ case 1:
+ offset += file->f_pos;
+ /* fallthrough */
+ case 0:
+ if (offset < 0 || offset > MAX_NON_LFS)
+ break;
+ file->f_pos = retval = offset;
+ }
+ return retval;
}
+static const struct file_operations proc_file_operations = {
+ .llseek = proc_file_lseek,
+ .read = proc_file_read,
+ .write = proc_file_write,
+};
+
static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
return error;
}
-static struct inode_operations proc_file_inode_operations = {
+static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ struct proc_dir_entry *de = PROC_I(inode)->pde;
+ if (de && de->nlink)
+ inode->i_nlink = de->nlink;
+
+ generic_fillattr(inode, stat);
+ return 0;
+}
+
+static const struct inode_operations proc_file_inode_operations = {
.setattr = proc_notify_change,
};
* returns the struct proc_dir_entry for "/proc/tty/driver", and
* returns "serial" in residual.
*/
-static int xlate_proc_name(const char *name,
- struct proc_dir_entry **ret, const char **residual)
+static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+ const char **residual)
{
const char *cp = name, *next;
struct proc_dir_entry *de;
int len;
- de = &proc_root;
+ de = *ret;
+ if (!de)
+ de = &proc_root;
+
while (1) {
next = strchr(cp, '/');
if (!next)
if (proc_match(len, cp, de))
break;
}
- if (!de)
+ if (!de) {
+ WARN(1, "name '%s'\n", name);
return -ENOENT;
+ }
cp += len + 1;
}
*residual = cp;
return 0;
}
-static DEFINE_IDR(proc_inum_idr);
+static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+ const char **residual)
+{
+ int rv;
+
+ spin_lock(&proc_subdir_lock);
+ rv = __xlate_proc_name(name, ret, residual);
+ spin_unlock(&proc_subdir_lock);
+ return rv;
+}
+
+static DEFINE_IDA(proc_inum_ida);
static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
-#define PROC_DYNAMIC_FIRST 0xF0000000UL
+#define PROC_DYNAMIC_FIRST 0xF0000000U
/*
* Return an inode number between PROC_DYNAMIC_FIRST and
* 0xffffffff, or zero on failure.
+ *
+ * Current inode allocations in the proc-fs (hex-numbers):
+ *
+ * 00000000 reserved
+ * 00000001-00000fff static entries (goners)
+ * 001 root-ino
+ *
+ * 00001000-00001fff unused
+ * 0001xxxx-7fffxxxx pid-dir entries for pid 1-7fff
+ * 80000000-efffffff unused
+ * f0000000-ffffffff dynamic entries
+ *
+ * Goal:
+ * Once we split the thing into several virtual filesystems,
+ * we will get rid of magical ranges (and this comment, BTW).
*/
static unsigned int get_inode_number(void)
{
- int i, inum = 0;
+ unsigned int i;
int error;
retry:
- if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
+ if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)
return 0;
spin_lock(&proc_inum_lock);
- error = idr_get_new(&proc_inum_idr, NULL, &i);
+ error = ida_get_new(&proc_inum_ida, &i);
spin_unlock(&proc_inum_lock);
if (error == -EAGAIN)
goto retry;
else if (error)
return 0;
- inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;
-
- /* inum will never be more than 0xf0ffffff, so no check
- * for overflow.
- */
-
- return inum;
+ if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+ spin_lock(&proc_inum_lock);
+ ida_remove(&proc_inum_ida, i);
+ spin_unlock(&proc_inum_lock);
+ return 0;
+ }
+ return PROC_DYNAMIC_FIRST + i;
}
static void release_inode_number(unsigned int inum)
{
- int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;
-
spin_lock(&proc_inum_lock);
- idr_remove(&proc_inum_idr, id);
+ ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
spin_unlock(&proc_inum_lock);
}
return NULL;
}
-static struct inode_operations proc_link_inode_operations = {
+static const struct inode_operations proc_link_inode_operations = {
.readlink = generic_readlink,
.follow_link = proc_follow_link,
};
return 1;
}
-static struct dentry_operations proc_dentry_operations =
+static const struct dentry_operations proc_dentry_operations =
{
.d_delete = proc_delete_dentry,
};
* Don't create negative dentries here, return -ENOENT by hand
* instead.
*/
-struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
+ struct dentry *dentry)
{
struct inode *inode = NULL;
- struct proc_dir_entry * de;
int error = -ENOENT;
- lock_kernel();
- de = PDE(dir);
- if (de) {
- for (de = de->subdir; de ; de = de->next) {
- if (de->namelen != dentry->d_name.len)
- continue;
- if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
- unsigned int ino = de->low_ino;
-
- error = -EINVAL;
- inode = proc_get_inode(dir->i_sb, ino, de);
- break;
- }
+ spin_lock(&proc_subdir_lock);
+ for (de = de->subdir; de ; de = de->next) {
+ if (de->namelen != dentry->d_name.len)
+ continue;
+ if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
+ unsigned int ino;
+
+ ino = de->low_ino;
+ pde_get(de);
+ spin_unlock(&proc_subdir_lock);
+ error = -EINVAL;
+ inode = proc_get_inode(dir->i_sb, ino, de);
+ goto out_unlock;
}
}
- unlock_kernel();
+ spin_unlock(&proc_subdir_lock);
+out_unlock:
if (inode) {
dentry->d_op = &proc_dentry_operations;
d_add(dentry, inode);
return NULL;
}
+ if (de)
+ pde_put(de);
return ERR_PTR(error);
}
+struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return proc_lookup_de(PDE(dir), dir, dentry);
+}
+
/*
* This returns non-zero if at EOF, so that the /proc
* root directory can use this and check if it should
* value of the readdir() call, as long as it's non-negative
* for success..
*/
-int proc_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
+ filldir_t filldir)
{
- struct proc_dir_entry * de;
unsigned int ino;
int i;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = filp->f_path.dentry->d_inode;
int ret = 0;
- lock_kernel();
-
ino = inode->i_ino;
- de = PDE(inode);
- if (!de) {
- ret = -EINVAL;
- goto out;
- }
i = filp->f_pos;
switch (i) {
case 0:
/* fall through */
case 1:
if (filldir(dirent, "..", 2, i,
- parent_ino(filp->f_dentry),
+ parent_ino(filp->f_path.dentry),
DT_DIR) < 0)
goto out;
i++;
filp->f_pos++;
/* fall through */
default:
+ spin_lock(&proc_subdir_lock);
de = de->subdir;
i -= 2;
for (;;) {
if (!de) {
ret = 1;
+ spin_unlock(&proc_subdir_lock);
goto out;
}
if (!i)
}
do {
+ struct proc_dir_entry *next;
+
+ /* filldir passes info to user space */
+ pde_get(de);
+ spin_unlock(&proc_subdir_lock);
if (filldir(dirent, de->name, de->namelen, filp->f_pos,
- de->low_ino, de->mode >> 12) < 0)
+ de->low_ino, de->mode >> 12) < 0) {
+ pde_put(de);
goto out;
+ }
+ spin_lock(&proc_subdir_lock);
filp->f_pos++;
- de = de->next;
+ next = de->next;
+ pde_put(de);
+ de = next;
} while (de);
+ spin_unlock(&proc_subdir_lock);
}
ret = 1;
-out: unlock_kernel();
+out:
return ret;
}
+int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+ struct inode *inode = filp->f_path.dentry->d_inode;
+
+ return proc_readdir_de(PDE(inode), filp, dirent, filldir);
+}
+
/*
* These are the generic /proc directory operations. They
* use the in-memory "struct proc_dir_entry" tree to parse
* the /proc directory.
*/
-static struct file_operations proc_dir_operations = {
+static const struct file_operations proc_dir_operations = {
+ .llseek = generic_file_llseek,
.read = generic_read_dir,
.readdir = proc_readdir,
};
/*
* proc directories can do almost nothing..
*/
-static struct inode_operations proc_dir_inode_operations = {
+static const struct inode_operations proc_dir_inode_operations = {
.lookup = proc_lookup,
+ .getattr = proc_getattr,
.setattr = proc_notify_change,
};
static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
{
unsigned int i;
+ struct proc_dir_entry *tmp;
i = get_inode_number();
if (i == 0)
return -EAGAIN;
dp->low_ino = i;
- dp->next = dir->subdir;
- dp->parent = dir;
- dir->subdir = dp;
+
if (S_ISDIR(dp->mode)) {
if (dp->proc_iops == NULL) {
dp->proc_fops = &proc_dir_operations;
if (dp->proc_iops == NULL)
dp->proc_iops = &proc_file_inode_operations;
}
- return 0;
-}
-/*
- * Kill an inode that got unregistered..
- */
-static void proc_kill_inodes(struct proc_dir_entry *de)
-{
- struct list_head *p;
- struct super_block *sb = proc_mnt->mnt_sb;
+ spin_lock(&proc_subdir_lock);
- /*
- * Actually it's a partial revoke().
- */
- file_list_lock();
- list_for_each(p, &sb->s_files) {
- struct file * filp = list_entry(p, struct file, f_list);
- struct dentry * dentry = filp->f_dentry;
- struct inode * inode;
- struct file_operations *fops;
-
- if (dentry->d_op != &proc_dentry_operations)
- continue;
- inode = dentry->d_inode;
- if (PDE(inode) != de)
- continue;
- fops = filp->f_op;
- filp->f_op = NULL;
- fops_put(fops);
- }
- file_list_unlock();
+ for (tmp = dir->subdir; tmp; tmp = tmp->next)
+ if (strcmp(tmp->name, dp->name) == 0) {
+ WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n",
+ dir->name, dp->name);
+ break;
+ }
+
+ dp->next = dir->subdir;
+ dp->parent = dir;
+ dir->subdir = dp;
+ spin_unlock(&proc_subdir_lock);
+
+ return 0;
}
-static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent,
+static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
const char *name,
mode_t mode,
nlink_t nlink)
/* make sure name is valid */
if (!name || !strlen(name)) goto out;
- if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0)
+ if (xlate_proc_name(name, parent, &fn) != 0)
goto out;
/* At this point there must not be any '/' characters beyond *fn */
ent->namelen = len;
ent->mode = mode;
ent->nlink = nlink;
+ atomic_set(&ent->count, 1);
+ ent->pde_users = 0;
+ spin_lock_init(&ent->pde_unload_lock);
+ ent->pde_unload_completion = NULL;
+ INIT_LIST_HEAD(&ent->pde_openers);
out:
return ent;
}
{
struct proc_dir_entry *ent;
- ent = proc_create(&parent,name,
+ ent = __proc_create(&parent, name,
(S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);
if (ent) {
}
return ent;
}
+EXPORT_SYMBOL(proc_symlink);
struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
struct proc_dir_entry *parent)
{
struct proc_dir_entry *ent;
- ent = proc_create(&parent, name, S_IFDIR | mode, 2);
+ ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
if (ent) {
- ent->proc_fops = &proc_dir_operations;
- ent->proc_iops = &proc_dir_inode_operations;
+ if (proc_register(parent, ent) < 0) {
+ kfree(ent);
+ ent = NULL;
+ }
+ }
+ return ent;
+}
+struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
+ struct proc_dir_entry *parent)
+{
+ struct proc_dir_entry *ent;
+
+ ent = __proc_create(&parent, name, S_IFDIR | S_IRUGO | S_IXUGO, 2);
+ if (ent) {
+ ent->data = net;
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
}
return ent;
}
+EXPORT_SYMBOL_GPL(proc_net_mkdir);
struct proc_dir_entry *proc_mkdir(const char *name,
struct proc_dir_entry *parent)
{
return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent);
}
+EXPORT_SYMBOL(proc_mkdir);
struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
struct proc_dir_entry *parent)
nlink = 1;
}
- ent = proc_create(&parent,name,mode,nlink);
+ ent = __proc_create(&parent, name, mode, nlink);
if (ent) {
- if (S_ISDIR(mode)) {
- ent->proc_fops = &proc_dir_operations;
- ent->proc_iops = &proc_dir_inode_operations;
- }
if (proc_register(parent, ent) < 0) {
kfree(ent);
ent = NULL;
}
return ent;
}
+EXPORT_SYMBOL(create_proc_entry);
+
+struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
+ struct proc_dir_entry *parent,
+ const struct file_operations *proc_fops,
+ void *data)
+{
+ struct proc_dir_entry *pde;
+ nlink_t nlink;
+
+ if (S_ISDIR(mode)) {
+ if ((mode & S_IALLUGO) == 0)
+ mode |= S_IRUGO | S_IXUGO;
+ nlink = 2;
+ } else {
+ if ((mode & S_IFMT) == 0)
+ mode |= S_IFREG;
+ if ((mode & S_IALLUGO) == 0)
+ mode |= S_IRUGO;
+ nlink = 1;
+ }
+
+ pde = __proc_create(&parent, name, mode, nlink);
+ if (!pde)
+ goto out;
+ pde->proc_fops = proc_fops;
+ pde->data = data;
+ if (proc_register(parent, pde) < 0)
+ goto out_free;
+ return pde;
+out_free:
+ kfree(pde);
+out:
+ return NULL;
+}
+EXPORT_SYMBOL(proc_create_data);
-void free_proc_entry(struct proc_dir_entry *de)
+static void free_proc_entry(struct proc_dir_entry *de)
{
unsigned int ino = de->low_ino;
release_inode_number(ino);
- if (S_ISLNK(de->mode) && de->data)
+ if (S_ISLNK(de->mode))
kfree(de->data);
kfree(de);
}
+void pde_put(struct proc_dir_entry *pde)
+{
+ if (atomic_dec_and_test(&pde->count))
+ free_proc_entry(pde);
+}
+
/*
* Remove a /proc entry and free it if it's not currently in use.
- * If it is in use, we set the 'deleted' flag.
*/
void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
{
struct proc_dir_entry **p;
- struct proc_dir_entry *de;
+ struct proc_dir_entry *de = NULL;
const char *fn = name;
int len;
- if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
- goto out;
+ spin_lock(&proc_subdir_lock);
+ if (__xlate_proc_name(name, &parent, &fn) != 0) {
+ spin_unlock(&proc_subdir_lock);
+ return;
+ }
len = strlen(fn);
+
for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (!proc_match(len, fn, *p))
- continue;
- de = *p;
- *p = de->next;
- de->next = NULL;
- if (S_ISDIR(de->mode))
- parent->nlink--;
- proc_kill_inodes(de);
- de->nlink = 0;
- WARN_ON(de->subdir);
- if (!atomic_read(&de->count))
- free_proc_entry(de);
- else {
- de->deleted = 1;
- printk("remove_proc_entry: %s/%s busy, count=%d\n",
- parent->name, de->name, atomic_read(&de->count));
+ if (proc_match(len, fn, *p)) {
+ de = *p;
+ *p = de->next;
+ de->next = NULL;
+ break;
}
- break;
}
-out:
- return;
+ spin_unlock(&proc_subdir_lock);
+ if (!de) {
+ WARN(1, "name '%s'\n", name);
+ return;
+ }
+
+ spin_lock(&de->pde_unload_lock);
+ /*
+ * Stop accepting new callers into module. If you're
+ * dynamically allocating ->proc_fops, save a pointer somewhere.
+ */
+ de->proc_fops = NULL;
+ /* Wait until all existing callers into module are done. */
+ if (de->pde_users > 0) {
+ DECLARE_COMPLETION_ONSTACK(c);
+
+ if (!de->pde_unload_completion)
+ de->pde_unload_completion = &c;
+
+ spin_unlock(&de->pde_unload_lock);
+
+ wait_for_completion(de->pde_unload_completion);
+
+ goto continue_removing;
+ }
+ spin_unlock(&de->pde_unload_lock);
+
+continue_removing:
+ spin_lock(&de->pde_unload_lock);
+ while (!list_empty(&de->pde_openers)) {
+ struct pde_opener *pdeo;
+
+ pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+ list_del(&pdeo->lh);
+ spin_unlock(&de->pde_unload_lock);
+ pdeo->release(pdeo->inode, pdeo->file);
+ kfree(pdeo);
+ spin_lock(&de->pde_unload_lock);
+ }
+ spin_unlock(&de->pde_unload_lock);
+
+ if (S_ISDIR(de->mode))
+ parent->nlink--;
+ de->nlink = 0;
+ WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
+ "'%s/%s', leaking at least '%s'\n", __func__,
+ de->parent->name, de->name, de->subdir->name);
+ pde_put(de);
}
+EXPORT_SYMBOL(remove_proc_entry);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff