summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAlexey Dobriyan <adobriyan@sw.ru>2007-07-15 23:39:00 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-07-16 09:05:39 -0700
commit786d7e1612f0b0adb6046f19b906609e4fe8b1ba (patch)
tree9d5f1623c19c9d3f84606ea160d57cd3c8c97ea9
parent5568b0e8028d966ddb16f0be44a9df1fcbd1dc8d (diff)
downloadop-kernel-dev-786d7e1612f0b0adb6046f19b906609e4fe8b1ba.zip
op-kernel-dev-786d7e1612f0b0adb6046f19b906609e4fe8b1ba.tar.gz
Fix rmmod/read/write races in /proc entries
Fix following races: =========================================== 1. Write via ->write_proc sleeps in copy_from_user(). Module disappears meanwhile. Or, more generically, system call done on /proc file, method supplied by module is called, module dissapeares meanwhile. pde = create_proc_entry() if (!pde) return -ENOMEM; pde->write_proc = ... open write copy_from_user pde = create_proc_entry(); if (!pde) { remove_proc_entry(); return -ENOMEM; /* module unloaded */ } *boom* ========================================== 2. bogo-revoke aka proc_kill_inodes() remove_proc_entry vfs_read proc_kill_inodes [check ->f_op validness] [check ->f_op->read validness] [verify_area, security permissions checks] ->f_op = NULL; if (file->f_op->read) /* ->f_op dereference, boom */ NOTE, NOTE, NOTE: file_operations are proxied for regular files only. Let's see how this scheme behaves, then extend if needed for directories. Directories creators in /proc only set ->owner for them, so proxying for directories may be unneeded. NOTE, NOTE, NOTE: methods being proxied are ->llseek, ->read, ->write, ->poll, ->unlocked_ioctl, ->ioctl, ->compat_ioctl, ->open, ->release. If your in-tree module uses something else, yell on me. Full audit pending. [akpm@linux-foundation.org: build fix] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/proc/generic.c32
-rw-r--r--fs/proc/inode.c254
-rw-r--r--include/linux/proc_fs.h13
3 files changed, 296 insertions, 3 deletions
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8a40e15..4f8e535 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -20,6 +20,7 @@
#include <linux/namei.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
+#include <linux/completion.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -613,6 +614,9 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent,
ent->namelen = len;
ent->mode = mode;
ent->nlink = nlink;
+ ent->pde_users = 0;
+ spin_lock_init(&ent->pde_unload_lock);
+ ent->pde_unload_completion = NULL;
out:
return ent;
}
@@ -734,9 +738,35 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
de = *p;
*p = de->next;
de->next = NULL;
+
+ 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);
+ spin_unlock(&proc_subdir_lock);
+
+ wait_for_completion(de->pde_unload_completion);
+
+ spin_lock(&proc_subdir_lock);
+ goto continue_removing;
+ }
+ spin_unlock(&de->pde_unload_lock);
+
+continue_removing:
if (S_ISDIR(de->mode))
parent->nlink--;
- proc_kill_inodes(de);
+ if (!S_ISREG(de->mode))
+ proc_kill_inodes(de);
de->nlink = 0;
WARN_ON(de->subdir);
if (!atomic_read(&de->count))
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d5ce65c..dd28e86 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -10,6 +10,7 @@
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
+#include <linux/completion.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
@@ -140,6 +141,251 @@ static const struct super_operations proc_sops = {
.remount_fs = proc_remount,
};
+static void pde_users_dec(struct proc_dir_entry *pde)
+{
+ spin_lock(&pde->pde_unload_lock);
+ pde->pde_users--;
+ if (pde->pde_unload_completion && pde->pde_users == 0)
+ complete(pde->pde_unload_completion);
+ spin_unlock(&pde->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ loff_t rv = -EINVAL;
+ loff_t (*llseek)(struct file *, loff_t, int);
+
+ spin_lock(&pde->pde_unload_lock);
+ /*
+ * remove_proc_entry() is going to delete PDE (as part of module
+ * cleanup sequence). No new callers into module allowed.
+ */
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ /*
+ * Bump refcount so that remove_proc_entry will wail for ->llseek to
+ * complete.
+ */
+ pde->pde_users++;
+ /*
+ * Save function pointer under lock, to protect against ->proc_fops
+ * NULL'ifying right after ->pde_unload_lock is dropped.
+ */
+ llseek = pde->proc_fops->llseek;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (!llseek)
+ llseek = default_llseek;
+ rv = llseek(file, offset, whence);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+ ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ read = pde->proc_fops->read;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (read)
+ rv = read(file, buf, count, ppos);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ ssize_t rv = -EIO;
+ ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ write = pde->proc_fops->write;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (write)
+ rv = write(file, buf, count, ppos);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ unsigned int rv = 0;
+ unsigned int (*poll)(struct file *, struct poll_table_struct *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ poll = pde->proc_fops->poll;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (poll)
+ rv = poll(file, pts);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ long rv = -ENOTTY;
+ long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long);
+ int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ unlocked_ioctl = pde->proc_fops->unlocked_ioctl;
+ ioctl = pde->proc_fops->ioctl;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (unlocked_ioctl) {
+ rv = unlocked_ioctl(file, cmd, arg);
+ if (rv == -ENOIOCTLCMD)
+ rv = -EINVAL;
+ } else if (ioctl) {
+ lock_kernel();
+ rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
+ unlock_kernel();
+ }
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ long rv = -ENOTTY;
+ long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ compat_ioctl = pde->proc_fops->compat_ioctl;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (compat_ioctl)
+ rv = compat_ioctl(file, cmd, arg);
+
+ pde_users_dec(pde);
+ return rv;
+}
+#endif
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ int rv = -EIO;
+ int (*mmap)(struct file *, struct vm_area_struct *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ mmap = pde->proc_fops->mmap;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (mmap)
+ rv = mmap(file, vma);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *pde = PDE(inode);
+ int rv = 0;
+ int (*open)(struct inode *, struct file *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ open = pde->proc_fops->open;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (open)
+ rv = open(inode, file);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *pde = PDE(inode);
+ int rv = 0;
+ int (*release)(struct inode *, struct file *);
+
+ spin_lock(&pde->pde_unload_lock);
+ if (!pde->proc_fops) {
+ spin_unlock(&pde->pde_unload_lock);
+ return rv;
+ }
+ pde->pde_users++;
+ release = pde->proc_fops->release;
+ spin_unlock(&pde->pde_unload_lock);
+
+ if (release)
+ rv = release(inode, file);
+
+ pde_users_dec(pde);
+ return rv;
+}
+
+static const struct file_operations proc_reg_file_ops = {
+ .llseek = proc_reg_llseek,
+ .read = proc_reg_read,
+ .write = proc_reg_write,
+ .poll = proc_reg_poll,
+ .unlocked_ioctl = proc_reg_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = proc_reg_compat_ioctl,
+#endif
+ .mmap = proc_reg_mmap,
+ .open = proc_reg_open,
+ .release = proc_reg_release,
+};
+
struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
struct proc_dir_entry *de)
{
@@ -166,8 +412,12 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
inode->i_nlink = de->nlink;
if (de->proc_iops)
inode->i_op = de->proc_iops;
- if (de->proc_fops)
- inode->i_fop = de->proc_fops;
+ if (de->proc_fops) {
+ if (S_ISREG(inode->i_mode))
+ inode->i_fop = &proc_reg_file_ops;
+ else
+ inode->i_fop = de->proc_fops;
+ }
}
return inode;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 3469f96..28e3664 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -7,6 +7,8 @@
#include <linux/magic.h>
#include <asm/atomic.h>
+struct completion;
+
/*
* The proc filesystem constants/structures
*/
@@ -56,6 +58,14 @@ struct proc_dir_entry {
gid_t gid;
loff_t size;
const struct inode_operations *proc_iops;
+ /*
+ * NULL ->proc_fops means "PDE is going away RSN" or
+ * "PDE is just created". In either case, e.g. ->read_proc won't be
+ * called because it's too late or too early, respectively.
+ *
+ * If you're allocating ->proc_fops dynamically, save a pointer
+ * somewhere.
+ */
const struct file_operations *proc_fops;
get_info_t *get_info;
struct module *owner;
@@ -66,6 +76,9 @@ struct proc_dir_entry {
atomic_t count; /* use count */
int deleted; /* delete flag */
void *set;
+ int pde_users; /* number of callers into module in progress */
+ spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
+ struct completion *pde_unload_completion;
};
struct kcore_list {
OpenPOWER on IntegriCloud