From c2319540cd7330fa9066e5b9b84d357a2c8631a2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 28 Nov 2007 16:21:23 -0800 Subject: [PATCH] proc: fix NULL ->i_fop oops proc_kill_inodes() can clear ->i_fop in the middle of vfs_readdir resulting in NULL dereference during "file->f_op->readdir(file, buf, filler)". The solution is to remove proc_kill_inodes() completely: a) we don't have tricky modules implementing their tricky readdir hooks which could keeping this revoke from hell. b) In a situation when module is gone but PDE still alive, standard readdir will return only "." and "..", because pde->next was cleared by remove_proc_entry(). c) the race proc_kill_inode() destined to prevent is not completely fixed, just race window made smaller, because vfs_readdir() is run without sb_lock held and without file_list_lock held. Effectively, ->i_fop is cleared at random moment, which can't fix properly anything. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000018 printing eip: c1061205 *pdpt = 0000000005b22001 *pde = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw sr_mod k8temp cdrom hwmon amd_rng Pid: 2033, comm: find Not tainted (2.6.24-rc1-b1d08ac064268d0ae2281e98bf5e82627e0f0c56 #2) EIP: 0060:[] EFLAGS: 00010246 CPU: 0 EIP is at vfs_readdir+0x47/0x74 EAX: c6b6a780 EBX: 00000000 ECX: c1061040 EDX: c5decf94 ESI: c6b6a780 EDI: fffffffe EBP: c9797c54 ESP: c5decf78 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process find (pid: 2033, ti=c5dec000 task=c64bba90 task.ti=c5dec000) Stack: c5decf94 c1061040 fffffff7 0805ffbc 00000000 c6b6a780 c1061295 0805ffbc 00000000 00000400 00000000 00000004 0805ffbc 4588eff4 c5dec000 c10026ba 00000004 0805ffbc 00000400 0805ffbc 4588eff4 bfdc6c70 000000dc 0000007b Call Trace: [] filldir64+0x0/0xc5 [] sys_getdents64+0x63/0xa5 [] sysenter_past_esp+0x5f/0x85 ======================= Code: 49 83 78 18 00 74 43 8d 6b 74 bf fe ff ff ff 89 e8 e8 b8 c0 12 00 f6 83 2c 01 00 00 10 75 22 8b 5e 10 8b 4c 24 04 89 f0 8b 14 24 53 18 f6 46 1a 04 89 c7 75 0b 8b 56 0c 8b 46 08 e8 c8 66 00 EIP: [] vfs_readdir+0x47/0x74 SS:ESP 0068:c5decf78 hch: "Nice, getting rid of this is a very good step formwards. Unfortunately we have another copy of this junk in security/selinux/selinuxfs.c:sel_remove_entries() which would need the same treatment." Signed-off-by: Alexey Dobriyan Acked-by: Christoph Hellwig Cc: Al Viro Cc: Stephen Smalley Cc: James Morris Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/generic.c | 37 ------------------------------------- fs/proc/internal.h | 2 -- fs/proc/root.c | 2 +- 3 files changed, 1 insertion(+), 40 deletions(-) diff --git a/fs/proc/generic.c b/fs/proc/generic.c index a9806bc21e..39f3d65190 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -555,41 +555,6 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp 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; - - /* - * Actually it's a partial revoke(). - */ - spin_lock(&sb_lock); - list_for_each_entry(sb, &proc_fs_type.fs_supers, s_instances) { - file_list_lock(); - list_for_each(p, &sb->s_files) { - struct file *filp = list_entry(p, struct file, - f_u.fu_list); - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode; - const 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(); - } - spin_unlock(&sb_lock); -} - static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, const char *name, mode_t mode, @@ -764,8 +729,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) continue_removing: if (S_ISDIR(de->mode)) parent->nlink--; - 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/internal.h b/fs/proc/internal.h index 1b2b6c6bb4..1820eb2ef7 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -78,5 +78,3 @@ static inline int proc_fd(struct inode *inode) { return PROC_I(inode)->fd; } - -extern struct file_system_type proc_fs_type; diff --git a/fs/proc/root.c b/fs/proc/root.c index 1f86bb860e..ec9cb3b6c9 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -98,7 +98,7 @@ static void proc_kill_sb(struct super_block *sb) put_pid_ns(ns); } -struct file_system_type proc_fs_type = { +static struct file_system_type proc_fs_type = { .name = "proc", .get_sb = proc_get_sb, .kill_sb = proc_kill_sb, -- 2.39.5