Replace pid_t in autofs4 with struct pid reference.
PATCH 1/1 Replace pid_t in autofs4 with struct pid reference.
I resurect and refreshed this old patch from
https://lists.linux-foundation.org/pipermail/containers/2007-February/003726.html
This patch makes automount to work within a container.
Make autofs4 container-friendly by caching struct pid reference rather than pid_t and using pid_nr() to retreive a task's pid_t.
ChangeLog:
- Refreshed against linux-next (added dev-ioctl.c)
- Fix Eric Biederman's comments - Use find_get_pid() to hold a reference to oz_pgrp and release while unmounting; separate out changes to autofs and autofs4.
- Also rollback my earlier change to autofs_wait_queue (pid and tgid in the wait queue are just used to write to a userspace daemon's pipe).
- Fix Cedric's comments: retain old prototype of parse_options() and move necessary change to its caller.
--- fs/autofs4/autofs_i.h | 28 ++++++++++++++-------------- fs/autofs4/dev-ioctl.c | 2 +- fs/autofs4/inode.c | 22 ++++++++++++++++------ fs/autofs4/root.c | 3 ++- fs/autofs4/waitq.c | 4 ++-- 5 files changed, 35 insertions(+), 24 deletions(-)
fs/autofs4/autofs_i.h +14 -14
@@ -39,25 +39,25 @@/* #define DEBUG */ #ifdef DEBUG -#define DPRINTK(fmt, args...) \ -do { \ - printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define DPRINTK(fmt, args...) \ +do { \ + printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0)#else #define DPRINTK(fmt, args...) do {} while (0)#endif -#define AUTOFS_WARN(fmt, args...) \ -do { \ - printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define AUTOFS_WARN(fmt, args...) \ +do { \ + printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0) -#define AUTOFS_ERROR(fmt, args...) \ -do { \ - printk(KERN_ERR "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define AUTOFS_ERROR(fmt, args...) \ +do { \ + printk(KERN_ERR "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0)/* Unified info structure. This is pointed to by both the dentry and
@@ -122,7 +122,7 @@ struct autofs_sb_info {u32 magic;int pipefd;struct file *pipe; -pid_t oz_pgrp; +struct pid *oz_pgrp;int catatonic;int version;int sub_version;
@@ -156,7 +156,7 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)filesystem without "magic".) */ static inline int autofs4_oz_mode (struct autofs_sb_info *sbi) { -return sbi->catatonic ||task_pgrp_nr (current) == sbi->oz_pgrp; +return sbi->catatonic ||task_pgrp (current) == sbi->oz_pgrp; }/* Does a dentry have some pending activity? */
fs/autofs4/dev-ioctl.c +1 -1
@@ -377,7 +377,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,fput (pipe); goto out; } - sbi->oz_pgrp =task_pgrp_nr (current); + sbi->oz_pgrp =task_pgrp (current); sbi->pipefd = pipefd; sbi->pipe = pipe; sbi->catatonic =0 ;
fs/autofs4/inode.c +16 -6
@@ -111,7 +111,7 @@ void autofs4_kill_sb(struct super_block *sb)/* Free wait queues, close pipe */ autofs4_catatonic_mode (sbi); - +put_pid (sbi->oz_pgrp); sb->s_fs_info =NULL ;kfree (sbi);
@@ -133,7 +133,7 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt)seq_printf (m,",uid=%u" , root_inode->i_uid);if (root_inode->i_gid !=0 )seq_printf (m,",gid=%u" , root_inode->i_gid); -seq_printf (m,",pgrp=%d" , sbi->oz_pgrp); +seq_printf (m,",pgrp=%d" ,pid_nr (sbi->oz_pgrp));seq_printf (m,",timeout=%lu" , sbi->exp_timeout/HZ );seq_printf (m,",minproto=%d" , sbi->min_proto);seq_printf (m,",maxproto=%d" , sbi->max_proto);
@@ -263,6 +263,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)int pipefd;struct autofs_sb_info *sbi;struct autofs_info *ino; +pid_t pgid; sbi =kzalloc (sizeof (*sbi),GFP_KERNEL );if (!sbi)
@@ -275,7 +276,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipe =NULL ; sbi->catatonic =1 ; sbi->exp_timeout =0 ; - sbi->oz_pgrp =task_pgrp_nr (current); + sbi->oz_pgrp =task_pgrp (current); sbi->sb = s; sbi->version =0 ; sbi->sub_version =0 ;
@@ -314,7 +315,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)/* Can this call block? */ if (parse_options (data, &pipefd, &root_inode->i_uid, &root_inode->i_gid, - &sbi->oz_pgrp, &sbi->type, &sbi->min_proto, + &pgid, &sbi->type, &sbi->min_proto, &sbi->max_proto)) {printk ("autofs: called with bogus options\n" ); goto fail_dput;
@@ -342,12 +343,19 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->version = sbi->max_proto; sbi->sub_version =AUTOFS_PROTO_SUBVERSION ; -DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, sbi->oz_pgrp); +DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, pgid); + + sbi->oz_pgrp =find_get_pid (pgid); +if (!sbi->oz_pgrp) { +printk ("autofs: could not find process group %d\n" , pgid); + goto fail_dput; + } + pipe =fget (pipefd);if (!pipe) {printk ("autofs: could not open pipe file descriptor\n" ); - goto fail_dput; + goto fail_put_pid; }if (!pipe->f_op || !pipe->f_op->write) goto fail_fput;
@@ -368,6 +376,8 @@ fail_fput:printk ("autofs: pipe file descriptor does not contain proper ops\n" );fput (pipe);/* fall through */ +fail_put_pid: +put_pid (sbi->oz_pgrp); fail_dput:dput (root); goto fail_free;
fs/autofs4/root.c +2 -1
@@ -539,7 +539,8 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s oz_mode =autofs4_oz_mode (sbi);DPRINTK ("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d" , - current->pid,task_pgrp_nr (current), sbi->catatonic, oz_mode); +pid_nr (task_pid (current)),task_pgrp_nr (current), + sbi->catatonic, oz_mode); active =autofs4_lookup_active (dentry);if (active) {
fs/autofs4/waitq.c +2 -2
@@ -387,8 +387,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, wq->ino =autofs4_get_ino (sbi); wq->uid =current_uid (); wq->gid =current_gid (); - wq->pid = current->pid; - wq->tgid = current->tgid; + wq->pid =pid_nr (task_pid (current)); + wq->tgid =pid_nr (task_tgid (current)); wq->status = -EINTR ;/* Status return if interrupted */ wq->wait_ctr =2 ;mutex_unlock (&sbi->wq_mutex);
Signature · 1 line
1.7.0.4
A message that is not in the archive (sent off-list or not yet received): 1285840564-10251-1-git-send-email-daniel.lezcano-GANU6spQydw@public.gmane.org
Quoted 157 lines · Daniel Lezcano
I resurect and refreshed this old patch from
https://lists.linux-foundation.org/pipermail/containers/2007-February/003726.htmlThis patch makes automount to work within a container.
Make autofs4 container-friendly by caching struct pid reference rather than
pid_tand usingpid_nr()to retreive a task'spid_t.ChangeLog:
- Refreshed against linux-next (addeddev-ioctl.c)
- Fix Eric Biederman's comments - Usefind_get_pid()to hold a reference tooz_pgrpand release while unmounting; separate out changes to autofs and autofs4.
- Also rollback my earlier change toautofs_wait_queue(pid and tgid in the wait queue are just used to write to a userspace daemon's pipe).
- Fix Cedric's comments: retain old prototype ofparse_options()and move necessary change to its caller.Signed-off-by Sukadev Bhattiprolu <sukadev-r/[email protected]>Signed-off-by Daniel Lezcano <[email protected]>Cc Ian Kent <[email protected]>Cc Cedric Le Goater <clg-NmTC/[email protected]>Cc Dave Hansen <haveblue-r/[email protected]>Cc Serge E. Hallyn <[email protected]>Cc Eric Biederman <ebiederm-aS9lmoZGLiVWk0Htik3J/[email protected]>Cc Helmut Lichtenberg <[email protected]>--- fs/autofs4/autofs_i.h | 28 ++++++++++++++-------------- fs/autofs4/dev-ioctl.c | 2 +- fs/autofs4/inode.c | 22 ++++++++++++++++------ fs/autofs4/root.c | 3 ++- fs/autofs4/waitq.c | 4 ++-- 5 files changed, 35 insertions(+), 24 deletions(-)fs/autofs4/autofs_i.h +14
-14@@ -39,25 +39,25 @@/* #define DEBUG */ #ifdef DEBUG -#define DPRINTK(fmt, args...) \ -do { \ - printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define DPRINTK(fmt, args...) \ +do { \ + printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0)#else #define DPRINTK(fmt, args...) do {} while (0)#endif -#define AUTOFS_WARN(fmt, args...) \ -do { \ - printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define AUTOFS_WARN(fmt, args...) \ +do { \ + printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0) -#define AUTOFS_ERROR(fmt, args...) \ -do { \ - printk(KERN_ERR "pid %d: %s: " fmt "\n", \ - current->pid, __func__, ##args); \ +#define AUTOFS_ERROR(fmt, args...) \ +do { \ + printk(KERN_ERR "pid %d: %s: " fmt "\n", \ + pid_nr(task_pid(current)), __func__, ##args); \ } while (0)/* Unified info structure. This is pointed to by both the dentry and @@ -122,7 +122,7 @@ struct autofs_sb_info {u32 magic;int pipefd;struct file *pipe; -pid_t oz_pgrp; +struct pid *oz_pgrp;int catatonic;int version;int sub_version;@@ -156,7 +156,7 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)filesystem without "magic".) */ static inline int autofs4_oz_mode (struct autofs_sb_info *sbi) { -return sbi->catatonic ||task_pgrp_nr (current) == sbi->oz_pgrp; +return sbi->catatonic ||task_pgrp (current) == sbi->oz_pgrp; }/* Does a dentry have some pending activity? */ fs/autofs4/dev-ioctl.c +1
-1@@ -377,7 +377,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,fput (pipe); goto out; } - sbi->oz_pgrp =task_pgrp_nr (current); + sbi->oz_pgrp =task_pgrp (current); sbi->pipefd = pipefd; sbi->pipe = pipe; sbi->catatonic =0 ;fs/autofs4/inode.c +5
-4@@ -111,7 +111,7 @@ void autofs4_kill_sb(struct super_block *sb)/* Free wait queues, close pipe */ autofs4_catatonic_mode (sbi); - +put_pid (sbi->oz_pgrp); sb->s_fs_info =NULL ;kfree (sbi);@@ -133,7 +133,7 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt)seq_printf (m,",uid=%u" , root_inode->i_uid);if (root_inode->i_gid !=0 )seq_printf (m,",gid=%u" , root_inode->i_gid); -seq_printf (m,",pgrp=%d" , sbi->oz_pgrp); +seq_printf (m,",pgrp=%d" ,pid_nr (sbi->oz_pgrp));seq_printf (m,",timeout=%lu" , sbi->exp_timeout/HZ );seq_printf (m,",minproto=%d" , sbi->min_proto);seq_printf (m,",maxproto=%d" , sbi->max_proto);@@ -263,6 +263,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)int pipefd;struct autofs_sb_info *sbi;struct autofs_info *ino; +pid_t pgid; sbi =kzalloc (sizeof (*sbi),GFP_KERNEL );if (!sbi)@@ -275,7 +276,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipe =NULL ; sbi->catatonic =1 ; sbi->exp_timeout =0 ; - sbi->oz_pgrp =task_pgrp_nr (current); + sbi->oz_pgrp =task_pgrp (current); sbi->sb = s; sbi->version =0 ; sbi->sub_version =0 ;@@ -314,7 +315,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)/* Can this call block? */ if (parse_options (data, &pipefd, &root_inode->i_uid, &root_inode->i_gid, - &sbi->oz_pgrp, &sbi->type, &sbi->min_proto, + &pgid, &sbi->type, &sbi->min_proto, &sbi->max_proto)) {printk ("autofs: called with bogus options\n" ); goto fail_dput;
fs/autofs4/inode.c int autofs4_fill_super(struct super_block *s, void *data, int silent) · line 348
Quoted 7 lines
fs/autofs4/inode.c +3
-1@@ -342,12 +343,19 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->version = sbi->max_proto; sbi->sub_version =AUTOFS_PROTO_SUBVERSION ; -DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, sbi->oz_pgrp); +DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, pgid); + + sbi->oz_pgrp =find_get_pid (pgid);
This is a little backward. You first get current's pgid pid, but don't take a reference; then parse_options gets current's pgid pid_nr (and keeps that if no pgid was specified), passes that back here, and here we get the pid_nr and take a ref. I was actually first going to say that I didn't want to block this patch on this, but it should be cleaned up at some point (i.e. at top of this function get the struct pid and get a ref, pass that to parse_options, and have parse_options get the specified pgid instead if a valid one was passed in.
But now I'm wondering whether this actually is unsafe, bc I'm not quite sure how to read the comment above task_pgrp() (in sched.h) says not to dereference this if it wasn't gotten under task_lock or rcu_read_lock. Which this isn't. So is this actually unsafe?
fs/autofs4/inode.c int autofs4_fill_super(struct super_block *s, void *data, int silent) · line 354
Quoted 6 lines
fs/autofs4/inode.c +5
-0+if (!sbi->oz_pgrp) { +printk ("autofs: could not find process group %d\n" , pgid); + goto fail_dput; + } + pipe =fget (pipefd);
thanks,
-serge
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 31 lines · Serge Hallyn
Quoted 29 lines · Daniel Lezcano
I resurect and refreshed this old patch from
https://lists.linux-foundation.org/pipermail/containers/2007-February/003726.htmlThis patch makes automount to work within a container.
Make autofs4 container-friendly by caching struct pid reference rather than
pid_tand usingpid_nr()to retreive a task'spid_t.ChangeLog:
- Refreshed against linux-next (addeddev-ioctl.c)
- Fix Eric Biederman's comments - Usefind_get_pid()to hold a reference tooz_pgrpand release while unmounting; separate out changes to autofs and autofs4.
- Also rollback my earlier change toautofs_wait_queue(pid and tgid in the wait queue are just used to write to a userspace daemon's pipe).
- Fix Cedric's comments: retain old prototype ofparse_options()and move necessary change to its caller.Signed-off-by Sukadev Bhattiprolu<sukadev-r/[email protected]>Signed-off-by Daniel Lezcano<[email protected]>Cc Ian Kent<[email protected]>Cc Cedric Le Goater<clg-NmTC/[email protected]>Cc Dave Hansen<haveblue-r/[email protected]>Cc Serge E. Hallyn<[email protected]>Cc Eric Biederman<ebiederm-aS9lmoZGLiVWk0Htik3J/[email protected]>Cc Helmut Lichtenberg<[email protected]>---
[ cut ]
Quoted 39 lines
Quoted 39 lines
fs/autofs4/inode.c +4
-3@@ -133,7 +133,7 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt)seq_printf (m,",uid=%u" , root_inode->i_uid);if (root_inode->i_gid !=0 )seq_printf (m,",gid=%u" , root_inode->i_gid); -seq_printf (m,",pgrp=%d" , sbi->oz_pgrp); +seq_printf (m,",pgrp=%d" ,pid_nr (sbi->oz_pgrp));seq_printf (m,",timeout=%lu" , sbi->exp_timeout/HZ );seq_printf (m,",minproto=%d" , sbi->min_proto);seq_printf (m,",maxproto=%d" , sbi->max_proto);@@ -263,6 +263,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)int pipefd;struct autofs_sb_info *sbi;struct autofs_info *ino; +pid_t pgid; sbi =kzalloc (sizeof (*sbi),GFP_KERNEL );if (!sbi)@@ -275,7 +276,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipe =NULL ; sbi->catatonic =1 ; sbi->exp_timeout =0 ; - sbi->oz_pgrp =task_pgrp_nr (current); + sbi->oz_pgrp =task_pgrp (current); sbi->sb = s; sbi->version =0 ; sbi->sub_version =0 ;@@ -314,7 +315,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)/* Can this call block? */ if (parse_options (data,&pipefd,&root_inode->i_uid,&root_inode->i_gid, - &sbi->oz_pgrp,&sbi->type,&sbi->min_proto, + &pgid,&sbi->type,&sbi->min_proto, &sbi->max_proto)) {printk ("autofs: called with bogus options\n" ); goto fail_dput;@@ -342,12 +343,19 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->version = sbi->max_proto; sbi->sub_version =AUTOFS_PROTO_SUBVERSION ;
Quoted 14 lines
fs/autofs4/inode.c int autofs4_fill_super(struct super_block *s, void *data, int silent) · line 355
Quoted 5 lines
fs/autofs4/inode.c +3
-1-DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, sbi->oz_pgrp); +DPRINTK ("pipe fd = %d, pgrp = %u" , pipefd, pgid); + + sbi->oz_pgrp =find_get_pid (pgid);This is a little backward. You first get current's pgid pid, but don't take a reference; then
parse_optionsgets current's pgidpid_nr(and keeps that if no pgid was specified), passes that back here, and here we get thepid_nrand take a ref. I was actually first going to say that I didn't want to block this patch on this, but it should be cleaned up at some point (i.e. at top of this function get the struct pid and get a ref, pass that toparse_options, and haveparse_optionsget the specified pgid instead if a valid one was passed in.
I agree, I will cleanup this part.
Also, I noticed the:
...
case Opt_pgrp:
if (match_int(args, &option))
return 1;
*pgrp = option;
break;
...ouch !
Quoted 5 lines
But now I'm wondering whether this actually is unsafe, bc I'm not quite sure how to read the comment above
task_pgrp()(insched.h) says not to dereference this if it wasn't gotten undertask_lockorrcu_read_lock. Which this isn't. So is this actually unsafe?
Good point.
task_pgrp_nr calls __task_pid_nr_ns which does rcu_read_lock. task_pgrp does not take any lock.
So you are right, replacing task_pgrp_nr by task_pgrp is unsafe.
I suppose get_task_pid(current, PIDTYPE_PGID) is the right call.
Thanks for looking at the patch.
-- Daniel