sys_unshare: simplify the not-really-implemented CLONE_THREAD/SIGHAND/VM code
Subsystems (3)
PATCH 1/1 sys_unshare: simplify the not-really-implemented CLONE_THREAD/SIGHAND/VM code
(on top of check_unshare_flags-kill-the-bogus-clone_sighand-sig-count-check.patch)
Cleanup.
sys_unshare(CLONE_THREAD/SIGHAND/VM) is not really implemented, and I doubt very much it will ever work. At least, nobody even tried since the original "unshare system call -v5: system call handler function" commit 99d1419d96d7df9cfa56bc977810be831bd5ef64 was applied more than 4 years ago.
And the code is not consistent. unshare_thread() always fails unconditionally, while unshare_sighand() and unshare_vm() pretend to work if there is nothing to unshare.
Remove unshare_thread(), unshare_sighand(), unshare_vm() helpers and related variables and add a simple CLONE_THREAD | CLONE_SIGHAND| CLONE_VM check into check_unshare_flags().
Also, move the "CLONE_NEWNS needs CLONE_FS" check from check_unshare_flags() to sys_unshare(). This looks more consistent and matches the similar do_sysvsem check in sys_unshare().
Note: with or without this patch "atomic_read(mm->mm_users) > 1" can give a false positive due to get_task_mm().
---
kernel/fork.c | 119 ++++++++++++---------------------------------------------- 1 file changed, 25 insertions(+), 94 deletions(-)
kernel/fork.c renamed from kernel/fork.c~UNSHARE_KILL_THE_BOGUS_CODE +25 -94
@@ -1500,38 +1500,24 @@ void __init proc_caches_init(void) }/* -* Check constraints on flags passed to the unshare system call and -* force unsharing of additional process context as appropriate. +* Check constraints on flags passed to the unshare system call. */ -static void check_unshare_flags (unsigned long *flags_ptr) +static int check_unshare_flags (unsigned long unshare_flags) { +if (unshare_flags & ~(CLONE_THREAD |CLONE_FS |CLONE_NEWNS |CLONE_SIGHAND | +CLONE_VM |CLONE_FILES |CLONE_SYSVSEM | +CLONE_NEWUTS |CLONE_NEWIPC |CLONE_NEWNET )) +return -EINVAL ;/* -* If unsharing a thread from a thread group, must also -* unshare vm. -*/ -if (*flags_ptr &CLONE_THREAD ) - *flags_ptr |=CLONE_VM ; - -/* -* If unsharing vm, must also unshare signal handlers. -*/ -if (*flags_ptr &CLONE_VM ) - *flags_ptr |=CLONE_SIGHAND ; - -/* -* If unsharing namespace, must also unshare filesystem information. +* Not implemented, but pretend it works if there is nothing to +* unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND +* needs to unshare vm. */ -if (*flags_ptr &CLONE_NEWNS ) - *flags_ptr |=CLONE_FS ; -} - -/* -* Unsharing of tasks created with CLONE_THREAD is not supported yet -*/ -static int unshare_thread (unsigned long unshare_flags) -{ -if (unshare_flags &CLONE_THREAD ) -return -EINVAL ; +if (unshare_flags & (CLONE_THREAD |CLONE_SIGHAND |CLONE_VM )) { +/* FIXME: get_task_mm() increments ->mm_users */ +if (atomic_read (¤t->mm->mm_users) >1 ) +return -EINVAL ; + }return 0 ; }
@@ -1558,34 +1544,6 @@ static int unshare_fs(unsigned long unsh }/* -* Unsharing of sighand is not supported yet -*/ -static int unshare_sighand (unsigned long unshare_flags,struct sighand_struct **new_sighp) -{ -struct sighand_struct *sigh = current->sighand; - -if ((unshare_flags &CLONE_SIGHAND ) &&atomic_read (&sigh->count) >1 ) -return -EINVAL ; -else -return 0 ; -} - -/* -* Unshare vm if it is being shared -*/ -static int unshare_vm (unsigned long unshare_flags,struct mm_struct **new_mmp) -{ -struct mm_struct *mm = current->mm; - -if ((unshare_flags &CLONE_VM ) && - (mm &&atomic_read (&mm->mm_users) >1 )) { -return -EINVAL ; - } - -return 0 ; -} - -/* * Unshare file descriptor table if it is being shared */ static int unshare_fd (unsigned long unshare_flags,struct files_struct **new_fdp)
@@ -1613,45 +1571,37 @@ static int unshare_fd(unsigned long unsh*/ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { -int err =0 ;struct fs_struct *fs, *new_fs =NULL ; -struct sighand_struct *new_sigh =NULL ; -struct mm_struct *mm, *new_mm =NULL , *active_mm =NULL ;struct files_struct *fd, *new_fd =NULL ;struct nsproxy *new_nsproxy =NULL ;int do_sysvsem =0 ; +int err; -check_unshare_flags (&unshare_flags); - -/* Return -EINVAL for all unsupported flags */ - err = -EINVAL ; -if (unshare_flags & ~(CLONE_THREAD |CLONE_FS |CLONE_NEWNS |CLONE_SIGHAND | -CLONE_VM |CLONE_FILES |CLONE_SYSVSEM | -CLONE_NEWUTS |CLONE_NEWIPC |CLONE_NEWNET )) + err =check_unshare_flags (unshare_flags); +if (err) goto bad_unshare_out;/* +* If unsharing namespace, must also unshare filesystem information. +*/ +if (unshare_flags &CLONE_NEWNS ) + unshare_flags |=CLONE_FS ; +/* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC |CLONE_SYSVSEM )) do_sysvsem =1 ; -if ((err =unshare_thread (unshare_flags))) - goto bad_unshare_out;if ((err =unshare_fs (unshare_flags, &new_fs))) - goto bad_unshare_cleanup_thread; -if ((err =unshare_sighand (unshare_flags, &new_sigh))) - goto bad_unshare_cleanup_fs; -if ((err =unshare_vm (unshare_flags, &new_mm))) - goto bad_unshare_cleanup_sigh; + goto bad_unshare_out;if ((err =unshare_fd (unshare_flags, &new_fd))) - goto bad_unshare_cleanup_vm; + goto bad_unshare_cleanup_fs;if ((err =unshare_nsproxy_namespaces (unshare_flags, &new_nsproxy, new_fs))) goto bad_unshare_cleanup_fd; -if (new_fs || new_mm || new_fd || do_sysvsem || new_nsproxy) { +if (new_fs || new_fd || do_sysvsem || new_nsproxy) {if (do_sysvsem) {/* * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1677,15 +1627,6 @@ SYSCALL_DEFINE1(unshare, unsigned long,write_unlock (&fs->lock); } -if (new_mm) { - mm = current->mm; - active_mm = current->active_mm; - current->mm = new_mm; - current->active_mm = new_mm; -activate_mm (active_mm, new_mm); - new_mm = mm; - } -if (new_fd) { fd = current->files; current->files = new_fd;
@@ -1702,20 +1643,10 @@ bad_unshare_cleanup_fd:if (new_fd)put_files_struct (new_fd); -bad_unshare_cleanup_vm: -if (new_mm) -mmput (new_mm); - -bad_unshare_cleanup_sigh: -if (new_sigh) -if (atomic_dec_and_test (&new_sigh->count)) -kmem_cache_free (sighand_cachep, new_sigh); - bad_unshare_cleanup_fs:if (new_fs)free_fs_struct (new_fs); -bad_unshare_cleanup_thread: bad_unshare_out:return err; }
Quoted 4 lines · Oleg Nesterov
(on top of check_unshare_flags-kill-the-bogus-clone_sighand-sig-count-check.patch)
Cleanup.
Quoted 8 lines
sys_unshare(CLONE_THREAD/SIGHAND/VM)is not really implemented, and I doubt very much it will ever work. At least, nobody even tried since the original "unshare system call -v5: system call handler function" commit99d1419d96d7df9cfa56bc977810be831bd5ef64was applied more than 4 years ago.And the code is not consistent.
unshare_thread()always fails unconditionally, whileunshare_sighand()andunshare_vm()pretend to work if there is nothing to unshare.
This is setting off alarm bells in my head.
I haven't traced this all through but I like your logic a lot less, and I think it is buggy. Why don't we need to look at sigh->count ?
The current logic is very fine grained but it does a lot of simple logical checks and it ties those checks together if a very maintainable way.
You require that we know upfront all of the dependencies, which is things change subtlety can be a maintenance challenge.
Quoted 10 lines
Remove
unshare_thread(),unshare_sighand(),unshare_vm()helpers and related variables and add a simpleCLONE_THREAD| CLONE_SIGHAND|CLONE_VMcheck intocheck_unshare_flags().Also, move the "
CLONE_NEWNSneedsCLONE_FS" check fromcheck_unshare_flags()tosys_unshare(). This looks more consistent and matches the similardo_sysvsemcheck insys_unshare().Note: with or without this patch "
atomic_read(mm->mm_users)> 1" can give a false positive due toget_task_mm().
I think the number of times get_task_mm is called on not current this isn't an interesting race.
Eric
Quoted 12 lines · Eric W. Biederman
Quoted 9 lines · Oleg Nesterov
(on top of check_unshare_flags-kill-the-bogus-clone_sighand-sig-count-check.patch)
Cleanup.
sys_unshare(CLONE_THREAD/SIGHAND/VM)is not really implemented, and I doubt very much it will ever work. At least, nobody even tried since the original "unshare system call -v5: system call handler function" commit99d1419d96d7df9cfa56bc977810be831bd5ef64was applied more than 4 years ago.
Quoted 8 lines
Quoted 3 lines
And the code is not consistent.
unshare_thread()always fails unconditionally, whileunshare_sighand()andunshare_vm()pretend to work if there is nothing to unshare.This is setting off alarm bells in my head.
I haven't traced this all through but I like your logic a lot less, and I think it is buggy. Why don't we need to look at
sigh->count?
CLONE_SIGHAND needs CLONE_VM in copy_process(). It is not possible that sighand->count > 1 while mm->mm_users <= 1.
Quoted 2 lines
The current logic is very fine grained but it does a lot of simple logical checks and it ties those checks together if a very maintainable way.
I'd say the current simple logic is simple but wrong ;)
Before the recent changes check_unshare_flags() did
if (*flags_ptr & CLONE_THREAD) *flags_ptr |= CLONE_VM; ... if ((*flags_ptr & CLONE_SIGHAND) && (atomic_read(¤t->signal->count) > 1)) *flags_ptr |= CLONE_THREAD;
Now, if we add CLONE_THREAD, why we do not add CLONE_VM here? This is not right.
And why unshare_thread() always fails even in single-threaded case?
But,
Quoted 2 lines
You require that we know upfront all of the dependencies, which is things change subtlety can be a maintenance challenge.
Fortunately this all is not implemented anyway.
My point was: lets simplify this code, mainly to reduce the output from, say, "grep CLONE_SIGHAND". In my opinion, it is a bit strange that the code which doesn't really work adds the unnecessary dependencies to CLONE_THREAD/etc subtleness.
Quoted 5 lines
Quoted 2 lines
Note: with or without this patch "
atomic_read(mm->mm_users)> 1" can give a false positive due toget_task_mm().I think the number of times
get_task_mmis called on not current this isn't an interesting race.
Sure. I just meant that this check is wrong, but it was copied from the current code. We could use current_is_single_threaded() though.
That said, I do not really care about this cleanup. I did it just because I sent another patch which touches check_unshare_flags(), and I was really surprised that ~70 lines in kernel/fork.c do nothing but confuse the reader.
Please nack this patch and lets forget it ;)
Oleg.
Quoted 4 lines · Oleg Nesterov
That said, I do not really care about this cleanup. I did it just because I sent another patch which touches
check_unshare_flags(), and I was really surprised that ~70 lines inkernel/fork.cdo nothing but confuse the reader.
I changed my mind. I do care ;)
Seriously, Eric, it is just stupid this code does nothing but complicates fork.c, and unless you prove this patch is wrong you can't convince me this patch is bad idea.
Quoted 1 line
Please nack this patch and lets forget it ;)
Yes. You have all rights to nack it and I won't insist even if I disagree. But please do this explicitly, otherwise I'll resend it.
Oleg.
Thanks,
Roland