Re: [PATCH 2/6] ipc: reorganize initialization of kern_ipc_perm.seq

[Dmitry Vyukov]

On Thu, Jul 5, 2018 at 7:59 AM, Manfred Spraul <manfred@xxxxxxxxxxxxxxxx> wrote:
> ipc_addid() initializes kern_ipc_perm.seq after having called
> ipc_idr_alloc().
>
> Thus a parallel semop() or msgrcv() that uses ipc_obtain_object_check()
> may see an uninitialized value.
>
> The patch moves the initialization of kern_ipc_perm.seq before the
> calls of ipc_idr_alloc().
>
> Notes:
> 1) This patch has a user space visible side effect:
> If /proc/sys/kernel/*_next_id is used (i.e.: checkpoint/restore) and
> if semget()/msgget()/shmget() fails in the final step of adding the id
> to the rhash tree, then .._next_id is cleared. Before the patch, is
> remained unmodified.
>
> There is no change of the behavior after a successful ..get() call:
> It always clears .._next_id, there is no impact to non checkpoint/restore
> code as that code does not use .._next_id.
>
> 2) The patch correctly documents that after a call to ipc_idr_alloc(),
> the full tear-down sequence must be used. The callers of ipc_addid()
> do not fullfill that, i.e. more bugfixes are required.
>
> Reported-by: syzbot+2827ef6b3385deb07eaf@xxxxxxxxxxxxxxxxxxxxxxxxx
> Signed-off-by: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
> Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
> Cc: Kees Cook <keescook@xxxxxxxxxxxx>
> Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
> Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
> Signed-off-by: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
> ---
>  Documentation/sysctl/kernel.txt |  3 ++-
>  ipc/util.c                      | 45 +++++++++++++++++++++++----------
>  2 files changed, 34 insertions(+), 14 deletions(-)
>
> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
> index eded671d55eb..b2d4a8f8fe97 100644
> --- a/Documentation/sysctl/kernel.txt
> +++ b/Documentation/sysctl/kernel.txt
> @@ -440,7 +440,8 @@ Notes:
>  1) kernel doesn't guarantee, that new object will have desired id. So,
>  it's up to userspace, how to handle an object with "wrong" id.
>  2) Toggle with non-default value will be set back to -1 by kernel after
> -successful IPC object allocation.
> +successful IPC object allocation. If an IPC object allocation syscall
> +fails, it is undefined if the value remains unmodified or is reset to -1.
>
>  ==============================================================
>
> diff --git a/ipc/util.c b/ipc/util.c
> index 4e81182fa0ac..662c28c6c9fa 100644
> --- a/ipc/util.c
> +++ b/ipc/util.c
> @@ -197,13 +197,24 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
>  /*
>   * Specify desired id for next allocated IPC object.
>   */
> -#define ipc_idr_alloc(ids, new)                                                \
> -       idr_alloc(&(ids)->ipcs_idr, (new),                              \
> -                 (ids)->next_id < 0 ? 0 : ipcid_to_idx((ids)->next_id),\
> -                 0, GFP_NOWAIT)
> +static inline int ipc_idr_alloc(struct ipc_ids *ids,
> +                               struct kern_ipc_perm *new)
> +{
> +       int key;
>
> -static inline int ipc_buildid(int id, struct ipc_ids *ids,
> -                             struct kern_ipc_perm *new)
> +       if (ids->next_id < 0) {
> +               key = idr_alloc(&ids->ipcs_idr, new, 0, 0, GFP_NOWAIT);
> +       } else {
> +               key = idr_alloc(&ids->ipcs_idr, new,
> +                               ipcid_to_idx(ids->next_id),
> +                               0, GFP_NOWAIT);
> +               ids->next_id = -1;
> +       }
> +       return key;
> +}
> +
> +static inline void ipc_set_seq(struct ipc_ids *ids,
> +                               struct kern_ipc_perm *new)
>  {
>         if (ids->next_id < 0) { /* default, behave as !CHECKPOINT_RESTORE */
>                 new->seq = ids->seq++;
> @@ -211,24 +222,19 @@ static inline int ipc_buildid(int id, struct ipc_ids *ids,
>                         ids->seq = 0;
>         } else {
>                 new->seq = ipcid_to_seqx(ids->next_id);
> -               ids->next_id = -1;
>         }
> -
> -       return SEQ_MULTIPLIER * new->seq + id;
>  }
>
>  #else
>  #define ipc_idr_alloc(ids, new)                                        \
>         idr_alloc(&(ids)->ipcs_idr, (new), 0, 0, GFP_NOWAIT)
>
> -static inline int ipc_buildid(int id, struct ipc_ids *ids,
> +static inline void ipc_set_seq(struct ipc_ids *ids,
>                               struct kern_ipc_perm *new)
>  {
>         new->seq = ids->seq++;
>         if (ids->seq > IPCID_SEQ_MAX)
>                 ids->seq = 0;
> -
> -       return SEQ_MULTIPLIER * new->seq + id;
>  }
>
>  #endif /* CONFIG_CHECKPOINT_RESTORE */
> @@ -270,6 +276,19 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
>         new->cuid = new->uid = euid;
>         new->gid = new->cgid = egid;
>
> +       ipc_set_seq(ids, new);
> +
> +       /*
> +        * As soon as a new object is inserted into the idr,
> +        * ipc_obtain_object_idr() or ipc_obtain_object_check() can find it,
> +        * and the lockless preparations for ipc operations can start.
> +        * This means especially: permission checks, audit calls, allocation
> +        * of undo structures, ...
> +        *
> +        * Thus the object must be fully initialized, and if something fails,
> +        * then the full tear-down sequence must be followed.
> +        * (i.e.: set new->deleted, reduce refcount, call_rcu())
> +        */
>         id = ipc_idr_alloc(ids, new);
>         idr_preload_end();
>
> @@ -291,7 +310,7 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
>         if (id > ids->max_id)
>                 ids->max_id = id;
>
> -       new->id = ipc_buildid(id, ids, new);
> +       new->id = SEQ_MULTIPLIER * new->seq + id;
>
>         return id;
>  }


Hi Manfred,

The series looks like a significant improvement to me. Thanks!

I feel that this code can be further simplified (unless I am missing
something here). Please take a look at this version:

https://github.com/dvyukov/linux/commit/f77aeaf80f3c4ab524db92184d874b03063fea3a?diff=split

This is on top of your patches. It basically does the same as your
code, but consolidates all id/seq assignment and dealing with next_id,
and deduplicates code re CONFIG_CHECKPOINT_RESTORE. Currently it's a
bit tricky to follow e.g. where exactly next_id is consumed and where
it needs to be left intact.
The only difference is that my code assigns new->id earlier. Not sure
if it can lead to anything bad. But if yes, then it seems that
currently uninitialized new->id is exposed. If necessary (?) we could
reset new->id in the same place where we set new->deleted.

Other patches in the series look good to me.

p.s. I've uploaded full context diffs of all patches here:
https://github.com/dvyukov/linux/commits/ipc1
commit f77aeaf80f3c4ab524db92184d874b03063fea3a
Author: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Date:   Thu Jul 5 10:15:26 2018 +0200

    ipc_idr_alloc refactoring

diff --git a/ipc/util.c b/ipc/util.c
index 776a9ce2905f..c98675d8612e 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -193,52 +193,32 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
 	return NULL;
 }
 
-#ifdef CONFIG_CHECKPOINT_RESTORE
 /*
  * Specify desired id for next allocated IPC object.
  */
-static inline int ipc_idr_alloc(struct ipc_ids *ids,
-				struct kern_ipc_perm *new)
+static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new)
 {
-	int key;
+	int key, next_id = -1;
 
-	if (ids->next_id < 0) {
-		key = idr_alloc(&ids->ipcs_idr, new, 0, 0, GFP_NOWAIT);
-	} else {
-		key = idr_alloc(&ids->ipcs_idr, new,
-				ipcid_to_idx(ids->next_id),
-				0, GFP_NOWAIT);
-		ids->next_id = -1;
-	}
-	return key;
-}
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	next_id = ids->next_id;
+	ids->next_id = -1;
+#endif
 
-static inline void ipc_set_seq(struct ipc_ids *ids,
-				struct kern_ipc_perm *new)
-{
-	if (ids->next_id < 0) { /* default, behave as !CHECKPOINT_RESTORE */
+	if (next_id < 0) { /* !CHECKPOINT_RESTORE or next_id is unset */
 		new->seq = ids->seq++;
 		if (ids->seq > IPCID_SEQ_MAX)
 			ids->seq = 0;
+		key = idr_alloc(&ids->ipcs_idr, new, 0, 0, GFP_NOWAIT);
 	} else {
-		new->seq = ipcid_to_seqx(ids->next_id);
+		new->seq = ipcid_to_seqx(next_id);
+		key = idr_alloc(&ids->ipcs_idr, new, ipcid_to_idx(next_id),
+				0, GFP_NOWAIT);
 	}
+	new->id = SEQ_MULTIPLIER * new->seq + key;
+	return key;
 }
 
-#else
-#define ipc_idr_alloc(ids, new)					\
-	idr_alloc(&(ids)->ipcs_idr, (new), 0, 0, GFP_NOWAIT)
-
-static inline void ipc_set_seq(struct ipc_ids *ids,
-			      struct kern_ipc_perm *new)
-{
-	new->seq = ids->seq++;
-	if (ids->seq > IPCID_SEQ_MAX)
-		ids->seq = 0;
-}
-
-#endif /* CONFIG_CHECKPOINT_RESTORE */
-
 /**
  * ipc_addid - add an ipc identifier
  * @ids: ipc identifier set
@@ -278,8 +258,6 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
 	current_euid_egid(&euid, &egid);
 	new->cuid = new->uid = euid;
 	new->gid = new->cgid = egid;
-
-	ipc_set_seq(ids, new);
 	new->deleted = false;
 
 	/*
@@ -317,9 +295,6 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
 	ids->in_use++;
 	if (id > ids->max_id)
 		ids->max_id = id;
-
-	new->id = SEQ_MULTIPLIER * new->seq + id;
-
 	return id;
 }