ipc: conserve sequence numbers in extended IPCMNI mode

The mixing in of a sequence number into the IPC IDs is probably to avoid
ID reuse in userspace as much as possible.  With extended IPCMNI mode, the
number of usable sequence numbers is greatly reduced leading to higher
chance of ID reuse.

To address this issue, we need to conserve the sequence number space as
much as possible.  Right now, the sequence number is incremented for every
new ID created.  In reality, we only need to increment the sequence number
when one or more IDs have been removed previously to make sure that those
IDs will not be reused when a new one is built.  This is being done only
in the new extended IPCMNI mode.

Link: http://lkml.kernel.org/r/1536352137-12003-5-git-send-email-longman@redhat.com
Signed-off-by: Waiman Long <longman@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

4 files changed, 20 insertions, 4 deletions

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 6ab8c1bada3f..7d5f553a3b24 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -16,6 +16,7 @@ struct user_namespace;
 struct ipc_ids {
 	int in_use;
 	unsigned short seq;
+	unsigned short deleted;
 	struct rw_semaphore rwsem;
 	struct idr ipcs_idr;
 	int max_idx;
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 73b7782eccf4..d9ac6caf6a5e 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -122,6 +122,7 @@ static int one = 1;
 static int int_max = INT_MAX;
 int ipc_mni = IPCMNI;
 int ipc_mni_shift = IPCMNI_SHIFT;
+bool ipc_mni_extended;
 
 static struct ctl_table ipc_kern_table[] = {
 	{
@@ -252,6 +253,7 @@ static int __init ipc_mni_extend(char *str)
 {
 	ipc_mni = IPCMNI_EXTEND;
 	ipc_mni_shift = IPCMNI_EXTEND_SHIFT;
+	ipc_mni_extended = true;
 	pr_info("IPCMNI extended to %d.\n", ipc_mni);
 	return 0;
 }
diff --git a/ipc/util.c b/ipc/util.c
index 07ae117ccdc0..3f11a81cf9b7 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -115,7 +115,8 @@ static const struct rhashtable_params ipc_kht_params = {
 void ipc_init_ids(struct ipc_ids *ids)
 {
 	ids->in_use = 0;
-	ids->seq = 0;
+	ids->deleted = false;
+	ids->seq = ipc_mni_extended ? 0 : -1; /* seq # is pre-incremented */
 	init_rwsem(&ids->rwsem);
 	rhashtable_init(&ids->key_ht, &ipc_kht_params);
 	idr_init(&ids->ipcs_idr);
@@ -198,6 +199,11 @@ static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new)
 {
 	int idx, next_id = -1;
 
+/*
+ * To conserve sequence number space with extended ipc_mni when new ID
+ * is built, the sequence number is incremented only when one or more
+ * IDs have been removed previously.
+ */
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	next_id = ids->next_id;
 	ids->next_id = -1;
@@ -216,9 +222,13 @@ static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new)
 	 */
 
 	if (next_id < 0) { /* !CHECKPOINT_RESTORE or next_id is unset */
-		new->seq = ids->seq++;
-		if (ids->seq > IPCID_SEQ_MAX)
-			ids->seq = 0;
+		if (!ipc_mni_extended || ids->deleted) {
+			ids->seq++;
+			if (ids->seq > IPCID_SEQ_MAX)
+				ids->seq = 0;
+			ids->deleted = false;
+		}
+		new->seq = ids->seq;
 		idx = idr_alloc(&ids->ipcs_idr, new, 0, 0, GFP_NOWAIT);
 	} else {
 		new->seq = ipcid_to_seqx(next_id);
@@ -436,6 +446,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 	idr_remove(&ids->ipcs_idr, idx);
 	ipc_kht_remove(ids, ipcp);
 	ids->in_use--;
+	ids->deleted = true;
 	ipcp->deleted = true;
 
 	if (unlikely(idx == ids->max_idx)) {
diff --git a/ipc/util.h b/ipc/util.h
index 644df117852c..127c0fedbd09 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -33,6 +33,7 @@
 #ifdef CONFIG_SYSVIPC_SYSCTL
 extern int ipc_mni;
 extern int ipc_mni_shift;
+extern bool ipc_mni_extended;
 
 #define IPCMNI_SEQ_SHIFT	ipc_mni_shift
 #define IPCMNI_IDX_MASK		((1 << ipc_mni_shift) - 1)
@@ -40,6 +41,7 @@ extern int ipc_mni_shift;
 #else /* CONFIG_SYSVIPC_SYSCTL */
 
 #define ipc_mni			IPCMNI
+#define ipc_mni_extended	false
 #define IPCMNI_SEQ_SHIFT	IPCMNI_SHIFT
 #define IPCMNI_IDX_MASK		((1 << IPCMNI_SHIFT) - 1)
 #endif /* CONFIG_SYSVIPC_SYSCTL */