crypto: pcrypt - Avoid deadlock by using per-instance padata queues

If the pcrypt template is used multiple times in an algorithm, then a
deadlock occurs because all pcrypt instances share the same
padata_instance, which completes requests in the order submitted.  That
is, the inner pcrypt request waits for the outer pcrypt request while
the outer request is already waiting for the inner.

This patch fixes this by allocating a set of queues for each pcrypt
instance instead of using two global queues.  In order to maintain
the existing user-space interface, the pinst structure remains global
so any sysfs modifications will apply to every pcrypt instance.

Note that when an update occurs we have to allocate memory for
every pcrypt instance.  Should one of the allocations fail we
will abort the update without rolling back changes already made.

The new per-instance data structure is called padata_shell and is
essentially a wrapper around parallel_data.

Reproducer:

	#include <linux/if_alg.h>
	#include <sys/socket.h>
	#include <unistd.h>

	int main()
	{
		struct sockaddr_alg addr = {
			.salg_type = "aead",
			.salg_name = "pcrypt(pcrypt(rfc4106-gcm-aesni))"
		};
		int algfd, reqfd;
		char buf[32] = { 0 };

		algfd = socket(AF_ALG, SOCK_SEQPACKET, 0);
		bind(algfd, (void *)&addr, sizeof(addr));
		setsockopt(algfd, SOL_ALG, ALG_SET_KEY, buf, 20);
		reqfd = accept(algfd, 0, 0);
		write(reqfd, buf, 32);
		read(reqfd, buf, 16);
	}

Reported-by: syzbot+56c7151cad94eec37c521f0e47d2eee53f9361c4@syzkaller.appspotmail.com
Fixes: 5068c7a883d1 ("crypto: pcrypt - Add pcrypt crypto parallelization wrapper")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 29 insertions, 5 deletions

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 23717eeaad23..cccab7a59787 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -9,6 +9,7 @@
 #ifndef PADATA_H
 #define PADATA_H
 
+#include <linux/compiler_types.h>
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
@@ -98,7 +99,7 @@ struct padata_cpumask {
  * struct parallel_data - Internal control structure, covers everything
  * that depends on the cpumask in use.
  *
- * @pinst: padata instance.
+ * @sh: padata_shell object.
  * @pqueue: percpu padata queues used for parallelization.
  * @squeue: percpu padata queues used for serialuzation.
  * @reorder_objects: Number of objects waiting in the reorder queues.
@@ -111,7 +112,7 @@ struct padata_cpumask {
  * @lock: Reorder lock.
  */
 struct parallel_data {
-	struct padata_instance		*pinst;
+	struct padata_shell		*ps;
 	struct padata_parallel_queue	__percpu *pqueue;
 	struct padata_serial_queue	__percpu *squeue;
 	atomic_t			reorder_objects;
@@ -125,13 +126,32 @@ struct parallel_data {
 };
 
 /**
+ * struct padata_shell - Wrapper around struct parallel_data, its
+ * purpose is to allow the underlying control structure to be replaced
+ * on the fly using RCU.
+ *
+ * @pinst: padat instance.
+ * @pd: Actual parallel_data structure which may be substituted on the fly.
+ * @opd: Pointer to old pd to be freed by padata_replace.
+ * @list: List entry in padata_instance list.
+ */
+struct padata_shell {
+	struct padata_instance		*pinst;
+	struct parallel_data __rcu	*pd;
+	struct parallel_data		*opd;
+	struct list_head		list;
+};
+
+/**
  * struct padata_instance - The overall control structure.
  *
  * @cpu_notifier: cpu hotplug notifier.
  * @parallel_wq: The workqueue used for parallel work.
  * @serial_wq: The workqueue used for serial work.
- * @pd: The internal control structure.
+ * @pslist: List of padata_shell objects attached to this instance.
  * @cpumask: User supplied cpumasks for parallel and serial works.
+ * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask.
+ * @omask: Temporary storage used to compute the notification mask.
  * @cpumask_change_notifier: Notifiers chain for user-defined notify
  *            callbacks that will be called when either @pcpu or @cbcpu
  *            or both cpumasks change.
@@ -143,8 +163,10 @@ struct padata_instance {
 	struct hlist_node		 node;
 	struct workqueue_struct		*parallel_wq;
 	struct workqueue_struct		*serial_wq;
-	struct parallel_data		*pd;
+	struct list_head		pslist;
 	struct padata_cpumask		cpumask;
+	struct padata_cpumask		rcpumask;
+	cpumask_var_t			omask;
 	struct blocking_notifier_head	 cpumask_change_notifier;
 	struct kobject                   kobj;
 	struct mutex			 lock;
@@ -156,7 +178,9 @@ struct padata_instance {
 
 extern struct padata_instance *padata_alloc_possible(const char *name);
 extern void padata_free(struct padata_instance *pinst);
-extern int padata_do_parallel(struct padata_instance *pinst,
+extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
+extern void padata_free_shell(struct padata_shell *ps);
+extern int padata_do_parallel(struct padata_shell *ps,
 			      struct padata_priv *padata, int *cb_cpu);
 extern void padata_do_serial(struct padata_priv *padata);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,