[PATCH v2 2/2] SUNRPC: Check svc pool percpu counter allocation

From: Chuck Lever <[email protected]>

__svc_create() initializes three per-pool percpu_counter stats and
ignores every return value. On SMP, percpu_counter_init() fails when
__alloc_percpu_gfp() cannot satisfy the allocation, leaving the failed
counter with fbc->counters == NULL and its embedded raw_spinlock_t,
list_head, and count never initialized. __svc_create() returns the
half-constructed svc_serv to nfsd, lockd, or the NFS callback service
anyway.

Once that service is live, the hot-path increments in
svc_xprt_enqueue(), svc_handle_xprt(), and
svc_pool_wake_idle_thread() reach a counter whose backing pointer is
NULL. The pointer is a per-cpu offset, so the access does not fault:
it resolves to offset zero of the current CPU's per-cpu area and
silently corrupts whatever variable lives there. A
/proc/fs/nfsd/pool_stats read walks the same NULL per-cpu storage and
returns garbage, and on CONFIG_DEBUG_SPINLOCK or lockdep it splats on
the never-initialized lock.

Creating the broken service requires a percpu allocation failure during
RPC server startup, so it is reachable only by a local administrator
under memory pressure or fault injection; a remote peer cannot induce
the bad state on its own.

Check each percpu_counter_init() return value in __svc_create() and
fail when an allocation fails, unwinding the counters already set up
in the current pool and in every pool initialized before it. A
discrete percpu_counter_destroy() per counter at teardown frees each
per-cpu allocation exactly once.

Fixes: ccf08bed6e7a ("SUNRPC: Replace pool stats with per-CPU variables")
Signed-off-by: Chuck Lever <[email protected]>
---
 net/sunrpc/svc.c | 45 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index ae9ec4bf34f7..009373737ea9 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -476,6 +476,35 @@ __svc_init_bc(struct svc_serv *serv)
 }
 #endif
 
+static int svc_pool_init_counters(struct svc_pool *pool)
+{
+	int err;
+
+	err = percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL);
+	if (err)
+		return err;
+	err = percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
+	if (err)
+		goto err_sockets;
+	err = percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
+	if (err)
+		goto err_threads;
+	return 0;
+
+err_threads:
+	percpu_counter_destroy(&pool->sp_sockets_queued);
+err_sockets:
+	percpu_counter_destroy(&pool->sp_messages_arrived);
+	return err;
+}
+
+static void svc_pool_destroy_counters(struct svc_pool *pool)
+{
+	percpu_counter_destroy(&pool->sp_messages_arrived);
+	percpu_counter_destroy(&pool->sp_sockets_queued);
+	percpu_counter_destroy(&pool->sp_threads_woken);
+}
+
 /*
  * Create an RPC service
  */
@@ -540,12 +569,18 @@ __svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats,
 		INIT_LIST_HEAD(&pool->sp_all_threads);
 		init_llist_head(&pool->sp_idle_threads);
 
-		percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL);
-		percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
-		percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
+		if (svc_pool_init_counters(pool))
+			goto out_err;
 	}
 
 	return serv;
+
+out_err:
+	while (i--)
+		svc_pool_destroy_counters(&serv->sv_pools[i]);
+	kfree(serv->sv_pools);
+	kfree(serv);
+	return NULL;
 }
 
 /**
@@ -624,9 +659,7 @@ svc_destroy(struct svc_serv **servp)
 	for (i = 0; i < serv->sv_nrpools; i++) {
 		struct svc_pool *pool = &serv->sv_pools[i];
 
-		percpu_counter_destroy(&pool->sp_messages_arrived);
-		percpu_counter_destroy(&pool->sp_sockets_queued);
-		percpu_counter_destroy(&pool->sp_threads_woken);
+		svc_pool_destroy_counters(pool);
 	}
 	kfree(serv->sv_pools);
 	kfree(serv);

-- 
2.54.0