From: NeilBrown <neilb@suse.de>
Date: Sun, 6 Mar 2022 23:41:44 +0000 (+1100)
Subject: SUNRPC/auth: async tasks mustn't block waiting for memory
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=a41b05edfedb939440e83666f23de3ef9af33acf;p=linux.git

SUNRPC/auth: async tasks mustn't block waiting for memory

When memory is short, new worker threads cannot be created and we depend
on the minimum one rpciod thread to be able to handle everything.  So it
must not block waiting for memory.

mempools are particularly a problem as memory can only be released back
to the mempool by an async rpc task running.  If all available workqueue
threads are waiting on the mempool, no thread is available to return
anything.

lookup_cred() can block on a mempool or kmalloc - and this can cause
deadlocks.  So add a new RPCAUTH_LOOKUP flag for async lookups and don't
block on memory.  If the -ENOMEM gets back to call_refreshresult(), wait
a short while and try again.  HZ>>4 is chosen as it is used elsewhere
for -ENOMEM retries.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 98da816b5fc2a..3e6ce288a7fc0 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -99,6 +99,7 @@ struct rpc_auth_create_args {
 
 /* Flags for rpcauth_lookupcred() */
 #define RPCAUTH_LOOKUP_NEW		0x01	/* Accept an uninitialised cred */
+#define RPCAUTH_LOOKUP_ASYNC		0x02	/* Don't block waiting for memory */
 
 /*
  * Client authentication ops
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index a9f0d17fdb0d6..6bfa19f9fa6a9 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -615,6 +615,8 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
 	};
 	struct rpc_cred *ret;
 
+	if (RPC_IS_ASYNC(task))
+		lookupflags |= RPCAUTH_LOOKUP_ASYNC;
 	ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags);
 	put_cred(acred.cred);
 	return ret;
@@ -631,6 +633,8 @@ rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags)
 
 	if (!acred.principal)
 		return NULL;
+	if (RPC_IS_ASYNC(task))
+		lookupflags |= RPCAUTH_LOOKUP_ASYNC;
 	return auth->au_ops->lookup_cred(auth, &acred, lookupflags);
 }
 
@@ -654,7 +658,7 @@ rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags)
 	};
 
 	if (flags & RPC_TASK_ASYNC)
-		lookupflags |= RPCAUTH_LOOKUP_NEW;
+		lookupflags |= RPCAUTH_LOOKUP_NEW | RPCAUTH_LOOKUP_ASYNC;
 	if (task->tk_op_cred)
 		/* Task must use exactly this rpc_cred */
 		new = get_rpccred(task->tk_op_cred);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index affd64a54f02d..ac08281082048 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1341,7 +1341,11 @@ gss_hash_cred(struct auth_cred *acred, unsigned int hashbits)
 static struct rpc_cred *
 gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
-	return rpcauth_lookup_credcache(auth, acred, flags, GFP_KERNEL);
+	gfp_t gfp = GFP_KERNEL;
+
+	if (flags & RPCAUTH_LOOKUP_ASYNC)
+		gfp = GFP_NOWAIT | __GFP_NOWARN;
+	return rpcauth_lookup_credcache(auth, acred, flags, gfp);
 }
 
 static struct rpc_cred *
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 3600d86416448..c629d366030ee 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -43,8 +43,14 @@ unx_destroy(struct rpc_auth *auth)
 static struct rpc_cred *
 unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 {
-	struct rpc_cred *ret = mempool_alloc(unix_pool, GFP_KERNEL);
-
+	gfp_t gfp = GFP_KERNEL;
+	struct rpc_cred *ret;
+
+	if (flags & RPCAUTH_LOOKUP_ASYNC)
+		gfp = GFP_NOWAIT | __GFP_NOWARN;
+	ret = mempool_alloc(unix_pool, gfp);
+	if (!ret)
+		return ERR_PTR(-ENOMEM);
 	rpcauth_init_cred(ret, acred, auth, &unix_credops);
 	ret->cr_flags = 1UL << RPCAUTH_CRED_UPTODATE;
 	return ret;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 97165a545cb3c..9556eb7b065b6 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1745,6 +1745,9 @@ call_refreshresult(struct rpc_task *task)
 		task->tk_cred_retry--;
 		trace_rpc_retry_refresh_status(task);
 		return;
+	case -ENOMEM:
+		rpc_delay(task, HZ >> 4);
+		return;
 	}
 	trace_rpc_refresh_status(task);
 	rpc_call_rpcerror(task, status);