Received-SPF: softfail (google.com: domain of transitioning linux-nfs-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   trondmy@kernel.org
To:     linux-nfs@vger.kernel.org
Cc:     Chuck Lever <chuck.lever@oracle.com>,
        Enrico Scholz <enrico.scholz@sigma-chemnitz.de>
Subject: [PATCH v2 1/9] NFS: Fix memory allocation in rpc_malloc()
Date:   Mon, 21 Mar 2022 21:47:38 -0400
Message-Id: <20220322014746.1052984-2-trondmy@kernel.org>
In-Reply-To: <20220322014746.1052984-1-trondmy@kernel.org>
References: <20220322014746.1052984-1-trondmy@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Trond Myklebust <trond.myklebust@hammerspace.com>

When in a low memory situation, we do want rpciod to kick off direct
reclaim in the case where that helps, however we don't want it looping
forever in mempool_alloc().
So first try allocating from the slab using GFP_KERNEL | __GFP_NORETRY,
and then fall back to a GFP_NOWAIT allocation from the mempool.

Ditto for rpc_alloc_task()

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/sched.h |  1 +
 net/sunrpc/sched.c           | 21 ++++++++++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 56710f8056d3..1d7a3e51b795 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -262,6 +262,7 @@ void		rpc_destroy_mempool(void);
 extern struct workqueue_struct *rpciod_workqueue;
 extern struct workqueue_struct *xprtiod_workqueue;
 void		rpc_prepare_task(struct rpc_task *task);
+gfp_t		rpc_task_gfp_mask(void);
 
 static inline int rpc_wait_for_completion_task(struct rpc_task *task)
 {
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 7c8f87ebdbc0..d59a033820be 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -57,6 +57,13 @@ struct workqueue_struct *rpciod_workqueue __read_mostly;
 struct workqueue_struct *xprtiod_workqueue __read_mostly;
 EXPORT_SYMBOL_GPL(xprtiod_workqueue);
 
+gfp_t rpc_task_gfp_mask(void)
+{
+	if (current->flags & PF_WQ_WORKER)
+		return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+	return GFP_KERNEL;
+}
+
 unsigned long
 rpc_task_timeout(const struct rpc_task *task)
 {
@@ -1030,15 +1037,15 @@ int rpc_malloc(struct rpc_task *task)
 	struct rpc_rqst *rqst = task->tk_rqstp;
 	size_t size = rqst->rq_callsize + rqst->rq_rcvsize;
 	struct rpc_buffer *buf;
-	gfp_t gfp = GFP_KERNEL;
-
-	if (RPC_IS_ASYNC(task))
-		gfp = GFP_NOWAIT | __GFP_NOWARN;
+	gfp_t gfp = rpc_task_gfp_mask();
 
 	size += sizeof(struct rpc_buffer);
-	if (size <= RPC_BUFFER_MAXSIZE)
-		buf = mempool_alloc(rpc_buffer_mempool, gfp);
-	else
+	if (size <= RPC_BUFFER_MAXSIZE) {
+		buf = kmem_cache_alloc(rpc_buffer_slabp, gfp);
+		/* Reach for the mempool if dynamic allocation fails */
+		if (!buf && RPC_IS_ASYNC(task))
+			buf = mempool_alloc(rpc_buffer_mempool, GFP_NOWAIT);
+	} else
 		buf = kmalloc(size, gfp);
 
 	if (!buf)
-- 
2.35.1