Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, NeilBrown <neilb@suse.de>,
        Trond Myklebust <trond.myklebust@hammerspace.com>,
        Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.16 133/285] SUNRPC/xprt: async tasks mustnt block waiting for memory
Date:   Tue, 12 Apr 2022 08:29:50 +0200
Message-Id: <20220412062947.504783605@linuxfoundation.org>
In-Reply-To: <20220412062943.670770901@linuxfoundation.org>
References: <20220412062943.670770901@linuxfoundation.org>
User-Agent: quilt/0.66
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: NeilBrown <neilb@suse.de>

[ Upstream commit a721035477fb5fb8abc738fbe410b07c12af3dc5 ]

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.

xprt_dynamic_alloc_slot can block indefinitely.  This can tie up all
workqueue threads and NFS can deadlock.  So when called from a
workqueue, set __GFP_NORETRY.

The rdma alloc_slot already does not block.  However it sets the error
to -EAGAIN suggesting this will trigger a sleep.  It does not.  As we
can see in call_reserveresult(), only -ENOMEM causes a sleep.  -EAGAIN
causes immediate retry.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprt.c               | 5 ++++-
 net/sunrpc/xprtrdma/transport.c | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 396a74974f60..75acde97d748 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1690,12 +1690,15 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task
 static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt)
 {
 	struct rpc_rqst *req = ERR_PTR(-EAGAIN);
+	gfp_t gfp_mask = GFP_KERNEL;
 
 	if (xprt->num_reqs >= xprt->max_reqs)
 		goto out;
 	++xprt->num_reqs;
 	spin_unlock(&xprt->reserve_lock);
-	req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS);
+	if (current->flags & PF_WQ_WORKER)
+		gfp_mask |= __GFP_NORETRY | __GFP_NOWARN;
+	req = kzalloc(sizeof(*req), gfp_mask);
 	spin_lock(&xprt->reserve_lock);
 	if (req != NULL)
 		goto out;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 6268af7e0310..256b06a92391 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -525,7 +525,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 	return;
 
 out_sleep:
-	task->tk_status = -EAGAIN;
+	task->tk_status = -ENOMEM;
 	xprt_add_backlog(xprt, task);
 }
 
-- 
2.35.1