Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Subject: [PATCH 04/11] SUNRPC/xprt: async tasks mustn't block waiting for
 memory
From:   NeilBrown <neilb@suse.de>
To:     Trond Myklebust <trond.myklebust@hammerspace.com>,
        Anna Schumaker <anna@kernel.org>
Cc:     linux-nfs@vger.kernel.org
Date:   Mon, 07 Mar 2022 10:41:44 +1100
Message-ID: <164661010495.31054.15493859799937151207.stgit@noble.brown>
In-Reply-To: <164660993703.31054.17075972410545449555.stgit@noble.brown>
References: <164660993703.31054.17075972410545449555.stgit@noble.brown>
User-Agent: StGit/0.23
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Precedence: bulk

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>
---
 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 a02de2bddb28..dbffb5147f16 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1687,12 +1687,15 @@ 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_NOFS;
 
 	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 5714bf880e95..923e4b512ee9 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -517,7 +517,7 @@ 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);
 }