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

[ 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>

diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 46304e647c4927c1568d7a4c3327db77e0e28292..441a8604c0607a6c9a6988ad9f105b2c296104e0 100644 (file)
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1635,12 +1635,15 @@ out:
 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 fb7a0ab27899fb9c95f43dc77c1a8ac76fa03393..9cf10cfb85c6513209bca8aa05f3de15d7786081 100644 (file)
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -519,7 +519,7 @@ 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);
 }