Commit 95503d29 authored by J. Bruce Fields's avatar J. Bruce Fields
Browse files

svcrpc: fix unlikely races preventing queueing of sockets 



In the rpc server, When something happens that might be reason to wake
up a thread to do something, what we do is

	- modify xpt_flags, sk_sock->flags, xpt_reserved, or
	  xpt_nr_rqsts to indicate the new situation
	- call svc_xprt_enqueue() to decide whether to wake up a thread.

svc_xprt_enqueue may require multiple conditions to be true before
queueing up a thread to handle the xprt.  In the SMP case, one of the
other CPU's may have set another required condition, and in that case,
although both CPUs run svc_xprt_enqueue(), it's possible that neither
call sees the writes done by the other CPU in time, and neither one
recognizes that all the required conditions have been set.  A socket
could therefore be ignored indefinitely.

Add memory barries to ensure that any svc_xprt_enqueue() call will
always see the conditions changed by other CPUs before deciding to
ignore a socket.

I've never seen this race reported.  In the unlikely event it happens,
another event will usually come along and the problem will fix itself.
So I don't think this is worth backporting to stable.

Chuck tried this patch and said "I don't see any performance
regressions, but my server has only a single last-level CPU cache."

Tested-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarJ. Bruce Fields <bfields@redhat.com>
parent 66c898ca

net/sunrpc/svc_xprt.c

+11 −1
Original line number Diff line number Diff line
@@ -357,6 +357,7 @@ static void svc_xprt_release_slot(struct svc_rqst *rqstp) 
	struct svc_xprt	*xprt = rqstp->rq_xprt;

	if (test_and_clear_bit(RQ_DATA, &rqstp->rq_flags)) {

		atomic_dec(&xprt->xpt_nr_rqsts);

		smp_wmb(); /* See smp_rmb() in svc_xprt_ready() */

		svc_xprt_enqueue(xprt);

	}

}
@@ -365,6 +366,15 @@ static bool svc_xprt_ready(struct svc_xprt *xprt) 
{

	unsigned long xpt_flags;



	/*

	 * If another cpu has recently updated xpt_flags,

	 * sk_sock->flags, xpt_reserved, or xpt_nr_rqsts, we need to

	 * know about it; otherwise it's possible that both that cpu and

	 * this one could call svc_xprt_enqueue() without either

	 * svc_xprt_enqueue() recognizing that the conditions below

	 * are satisfied, and we could stall indefinitely:

	 */

	smp_rmb();

	xpt_flags = READ_ONCE(xprt->xpt_flags);



	if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE)))
@@ -479,7 +489,7 @@ void svc_reserve(struct svc_rqst *rqstp, int space) 
	if (xprt && space < rqstp->rq_reserved) {

		atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);

		rqstp->rq_reserved = space;



		smp_wmb(); /* See smp_rmb() in svc_xprt_ready() */

		svc_xprt_enqueue(xprt);

	}

}

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

+2 −1
Original line number Diff line number Diff line
@@ -314,8 +314,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) 


	spin_lock(&rdma->sc_rq_dto_lock);

	list_add_tail(&ctxt->rc_list, &rdma->sc_rq_dto_q);

	spin_unlock(&rdma->sc_rq_dto_lock);

	/* Note the unlock pairs with the smp_rmb in svc_xprt_ready: */

	set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);

	spin_unlock(&rdma->sc_rq_dto_lock);

	if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags))

		svc_xprt_enqueue(&rdma->sc_xprt);

	goto out;

net/sunrpc/xprtrdma/svc_rdma_rw.c

+2 −1
Original line number Diff line number Diff line
@@ -287,9 +287,10 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) 
		spin_lock(&rdma->sc_rq_dto_lock);

		list_add_tail(&info->ri_readctxt->rc_list,

			      &rdma->sc_read_complete_q);

		/* Note the unlock pairs with the smp_rmb in svc_xprt_ready: */

		set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);

		spin_unlock(&rdma->sc_rq_dto_lock);



		set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);

		svc_xprt_enqueue(&rdma->sc_xprt);

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE