Return-Path: Received: from cmrelayp1.emulex.com ([138.239.112.140]:63381 "EHLO CMRELAYP1.ad.emulex.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1752817AbbG2HXj (ORCPT ); Wed, 29 Jul 2015 03:23:39 -0400 From: Devesh Sharma To: linux-rdma@vger.kernel.org Cc: linux-nfs@vger.kernel.org, Devesh Sharma Subject: [PATCH v1] xprtrdma: take vendor driver refcount at client Date: Wed, 29 Jul 2015 18:11:01 +0530 Message-Id: <1438173661-12497-1-git-send-email-devesh.sharma@avagotech.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: Thanks Chuck Lever for the valuable feedback and suggestions. This is a rework of the following patch sent almost a year back: http://www.mail-archive.com/linux-rdma%40vger.kernel.org/msg20730.html In presence of active mount if someone tries to rmmod vendor-driver, the command remains stuck forever waiting for destruction of all rdma-cm-id. in worst case client can crash during shutdown with active mounts. The existing code assumes that ia->ri_id->device cannot change during the lifetime of a transport. xprtrdma do not have support for DEVICE_REMOVAL event either. Lifting that assumption and adding support for DEVICE_REMOVAL event is a long chain of work, and is in plan. The community decided that preventing the hang right now is more important than waiting for architectural changes. Thus, this patch intorduces a temorary workaround to acquire module reference count during the mount of a nfs-rdma mount point. CC:chuck.lever@oracle.com CC:linux-nfs@vger.kernel.org Signed-off-by: Devesh Sharma Reviewed-by: Sagi Grimberg --- net/sunrpc/xprtrdma/verbs.c | 38 ++++++++++++++++++++++++++++++-------- 1 files changed, 30 insertions(+), 8 deletions(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 891c4ed..d59d638 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -52,6 +52,7 @@ #include #include #include +#include /* try_module_get()/module_put() */ #include "xprt_rdma.h" @@ -414,6 +415,14 @@ connected: return 0; } +static void rpcrdma_destroy_id(struct rdma_cm_id *id) +{ + if (id) { + module_put(id->device->owner); + rdma_destroy_id(id); + } +} + static struct rdma_cm_id * rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia, struct sockaddr *addr) @@ -440,6 +449,18 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); + + /* FIXME: We hate to break the notion of ULP<-->Core<-->Provider + * by calling try_module_get() on vendor driver. This is to prevent a + * system hang or a possible crash during reboot with active nfs-rdma + * mount. We will keep this workaround until xprtrdma comes back with a + * massive architectural changes to have proper fix. + */ + if (!ia->ri_async_rc && !try_module_get(id->device->owner)) { + dprintk("RPC: %s: Failed to get device module\n", + __func__); + ia->ri_async_rc = -ENODEV; + } rc = ia->ri_async_rc; if (rc) goto out; @@ -449,16 +470,17 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, if (rc) { dprintk("RPC: %s: rdma_resolve_route() failed %i\n", __func__, rc); - goto out; + goto put; } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); rc = ia->ri_async_rc; if (rc) - goto out; + goto put; return id; - +put: + module_put(id->device->owner); out: rdma_destroy_id(id); return ERR_PTR(rc); @@ -592,7 +614,7 @@ out3: ib_dealloc_pd(ia->ri_pd); ia->ri_pd = NULL; out2: - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; out1: return rc; @@ -618,7 +640,7 @@ rpcrdma_ia_close(struct rpcrdma_ia *ia) if (ia->ri_id != NULL && !IS_ERR(ia->ri_id)) { if (ia->ri_id->qp) rdma_destroy_qp(ia->ri_id); - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; } @@ -825,7 +847,7 @@ retry: if (ia->ri_device != id->device) { printk("RPC: %s: can't reconnect on " "different device!\n", __func__); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -834,7 +856,7 @@ retry: if (rc) { dprintk("RPC: %s: rdma_create_qp failed %i\n", __func__, rc); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -845,7 +867,7 @@ retry: write_unlock(&ia->ri_qplock); rdma_destroy_qp(old); - rdma_destroy_id(old); + rpcrdma_destroy_id(old); } else { dprintk("RPC: %s: connecting...\n", __func__); rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); -- 1.7.1