On Aug 3, 2015, at 1:05 PM, Chuck Lever <chuck.lever@xxxxxxxxxx> wrote: > From: Devesh Sharma <devesh.sharma@xxxxxxxxxxxxx> > > 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 introduces a temporary workaround to acquire HCA driver > module reference count during the mount of a nfs-rdma mount point. > > Signed-off-by: Devesh Sharma <devesh.sharma@xxxxxxxxxxxxx> > Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx> > Reviewed-by: Sagi Grimberg <sagig@xxxxxxxxxxxxxxxxxx> > --- > net/sunrpc/xprtrdma/verbs.c | 41 +++++++++++++++++++++++++++++++++-------- > 1 file changed, 33 insertions(+), 8 deletions(-) > > diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c > index b4d4f63..b98fb3b 100644 > --- a/net/sunrpc/xprtrdma/verbs.c > +++ b/net/sunrpc/xprtrdma/verbs.c > @@ -52,6 +52,7 @@ > #include <linux/prefetch.h> > #include <linux/sunrpc/addr.h> > #include <asm/bitops.h> > +#include <linux/module.h> /* try_module_get()/module_put() */ > > #include "xprt_rdma.h" > > @@ -414,6 +415,16 @@ connected: > return 0; > } > > +static void rpcrdma_destroy_id(struct rdma_cm_id *id) > +{ > + if (id) { > + pr_warn("%s: releasing provider for id %p\n", > + __func__, id); Oops, that pr_warn() was added for testing. I've removed this in the git repo. > + 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) > @@ -440,25 +451,39 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, > } > wait_for_completion_interruptible_timeout(&ia->ri_done, > msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); > + > + /* FIXME: > + * Until xprtrdma supports DEVICE_REMOVAL, the provider must > + * be pinned while there are active NFS/RDMA mounts to prevent > + * hangs and crashes at umount time. > + */ > + 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; > > + pr_warn("%s: pinning provider for id %p\n", __func__, id); Ditto. > + > ia->ri_async_rc = -ETIMEDOUT; > rc = rdma_resolve_route(id, RDMA_RESOLVE_TIMEOUT); > 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); > @@ -566,7 +591,7 @@ 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; > @@ -584,7 +609,7 @@ 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; > } > > @@ -794,7 +819,7 @@ 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; > } > @@ -803,7 +828,7 @@ 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; > } > @@ -814,7 +839,7 @@ 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); > > -- > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Chuck Lever -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
