Hi Doug, On 09/03/2015 04:11 PM, Doug Ledford wrote: > On 07/30/2015 07:00 AM, Devesh Sharma wrote: >> 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 introduces a temporary workaround to acquire HCA driver >> module reference count during the mount of a nfs-rdma mount point. >> >> Cc: chuck.lever@xxxxxxxxxx >> Cc: linux-nfs@xxxxxxxxxxxxxxx >> Signed-off-by: Devesh Sharma <devesh.sharma@xxxxxxxxxxxxx> >> Reviewed-by: Sagi Grimberg <sagig@xxxxxxxxxxxxxxxxxx> > > Chuck, was this given final approval, and if so, who's tree is it > expected to go through? Just trying to make sure I don't need to do > anything here as I don't see a rejection in my linux-rdma folder, but I > also didn't see it in the initial 4.3 nfs merge. This was approved and went through my tree to Trond. I don't think he's sent out the v4.3 pull request yet, but hopefully it won't be too much longer! Thanks, Anna > >> --- >> 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..1c3c420 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 +415,14 @@ 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 HCA 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); >> > > -- 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
