From: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org> To: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Subject: [PATCH v1 03/12] xprtrdma: Fix FRWR invalidation error recovery Date: Tue, 23 May 2017 10:54:02 -0400 [thread overview] Message-ID: <20170523145402.961.7601.stgit@manet.1015granger.net> (raw) In-Reply-To: <20170523142629.961.81233.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org> When ib_post_send() fails, all LOCAL_INV WRs past @bad_wr have to be examined, and the MRs reset by hand. I'm not sure how the existing code can work by comparing R_keys. Restructure the logic so that instead it walks the chain of WRs, starting from the first bad one. Make sure to wait for completion if at least one WR was actually posted. Otherwise, if the ib_post_send fails, we can end up DMA-unmapping the MR while LOCAL_INV operations are in flight. Commit 7a89f9c626e3 ("xprtrdma: Honor ->send_request API contract") added the rdma_disconnect() call site. The disconnect actually causes more problems than it solves, and SQ overruns happen only as a result of software bugs. So remove it. Fixes: d7a21c1bed54 ("xprtrdma: Reset MRs in frwr_op_unmap_sync()") Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org> --- net/sunrpc/xprtrdma/frwr_ops.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 33ede72..98808d0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -521,12 +521,13 @@ * unless ri_id->qp is a valid pointer. */ r_xprt->rx_stats.local_inv_needed++; + bad_wr = NULL; rc = ib_post_send(ia->ri_id->qp, first, &bad_wr); + if (bad_wr != first) + wait_for_completion(&f->fr_linv_done); if (rc) goto reset_mrs; - wait_for_completion(&f->fr_linv_done); - /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ @@ -543,17 +544,19 @@ reset_mrs: pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc); - rdma_disconnect(ia->ri_id); /* Find and reset the MRs in the LOCAL_INV WRs that did not - * get posted. This is synchronous, and slow. + * get posted. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) { - f = &mw->frmr; - if (mw->mw_handle == bad_wr->ex.invalidate_rkey) { - __frwr_reset_mr(ia, mw); - bad_wr = bad_wr->next; - } + rpcrdma_init_cqcount(&r_xprt->rx_ep, -count); + while (bad_wr) { + f = container_of(bad_wr, struct rpcrdma_frmr, + fr_invwr); + mw = container_of(f, struct rpcrdma_mw, frmr); + + __frwr_reset_mr(ia, mw); + + bad_wr = bad_wr->next; } goto unmap; } -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html
WARNING: multiple messages have this Message-ID (diff)
From: Chuck Lever <chuck.lever@oracle.com> To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org Subject: [PATCH v1 03/12] xprtrdma: Fix FRWR invalidation error recovery Date: Tue, 23 May 2017 10:54:02 -0400 [thread overview] Message-ID: <20170523145402.961.7601.stgit@manet.1015granger.net> (raw) In-Reply-To: <20170523142629.961.81233.stgit@manet.1015granger.net> When ib_post_send() fails, all LOCAL_INV WRs past @bad_wr have to be examined, and the MRs reset by hand. I'm not sure how the existing code can work by comparing R_keys. Restructure the logic so that instead it walks the chain of WRs, starting from the first bad one. Make sure to wait for completion if at least one WR was actually posted. Otherwise, if the ib_post_send fails, we can end up DMA-unmapping the MR while LOCAL_INV operations are in flight. Commit 7a89f9c626e3 ("xprtrdma: Honor ->send_request API contract") added the rdma_disconnect() call site. The disconnect actually causes more problems than it solves, and SQ overruns happen only as a result of software bugs. So remove it. Fixes: d7a21c1bed54 ("xprtrdma: Reset MRs in frwr_op_unmap_sync()") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- net/sunrpc/xprtrdma/frwr_ops.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 33ede72..98808d0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -521,12 +521,13 @@ * unless ri_id->qp is a valid pointer. */ r_xprt->rx_stats.local_inv_needed++; + bad_wr = NULL; rc = ib_post_send(ia->ri_id->qp, first, &bad_wr); + if (bad_wr != first) + wait_for_completion(&f->fr_linv_done); if (rc) goto reset_mrs; - wait_for_completion(&f->fr_linv_done); - /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ @@ -543,17 +544,19 @@ reset_mrs: pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc); - rdma_disconnect(ia->ri_id); /* Find and reset the MRs in the LOCAL_INV WRs that did not - * get posted. This is synchronous, and slow. + * get posted. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) { - f = &mw->frmr; - if (mw->mw_handle == bad_wr->ex.invalidate_rkey) { - __frwr_reset_mr(ia, mw); - bad_wr = bad_wr->next; - } + rpcrdma_init_cqcount(&r_xprt->rx_ep, -count); + while (bad_wr) { + f = container_of(bad_wr, struct rpcrdma_frmr, + fr_invwr); + mw = container_of(f, struct rpcrdma_mw, frmr); + + __frwr_reset_mr(ia, mw); + + bad_wr = bad_wr->next; } goto unmap; }
next prev parent reply other threads:[~2017-05-23 14:54 UTC|newest] Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-05-23 14:53 [PATCH v1 00/12] NFS/RDMA client-side patches proposed for v4.13 Chuck Lever 2017-05-23 14:53 ` Chuck Lever [not found] ` <20170523142629.961.81233.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org> 2017-05-23 14:53 ` [PATCH v1 01/12] xprtrdma: Don't defer MR recovery if ro_map fails Chuck Lever 2017-05-23 14:53 ` Chuck Lever 2017-05-23 14:53 ` [PATCH v1 02/12] xprtrdma: On invalidation failure, remove MWs from rl_registered Chuck Lever 2017-05-23 14:53 ` Chuck Lever 2017-05-23 14:54 ` Chuck Lever [this message] 2017-05-23 14:54 ` [PATCH v1 03/12] xprtrdma: Fix FRWR invalidation error recovery Chuck Lever 2017-05-23 14:54 ` [PATCH v1 04/12] xprtrdma: Pre-mark remotely invalidated MRs Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 05/12] xprtrdma: Pass only the list of registered MRs to ro_unmap_sync Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 06/12] xprtrdma: Rename rpcrdma_req::rl_free Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 07/12] xprtrdma: Fix client lock-up after application signal fires Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 08/12] NFSv4.1: Handle EXCHGID4_FLAG_CONFIRMED_R during NFSv4.1 migration Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 09/12] xprtrdma: Demote "connect" log messages Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:54 ` [PATCH v1 10/12] xprtrdma: FMR does not need list_del_init() Chuck Lever 2017-05-23 14:54 ` Chuck Lever 2017-05-23 14:55 ` [PATCH v1 11/12] xprtrdma: Replace PAGE_MASK with offset_in_page() Chuck Lever 2017-05-23 14:55 ` Chuck Lever 2017-05-23 14:55 ` [PATCH v1 12/12] xprtrdma: Fix documenting comments in frwr_ops.c Chuck Lever 2017-05-23 14:55 ` Chuck Lever
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20170523145402.961.7601.stgit@manet.1015granger.net \ --to=chuck.lever-qhclzuegtsvqt0dzr+alfa@public.gmane.org \ --cc=linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \ --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.