From: Long Li <longli@linuxonhyperv.com>
To: Steve French <sfrench@samba.org>,
linux-cifs@vger.kernel.org, samba-technical@lists.samba.org,
linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org
Cc: Long Li <longli@microsoft.com>
Subject: [Patch v3 10/16] CIFS: SMBD: Do not call ib_dereg_mr on invalidated memory registration
Date: Sat, 8 Sep 2018 02:13:42 +0000 [thread overview]
Message-ID: <20180908021348.19956-11-longli@linuxonhyperv.com> (raw)
In-Reply-To: <20180908021348.19956-1-longli@linuxonhyperv.com>
From: Long Li <longli@microsoft.com>
It is not necessary to deregister a memory registration after it has been
successfully invalidated.
Signed-off-by: Long Li <longli@microsoft.com>
---
fs/cifs/smbdirect.c | 82 ++++++++++++++++++++++++++---------------------------
1 file changed, 41 insertions(+), 41 deletions(-)
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index ba53c52..b470cd0 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -2296,50 +2296,50 @@ static void smbd_mr_recovery_work(struct work_struct *work)
int rc;
list_for_each_entry(smbdirect_mr, &info->mr_list, list) {
- if (smbdirect_mr->state == MR_INVALIDATED ||
- smbdirect_mr->state == MR_ERROR) {
-
- if (smbdirect_mr->state == MR_INVALIDATED) {
- ib_dma_unmap_sg(
- info->id->device, smbdirect_mr->sgl,
- smbdirect_mr->sgl_count,
- smbdirect_mr->dir);
- smbdirect_mr->state = MR_READY;
- } else if (smbdirect_mr->state == MR_ERROR) {
-
- /* recover this MR entry */
- rc = ib_dereg_mr(smbdirect_mr->mr);
- if (rc) {
- log_rdma_mr(ERR,
- "ib_dereg_mr failed rc=%x\n",
- rc);
- smbd_disconnect_rdma_connection(info);
- }
+ if (smbdirect_mr->state == MR_INVALIDATED)
+ ib_dma_unmap_sg(
+ info->id->device, smbdirect_mr->sgl,
+ smbdirect_mr->sgl_count,
+ smbdirect_mr->dir);
+ else if (smbdirect_mr->state == MR_ERROR) {
+
+ /* recover this MR entry */
+ rc = ib_dereg_mr(smbdirect_mr->mr);
+ if (rc) {
+ log_rdma_mr(ERR,
+ "ib_dereg_mr failed rc=%x\n",
+ rc);
+ smbd_disconnect_rdma_connection(info);
+ continue;
+ }
- smbdirect_mr->mr = ib_alloc_mr(
- info->pd, info->mr_type,
+ smbdirect_mr->mr = ib_alloc_mr(
+ info->pd, info->mr_type,
+ info->max_frmr_depth);
+ if (IS_ERR(smbdirect_mr->mr)) {
+ log_rdma_mr(ERR,
+ "ib_alloc_mr failed mr_type=%x "
+ "max_frmr_depth=%x\n",
+ info->mr_type,
info->max_frmr_depth);
- if (IS_ERR(smbdirect_mr->mr)) {
- log_rdma_mr(ERR,
- "ib_alloc_mr failed mr_type=%x "
- "max_frmr_depth=%x\n",
- info->mr_type,
- info->max_frmr_depth);
- smbd_disconnect_rdma_connection(info);
- }
-
- smbdirect_mr->state = MR_READY;
+ smbd_disconnect_rdma_connection(info);
+ continue;
}
- /* smbdirect_mr->state is updated by this function
- * and is read and updated by I/O issuing CPUs trying
- * to get a MR, the call to atomic_inc_return
- * implicates a memory barrier and guarantees this
- * value is updated before waking up any calls to
- * get_mr() from the I/O issuing CPUs
- */
- if (atomic_inc_return(&info->mr_ready_count) == 1)
- wake_up_interruptible(&info->wait_mr);
- }
+ } else
+ /* This MR is being used, don't recover it */
+ continue;
+
+ smbdirect_mr->state = MR_READY;
+
+ /* smbdirect_mr->state is updated by this function
+ * and is read and updated by I/O issuing CPUs trying
+ * to get a MR, the call to atomic_inc_return
+ * implicates a memory barrier and guarantees this
+ * value is updated before waking up any calls to
+ * get_mr() from the I/O issuing CPUs
+ */
+ if (atomic_inc_return(&info->mr_ready_count) == 1)
+ wake_up_interruptible(&info->wait_mr);
}
}
--
2.7.4
next prev parent reply other threads:[~2018-09-08 2:13 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-08 2:13 [Patch v3 00/16] CIFS: add support for direct I/O Long Li
2018-09-08 2:13 ` [Patch v3 01/16] CIFS: Add support for direct pages in rdata Long Li
2018-09-08 2:13 ` [Patch v3 02/16] CIFS: Use offset when reading pages Long Li
2018-09-08 2:13 ` [Patch v3 03/16] CIFS: Add support for direct pages in wdata Long Li
2018-09-08 2:13 ` [Patch v3 04/16] CIFS: pass page offset when issuing SMB write Long Li
2018-09-08 2:13 ` [Patch v3 05/16] CIFS: Calculate the correct request length based on page offset and tail size Long Li
2018-09-08 2:13 ` [Patch v3 06/16] CIFS: Introduce helper function to get page offset and length in smb_rqst Long Li
2018-09-08 2:13 ` [Patch v3 07/16] CIFS: When sending data on socket, pass the correct page offset Long Li
2018-09-08 2:13 ` [Patch v3 08/16] CIFS: SMBD: Support page offset in RDMA send Long Li
2018-09-08 2:13 ` [Patch v3 09/16] CIFS: SMBD: Support page offset in RDMA recv Long Li
2018-09-08 2:13 ` Long Li [this message]
2018-09-08 2:13 ` [Patch v3 11/16] CIFS: SMBD: Support page offset in memory registration Long Li
2018-09-08 2:13 ` [Patch v3 12/16] CIFS: Pass page offset for calculating signature Long Li
2018-09-08 2:13 ` [Patch v3 13/16] CIFS: Pass page offset for encrypting Long Li
2018-09-08 2:13 ` [Patch v3 14/16] CIFS: Add support for direct I/O read Long Li
2018-09-08 2:13 ` [Patch v3 15/16] CIFS: Add support for direct I/O write Long Li
2018-09-08 2:13 ` [Patch v3 16/16] CIFS: Add direct I/O functions to file_operations Long Li
2018-09-15 9:28 ` [Patch v3 00/16] CIFS: add support for direct I/O Steve French
2018-09-15 20:57 ` Long Li
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=20180908021348.19956-11-longli@linuxonhyperv.com \
--to=longli@linuxonhyperv.com \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=longli@microsoft.com \
--cc=samba-technical@lists.samba.org \
--cc=sfrench@samba.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).