lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20171107085514.12693-20-longli@exchange.microsoft.com>
Date:   Tue,  7 Nov 2017 01:55:11 -0700
From:   Long Li <longli@...hange.microsoft.com>
To:     Steve French <sfrench@...ba.org>, linux-cifs@...r.kernel.org,
        samba-technical@...ts.samba.org, linux-kernel@...r.kernel.org,
        linux-rdma@...r.kernel.org, Christoph Hellwig <hch@...radead.org>,
        Tom Talpey <ttalpey@...rosoft.com>,
        Matthew Wilcox <mawilcox@...rosoft.com>,
        Stephen Hemminger <sthemmin@...rosoft.com>
Cc:     Long Li <longli@...rosoft.com>
Subject: [Patch v7 19/22] CIFS: SMBD: Upper layer performs SMB write via RDMA read through memory registration

From: Long Li <longli@...rosoft.com>

When sending I/O, if size is larger than rdma_readwrite_threshold we prepare
to send SMB write packet for a RDMA read via memory registration. The actual
I/O is done by remote peer through local RDMA hardware. Modify the relevant
fields in the packet accordingly, and append a smbd_buffer_descriptor_v1 to
the end of the SMB write packet.

On write I/O finish, deregister the memory region if this was for a RDMA read.
If remote invalidation is not used, the call to smbd_deregister_mr will do
local invalidation and possibly wait. Memory region is normally deregistered
in MID callback as soon as it's used. There are situations where the MID may
not be created on I/O failure, under which memory region is deregistered when
write data context is released.

Signed-off-by: Long Li <longli@...rosoft.com>
---
 fs/cifs/cifsglob.h |  3 +++
 fs/cifs/cifssmb.c  |  7 ++++++
 fs/cifs/smb2pdu.c  | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 72 insertions(+), 4 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 5585516..66f210d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1168,6 +1168,9 @@ struct cifs_writedata {
 	pid_t				pid;
 	unsigned int			bytes;
 	int				result;
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	struct smbd_mr			*mr;
+#endif
 	unsigned int			pagesz;
 	unsigned int			tailsz;
 	unsigned int			credits;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 5857009..e012e3f 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -43,6 +43,7 @@
 #include "cifs_unicode.h"
 #include "cifs_debug.h"
 #include "fscache.h"
+#include "smbdirect.h"
 
 #ifdef CONFIG_CIFS_POSIX
 static struct {
@@ -1911,6 +1912,12 @@ cifs_writedata_release(struct kref *refcount)
 {
 	struct cifs_writedata *wdata = container_of(refcount,
 					struct cifs_writedata, refcount);
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	if (wdata->mr) {
+		smbd_deregister_mr(wdata->mr);
+		wdata->mr = NULL;
+	}
+#endif
 
 	if (wdata->cfile)
 		cifsFileInfo_put(wdata->cfile);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 32ad590..c8afb83 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -48,6 +48,7 @@
 #include "smb2glob.h"
 #include "cifspdu.h"
 #include "cifs_spnego.h"
+#include "smbdirect.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -2656,7 +2657,19 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		wdata->result = -EIO;
 		break;
 	}
-
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	/*
+	 * If this wdata has a memory registered, the MR can be freed
+	 * The number of MRs available is limited, it's important to recover
+	 * used MR as soon as I/O is finished. Hold MR longer in the later
+	 * I/O process can possibly result in I/O deadlock due to lack of MR
+	 * to send request on I/O retry
+	 */
+	if (wdata->mr) {
+		smbd_deregister_mr(wdata->mr);
+		wdata->mr = NULL;
+	}
+#endif
 	if (wdata->result)
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
 
@@ -2707,7 +2720,42 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	req->DataOffset = cpu_to_le16(
 				offsetof(struct smb2_write_req, Buffer) - 4);
 	req->RemainingBytes = 0;
-
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	/*
+	 * If we want to do a server RDMA read, fill in and append
+	 * smbd_buffer_descriptor_v1 to the end of write request
+	 */
+	if (server->rdma && wdata->bytes >=
+		server->smbd_conn->rdma_readwrite_threshold) {
+
+		struct smbd_buffer_descriptor_v1 *v1;
+		bool need_invalidate = server->dialect == SMB30_PROT_ID;
+
+		wdata->mr = smbd_register_mr(
+				server->smbd_conn, wdata->pages,
+				wdata->nr_pages, wdata->tailsz,
+				false, need_invalidate);
+		if (!wdata->mr) {
+			rc = -ENOBUFS;
+			goto async_writev_out;
+		}
+		req->Length = 0;
+		req->DataOffset = 0;
+		req->RemainingBytes =
+			(wdata->nr_pages-1)*PAGE_SIZE + wdata->tailsz;
+		req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE;
+		if (need_invalidate)
+			req->Channel = SMB2_CHANNEL_RDMA_V1;
+		req->WriteChannelInfoOffset =
+			offsetof(struct smb2_write_req, Buffer) - 4;
+		req->WriteChannelInfoLength =
+			sizeof(struct smbd_buffer_descriptor_v1);
+		v1 = (struct smbd_buffer_descriptor_v1 *) &req->Buffer[0];
+		v1->offset = wdata->mr->mr->iova;
+		v1->token = wdata->mr->mr->rkey;
+		v1->length = wdata->mr->mr->length;
+	}
+#endif
 	/* 4 for rfc1002 length field and 1 for Buffer */
 	iov[0].iov_len = 4;
 	iov[0].iov_base = req;
@@ -2720,12 +2768,22 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
 	rqst.rq_tailsz = wdata->tailsz;
-
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	if (wdata->mr) {
+		iov[1].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
+		rqst.rq_npages = 0;
+	}
+#endif
 	cifs_dbg(FYI, "async write at %llu %u bytes\n",
 		 wdata->offset, wdata->bytes);
 
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	/* For RDMA read, I/O size is in RemainingBytes not in Length */
+	if (!wdata->mr)
+		req->Length = cpu_to_le32(wdata->bytes);
+#else
 	req->Length = cpu_to_le32(wdata->bytes);
-
+#endif
 	inc_rfc1001_len(&req->hdr, wdata->bytes - 1 /* Buffer */);
 
 	if (wdata->credits) {
-- 
2.7.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ