From: Long Li <[email protected]>
Starting with SMB2 dialect 3.0, Microsoft introduced SMBDirect transport
protocol for transferring upper layer (SMB2) payload over RDMA via Infiniband,
RoCE or iWARP. The prococol is published in [MS-SMBD]
(https://msdn.microsoft.com/en-us/library/hh536346.aspx).
Patch v2 added RDMA read/write via memory registration, and addressed
feedbacks on v1.
Patch v3 improved performance by introducing an additional queue for handling
empty packets and reducing lock contention on IRQ path. Also added light
weight profiling by reading TSC and addressed feedbacks on v2.
Long Li (19):
CIFS: Add rdma mount option
CIFS: SMBD: Add SMBDirect protocol and transport constants
CIFS: SMBD: Implement SMBDirect transport
CIFS: SMBD: Add SMBDirect transport to SMB connection and Makefile
CIFS: SMBD: Connect to SMBDirect session
CIFS: SMBD: Reconnect to SMBDirect session
CIFS: SMBD: Destroy SMBDirect session on shutdown or umount
CIFS: SMBD: Set SMBDirect maximum read or write size for I/O
CIFS: SMBD: Receive data from SMBDirect
CIFS: SMBD: Send data through SMBDirect
CIFS: SMBD: Define memory registration for I/O data
CIFS: SMBD: Fix the definition for SMB2_CHANNEL_RDMA_V1_INVALIDATE
CIFS: SMBD: Implement SMB write via RDMA read through memory
registration
CIFS: SMBD: Deregister memory on finishing SMB write
CIFS: SMBD: Add parameter rdata to smb2_new_read_req
CIFS: SMBD: Read correct returned data length for RDMA write (SMB
read) I/O
CIFS: SMBD: Implement SMB read via RDMA write through memory
registration
CIFS: SMBD: Deregister memory when finishing SMB read
CIFS: SMBD: Add SMBDirect debug counters
fs/cifs/Makefile | 2 +-
fs/cifs/cifs_debug.c | 84 ++
fs/cifs/cifsfs.c | 2 +
fs/cifs/cifsglob.h | 17 +-
fs/cifs/cifssmb.c | 10 +-
fs/cifs/connect.c | 46 +-
fs/cifs/file.c | 10 +
fs/cifs/smb1ops.c | 2 +-
fs/cifs/smb2ops.c | 21 +-
fs/cifs/smb2pdu.c | 114 ++-
fs/cifs/smb2pdu.h | 2 +-
fs/cifs/smbdirect.c | 2639 ++++++++++++++++++++++++++++++++++++++++++++++++++
fs/cifs/smbdirect.h | 324 +++++++
fs/cifs/transport.c | 7 +
14 files changed, 3260 insertions(+), 20 deletions(-)
create mode 100644 fs/cifs/smbdirect.c
create mode 100644 fs/cifs/smbdirect.h
--
2.7.4
From: Long Li <[email protected]>
Add "rdma" to CIFS mount options to connect to SMB Direct.
Add checks to validate this is used on SMB 3.X dialects.
To connect to SMBDirect, use "mount.cifs -o rdma,vers=3.x".
At the time of this patch, 3.x can be 3.0, 3.02 or 3.1.1.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/cifs_debug.c | 2 ++
fs/cifs/cifsfs.c | 2 ++
fs/cifs/cifsglob.h | 3 +++
fs/cifs/connect.c | 15 ++++++++++++++-
4 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9727e1d..ba0870d 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -171,6 +171,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
ses->ses_count, ses->serverOS, ses->serverNOS,
ses->capabilities, ses->status);
}
+ if (server->rdma)
+ seq_printf(m, "RDMA\n\t");
seq_printf(m, "TCP status: %d\n\tLocal Users To "
"Server: %d SecMode: 0x%x Req On Wire: %d",
server->tcpStatus, server->srv_count,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index fe0c8dc..a628800 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -330,6 +330,8 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
default:
seq_puts(s, "(unknown)");
}
+ if (server->rdma)
+ seq_puts(s, ",rdma");
}
static void
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8289f95..703c2fb 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -531,6 +531,7 @@ struct smb_vol {
bool nopersistent:1;
bool resilient:1; /* noresilient not required since not fored for CA */
bool domainauto:1;
+ bool rdma:1;
unsigned int rsize;
unsigned int wsize;
bool sockopt_tcp_nodelay:1;
@@ -649,6 +650,8 @@ struct TCP_Server_Info {
bool sec_kerberos; /* supports plain Kerberos */
bool sec_mskerberos; /* supports legacy MS Kerberos */
bool large_buf; /* is current buffer large? */
+ /* use SMBD connection instead of socket */
+ bool rdma;
struct delayed_work echo; /* echo ping workqueue job */
char *smallbuf; /* pointer to current "small" buffer */
char *bigbuf; /* pointer to current "big" buffer */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2eeaac6..19fdca8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -94,7 +94,7 @@ enum {
Opt_multiuser, Opt_sloppy, Opt_nosharesock,
Opt_persistent, Opt_nopersistent,
Opt_resilient, Opt_noresilient,
- Opt_domainauto,
+ Opt_domainauto, Opt_rdma,
/* Mount options which take numeric value */
Opt_backupuid, Opt_backupgid, Opt_uid,
@@ -185,6 +185,7 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_resilient, "resilienthandles"},
{ Opt_noresilient, "noresilienthandles"},
{ Opt_domainauto, "domainauto"},
+ { Opt_rdma, "rdma"},
{ Opt_backupuid, "backupuid=%s" },
{ Opt_backupgid, "backupgid=%s" },
@@ -1541,6 +1542,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
case Opt_domainauto:
vol->domainauto = true;
break;
+ case Opt_rdma:
+ vol->rdma = true;
+ break;
/* Numeric Values */
case Opt_backupuid:
@@ -1931,6 +1935,11 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
goto cifs_parse_mount_err;
}
+ if (vol->rdma && vol->vals->protocol_id < SMB30_PROT_ID) {
+ cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
+ goto cifs_parse_mount_err;
+ }
+
#ifndef CONFIG_KEYS
/* Muliuser mounts require CONFIG_KEYS support */
if (vol->multiuser) {
@@ -2134,6 +2143,9 @@ static int match_server(struct TCP_Server_Info *server, struct smb_vol *vol)
if (server->echo_interval != vol->echo_interval * HZ)
return 0;
+ if (server->rdma != vol->rdma)
+ return 0;
+
return 1;
}
@@ -2234,6 +2246,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
tcp_ses->noblocksnd = volume_info->noblocksnd;
tcp_ses->noautotune = volume_info->noautotune;
tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay;
+ tcp_ses->rdma = volume_info->rdma;
tcp_ses->in_flight = 0;
tcp_ses->credits = 1;
init_waitqueue_head(&tcp_ses->response_q);
--
2.7.4
From: Long Li <[email protected]>
Add SMBDirect as an optional connection to the SMB session structure in CIFS.
When SMB session is connected through SMBDirect, upper layer uses this
connection to carry payloads.
With the transport code hooked up to upper layer, add SMBDirect code to
Makefile.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/Makefile | 2 +-
fs/cifs/cifsglob.h | 2 ++
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index eed7eb0..6bb9863 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -18,4 +18,4 @@ cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o
cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o
cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o smb2maperror.o smb2transport.o \
- smb2misc.o smb2pdu.o smb2inode.o smb2file.o
+ smb2misc.o smb2pdu.o smb2inode.o smb2file.o smbdirect.o
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 703c2fb..dc5404d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -652,6 +652,8 @@ struct TCP_Server_Info {
bool large_buf; /* is current buffer large? */
/* use SMBD connection instead of socket */
bool rdma;
+ /* point to the SMBD connection if RDMA is used instead of socket */
+ struct smbd_connection *smbd_conn;
struct delayed_work echo; /* echo ping workqueue job */
char *smallbuf; /* pointer to current "small" buffer */
char *bigbuf; /* pointer to current "big" buffer */
--
2.7.4
From: Long Li <[email protected]>
When RDMA write is used for SMB read, the returned data length is in
DataRemaining in the response packet. Reading it properly by adding a
parameter to specifiy where the returned data length is.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/cifsglob.h | 10 ++++++++--
fs/cifs/cifssmb.c | 4 ++--
fs/cifs/smb1ops.c | 2 +-
fs/cifs/smb2ops.c | 8 ++++++--
4 files changed, 17 insertions(+), 7 deletions(-)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index dcd2b63..d391767 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -231,8 +231,14 @@ struct smb_version_operations {
__u64 (*get_next_mid)(struct TCP_Server_Info *);
/* data offset from read response message */
unsigned int (*read_data_offset)(char *);
- /* data length from read response message */
- unsigned int (*read_data_length)(char *);
+ /*
+ * Data length from read response message
+ * When in_remaining is true, the returned data length is in
+ * message field DataRemaining for out-of-band data read (e.g through
+ * Memory Registration RDMA write in SMBD).
+ * Otherwise, the returned data length is in message field DataLength.
+ */
+ unsigned int (*read_data_length)(char *, bool in_remaining);
/* map smb to linux error */
int (*map_error)(char *, bool);
/* find mid corresponding to the response message */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 6e1de21..ff2848b 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1524,8 +1524,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
rdata->iov[0].iov_base, server->total_read);
/* how much data is in the response? */
- data_len = server->ops->read_data_length(buf);
- if (data_offset + data_len > buflen) {
+ data_len = server->ops->read_data_length(buf, rdata->mr);
+ if (!rdata->mr && (data_offset + data_len > buflen)) {
/* data_len is corrupt -- discard frame */
rdata->result = -EIO;
return cifs_readv_discard(server, mid);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index a723df3..27a8280 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -87,7 +87,7 @@ cifs_read_data_offset(char *buf)
}
static unsigned int
-cifs_read_data_length(char *buf)
+cifs_read_data_length(char *buf, bool in_remaining)
{
READ_RSP *rsp = (READ_RSP *)buf;
return (le16_to_cpu(rsp->DataLengthHigh) << 16) +
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index e67f5f0..4067629 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -747,9 +747,13 @@ smb2_read_data_offset(char *buf)
}
static unsigned int
-smb2_read_data_length(char *buf)
+smb2_read_data_length(char *buf, bool in_remaining)
{
struct smb2_read_rsp *rsp = (struct smb2_read_rsp *)buf;
+
+ if (in_remaining)
+ return le32_to_cpu(rsp->DataRemaining);
+
return le32_to_cpu(rsp->DataLength);
}
@@ -2181,7 +2185,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
}
data_offset = server->ops->read_data_offset(buf) + 4;
- data_len = server->ops->read_data_length(buf);
+ data_len = server->ops->read_data_length(buf, rdata->mr);
if (data_offset < server->vals->read_rsp_size) {
/*
--
2.7.4
From: Long Li <[email protected]>
Export SMBDirect debug counters to /proc/fs/cifs/DebugData.
Those are used for debugging, troubleshooting and profiling.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/cifs_debug.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 82 insertions(+)
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index ba0870d..dad13d5 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -30,6 +30,7 @@
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifsfs.h"
+#include "smbdirect.h"
void
cifs_dump_mem(char *label, void *data, int length)
@@ -152,6 +153,87 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
list_for_each(tmp1, &cifs_tcp_ses_list) {
server = list_entry(tmp1, struct TCP_Server_Info,
tcp_ses_list);
+
+ if (!server->rdma)
+ goto skip_rdma;
+
+ seq_printf(m, "\nSMBDirect (in hex) protocol version: %x "
+ "transport status: %x",
+ server->smbd_conn->protocol,
+ server->smbd_conn->transport_status);
+ seq_printf(m, "\nConn receive_credit_max: %x "
+ "send_credit_target: %x max_send_size: %x",
+ server->smbd_conn->receive_credit_max,
+ server->smbd_conn->send_credit_target,
+ server->smbd_conn->max_send_size);
+ seq_printf(m, "\nConn max_fragmented_recv_size: %x "
+ "max_fragmented_send_size: %x max_receive_size:%x",
+ server->smbd_conn->max_fragmented_recv_size,
+ server->smbd_conn->max_fragmented_send_size,
+ server->smbd_conn->max_receive_size);
+ seq_printf(m, "\nConn keep_alive_interval: %x "
+ "max_readwrite_size: %x rdma_readwrite_threshold: %x",
+ server->smbd_conn->keep_alive_interval,
+ server->smbd_conn->max_readwrite_size,
+ server->smbd_conn->rdma_readwrite_threshold);
+ seq_printf(m, "\nDebug count_get_receive_buffer: %x "
+ "count_put_receive_buffer: %x count_send_empty: %x",
+ server->smbd_conn->count_get_receive_buffer,
+ server->smbd_conn->count_put_receive_buffer,
+ server->smbd_conn->count_send_empty);
+ seq_printf(m, "\nRead Queue count_reassembly_queue: %x "
+ "count_enqueue_reassembly_queue: %x "
+ "count_dequeue_reassembly_queue: %x "
+ "fragment_reassembly_remaining: %x "
+ "reassembly_data_length: %x "
+ "reassembly_queue_length: %x",
+ server->smbd_conn->count_reassembly_queue,
+ server->smbd_conn->count_enqueue_reassembly_queue,
+ server->smbd_conn->count_dequeue_reassembly_queue,
+ server->smbd_conn->fragment_reassembly_remaining,
+ server->smbd_conn->reassembly_data_length,
+ server->smbd_conn->reassembly_queue_length);
+ seq_printf(m, "\nCurrent Credits send_credits: %x "
+ "receive_credits: %x receive_credit_target: %x",
+ atomic_read(&server->smbd_conn->send_credits),
+ atomic_read(&server->smbd_conn->receive_credits),
+ server->smbd_conn->receive_credit_target);
+ seq_printf(m, "\nPending send_pending: %x send_payload_pending:"
+ " %x smbd_send_pending: %x smbd_recv_pending: %x",
+ atomic_read(&server->smbd_conn->send_pending),
+ atomic_read(&server->smbd_conn->send_payload_pending),
+ server->smbd_conn->smbd_send_pending,
+ server->smbd_conn->smbd_recv_pending);
+ seq_printf(m, "\nReceive buffers count_receive_queue: %x "
+ "count_empty_packet_queue: %x",
+ server->smbd_conn->count_receive_queue,
+ server->smbd_conn->count_empty_packet_queue);
+ seq_printf(m, "\nMR responder_resources: %x "
+ "max_frmr_depth: %x mr_type: %x",
+ server->smbd_conn->responder_resources,
+ server->smbd_conn->max_frmr_depth,
+ server->smbd_conn->mr_type);
+ seq_printf(m, "\nMR mr_ready_count: %x mr_used_count: %x",
+ atomic_read(&server->smbd_conn->mr_ready_count),
+ atomic_read(&server->smbd_conn->mr_used_count));
+
+ seq_printf(m, "\nTSC cycle histogram in I/O path: "
+ "(the number of most significant bits)");
+ seq_printf(m, "\nsmbd_register_mr cycles [1/10000]: ");
+ profiling_display_histogram(m, server->smbd_conn->smbd_register_mr_cycles);
+
+ seq_printf(m, "\nsmbd_deregister_mr cycles [1/10000]: ");
+ profiling_display_histogram(m, server->smbd_conn->smbd_deregister_mr_cycles);
+
+ seq_printf(m, "\nsmbd_send cycles [1/10000]: ");
+ profiling_display_histogram(m, server->smbd_conn->smbd_write_cycles);
+
+ seq_printf(m, "\nsmbd_recv cycles [1/10000]: ");
+ profiling_display_histogram(m, server->smbd_conn->smbd_recv_cycles);
+
+ seq_printf(m, "\nrecv_done cycles [1/10000]: ");
+ profiling_display_histogram(m, server->smbd_conn->recv_done_cycles);
+skip_rdma:
seq_printf(m, "\nNumber of credits: %d", server->credits);
i++;
list_for_each(tmp2, &server->smb_ses_list) {
--
2.7.4
From: Long Li <[email protected]>
When SMB read is finished, deregister the memory regions if RDMA write is used
for this SMB read. smbd_deregister_mr may need to do local invalidation and
sleep, if server remote invalidation is not used.
There are situations where the MID may not be created on I/O failure, under
which memory region is deregistered when read data context is released.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/file.c | 5 +++++
fs/cifs/smb2pdu.c | 10 ++++++++++
2 files changed, 15 insertions(+)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 41460a5..5a6df25 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2910,6 +2910,11 @@ cifs_readdata_release(struct kref *refcount)
struct cifs_readdata *rdata = container_of(refcount,
struct cifs_readdata, refcount);
+ if (rdata->mr) {
+ smbd_deregister_mr(rdata->mr);
+ rdata->mr = NULL;
+ }
+
if (rdata->cfile)
cifsFileInfo_put(rdata->cfile);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 1f08c75..43a7b60 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2504,6 +2504,16 @@ smb2_readv_callback(struct mid_q_entry *mid)
rdata->result = -EIO;
}
+ /*
+ * If this rdata has a memmory registered, the MR can be freed
+ * MR needs to be freed as soon as I/O finishes to prevent deadlock
+ * because they have limited number and are used for future I/Os
+ */
+ if (rdata->mr) {
+ smbd_deregister_mr(rdata->mr);
+ rdata->mr = NULL;
+ }
+
if (rdata->result)
cifs_stats_fail_inc(tcon, SMB2_READ_HE);
--
2.7.4
From: Long Li <[email protected]>
With SMBDirect connected, use it for receiving data via RDMA recv.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/connect.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4f62337..29f384f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -546,7 +546,10 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
if (server_unresponsive(server))
return -ECONNABORTED;
- length = sock_recvmsg(server->ssocket, smb_msg, 0);
+ if (server->smbd_conn)
+ length = smbd_recv(server->smbd_conn, smb_msg);
+ else
+ length = sock_recvmsg(server->ssocket, smb_msg, 0);
if (server->tcpStatus == CifsExiting)
return -ESHUTDOWN;
--
2.7.4
From: Long Li <[email protected]>
If I/O size is larger than rdma_readwrite_threshold, use RDMA write for
SMB read by specifying channel SMB2_CHANNEL_RDMA_V1 or
SMB2_CHANNEL_RDMA_V1_INVALIDATE in the SMB packet, depending on SMB dialect
used. Append a smbd_buffer_descriptor_v1 to the end of the SMB packet and fill
in other values to indicate this SMB read uses RDMA write.
There is no need to read from the transport for incoming payload. At the time
SMB read response comes back, the data is already transfered and placed in the
pages by RDMA hardware.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/file.c | 5 +++++
fs/cifs/smb2pdu.c | 33 +++++++++++++++++++++++++++++++++
2 files changed, 38 insertions(+)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index dec70b3..41460a5 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -42,6 +42,7 @@
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
#include "fscache.h"
+#include "smbdirect.h"
static inline int cifs_convert_flags(unsigned int flags)
@@ -3037,6 +3038,8 @@ uncached_fill_pages(struct TCP_Server_Info *server,
}
if (iter)
result = copy_page_from_iter(page, 0, n, iter);
+ else if (rdata->mr)
+ result = n;
else
result = cifs_read_page_from_socket(server, page, n);
if (result < 0)
@@ -3606,6 +3609,8 @@ readpages_fill_pages(struct TCP_Server_Info *server,
if (iter)
result = copy_page_from_iter(page, 0, n, iter);
+ else if (rdata->mr)
+ result = n;
else
result = cifs_read_page_from_socket(server, page, n);
if (result < 0)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index fbad987..1f08c75 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2392,6 +2392,39 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
req->Length = cpu_to_le32(io_parms->length);
req->Offset = cpu_to_le64(io_parms->offset);
+ /*
+ * If we want to do a RDMA write, fill in and append
+ * smbd_buffer_descriptor_v1 to the end of read request
+ */
+ if (server->rdma && rdata &&
+ rdata->bytes > server->smbd_conn->rdma_readwrite_threshold) {
+
+ struct smbd_buffer_descriptor_v1 *v1;
+ bool need_invalidate =
+ io_parms->tcon->ses->server->dialect == SMB30_PROT_ID;
+
+ rdata->mr = smbd_register_mr(
+ server->smbd_conn, rdata->pages,
+ rdata->nr_pages, rdata->tailsz,
+ true, need_invalidate);
+ if (!rdata->mr)
+ return -ENOBUFS;
+
+ req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE;
+ if (need_invalidate)
+ req->Channel = SMB2_CHANNEL_RDMA_V1;
+ req->ReadChannelInfoOffset =
+ offsetof(struct smb2_read_plain_req, Buffer);
+ req->ReadChannelInfoLength =
+ sizeof(struct smbd_buffer_descriptor_v1);
+ v1 = (struct smbd_buffer_descriptor_v1 *) &req->Buffer[0];
+ v1->offset = rdata->mr->mr->iova;
+ v1->token = rdata->mr->mr->rkey;
+ v1->length = rdata->mr->mr->length;
+
+ *total_len += sizeof(*v1) - 1;
+ }
+
if (request_type & CHAINED_REQUEST) {
if (!(request_type & END_OF_CHAIN)) {
/* next 8-byte aligned request */
--
2.7.4
From: Long Li <[email protected]>
When we assemble the SMB read packet header, we need to know the I/O layout
if this request is to use a RDMA write. rdata has all the information we need
for memory registration. Add rdata to smb2_new_read_req.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smb2pdu.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5551053..fbad987 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2363,18 +2363,21 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
*/
static int
smb2_new_read_req(void **buf, unsigned int *total_len,
- struct cifs_io_parms *io_parms, unsigned int remaining_bytes,
- int request_type)
+ struct cifs_io_parms *io_parms, struct cifs_readdata *rdata,
+ unsigned int remaining_bytes, int request_type)
{
int rc = -EACCES;
struct smb2_read_plain_req *req = NULL;
struct smb2_sync_hdr *shdr;
+ struct TCP_Server_Info *server;
rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, (void **) &req,
total_len);
if (rc)
return rc;
- if (io_parms->tcon->ses->server == NULL)
+
+ server = io_parms->tcon->ses->server;
+ if (server == NULL)
return -ECONNABORTED;
shdr = &req->sync_hdr;
@@ -2502,7 +2505,8 @@ smb2_async_readv(struct cifs_readdata *rdata)
server = io_parms.tcon->ses->server;
- rc = smb2_new_read_req((void **) &buf, &total_len, &io_parms, 0, 0);
+ rc = smb2_new_read_req(
+ (void **) &buf, &total_len, &io_parms, rdata, 0, 0);
if (rc) {
if (rc == -EAGAIN && rdata->credits) {
/* credits was reset by reconnect */
@@ -2570,7 +2574,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
struct cifs_ses *ses = io_parms->tcon->ses;
*nbytes = 0;
- rc = smb2_new_read_req((void **)&req, &total_len, io_parms, 0, 0);
+ rc = smb2_new_read_req((void **)&req, &total_len, io_parms, NULL, 0, 0);
if (rc)
return rc;
--
2.7.4
From: Long Li <[email protected]>
To prepare for RDMA read/write using memory registration, add memory
registartion pointers to upper layer data I/O context.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/cifsglob.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index dc5404d..dcd2b63 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1166,6 +1166,7 @@ struct cifs_readdata {
struct cifs_readdata *rdata,
struct iov_iter *iter);
struct kvec iov[2];
+ struct smbd_mr *mr;
unsigned int pagesz;
unsigned int tailsz;
unsigned int credits;
@@ -1188,6 +1189,7 @@ struct cifs_writedata {
pid_t pid;
unsigned int bytes;
int result;
+ struct smbd_mr *mr;
unsigned int pagesz;
unsigned int tailsz;
unsigned int credits;
--
2.7.4
From: Long Li <[email protected]>
To prepare for protocol implementation, add constants and user-configurable
values in the SMBDirect protocol.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smbdirect.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/cifs/smbdirect.h | 20 ++++++++++++++
2 files changed, 98 insertions(+)
create mode 100644 fs/cifs/smbdirect.c
create mode 100644 fs/cifs/smbdirect.h
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
new file mode 100644
index 0000000..d785bc1
--- /dev/null
+++ b/fs/cifs/smbdirect.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2017, Microsoft Corporation.
+ *
+ * Author(s): Long Li <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+#include <linux/module.h>
+#include "smbdirect.h"
+#include "cifs_debug.h"
+
+/* SMBD version number */
+#define SMBD_V1 0x0100
+
+/* Port numbers for SMBD transport */
+#define SMB_PORT 445
+#define SMBD_PORT 5445
+
+/* Address lookup and resolve timeout in ms */
+#define RDMA_RESOLVE_TIMEOUT 5000
+
+/* SMBD negotiation timeout in seconds */
+#define SMBD_NEGOTIATE_TIMEOUT 120
+
+/* SMBD minimum receive size and fragmented sized defined in [MS-SMBD] */
+#define SMBD_MIN_RECEIVE_SIZE 128
+#define SMBD_MIN_FRAGMENTED_SIZE 131072
+
+/*
+ * Default maximum number of RDMA read/write outstanding on this connection
+ * This value is possibly decreased during QP creation on hardware limit
+ */
+#define SMBD_CM_RESPONDER_RESOURCES 32
+
+/* Maximum number of retries on data transfer operations */
+#define SMBD_CM_RETRY 6
+/* No need to retry on Receiver Not Ready since SMBD manages credits */
+#define SMBD_CM_RNR_RETRY 0
+
+/*
+ * User configurable initial values per SMBD transport connection
+ * as defined in [MS-SMBD] 3.1.1.1
+ * Those may change after a SMBD negotiation
+ */
+/* The local peer's maximum number of credits to grant to the peer */
+static int receive_credit_max = 255;
+/* The remote peer's credit request of local peer */
+static int send_credit_target = 255;
+/* The maximum single message size can be sent to remote peer */
+static int max_send_size = 1364;
+/* The maximum fragmented upper-layer payload receive size supported */
+static int max_fragmented_recv_size = 1024 * 1024;
+/* The maximum single-message size which can be received */
+static int max_receive_size = 8192;
+
+/* The timeout to initiate send of a keepalive message on idle */
+static int keep_alive_interval = 120;
+
+/*
+ * User configurable initial values for RDMA transport
+ * The actual values used may be lower and are limited to hardware capabilities
+ */
+/* Default maximum number of SGEs in a RDMA send/recv */
+static int max_send_sge = SMBDIRECT_MAX_SGE;
+static int max_recv_sge = SMBDIRECT_MAX_SGE;
+/* Default maximum number of SGEs in a RDMA write/read */
+static int max_frmr_depth = 2048;
+
+/* If payload is less than this byte, use RDMA send/recv not read/write */
+static int rdma_readwrite_threshold = 4096;
diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h
new file mode 100644
index 0000000..06eeb0b
--- /dev/null
+++ b/fs/cifs/smbdirect.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2017, Microsoft Corporation.
+ *
+ * Author(s): Long Li <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+#ifndef _SMBDIRECT_H
+#define _SMBDIRECT_H
+
+#define SMBDIRECT_MAX_SGE 16
+#endif
--
2.7.4
From: Long Li <[email protected]>
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 <[email protected]>
---
fs/cifs/cifssmb.c | 6 ++++++
fs/cifs/smb2pdu.c | 12 ++++++++++++
2 files changed, 18 insertions(+)
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index fbb0d4c..6e1de21 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 {
@@ -1905,6 +1906,11 @@ cifs_writedata_release(struct kref *refcount)
struct cifs_writedata *wdata = container_of(refcount,
struct cifs_writedata, refcount);
+ if (wdata->mr) {
+ smbd_deregister_mr(wdata->mr);
+ wdata->mr = NULL;
+ }
+
if (wdata->cfile)
cifsFileInfo_put(wdata->cfile);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5581afd..5551053 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2666,6 +2666,18 @@ smb2_writev_callback(struct mid_q_entry *mid)
break;
}
+ /*
+ * 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;
+ }
+
if (wdata->result)
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
--
2.7.4
From: Long Li <[email protected]>
When connecting over SMBDirect, the transport negotiates its maximum I/O sizes
with the server and determines how to choose to do RDMA send/recv vs
read/write. Expose these maximum I/O sizes to upper layer so we will get the
correct sized payloads.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smb2ops.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 06494e1..e67f5f0 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -32,6 +32,7 @@
#include "smb2status.h"
#include "smb2glob.h"
#include "cifs_ioctl.h"
+#include "smbdirect.h"
static int
change_conf(struct TCP_Server_Info *server)
@@ -249,7 +250,11 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
/* start with specified wsize, or default */
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
- wsize = min_t(unsigned int, wsize, server->max_write);
+ if (server->rdma)
+ wsize = min_t(unsigned int,
+ wsize, server->smbd_conn->max_readwrite_size);
+ else
+ wsize = min_t(unsigned int, wsize, server->max_write);
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
@@ -265,7 +270,11 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
/* start with specified rsize, or default */
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
- rsize = min_t(unsigned int, rsize, server->max_read);
+ if (server->rdma)
+ rsize = min_t(unsigned int,
+ rsize, server->smbd_conn->max_readwrite_size);
+ else
+ rsize = min_t(unsigned int, rsize, server->max_read);
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
--
2.7.4
From: Long Li <[email protected]>
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.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smb2pdu.c | 45 ++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 44 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5cc5f6c..5581afd 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
@@ -2716,6 +2717,41 @@ smb2_async_writev(struct cifs_writedata *wdata,
offsetof(struct smb2_write_req, Buffer) - 4);
req->RemainingBytes = 0;
+ /*
+ * 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;
+ }
+
/* 4 for rfc1002 length field and 1 for Buffer */
iov[0].iov_len = 4;
iov[0].iov_base = req;
@@ -2729,10 +2765,17 @@ smb2_async_writev(struct cifs_writedata *wdata,
rqst.rq_pagesz = wdata->pagesz;
rqst.rq_tailsz = wdata->tailsz;
+ if (wdata->mr) {
+ iov[1].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
+ rqst.rq_npages = 0;
+ }
+
cifs_dbg(FYI, "async write at %llu %u bytes\n",
wdata->offset, wdata->bytes);
- req->Length = cpu_to_le32(wdata->bytes);
+ /* For RDMA read, I/O size is in RemainingBytes not in Length */
+ if (!wdata->mr)
+ req->Length = cpu_to_le32(wdata->bytes);
inc_rfc1001_len(&req->hdr, wdata->bytes - 1 /* Buffer */);
--
2.7.4
From: Long Li <[email protected]>
When CIFS wants to umount, call shutdown on transport when SMBDirect is used.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/connect.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 341a3fd..4f62337 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -708,6 +708,11 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
/* give those requests time to exit */
msleep(125);
+ if (server->smbd_conn) {
+ smbd_destroy(server->smbd_conn);
+ server->smbd_conn = NULL;
+ }
+
if (server->ssocket) {
sock_release(server->ssocket);
server->ssocket = NULL;
--
2.7.4
From: Long Li <[email protected]>
The channel value for requesting server remote invalidating local memory
registration should be 0x00000002
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smb2pdu.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 18700fd..0417a36 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -832,7 +832,7 @@ struct smb2_flush_rsp {
/* Channel field for read and write: exactly one of following flags can be set*/
#define SMB2_CHANNEL_NONE 0x00000000
#define SMB2_CHANNEL_RDMA_V1 0x00000001 /* SMB3 or later */
-#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */
+#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000002 /* SMB3.02 or later */
/* SMB2 read request without RFC1001 length at the beginning */
struct smb2_read_plain_req {
--
2.7.4
From: Long Li <[email protected]>
When "rdma" is specified in the mount option, CIFS attempts to connect to
SMBDirect instead of TCP socket.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/connect.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 19fdca8..43b4d54 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -45,6 +45,7 @@
#include <linux/parser.h>
#include <linux/bvec.h>
+#include "smbdirect.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
@@ -2289,12 +2290,26 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
else
tcp_ses->echo_interval = SMB_ECHO_INTERVAL_DEFAULT * HZ;
+ if (tcp_ses->rdma) {
+ tcp_ses->smbd_conn = smbd_get_connection(
+ tcp_ses, (struct sockaddr *)&volume_info->dstaddr);
+ if (tcp_ses->smbd_conn) {
+ cifs_dbg(VFS, "RDMA transport established\n");
+ rc = 0;
+ goto connected;
+ } else {
+ rc = -ENOENT;
+ goto out_err_crypto_release;
+ }
+ }
+
rc = ip_connect(tcp_ses);
if (rc < 0) {
cifs_dbg(VFS, "Error connecting to socket. Aborting operation.\n");
goto out_err_crypto_release;
}
+connected:
/*
* since we're in a cifs function already, we know that
* this will succeed. No need for try_module_get().
--
2.7.4
From: Long Li <[email protected]>
With SMBDirect connected, use it for sending data via RDMA send.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/transport.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index ba62aaf..bddb699 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -37,6 +37,7 @@
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_debug.h"
+#include "smbdirect.h"
void
cifs_wake_up_task(struct mid_q_entry *mid)
@@ -230,6 +231,11 @@ __smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
struct msghdr smb_msg;
int val = 1;
+ if (server->smbd_conn) {
+ rc = smbd_send(server->smbd_conn, rqst);
+ goto done;
+ }
+
if (ssocket == NULL)
return -ENOTSOCK;
@@ -299,6 +305,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
server->tcpStatus = CifsNeedReconnect;
}
+done:
if (rc < 0 && rc != -EINTR)
cifs_dbg(VFS, "Error %d sending data on socket to server\n",
rc);
--
2.7.4
From: Long Li <[email protected]>
Do a reconnect on SMBDirect when it is used as the connection. Reconnect can
happen for many reasons and it's mostly the decision of upper layer SMB2 not
SMBDirect.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/connect.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 43b4d54..341a3fd 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -409,7 +409,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
/* we should try only the port we connected to before */
mutex_lock(&server->srv_mutex);
- rc = generic_ip_connect(server);
+ if (server->rdma)
+ rc = smbd_reconnect(server);
+ else
+ rc = generic_ip_connect(server);
+
if (rc) {
cifs_dbg(FYI, "reconnect error %d\n", rc);
mutex_unlock(&server->srv_mutex);
--
2.7.4
From: Long Li <[email protected]>
Add code to implement SMBDirect transport and protocol.
1. Add transport APIs in the header file. Upper layer code uses transport
through the APIs. Those include:
Connection management:
smbd_get_connection
smbd_reconnect
smbd_destroy
Transfer payload through RDMA send/recv:
smbd_recv
smbd_send
Memory registration (for transferring payload through RDMA write/read):
smbd_register_mr
smbd_deregister_mr
2. Define SMBDirect connection in the header file. A connection is based on
a RC QP in RDMA.
3. The implementation doesn't maintain send buffers or send queue for
transferring payload via RDMA send. There is no data copy in the transport
on send.
4. On the receive path, the implementation maintains receive buffers and a
reassembly queue for transferring payload via RDMA recv. There is data copy
in the transport on recv when it copies the payload to upper layer.
5. The implementation recognizes the RFC1002 header length use in the SMB
upper layer payloads in CIFS. Because this length is mainly used for TCP and
not applicable to RDMA, it is handled as a out-of-band information and is
never sent over the wire, and the trasnport behaves like TCP to upper layer
by processing and exposing the length correctly on data payloads.
6. SMBDirect protocol enforces credits on RDMA send or recv, credits are
exchanged and mutually managed by SMB server and client. It's important that
credits are accurately managed so they are implemented as atomic variables.
7. Each connection defines a user-configurable rdma_readwrite_threshold.
Upper layer payloads larger than rdma_readwrite_threshold are sent through
RDMA read, and are received via RDMA write. There are fixed number of
registered memory regions per connection for doing RDMA read/write. There
is no data copy in the transport on RDMA read/write.
8. Profiling data are recorded on I/O path by reading processor TSC register
and store the leading zeros in histogram. Profiling is always enabled and
exported in /proc/fs/cifs/DebugData.
Signed-off-by: Long Li <[email protected]>
---
fs/cifs/smbdirect.c | 2561 +++++++++++++++++++++++++++++++++++++++++++++++++++
fs/cifs/smbdirect.h | 304 ++++++
2 files changed, 2865 insertions(+)
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index d785bc1..a59de6f 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -16,6 +16,41 @@
#include <linux/module.h>
#include "smbdirect.h"
#include "cifs_debug.h"
+#include <asm/msr.h>
+
+static struct smbd_response *get_empty_queue_buffer(
+ struct smbd_connection *info);
+static struct smbd_response *get_receive_buffer(
+ struct smbd_connection *info);
+static void put_receive_buffer(
+ struct smbd_connection *info,
+ struct smbd_response *response,
+ bool lock);
+static int allocate_receive_buffers(struct smbd_connection *info, int num_buf);
+static void destroy_receive_buffers(struct smbd_connection *info);
+
+static void put_empty_packet(
+ struct smbd_connection *info, struct smbd_response *response);
+static void enqueue_reassembly(
+ struct smbd_connection *info,
+ struct smbd_response *response, int data_length);
+static struct smbd_response *_get_first_reassembly(
+ struct smbd_connection *info);
+
+static int smbd_post_recv(
+ struct smbd_connection *info,
+ struct smbd_response *response);
+
+static int smbd_post_send_empty(struct smbd_connection *info);
+static int smbd_post_send_data(
+ struct smbd_connection *info,
+ struct kvec *iov, int n_vec, int remaining_data_length);
+static int smbd_post_send_page(struct smbd_connection *info,
+ struct page *page, unsigned long offset,
+ size_t size, int remaining_data_length);
+
+static void destroy_mr_list(struct smbd_connection *info);
+static int allocate_mr_list(struct smbd_connection *info);
/* SMBD version number */
#define SMBD_V1 0x0100
@@ -76,3 +111,2529 @@ static int max_frmr_depth = 2048;
/* If payload is less than this byte, use RDMA send/recv not read/write */
static int rdma_readwrite_threshold = 4096;
+
+/* Transport logging functions
+ * Logging are defined as classes. They can be OR'ed to define the actual
+ * logging level via module parameter smbd_logging_class
+ * e.g. cifs.smbd_logging_class=0x500 will log all log_rdma_recv() and
+ * log_rdma_event()
+ */
+#define LOG_OUTGOING 0x1
+#define LOG_INCOMING 0x2
+#define LOG_READ 0x4
+#define LOG_WRITE 0x8
+#define LOG_RDMA_SEND 0x10
+#define LOG_RDMA_RECV 0x20
+#define LOG_KEEP_ALIVE 0x40
+#define LOG_RDMA_EVENT 0x80
+#define LOG_RDMA_MR 0x100
+static unsigned int smbd_logging_class = 0;
+module_param(smbd_logging_class, uint, 0644);
+MODULE_PARM_DESC(smbd_logging_class,
+ "Logging class for SMBD transport 0x0 to 0x100");
+
+#define ERR 0x0
+#define INFO 0x1
+static unsigned int smbd_logging_level = ERR;
+module_param(smbd_logging_level, uint, 0644);
+MODULE_PARM_DESC(smbd_logging_level,
+ "Logging level for SMBD transport, 0 (default): error, 1: info");
+
+#define log_rdma(level, class, fmt, args...) \
+do { \
+ if (level <= smbd_logging_level || class & smbd_logging_class) \
+ cifs_dbg(VFS, "%s:%d " fmt, __func__, __LINE__, ##args);\
+} while (0)
+
+#define log_outgoing(level, fmt, args...) \
+ log_rdma(level, LOG_OUTGOING, fmt, ##args)
+#define log_incoming(level, fmt, args...) \
+ log_rdma(level, LOG_INCOMING, fmt, ##args)
+#define log_read(level, fmt, args...) log_rdma(level, LOG_READ, fmt, ##args)
+#define log_write(level, fmt, args...) log_rdma(level, LOG_WRITE, fmt, ##args)
+#define log_rdma_send(level, fmt, args...) \
+ log_rdma(level, LOG_RDMA_SEND, fmt, ##args)
+#define log_rdma_recv(level, fmt, args...) \
+ log_rdma(level, LOG_RDMA_RECV, fmt, ##args)
+#define log_keep_alive(level, fmt, args...) \
+ log_rdma(level, LOG_KEEP_ALIVE, fmt, ##args)
+#define log_rdma_event(level, fmt, args...) \
+ log_rdma(level, LOG_RDMA_EVENT, fmt, ##args)
+#define log_rdma_mr(level, fmt, args...) \
+ log_rdma(level, LOG_RDMA_MR, fmt, ##args)
+
+void profiling_display_histogram(
+ struct seq_file *m, unsigned long long array[])
+{
+ int i;
+ unsigned long long total = 0;
+
+ for (i = 0; i < SIZE_LONG_LONG; i++)
+ total += array[i];
+
+ for (i = 0; i < SIZE_LONG_LONG; i++)
+ if (array[i])
+ seq_printf(m, "%d:%llu ", i, array[i] * 10000 / total);
+}
+
+static inline void profiling_add_histogram(
+ unsigned long long value, unsigned long long array[])
+{
+ array[__builtin_clzll(value)]++;
+}
+
+/*
+ * Destroy the transport and related RDMA and memory resources
+ * Need to go through all the pending counters and make sure on one is using
+ * the transport while it is destroyed
+ */
+static void smbd_destroy_rdma_work(struct work_struct *work)
+{
+ struct smbd_response *response;
+ struct smbd_connection *info =
+ container_of(work, struct smbd_connection, destroy_work);
+ unsigned long flags;
+
+ log_rdma_event(INFO, "destroying qp\n");
+ ib_drain_qp(info->id->qp);
+ rdma_destroy_qp(info->id);
+
+ /* Unblock all I/O waiting on the send queue */
+ wake_up_interruptible_all(&info->wait_send_queue);
+
+ log_rdma_event(INFO, "cancelling idle timer\n");
+ cancel_delayed_work_sync(&info->idle_timer_work);
+ log_rdma_event(INFO, "cancelling send immediate work\n");
+ cancel_delayed_work_sync(&info->send_immediate_work);
+
+ log_rdma_event(INFO, "wait for all send to finish\n");
+ wait_event(info->wait_smbd_send_pending,
+ info->smbd_send_pending == 0);
+
+ log_rdma_event(INFO, "wait for all recv to finish\n");
+ wake_up_interruptible(&info->wait_reassembly_queue);
+ wait_event(info->wait_smbd_recv_pending,
+ info->smbd_recv_pending == 0);
+
+ log_rdma_event(INFO, "wait for all send posted to IB to finish\n");
+ wait_event(info->wait_send_pending,
+ atomic_read(&info->send_pending) == 0);
+ wait_event(info->wait_send_payload_pending,
+ atomic_read(&info->send_payload_pending) == 0);
+
+ log_rdma_event(INFO, "freeing mr list\n");
+ wake_up_interruptible_all(&info->wait_mr);
+ wait_event(info->wait_for_mr_cleanup,
+ atomic_read(&info->mr_used_count) == 0);
+ destroy_mr_list(info);
+
+ /* It's not posssible for upper layer to get to reassembly */
+ log_rdma_event(INFO, "drain the reassembly queue\n");
+ do {
+ spin_lock_irqsave(&info->reassembly_queue_lock, flags);
+ response = _get_first_reassembly(info);
+ if (response) {
+ list_del(&response->list);
+ spin_unlock_irqrestore(
+ &info->reassembly_queue_lock, flags);
+ put_receive_buffer(info, response, true);
+ }
+ } while (response);
+ spin_unlock_irqrestore(&info->reassembly_queue_lock, flags);
+ info->reassembly_data_length = 0;
+// wake_up_interruptible(&info->wait_reassembly_queue);
+
+ log_rdma_event(INFO, "free receive buffers\n");
+ wait_event(info->wait_receive_queues,
+ info->count_receive_queue + info->count_empty_packet_queue
+ == info->receive_credit_max);
+ destroy_receive_buffers(info);
+
+ ib_free_cq(info->send_cq);
+ ib_free_cq(info->recv_cq);
+ ib_dealloc_pd(info->pd);
+ rdma_destroy_id(info->id);
+
+ /* free mempools */
+ mempool_destroy(info->request_mempool);
+ kmem_cache_destroy(info->request_cache);
+
+ mempool_destroy(info->response_mempool);
+ kmem_cache_destroy(info->response_cache);
+
+ info->transport_status = SMBD_DESTROYED;
+ wake_up_all(&info->wait_destroy);
+}
+
+static int smbd_process_disconnected(struct smbd_connection *info)
+{
+// queue_work(info->workqueue, &info->destroy_work);
+ schedule_work(&info->destroy_work);
+ return 0;
+}
+
+static void smbd_disconnect_rdma_work(struct work_struct *work)
+{
+ struct smbd_connection *info =
+ container_of(work, struct smbd_connection, disconnect_work);
+
+ if (info->transport_status == SMBD_CONNECTED) {
+ info->transport_status = SMBD_DISCONNECTING;
+ rdma_disconnect(info->id);
+ }
+}
+
+static void smbd_disconnect_rdma_connection(struct smbd_connection *info)
+{
+ queue_work(info->workqueue, &info->disconnect_work);
+}
+
+/* Upcall from RDMA CM */
+static int smbd_conn_upcall(
+ struct rdma_cm_id *id, struct rdma_cm_event *event)
+{
+ struct smbd_connection *info = id->context;
+
+ log_rdma_event(INFO, "event=%d status=%d\n",
+ event->event, event->status);
+
+ switch (event->event) {
+ case RDMA_CM_EVENT_ADDR_RESOLVED:
+ case RDMA_CM_EVENT_ROUTE_RESOLVED:
+ info->ri_rc = 0;
+ complete(&info->ri_done);
+ break;
+
+ case RDMA_CM_EVENT_ADDR_ERROR:
+ info->ri_rc = -EHOSTUNREACH;
+ complete(&info->ri_done);
+ break;
+
+ case RDMA_CM_EVENT_ROUTE_ERROR:
+ info->ri_rc = -ENETUNREACH;
+ complete(&info->ri_done);
+ break;
+
+ case RDMA_CM_EVENT_ESTABLISHED:
+ log_rdma_event(INFO, "connected event=%d\n", event->event);
+ info->transport_status = SMBD_CONNECTED;
+ wake_up_interruptible(&info->conn_wait);
+ break;
+
+ case RDMA_CM_EVENT_CONNECT_ERROR:
+ case RDMA_CM_EVENT_UNREACHABLE:
+ case RDMA_CM_EVENT_REJECTED:
+ log_rdma_event(INFO, "connecting failed event=%d\n", event->event);
+ info->transport_status = SMBD_DISCONNECTED;
+ wake_up_interruptible(&info->conn_wait);
+ break;
+
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ case RDMA_CM_EVENT_DISCONNECTED:
+ /* This happenes when we fail the negotiation */
+ if (info->transport_status == SMBD_NEGOTIATE_FAILED) {
+ info->transport_status = SMBD_DISCONNECTED;
+ wake_up(&info->conn_wait);
+ break;
+ }
+
+ info->transport_status = SMBD_DISCONNECTED;
+ smbd_process_disconnected(info);
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+/* Upcall from RDMA QP */
+static void
+smbd_qp_async_error_upcall(struct ib_event *event, void *context)
+{
+ struct smbd_connection *info = context;
+
+ log_rdma_event(ERR, "%s on device %s info %p\n",
+ ib_event_msg(event->event), event->device->name, info);
+
+ switch (event->event) {
+ case IB_EVENT_CQ_ERR:
+ case IB_EVENT_QP_FATAL:
+ smbd_disconnect_rdma_connection(info);
+
+ default:
+ break;
+ }
+}
+
+static inline void *smbd_request_payload(struct smbd_request *request)
+{
+ return (void *)request->packet;
+}
+
+static inline void *smbd_response_payload(struct smbd_response *response)
+{
+ return (void *)response->packet;
+}
+
+/* Called when a RDMA send is done */
+static void send_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ int i;
+ struct smbd_request *request =
+ container_of(wc->wr_cqe, struct smbd_request, cqe);
+
+ log_rdma_send(INFO, "smbd_request %p completed wc->status=%d\n",
+ request, wc->status);
+
+ if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) {
+ log_rdma_send(ERR, "wc->status=%d wc->opcode=%d\n",
+ wc->status, wc->opcode);
+ smbd_disconnect_rdma_connection(request->info);
+ }
+
+ for (i = 0; i < request->num_sge; i++)
+ ib_dma_unmap_single(request->info->id->device,
+ request->sge[i].addr,
+ request->sge[i].length,
+ DMA_TO_DEVICE);
+
+ if (request->has_payload) {
+ if (atomic_dec_and_test(&request->info->send_payload_pending))
+ wake_up(&request->info->wait_send_payload_pending);
+ } else {
+ if (atomic_dec_and_test(&request->info->send_pending))
+ wake_up(&request->info->wait_send_pending);
+ }
+
+ mempool_free(request, request->info->request_mempool);
+}
+
+static void dump_smbd_negotiate_resp(struct smbd_negotiate_resp *resp)
+{
+ log_rdma_event(INFO, "resp message min_version %u max_version %u "
+ "negotiated_version %u credits_requested %u "
+ "credits_granted %u status %u max_readwrite_size %u "
+ "preferred_send_size %u max_receive_size %u "
+ "max_fragmented_size %u\n",
+ resp->min_version, resp->max_version, resp->negotiated_version,
+ resp->credits_requested, resp->credits_granted, resp->status,
+ resp->max_readwrite_size, resp->preferred_send_size,
+ resp->max_receive_size, resp->max_fragmented_size);
+}
+
+/*
+ * Process a negotiation response message, according to [MS-SMBD]3.1.5.7
+ * response, packet_length: the negotiation response message
+ * return value: true if negotiation is a success, false if failed
+ */
+static bool process_negotiation_response(
+ struct smbd_response *response, int packet_length)
+{
+ struct smbd_connection *info = response->info;
+ struct smbd_negotiate_resp *packet = smbd_response_payload(response);
+
+ if (packet_length < sizeof(struct smbd_negotiate_resp)) {
+ log_rdma_event(ERR,
+ "error: packet_length=%d\n", packet_length);
+ return false;
+ }
+
+ if (le16_to_cpu(packet->negotiated_version) != SMBD_V1) {
+ log_rdma_event(ERR, "error: negotiated_version=%x\n",
+ le16_to_cpu(packet->negotiated_version));
+ return false;
+ }
+ info->protocol = le16_to_cpu(packet->negotiated_version);
+
+ if (packet->credits_requested == 0) {
+ log_rdma_event(ERR, "error: credits_requested==0\n");
+ return false;
+ }
+ info->receive_credit_target = le16_to_cpu(packet->credits_requested);
+
+ if (packet->credits_granted == 0) {
+ log_rdma_event(ERR, "error: credits_granted==0\n");
+ return false;
+ }
+ atomic_set(&info->send_credits, le16_to_cpu(packet->credits_granted));
+
+ atomic_set(&info->receive_credits, 0);
+
+ if (le32_to_cpu(packet->preferred_send_size) > info->max_receive_size) {
+ log_rdma_event(ERR, "error: preferred_send_size=%d\n",
+ le32_to_cpu(packet->preferred_send_size));
+ return false;
+ }
+ info->max_receive_size = le32_to_cpu(packet->preferred_send_size);
+
+ if (le32_to_cpu(packet->max_receive_size) < SMBD_MIN_RECEIVE_SIZE) {
+ log_rdma_event(ERR, "error: max_receive_size=%d\n",
+ le32_to_cpu(packet->max_receive_size));
+ return false;
+ }
+ info->max_send_size = min_t(int, info->max_send_size,
+ le32_to_cpu(packet->max_receive_size));
+
+ if (le32_to_cpu(packet->max_fragmented_size) <
+ SMBD_MIN_FRAGMENTED_SIZE) {
+ log_rdma_event(ERR, "error: max_fragmented_size=%d\n",
+ le32_to_cpu(packet->max_fragmented_size));
+ return false;
+ }
+ info->max_fragmented_send_size =
+ le32_to_cpu(packet->max_fragmented_size);
+ info->rdma_readwrite_threshold =
+ rdma_readwrite_threshold > info->max_fragmented_send_size ?
+ info->max_fragmented_send_size :
+ rdma_readwrite_threshold;
+
+
+ info->max_readwrite_size = min_t(u32,
+ le32_to_cpu(packet->max_readwrite_size),
+ info->max_frmr_depth * PAGE_SIZE);
+ info->max_frmr_depth = info->max_readwrite_size / PAGE_SIZE;
+
+ return true;
+}
+
+/*
+ * Check and schedule to send an immediate packet
+ * This is used to extend credtis to remote peer to keep the transport busy
+ */
+static void check_and_send_immediate(struct smbd_connection *info)
+{
+ if (info->transport_status != SMBD_CONNECTED)
+ return;
+
+ info->send_immediate = true;
+
+ /*
+ * Promptly send a packet if our peer is running low on receive
+ * credits
+ */
+ if (atomic_read(&info->receive_credits) <
+ info->receive_credit_target - 1)
+ queue_delayed_work(
+ info->workqueue, &info->send_immediate_work, 0);
+}
+
+static void smbd_post_send_credits(struct work_struct *work)
+{
+ int ret = 0;
+ int use_receive_queue = 1;
+ int rc;
+ struct smbd_response *response;
+ struct smbd_connection *info =
+ container_of(work, struct smbd_connection,
+ post_send_credits_work);
+
+ if (info->transport_status != SMBD_CONNECTED) {
+ wake_up(&info->wait_receive_queues);
+ return;
+ }
+
+ if (info->receive_credit_target >
+ atomic_read(&info->receive_credits)) {
+ while (true) {
+ if (use_receive_queue)
+ response = get_receive_buffer(info);
+ else
+ response = get_empty_queue_buffer(info);
+ if (!response) {
+ /* now switch to emtpy packet queue */
+ if (use_receive_queue) {
+ use_receive_queue = 0;
+ continue;
+ } else
+ break;
+ }
+
+ response->type = SMBD_TRANSFER_DATA;
+ response->first_segment = false;
+ rc = smbd_post_recv(info, response);
+ if (rc) {
+ log_rdma_recv(ERR,
+ "post_recv failed rc=%d\n", rc);
+ put_receive_buffer(info, response, true);
+ break;
+ }
+
+ ret++;
+ }
+ }
+
+ spin_lock(&info->lock_new_credits_offered);
+ info->new_credits_offered += ret;
+ spin_unlock(&info->lock_new_credits_offered);
+
+ atomic_add(ret, &info->receive_credits);
+
+ /* Check if we can post new receive and grant credits to peer */
+ check_and_send_immediate(info);
+}
+
+static void smbd_recv_done_work(struct work_struct *work)
+{
+ struct smbd_connection *info =
+ container_of(work, struct smbd_connection, recv_done_work);
+
+ /*
+ * We may have new send credits granted from remote peer
+ * If any sender is blcoked on lack of credets, unblock it
+ */
+ if (atomic_read(&info->send_credits))
+ wake_up_interruptible(&info->wait_send_queue);
+
+ /*
+ * Check if we need to send something to remote peer to
+ * grant more credits or respond to KEEP_ALIVE packet
+ */
+ check_and_send_immediate(info);
+}
+
+/* Called from softirq, when recv is done */
+static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ struct smbd_data_transfer *data_transfer;
+ struct smbd_response *response =
+ container_of(wc->wr_cqe, struct smbd_response, cqe);
+ struct smbd_connection *info = response->info;
+ unsigned long long t1 = rdtsc();
+ int data_length = 0;
+
+ log_rdma_recv(INFO, "response=%p type=%d wc status=%d wc opcode %d "
+ "byte_len=%d pkey_index=%x\n",
+ response, response->type, wc->status, wc->opcode,
+ wc->byte_len, wc->pkey_index);
+
+ if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) {
+ log_rdma_recv(INFO, "wc->status=%d opcode=%d\n",
+ wc->status, wc->opcode);
+ smbd_disconnect_rdma_connection(info);
+ goto error;
+ }
+
+ ib_dma_sync_single_for_cpu(
+ wc->qp->device,
+ response->sge.addr,
+ response->sge.length,
+ DMA_FROM_DEVICE);
+
+ switch (response->type) {
+ /* SMBD negotiation response */
+ case SMBD_NEGOTIATE_RESP:
+ dump_smbd_negotiate_resp(smbd_response_payload(response));
+ info->full_packet_received = true;
+ info->negotiate_done =
+ process_negotiation_response(response, wc->byte_len);
+ complete(&info->negotiate_completion);
+ break;
+
+ /* SMBD data transfer packet */
+ case SMBD_TRANSFER_DATA:
+ data_transfer = smbd_response_payload(response);
+ data_length = le32_to_cpu(data_transfer->data_length);
+
+ /*
+ * If this is a packet with data playload place the data in
+ * reassembly queue and wake up the reading thread
+ */
+ if (data_length) {
+ if (info->full_packet_received)
+ response->first_segment = true;
+
+ if (le32_to_cpu(data_transfer->remaining_data_length))
+ info->full_packet_received = false;
+ else
+ info->full_packet_received = true;
+
+ enqueue_reassembly(
+ info,
+ response,
+ data_length);
+ } else
+ put_empty_packet(info, response);
+
+ if (data_length) {
+ wake_up_interruptible(&info->wait_reassembly_queue);
+ profiling_add_histogram(rdtsc()-t1, info->recv_done_cycles);
+ }
+
+ atomic_dec(&info->receive_credits);
+ info->receive_credit_target =
+ le16_to_cpu(data_transfer->credits_requested);
+ atomic_add(le16_to_cpu(data_transfer->credits_granted),
+ &info->send_credits);
+
+ log_incoming(INFO, "data flags %d data_offset %d "
+ "data_length %d remaining_data_length %d\n",
+ le16_to_cpu(data_transfer->flags),
+ le32_to_cpu(data_transfer->data_offset),
+ le32_to_cpu(data_transfer->data_length),
+ le32_to_cpu(data_transfer->remaining_data_length));
+
+ /* Send a KEEP_ALIVE response right away if requested */
+ info->keep_alive_requested = KEEP_ALIVE_NONE;
+ if (le16_to_cpu(data_transfer->flags) &
+ le16_to_cpu(SMB_DIRECT_RESPONSE_REQUESTED)) {
+ info->keep_alive_requested = KEEP_ALIVE_PENDING;
+ }
+
+ queue_work(info->workqueue, &info->recv_done_work);
+ return;
+
+ default:
+ log_rdma_recv(ERR,
+ "unexpected response type=%d\n", response->type);
+ }
+
+error:
+ put_receive_buffer(info, response, true);
+}
+
+static struct rdma_cm_id *smbd_create_id(
+ struct smbd_connection *info,
+ struct sockaddr *dstaddr, int port)
+{
+ struct rdma_cm_id *id;
+ int rc;
+ __be16 *sport;
+
+ id = rdma_create_id(&init_net, smbd_conn_upcall, info,
+ RDMA_PS_TCP, IB_QPT_RC);
+ if (IS_ERR(id)) {
+ rc = PTR_ERR(id);
+ log_rdma_event(ERR, "rdma_create_id() failed %i\n", rc);
+ return id;
+ }
+
+ if (dstaddr->sa_family == AF_INET6)
+ sport = &((struct sockaddr_in6 *)dstaddr)->sin6_port;
+ else
+ sport = &((struct sockaddr_in *)dstaddr)->sin_port;
+
+ *sport = htons(port);
+
+ init_completion(&info->ri_done);
+ info->ri_rc = -ETIMEDOUT;
+
+ rc = rdma_resolve_addr(id, NULL, (struct sockaddr *)dstaddr,
+ RDMA_RESOLVE_TIMEOUT);
+ if (rc) {
+ log_rdma_event(ERR, "rdma_resolve_addr() failed %i\n", rc);
+ goto out;
+ }
+ wait_for_completion_interruptible_timeout(
+ &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT));
+ rc = info->ri_rc;
+ if (rc) {
+ log_rdma_event(ERR, "rdma_resolve_addr() completed %i\n", rc);
+ goto out;
+ }
+
+ info->ri_rc = -ETIMEDOUT;
+ rc = rdma_resolve_route(id, RDMA_RESOLVE_TIMEOUT);
+ if (rc) {
+ log_rdma_event(ERR, "rdma_resolve_route() failed %i\n", rc);
+ goto out;
+ }
+ wait_for_completion_interruptible_timeout(
+ &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT));
+ rc = info->ri_rc;
+ if (rc) {
+ log_rdma_event(ERR, "rdma_resolve_route() completed %i\n", rc);
+ goto out;
+ }
+
+ return id;
+
+out:
+ rdma_destroy_id(id);
+ return ERR_PTR(rc);
+}
+
+/*
+ * Test if FRWR (Fast Registration Work Requests) is supported on the device
+ * This implementation requries FRWR on RDMA read/write
+ * return value: true if it is supported
+ */
+static bool frwr_is_supported(struct ib_device_attr *attrs)
+{
+ if (!(attrs->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
+ return false;
+ if (attrs->max_fast_reg_page_list_len == 0)
+ return false;
+ return true;
+}
+
+static int smbd_ia_open(
+ struct smbd_connection *info,
+ struct sockaddr *dstaddr, int port)
+{
+ int rc;
+
+ info->id = smbd_create_id(info, dstaddr, port);
+ if (IS_ERR(info->id)) {
+ rc = PTR_ERR(info->id);
+ goto out1;
+ }
+
+ if (!frwr_is_supported(&info->id->device->attrs)) {
+ log_rdma_event(ERR,
+ "Fast Registration Work Requests "
+ "(FRWR) is not supported\n");
+ log_rdma_event(ERR,
+ "Device capability flags = %llx "
+ "max_fast_reg_page_list_len = %u\n",
+ info->id->device->attrs.device_cap_flags,
+ info->id->device->attrs.max_fast_reg_page_list_len);
+ rc = -EPROTONOSUPPORT;
+ goto out2;
+ }
+ info->max_frmr_depth = min_t(int,
+ max_frmr_depth,
+ info->id->device->attrs.max_fast_reg_page_list_len);
+ info->mr_type = IB_MR_TYPE_MEM_REG;
+ if (info->id->device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
+ info->mr_type = IB_MR_TYPE_SG_GAPS;
+
+ info->pd = ib_alloc_pd(info->id->device, 0);
+ if (IS_ERR(info->pd)) {
+ rc = PTR_ERR(info->pd);
+ log_rdma_event(ERR, "ib_alloc_pd() returned %d\n", rc);
+ goto out2;
+ }
+
+ return 0;
+
+out2:
+ rdma_destroy_id(info->id);
+ info->id = NULL;
+
+out1:
+ return rc;
+}
+
+/*
+ * Send a negotiation request message to the peer
+ * The negotiation procedure is in [MS-SMBD] 3.1.5.2 and 3.1.5.3
+ * After negotiation, the transport is connected and ready for
+ * carrying upper layer SMB payload
+ */
+static int smbd_post_send_negotiate_req(struct smbd_connection *info)
+{
+ struct ib_send_wr send_wr, *send_wr_fail;
+ int rc = -ENOMEM;
+ struct smbd_request *request;
+ struct smbd_negotiate_req *packet;
+
+ request = mempool_alloc(info->request_mempool, GFP_KERNEL);
+ if (!request)
+ return rc;
+
+ request->info = info;
+
+ packet = smbd_request_payload(request);
+ packet->min_version = cpu_to_le16(SMBD_V1);
+ packet->max_version = cpu_to_le16(SMBD_V1);
+ packet->reserved = 0;
+ packet->credits_requested = cpu_to_le16(info->send_credit_target);
+ packet->preferred_send_size = cpu_to_le32(info->max_send_size);
+ packet->max_receive_size = cpu_to_le32(info->max_receive_size);
+ packet->max_fragmented_size =
+ cpu_to_le32(info->max_fragmented_recv_size);
+
+ request->num_sge = 1;
+ request->sge[0].addr = ib_dma_map_single(
+ info->id->device, (void *)packet,
+ sizeof(*packet), DMA_TO_DEVICE);
+ if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) {
+ rc = -EIO;
+ goto dma_mapping_failed;
+ }
+
+ request->sge[0].length = sizeof(*packet);
+ request->sge[0].lkey = info->pd->local_dma_lkey;
+
+ ib_dma_sync_single_for_device(
+ info->id->device, request->sge[0].addr,
+ request->sge[0].length, DMA_TO_DEVICE);
+
+ request->cqe.done = send_done;
+
+ send_wr.next = NULL;
+ send_wr.wr_cqe = &request->cqe;
+ send_wr.sg_list = request->sge;
+ send_wr.num_sge = request->num_sge;
+ send_wr.opcode = IB_WR_SEND;
+ send_wr.send_flags = IB_SEND_SIGNALED;
+
+ log_rdma_send(INFO, "sge addr=%llx length=%x lkey=%x\n",
+ request->sge[0].addr,
+ request->sge[0].length, request->sge[0].lkey);
+
+ request->has_payload = false;
+ atomic_inc(&info->send_pending);
+ rc = ib_post_send(info->id->qp, &send_wr, &send_wr_fail);
+ if (!rc)
+ return 0;
+
+ /* if we reach here, post send failed */
+ log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
+ atomic_dec(&info->send_pending);
+ ib_dma_unmap_single(info->id->device, request->sge[0].addr,
+ request->sge[0].length, DMA_TO_DEVICE);
+
+dma_mapping_failed:
+ mempool_free(request, info->request_mempool);
+ return rc;
+}
+
+/*
+ * Extend the credits to remote peer
+ * This implements [MS-SMBD] 3.1.5.9
+ * The idea is that we should extend credits to remote peer as quickly as
+ * it's allowed, to maintain data flow. We allocate as much receive
+ * buffer as possible, and extend the receive credits to remote peer
+ * return value: the new credtis being granted.
+ */
+static int manage_credits_prior_sending(struct smbd_connection *info)
+{
+ int new_credits;
+
+ spin_lock(&info->lock_new_credits_offered);
+ new_credits = info->new_credits_offered;
+ info->new_credits_offered = 0;
+ spin_unlock(&info->lock_new_credits_offered);
+
+ return new_credits;
+}
+
+/*
+ * Check if we need to send a KEEP_ALIVE message
+ * The idle connection timer triggers a KEEP_ALIVE message when expires
+ * SMB_DIRECT_RESPONSE_REQUESTED is set in the message flag to have peer send
+ * back a response.
+ * return value:
+ * 1 if SMB_DIRECT_RESPONSE_REQUESTED needs to be set
+ * 0: otherwise
+ */
+static int manage_keep_alive_before_sending(struct smbd_connection *info)
+{
+ if (info->keep_alive_requested == KEEP_ALIVE_PENDING) {
+ info->keep_alive_requested = KEEP_ALIVE_SENT;
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Build and prepare the SMBD packet header
+ * This function waits for avaialbe send credits and build a SMBD packet
+ * header. The caller then optional append payload to the packet after
+ * the header
+ * intput values
+ * size: the size of the payload
+ * remaining_data_length: remaining data to send if this is part of a
+ * fragmented packet
+ * output values
+ * request_out: the request allocated from this function
+ * return values: 0 on success, otherwise actual error code returned
+ */
+static int smbd_create_header(struct smbd_connection *info,
+ int size, int remaining_data_length,
+ struct smbd_request **request_out)
+{
+ struct smbd_request *request;
+ struct smbd_data_transfer *packet;
+ int header_length;
+ int rc;
+
+ /* Wait for send credits. A SMBD packet needs one credit */
+ rc = wait_event_interruptible(info->wait_send_queue,
+ atomic_read(&info->send_credits) > 0 ||
+ info->transport_status != SMBD_CONNECTED);
+ if (rc)
+ return rc;
+
+ if (info->transport_status != SMBD_CONNECTED) {
+ log_outgoing(ERR, "disconnected not sending\n");
+ return -ENOENT;
+ }
+ atomic_dec(&info->send_credits);
+
+ request = mempool_alloc(info->request_mempool, GFP_KERNEL);
+ if (!request) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ request->info = info;
+
+ /* Fill in the packet header */
+ packet = smbd_request_payload(request);
+ packet->credits_requested = cpu_to_le16(info->send_credit_target);
+ packet->credits_granted =
+ cpu_to_le16(manage_credits_prior_sending(info));
+ info->send_immediate = false;
+
+ packet->flags = 0;
+ if (manage_keep_alive_before_sending(info))
+ packet->flags |= cpu_to_le16(SMB_DIRECT_RESPONSE_REQUESTED);
+
+ packet->reserved = 0;
+ if (!size)
+ packet->data_offset = 0;
+ else
+ packet->data_offset = cpu_to_le32(24);
+ packet->data_length = cpu_to_le32(size);
+ packet->remaining_data_length = cpu_to_le32(remaining_data_length);
+ packet->padding = 0;
+
+ log_outgoing(INFO, "credits_requested=%d credits_granted=%d "
+ "data_offset=%d data_length=%d remaining_data_length=%d\n",
+ le16_to_cpu(packet->credits_requested),
+ le16_to_cpu(packet->credits_granted),
+ le32_to_cpu(packet->data_offset),
+ le32_to_cpu(packet->data_length),
+ le32_to_cpu(packet->remaining_data_length));
+
+ /* Map the packet to DMA */
+ header_length = sizeof(struct smbd_data_transfer);
+ /* If this is a packet without payload, don't send padding */
+ if (!size)
+ header_length = offsetof(struct smbd_data_transfer, padding);
+
+ request->num_sge = 1;
+ request->sge[0].addr = ib_dma_map_single(info->id->device,
+ (void *)packet,
+ header_length,
+ DMA_BIDIRECTIONAL);
+ if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) {
+ mempool_free(request, info->request_mempool);
+ rc = -EIO;
+ goto err;
+ }
+
+ request->sge[0].length = header_length;
+ request->sge[0].lkey = info->pd->local_dma_lkey;
+
+ *request_out = request;
+ return 0;
+
+err:
+ atomic_inc(&info->send_credits);
+ return rc;
+}
+
+static void smbd_destroy_header(struct smbd_connection *info,
+ struct smbd_request *request)
+{
+
+ ib_dma_unmap_single(info->id->device,
+ request->sge[0].addr,
+ request->sge[0].length,
+ DMA_TO_DEVICE);
+ mempool_free(request, info->request_mempool);
+ atomic_inc(&info->send_credits);
+}
+
+/* Post the send request */
+static int smbd_post_send(struct smbd_connection *info,
+ struct smbd_request *request, bool has_payload)
+{
+ struct ib_send_wr send_wr, *send_wr_fail;
+ int rc, i;
+
+ for (i = 0; i < request->num_sge; i++) {
+ log_rdma_send(INFO,
+ "rdma_request sge[%d] addr=%llu legnth=%u\n",
+ i, request->sge[0].addr, request->sge[0].length);
+ ib_dma_sync_single_for_device(
+ info->id->device,
+ request->sge[i].addr,
+ request->sge[i].length,
+ DMA_TO_DEVICE);
+ }
+
+ request->cqe.done = send_done;
+
+ send_wr.next = NULL;
+ send_wr.wr_cqe = &request->cqe;
+ send_wr.sg_list = request->sge;
+ send_wr.num_sge = request->num_sge;
+ send_wr.opcode = IB_WR_SEND;
+ send_wr.send_flags = IB_SEND_SIGNALED;
+
+ if (has_payload) {
+ request->has_payload = true;
+ atomic_inc(&info->send_payload_pending);
+ } else {
+ request->has_payload = false;
+ atomic_inc(&info->send_pending);
+ }
+
+ rc = ib_post_send(info->id->qp, &send_wr, &send_wr_fail);
+ if (rc) {
+ log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc);
+ if (has_payload) {
+ if (atomic_dec_and_test(&info->send_payload_pending))
+ wake_up(&info->wait_send_payload_pending);
+ } else {
+ if (atomic_dec_and_test(&info->send_pending))
+ wake_up(&info->wait_send_pending);
+ }
+ } else
+ /* Reset timer for idle connection after packet is sent */
+ mod_delayed_work(info->workqueue, &info->idle_timer_work,
+ info->keep_alive_interval*HZ);
+
+ return rc;
+}
+
+/*
+ * Send a page
+ * page: the page to send
+ * offset: offset in the page to send
+ * size: length in the page to send
+ * remaining_data_length: remaining data to send in this payload
+ */
+static int smbd_post_send_page(struct smbd_connection *info, struct page *page,
+ unsigned long offset, size_t size, int remaining_data_length)
+{
+ struct smbd_request *request;
+ int rc;
+
+ rc = smbd_create_header(info, size, remaining_data_length, &request);
+ if (rc)
+ return rc;
+
+ /* Add payload to packet */
+ request->num_sge++;
+ request->sge[1].addr = ib_dma_map_page(info->id->device, page,
+ offset, size, DMA_BIDIRECTIONAL);
+ if (ib_dma_mapping_error(info->id->device, request->sge[1].addr)) {
+ smbd_destroy_header(info, request);
+ return -EIO;
+ }
+ request->sge[1].length = size;
+ request->sge[1].lkey = info->pd->local_dma_lkey;
+
+ rc = smbd_post_send(info, request, true);
+ if (rc) {
+ ib_dma_unmap_single(info->id->device,
+ request->sge[1].addr,
+ request->sge[1].length,
+ DMA_TO_DEVICE);
+ smbd_destroy_header(info, request);
+
+ }
+ return rc;
+}
+
+/*
+ * Send an empty message
+ * Empty message is used to extend credits to peer to for keep live
+ * while there is no upper layer payload to send at the time
+ */
+static int smbd_post_send_empty(struct smbd_connection *info)
+{
+ struct smbd_request *request;
+ int rc;
+
+ rc = smbd_create_header(info, 0, 0, &request);
+ if (rc)
+ return rc;
+
+ info->count_send_empty++;
+ rc = smbd_post_send(info, request, false);
+ if (rc)
+ smbd_destroy_header(info, request);
+
+ return rc;
+}
+
+/*
+ * Send a data buffer
+ * iov: the iov array describing the data buffers
+ * n_vec: number of iov array
+ * remaining_data_length: remaining data to send following this packet
+ * in segmented SMBD packet
+ */
+static int smbd_post_send_data(
+ struct smbd_connection *info, struct kvec *iov, int n_vec,
+ int remaining_data_length)
+{
+ struct smbd_request *request;
+ int rc, i;
+ u32 data_length = 0;
+
+ for (i = 0; i < n_vec; i++)
+ data_length += iov[i].iov_len;
+ rc = smbd_create_header(
+ info, data_length, remaining_data_length, &request);
+ if (rc)
+ return rc;
+
+ for (i = 0; i < n_vec; i++) {
+ request->sge[i+1].addr =
+ ib_dma_map_single(info->id->device, iov[i].iov_base,
+ iov[i].iov_len, DMA_BIDIRECTIONAL);
+ if (ib_dma_mapping_error(
+ info->id->device, request->sge[i+1].addr)) {
+ rc = -EIO;
+ request->sge[i+1].addr = 0;
+ goto dma_mapping_failure;
+ }
+ request->sge[i+1].length = iov[i].iov_len;
+ request->sge[i+1].lkey = info->pd->local_dma_lkey;
+ request->num_sge++;
+ }
+
+ rc = smbd_post_send(info, request, true);
+ if (!rc)
+ return 0;
+
+dma_mapping_failure:
+ for (i = 1; i < request->num_sge; i++)
+ if (request->sge[i].addr)
+ ib_dma_unmap_single(info->id->device,
+ request->sge[i].addr,
+ request->sge[i].length,
+ DMA_TO_DEVICE);
+ smbd_destroy_header(info, request);
+ return rc;
+}
+
+/*
+ * Post a receive request to the transport
+ * The remote peer can only send data when a receive request is posted
+ * The interaction is controlled by send/receive credit system
+ */
+static int smbd_post_recv(
+ struct smbd_connection *info, struct smbd_response *response)
+{
+ struct ib_recv_wr recv_wr, *recv_wr_fail = NULL;
+ int rc = -EIO;
+
+ response->sge.addr = ib_dma_map_single(
+ info->id->device, response->packet,
+ info->max_receive_size, DMA_FROM_DEVICE);
+ if (ib_dma_mapping_error(info->id->device, response->sge.addr))
+ return rc;
+
+ response->sge.length = info->max_receive_size;
+ response->sge.lkey = info->pd->local_dma_lkey;
+
+ response->cqe.done = recv_done;
+
+ recv_wr.wr_cqe = &response->cqe;
+ recv_wr.next = NULL;
+ recv_wr.sg_list = &response->sge;
+ recv_wr.num_sge = 1;
+
+ rc = ib_post_recv(info->id->qp, &recv_wr, &recv_wr_fail);
+ if (rc) {
+ ib_dma_unmap_single(info->id->device, response->sge.addr,
+ response->sge.length, DMA_FROM_DEVICE);
+
+ log_rdma_recv(ERR, "ib_post_recv failed rc=%d\n", rc);
+ }
+
+ return rc;
+}
+
+/* Perform SMBD negotiate according to [MS-SMBD] 3.1.5.2 */
+static int smbd_negotiate(struct smbd_connection *info)
+{
+ int rc;
+ struct smbd_response *response = get_receive_buffer(info);
+
+ response->type = SMBD_NEGOTIATE_RESP;
+ rc = smbd_post_recv(info, response);
+ log_rdma_event(INFO,
+ "smbd_post_recv rc=%d iov.addr=%llx iov.length=%x "
+ "iov.lkey=%x\n",
+ rc, response->sge.addr,
+ response->sge.length, response->sge.lkey);
+ if (rc)
+ return rc;
+
+ init_completion(&info->negotiate_completion);
+ info->negotiate_done = false;
+ rc = smbd_post_send_negotiate_req(info);
+ if (rc)
+ return rc;
+
+ rc = wait_for_completion_interruptible_timeout(
+ &info->negotiate_completion, SMBD_NEGOTIATE_TIMEOUT * HZ);
+ log_rdma_event(INFO, "wait_for_completion_timeout rc=%d\n", rc);
+
+ if (info->negotiate_done)
+ return 0;
+
+ if (rc == 0)
+ rc = -ETIMEDOUT;
+ else if (rc == -ERESTARTSYS)
+ rc = -EINTR;
+ else
+ rc = -ENOTCONN;
+
+ return rc;
+}
+
+static void put_empty_packet(
+ struct smbd_connection *info, struct smbd_response *response)
+{
+ spin_lock(&info->empty_packet_queue_lock);
+ list_add_tail(&response->list, &info->empty_packet_queue);
+ info->count_empty_packet_queue++;
+ spin_unlock(&info->empty_packet_queue_lock);
+
+ queue_work(info->workqueue, &info->post_send_credits_work);
+}
+
+/*
+ * Implement Connection.FragmentReassemblyBuffer defined in [MS-SMBD] 3.1.1.1
+ * This is a queue for reassembling upper layer payload and present to upper
+ * layer. All the inncoming payload go to the reassembly queue, regardless of
+ * if reassembly is required. The uuper layer code reads from the queue for all
+ * incoming payloads.
+ * Put a received packet to the reassembly queue
+ * response: the packet received
+ * data_length: the size of payload in this packet
+ */
+static void enqueue_reassembly(
+ struct smbd_connection *info,
+ struct smbd_response *response,
+ int data_length)
+{
+ spin_lock(&info->reassembly_queue_lock);
+ list_add_tail(&response->list, &info->reassembly_queue);
+ info->reassembly_queue_length++;
+ /*
+ * Make sure reassembly_data_length is updated after list and
+ * reassembly_queue_length are updated. On the dequeue side
+ * reassembly_data_length is checked without a lock to determine
+ * if reassembly_queue_length and list is up to date
+ */
+ virt_wmb();
+ info->reassembly_data_length += data_length;
+ spin_unlock(&info->reassembly_queue_lock);
+ info->count_reassembly_queue++;
+ info->count_enqueue_reassembly_queue++;
+}
+
+/*
+ * Get the first entry at the front of reassembly queue
+ * Caller is responsible for locking
+ * return value: the first entry if any, NULL if queue is empty
+ */
+static struct smbd_response *_get_first_reassembly(struct smbd_connection *info)
+{
+ struct smbd_response *ret = NULL;
+
+ if (!list_empty(&info->reassembly_queue)) {
+ ret = list_first_entry(
+ &info->reassembly_queue,
+ struct smbd_response, list);
+ }
+ return ret;
+}
+
+static struct smbd_response *get_empty_queue_buffer(
+ struct smbd_connection *info)
+{
+ struct smbd_response *ret = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&info->empty_packet_queue_lock, flags);
+ if (!list_empty(&info->empty_packet_queue)) {
+ ret = list_first_entry(
+ &info->empty_packet_queue,
+ struct smbd_response, list);
+ list_del(&ret->list);
+ info->count_empty_packet_queue--;
+ }
+ spin_unlock_irqrestore(&info->empty_packet_queue_lock, flags);
+
+ return ret;
+}
+
+/*
+ * Get a receive buffer
+ * For each remote send, we need to post a receive. The receive buffers are
+ * pre-allocated in advance.
+ * return value: the receive buffer, NULL if none is available
+ */
+static struct smbd_response *get_receive_buffer(struct smbd_connection *info)
+{
+ struct smbd_response *ret = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&info->receive_queue_lock, flags);
+ if (!list_empty(&info->receive_queue)) {
+ ret = list_first_entry(
+ &info->receive_queue,
+ struct smbd_response, list);
+ list_del(&ret->list);
+ info->count_receive_queue--;
+ info->count_get_receive_buffer++;
+ }
+ spin_unlock_irqrestore(&info->receive_queue_lock, flags);
+
+ return ret;
+}
+
+/*
+ * Return a receive buffer
+ * Upon returning of a receive buffer, we can post new receive and extend
+ * more receive credits to remote peer. This is done immediately after a
+ * receive buffer is returned.
+ */
+static void put_receive_buffer(
+ struct smbd_connection *info, struct smbd_response *response,
+ bool lock)
+{
+ unsigned long flags;
+
+ ib_dma_unmap_single(info->id->device, response->sge.addr,
+ response->sge.length, DMA_FROM_DEVICE);
+
+ if (lock)
+ spin_lock_irqsave(&info->receive_queue_lock, flags);
+ list_add_tail(&response->list, &info->receive_queue);
+ info->count_receive_queue++;
+ info->count_put_receive_buffer++;
+ if (lock)
+ spin_unlock_irqrestore(&info->receive_queue_lock, flags);
+
+ queue_work(info->workqueue, &info->post_send_credits_work);
+}
+
+/* Preallocate all receive buffer on transport establishment */
+static int allocate_receive_buffers(struct smbd_connection *info, int num_buf)
+{
+ int i;
+ struct smbd_response *response;
+
+ INIT_LIST_HEAD(&info->reassembly_queue);
+ spin_lock_init(&info->reassembly_queue_lock);
+ info->reassembly_data_length = 0;
+ info->reassembly_queue_length = 0;
+
+ INIT_LIST_HEAD(&info->receive_queue);
+ spin_lock_init(&info->receive_queue_lock);
+ info->count_receive_queue = 0;
+
+ INIT_LIST_HEAD(&info->empty_packet_queue);
+ spin_lock_init(&info->empty_packet_queue_lock);
+ info->count_empty_packet_queue = 0;
+
+ init_waitqueue_head(&info->wait_receive_queues);
+
+ for (i = 0; i < num_buf; i++) {
+ response = mempool_alloc(info->response_mempool, GFP_KERNEL);
+ if (!response)
+ goto allocate_failed;
+
+ response->info = info;
+ list_add_tail(&response->list, &info->receive_queue);
+ info->count_receive_queue++;
+ }
+
+ return 0;
+
+allocate_failed:
+ while (!list_empty(&info->receive_queue)) {
+ response = list_first_entry(
+ &info->receive_queue,
+ struct smbd_response, list);
+ list_del(&response->list);
+ info->count_receive_queue--;
+
+ mempool_free(response, info->response_mempool);
+ }
+ return -ENOMEM;
+}
+
+static void destroy_receive_buffers(struct smbd_connection *info)
+{
+ struct smbd_response *response;
+
+ while ((response = get_receive_buffer(info)))
+ mempool_free(response, info->response_mempool);
+
+ while ((response = get_empty_queue_buffer(info)))
+ mempool_free(response, info->response_mempool);
+}
+
+/*
+ * Check and send an immediate or keep alive packet
+ * The condition to send those packets are defined in [MS-SMBD] 3.1.1.1
+ * Connection.KeepaliveRequested and Connection.SendImmediate
+ * The idea is to extend credits to server as soon as it becomes available
+ */
+static void send_immediate_work(struct work_struct *work)
+{
+ struct smbd_connection *info = container_of(
+ work, struct smbd_connection,
+ send_immediate_work.work);
+
+ if (info->keep_alive_requested == KEEP_ALIVE_PENDING ||
+ info->send_immediate) {
+ log_keep_alive(INFO, "send an empty message\n");
+ smbd_post_send_empty(info);
+ }
+}
+
+/* Implement idle connection timer [MS-SMBD] 3.1.6.2 */
+static void idle_connection_timer(struct work_struct *work)
+{
+ struct smbd_connection *info = container_of(
+ work, struct smbd_connection,
+ idle_timer_work.work);
+
+ if (info->keep_alive_requested != KEEP_ALIVE_NONE) {
+ log_keep_alive(ERR,
+ "error status info->keep_alive_requested=%d\n",
+ info->keep_alive_requested);
+ smbd_disconnect_rdma_connection(info);
+ return;
+ }
+
+ log_keep_alive(INFO, "about to send an empty idle message\n");
+ smbd_post_send_empty(info);
+
+ /* Setup the next idle timeout work */
+ queue_delayed_work(info->workqueue, &info->idle_timer_work,
+ info->keep_alive_interval*HZ);
+}
+
+/* Destroy this SMBD connection, called from upper layer */
+void smbd_destroy(struct smbd_connection *info)
+{
+ log_rdma_event(INFO, "destroying rdma session\n");
+
+ /* Kick off the disconnection process */
+ smbd_disconnect_rdma_connection(info);
+
+ log_rdma_event(INFO, "wait for transport being destroyed\n");
+ wait_event(info->wait_destroy,
+ info->transport_status == SMBD_DESTROYED);
+
+ destroy_workqueue(info->workqueue);
+ kfree(info);
+}
+
+/*
+ * Reconnect this SMBD connection, called from upper layer
+ * return value: 0 on success, or actual error code
+ */
+int smbd_reconnect(struct TCP_Server_Info *server)
+{
+ log_rdma_event(INFO, "reconnecting rdma session\n");
+
+ /* why reconnect while it is still connected? */
+ if (server->smbd_conn->transport_status == SMBD_CONNECTED) {
+ log_rdma_event(ERR, "still connected, not reconnecting\n");
+ return -EINVAL;
+ }
+
+ /* wait until the transport is destroyed */
+ wait_event(server->smbd_conn->wait_destroy,
+ server->smbd_conn->transport_status == SMBD_DESTROYED);
+
+ destroy_workqueue(server->smbd_conn->workqueue);
+ kfree(server->smbd_conn);
+
+ log_rdma_event(INFO, "creating rdma session\n");
+ server->smbd_conn = smbd_get_connection(
+ server, (struct sockaddr *) &server->dstaddr);
+
+ return server->smbd_conn ? 0 : -ENOENT;
+}
+
+static void destroy_caches_and_workqueue(struct smbd_connection *info)
+{
+ destroy_receive_buffers(info);
+ destroy_workqueue(info->workqueue);
+ mempool_destroy(info->response_mempool);
+ kmem_cache_destroy(info->response_cache);
+ mempool_destroy(info->request_mempool);
+ kmem_cache_destroy(info->request_cache);
+}
+
+#define MAX_NAME_LEN 80
+static int allocate_caches_and_workqueue(struct smbd_connection *info)
+{
+ char name[MAX_NAME_LEN];
+ int rc;
+
+ snprintf(name, MAX_NAME_LEN, "smbd_request_%p", info);
+ info->request_cache =
+ kmem_cache_create(
+ name,
+ sizeof(struct smbd_request) +
+ sizeof(struct smbd_data_transfer),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!info->request_cache)
+ return -ENOMEM;
+
+ info->request_mempool =
+ mempool_create(info->send_credit_target, mempool_alloc_slab,
+ mempool_free_slab, info->request_cache);
+ if (!info->request_mempool)
+ goto out1;
+
+ snprintf(name, MAX_NAME_LEN, "smbd_response_%p", info);
+ info->response_cache =
+ kmem_cache_create(
+ name,
+ sizeof(struct smbd_response) +
+ info->max_receive_size,
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!info->response_cache)
+ goto out2;
+
+ info->response_mempool =
+ mempool_create(info->receive_credit_max, mempool_alloc_slab,
+ mempool_free_slab, info->response_cache);
+ if (!info->response_mempool)
+ goto out3;
+
+ snprintf(name, MAX_NAME_LEN, "smbd_%p", info);
+ info->workqueue = create_workqueue(name);
+ if (!info->workqueue)
+ goto out4;
+
+ rc = allocate_receive_buffers(info, info->receive_credit_max);
+ if (rc) {
+ log_rdma_event(ERR, "failed to allocate receive buffers\n");
+ goto out5;
+ }
+
+ return 0;
+
+out5:
+ destroy_workqueue(info->workqueue);
+out4:
+ mempool_destroy(info->response_mempool);
+out3:
+ kmem_cache_destroy(info->response_cache);
+out2:
+ mempool_destroy(info->request_mempool);
+out1:
+ kmem_cache_destroy(info->request_cache);
+ return -ENOMEM;
+}
+
+/* Create a SMBD connection, called by upper layer */
+struct smbd_connection *_smbd_get_connection(
+ struct TCP_Server_Info *server, struct sockaddr *dstaddr, int port)
+{
+ int rc;
+ struct smbd_connection *info;
+ struct rdma_conn_param conn_param;
+ struct ib_qp_init_attr qp_attr;
+ struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr;
+
+ info = kzalloc(sizeof(struct smbd_connection), GFP_KERNEL);
+ if (!info)
+ return NULL;
+
+ info->transport_status = SMBD_CONNECTING;
+ rc = smbd_ia_open(info, dstaddr, port);
+ if (rc) {
+ log_rdma_event(INFO, "smbd_ia_open rc=%d\n", rc);
+ goto create_id_failed;
+ }
+
+ if (send_credit_target > info->id->device->attrs.max_cqe ||
+ send_credit_target > info->id->device->attrs.max_qp_wr) {
+ log_rdma_event(ERR,
+ "consider lowering send_credit_target = %d. "
+ "Possible CQE overrun, device "
+ "reporting max_cpe %d max_qp_wr %d\n",
+ send_credit_target,
+ info->id->device->attrs.max_cqe,
+ info->id->device->attrs.max_qp_wr);
+ goto config_failed;
+ }
+
+ if (receive_credit_max > info->id->device->attrs.max_cqe ||
+ receive_credit_max > info->id->device->attrs.max_qp_wr) {
+ log_rdma_event(ERR,
+ "consider lowering receive_credit_max = %d. "
+ "Possible CQE overrun, device "
+ "reporting max_cpe %d max_qp_wr %d\n",
+ receive_credit_max,
+ info->id->device->attrs.max_cqe,
+ info->id->device->attrs.max_qp_wr);
+ goto config_failed;
+ }
+
+ info->receive_credit_max = receive_credit_max;
+ info->send_credit_target = send_credit_target;
+ info->max_send_size = max_send_size;
+ info->max_fragmented_recv_size = max_fragmented_recv_size;
+ info->max_receive_size = max_receive_size;
+ info->keep_alive_interval = keep_alive_interval;
+
+ max_send_sge = min_t(int, max_send_sge,
+ info->id->device->attrs.max_sge);
+ max_recv_sge = min_t(int, max_recv_sge,
+ info->id->device->attrs.max_sge_rd);
+
+ info->send_cq = NULL;
+ info->recv_cq = NULL;
+ info->send_cq = ib_alloc_cq(info->id->device, info,
+ info->send_credit_target, 0, IB_POLL_SOFTIRQ);
+ if (IS_ERR(info->send_cq)) {
+ info->send_cq = NULL;
+ goto alloc_cq_failed;
+ }
+
+ info->recv_cq = ib_alloc_cq(info->id->device, info,
+ info->receive_credit_max, 0, IB_POLL_SOFTIRQ);
+ if (IS_ERR(info->recv_cq)) {
+ info->recv_cq = NULL;
+ goto alloc_cq_failed;
+ }
+
+ memset(&qp_attr, 0, sizeof(qp_attr));
+ qp_attr.event_handler = smbd_qp_async_error_upcall;
+ qp_attr.qp_context = info;
+ qp_attr.cap.max_send_wr = info->send_credit_target;
+ qp_attr.cap.max_recv_wr = info->receive_credit_max;
+ qp_attr.cap.max_send_sge = max_send_sge;
+ qp_attr.cap.max_recv_sge = max_recv_sge;
+ qp_attr.cap.max_inline_data = 0;
+ qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+ qp_attr.qp_type = IB_QPT_RC;
+ qp_attr.send_cq = info->send_cq;
+ qp_attr.recv_cq = info->recv_cq;
+ qp_attr.port_num = ~0;
+
+ rc = rdma_create_qp(info->id, info->pd, &qp_attr);
+ if (rc) {
+ log_rdma_event(ERR, "rdma_create_qp failed %i\n", rc);
+ goto create_qp_failed;
+ }
+
+ memset(&conn_param, 0, sizeof(conn_param));
+ conn_param.private_data = NULL;
+ conn_param.private_data_len = 0;
+ conn_param.initiator_depth = 0;
+
+ conn_param.responder_resources =
+ info->id->device->attrs.max_qp_rd_atom
+ < SMBD_CM_RESPONDER_RESOURCES ?
+ info->id->device->attrs.max_qp_rd_atom :
+ SMBD_CM_RESPONDER_RESOURCES;
+ info->responder_resources = conn_param.responder_resources;
+ log_rdma_mr(INFO, "responder_resources=%d\n",
+ info->responder_resources);
+
+ conn_param.retry_count = SMBD_CM_RETRY;
+ conn_param.rnr_retry_count = SMBD_CM_RNR_RETRY;
+ conn_param.flow_control = 0;
+ init_waitqueue_head(&info->wait_destroy);
+
+ log_rdma_event(INFO, "connecting to IP %pI4 port %d\n",
+ &addr_in->sin_addr, port);
+
+ init_waitqueue_head(&info->conn_wait);
+ rc = rdma_connect(info->id, &conn_param);
+ if (rc) {
+ log_rdma_event(ERR, "rdma_connect() failed with %i\n", rc);
+ goto rdma_connect_failed;
+ }
+
+ wait_event_interruptible(
+ info->conn_wait, info->transport_status != SMBD_CONNECTING);
+
+ if (info->transport_status != SMBD_CONNECTED) {
+ log_rdma_event(INFO, "rdma_connect failed\n");
+ goto rdma_connect_failed;
+ }
+
+ log_rdma_event(INFO, "rdma_connect connected\n");
+
+ rc = allocate_caches_and_workqueue(info);
+ if (rc) {
+ log_rdma_event(ERR, "cache allocation failed\n");
+ goto allocate_cache_failed;
+ }
+
+ init_waitqueue_head(&info->wait_send_queue);
+ init_waitqueue_head(&info->wait_reassembly_queue);
+
+ INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer);
+ INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work);
+ queue_delayed_work(info->workqueue, &info->idle_timer_work,
+ info->keep_alive_interval*HZ);
+
+ init_waitqueue_head(&info->wait_smbd_send_pending);
+ info->smbd_send_pending = 0;
+
+ init_waitqueue_head(&info->wait_smbd_recv_pending);
+ info->smbd_recv_pending = 0;
+
+ init_waitqueue_head(&info->wait_send_pending);
+ atomic_set(&info->send_pending, 0);
+
+ init_waitqueue_head(&info->wait_send_payload_pending);
+ atomic_set(&info->send_payload_pending, 0);
+
+ INIT_WORK(&info->disconnect_work, smbd_disconnect_rdma_work);
+ INIT_WORK(&info->destroy_work, smbd_destroy_rdma_work);
+ INIT_WORK(&info->recv_done_work, smbd_recv_done_work);
+ INIT_WORK(&info->post_send_credits_work, smbd_post_send_credits);
+ info->new_credits_offered = 0;
+ spin_lock_init(&info->lock_new_credits_offered);
+
+ rc = smbd_negotiate(info);
+ if (rc) {
+ log_rdma_event(ERR, "smbd_negotiate rc=%d\n", rc);
+ goto negotiation_failed;
+ }
+
+ rc = allocate_mr_list(info);
+ if (rc) {
+ log_rdma_mr(ERR, "memory registration allocation failed\n");
+ goto allocate_mr_failed;
+ }
+
+ return info;
+
+allocate_mr_failed:
+ /* At this point, need to a full transport shutdown */
+ smbd_destroy(info);
+ return NULL;
+
+negotiation_failed:
+ cancel_delayed_work_sync(&info->idle_timer_work);
+ destroy_caches_and_workqueue(info);
+ info->transport_status = SMBD_NEGOTIATE_FAILED;
+ init_waitqueue_head(&info->conn_wait);
+ rdma_disconnect(info->id);
+ wait_event(info->conn_wait,
+ info->transport_status == SMBD_DISCONNECTED);
+
+allocate_cache_failed:
+rdma_connect_failed:
+ rdma_destroy_qp(info->id);
+
+create_qp_failed:
+alloc_cq_failed:
+ if (info->send_cq)
+ ib_free_cq(info->send_cq);
+ if (info->recv_cq)
+ ib_free_cq(info->recv_cq);
+
+config_failed:
+ ib_dealloc_pd(info->pd);
+ rdma_destroy_id(info->id);
+
+create_id_failed:
+ kfree(info);
+ return NULL;
+}
+
+struct smbd_connection *smbd_get_connection(
+ struct TCP_Server_Info *server, struct sockaddr *dstaddr)
+{
+ struct smbd_connection *ret;
+ int port = SMBD_PORT;
+
+try_again:
+ ret = _smbd_get_connection(server, dstaddr, port);
+
+ /* Try SMB_PORT if SMBD_PORT doesn't work */
+ if (!ret && port == SMBD_PORT) {
+ port = SMB_PORT;
+ goto try_again;
+ }
+ return ret;
+}
+
+/*
+ * Receive data from receive reassembly queue
+ * All the incoming data packets are placed in reassembly queue
+ * buf: the buffer to read data into
+ * size: the length of data to read
+ * return value: actual data read
+ * Note: this implementation copies the data from reassebmly queue to receive
+ * buffers used by upper layer. This is not the optimal code path. A better way
+ * to do it is to not have upper layer allocate its receive buffers but rather
+ * borrow the buffer from reassembly queue, and return it after data is
+ * consumed. But this will require more changes to upper layer code, and also
+ * need to consider packet boundaries while they still being reassembled.
+ */
+int smbd_recv_buf(struct smbd_connection *info, char *buf, unsigned int size)
+{
+ struct smbd_response *response;
+ struct smbd_data_transfer *data_transfer;
+ int to_copy, to_read, data_read, offset;
+ u32 data_length, remaining_data_length, data_offset;
+ int rc;
+ unsigned long flags;
+
+again:
+ if (info->transport_status != SMBD_CONNECTED) {
+ log_read(ERR, "disconnected\n");
+ return -ENODEV;
+ }
+
+ /*
+ * No need to hold the reassembly queue lock all the time as we are
+ * the only one reading from the front of the queue. The transport
+ * may add more entries to the back of the queeu at the same time
+ */
+ log_read(INFO, "size=%d info->reassembly_data_length=%d\n", size,
+ info->reassembly_data_length);
+ if (info->reassembly_data_length >= size) {
+ unsigned long long t1 = rdtsc();
+ int queue_length;
+ int queue_removed = 0;
+
+ /*
+ * Need to make sure reassembly_data_length is read before
+ * reading reassembly_queue_length and calling
+ * _get_first_reassembly. This call is lock free
+ * as we never read at the end of the queue which are being
+ * updated in SOFTIRQ as more data is received
+ */
+ virt_rmb();
+ queue_length = info->reassembly_queue_length;
+ data_read = 0;
+ to_read = size;
+ offset = info->first_entry_offset;
+ while (data_read < size) {
+ response = _get_first_reassembly(info);
+ data_transfer = smbd_response_payload(response);
+ data_length = le32_to_cpu(data_transfer->data_length);
+ remaining_data_length =
+ le32_to_cpu(
+ data_transfer->remaining_data_length);
+ data_offset = le32_to_cpu(data_transfer->data_offset);
+
+ /*
+ * The upper layer expects RFC1002 length at the
+ * beginning of the payload. Return it to indicate
+ * the total length of the packet. This minimize the
+ * change to upper layer packet processing logic. This
+ * will be eventually remove when an intermediate
+ * transport layer is added
+ */
+ if (response->first_segment && size == 4) {
+ unsigned int rfc1002_len =
+ data_length + remaining_data_length;
+ *((__be32 *)buf) = cpu_to_be32(rfc1002_len);
+ data_read = 4;
+ response->first_segment = false;
+ log_read(INFO, "returning rfc1002 length %d\n",
+ rfc1002_len);
+ goto read_rfc1002_done;
+ }
+
+ to_copy = min_t(int, data_length - offset, to_read);
+ memcpy(
+ buf + data_read,
+ (char *)data_transfer + data_offset + offset,
+ to_copy);
+
+ /* move on to the next buffer? */
+ if (to_copy == data_length - offset) {
+ queue_length--;
+ /*
+ * No need to lock if we are not at the
+ * end of the queue
+ */
+ if (!queue_length)
+ spin_lock_irqsave(
+ &info->reassembly_queue_lock,
+ flags);
+ list_del(&response->list);
+ queue_removed++;
+ if (!queue_length)
+ spin_unlock_irqrestore(
+ &info->reassembly_queue_lock,
+ flags);
+
+ info->count_reassembly_queue--;
+ info->count_dequeue_reassembly_queue++;
+ put_receive_buffer(info, response, true);
+ offset = 0;
+ log_read(INFO, "put_receive_buffer offset=0\n");
+ } else
+ offset += to_copy;
+
+ to_read -= to_copy;
+ data_read += to_copy;
+
+ log_read(INFO, "_get_first_reassembly memcpy %d bytes "
+ "data_transfer_length-offset=%d after that "
+ "to_read=%d data_read=%d offset=%d\n",
+ to_copy, data_length - offset,
+ to_read, data_read, offset);
+ }
+
+ spin_lock_irqsave(&info->reassembly_queue_lock, flags);
+ info->reassembly_data_length -= data_read;
+ info->reassembly_queue_length -= queue_removed;
+ spin_unlock_irqrestore(&info->reassembly_queue_lock, flags);
+
+ info->first_entry_offset = offset;
+ log_read(INFO, "returning to thread data_read=%d "
+ "reassembly_data_length=%d first_entry_offset=%d\n",
+ data_read, info->reassembly_data_length,
+ info->first_entry_offset);
+read_rfc1002_done:
+ profiling_add_histogram(rdtsc() - t1, info->smbd_recv_cycles);
+ return data_read;
+ }
+
+ log_read(INFO, "wait_event on more data\n");
+ rc = wait_event_interruptible(
+ info->wait_reassembly_queue,
+ info->reassembly_data_length >= size ||
+ info->transport_status != SMBD_CONNECTED);
+ /* Don't return any data if interrupted */
+ if (rc)
+ return -ENODEV;
+
+ goto again;
+}
+
+/*
+ * Receive a page from receive reassembly queue
+ * page: the page to read data into
+ * to_read: the length of data to read
+ * return value: actual data read
+ */
+int smbd_recv_page(struct smbd_connection *info,
+ struct page *page, unsigned int to_read)
+{
+ int ret;
+ char *to_address;
+
+ /* make sure we have the page ready for read */
+ ret = wait_event_interruptible(
+ info->wait_reassembly_queue,
+ info->reassembly_data_length >= to_read ||
+ info->transport_status != SMBD_CONNECTED);
+ if (ret)
+ return 0;
+
+ /* now we can read from reassembly queue and not sleep */
+ to_address = kmap_atomic(page);
+
+ log_read(INFO, "reading from page=%p address=%p to_read=%d\n",
+ page, to_address, to_read);
+
+ ret = smbd_recv_buf(info, to_address, to_read);
+ kunmap_atomic(to_address);
+
+ return ret;
+}
+
+/*
+ * Receive data from transport
+ * msg: a msghdr point to the buffer, can be ITER_KVEC or ITER_BVEC
+ * return: total bytes read, or 0. SMB Direct will not do partial read.
+ */
+int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
+{
+ char *buf;
+ struct page *page;
+ unsigned int to_read;
+ int rc;
+
+ info->smbd_recv_pending++;
+
+ switch (msg->msg_iter.type) {
+ case READ | ITER_KVEC:
+ buf = msg->msg_iter.kvec->iov_base;
+ to_read = msg->msg_iter.kvec->iov_len;
+ rc = smbd_recv_buf(info, buf, to_read);
+ break;
+
+ case READ | ITER_BVEC:
+ page = msg->msg_iter.bvec->bv_page;
+ to_read = msg->msg_iter.bvec->bv_len;
+ rc = smbd_recv_page(info, page, to_read);
+ break;
+
+ default:
+ /* It's a bug in upper layer to get there */
+ cifs_dbg(VFS, "CIFS: invalid msg type %d\n",
+ msg->msg_iter.type);
+ rc = -EIO;
+ }
+
+ info->smbd_recv_pending--;
+ wake_up(&info->wait_smbd_recv_pending);
+
+ /* SMBDirect will read it all or nothing */
+ if (rc > 0)
+ msg->msg_iter.count = 0;
+ return rc;
+}
+
+/*
+ * Send data to transport
+ * Each rqst is transported as a SMBDirect payload
+ * rqst: the data to write
+ * return value: 0 if successfully write, otherwise error code
+ */
+int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
+{
+ struct kvec vec;
+ int nvecs;
+ int size;
+ int buflen = 0, remaining_data_length;
+ int start, i, j;
+ int max_iov_size =
+ info->max_send_size - sizeof(struct smbd_data_transfer);
+ struct kvec iov[SMBDIRECT_MAX_SGE];
+ int rc;
+ unsigned long long t1 = rdtsc();
+
+ info->smbd_send_pending++;
+ if (info->transport_status != SMBD_CONNECTED) {
+ rc = -ENODEV;
+ goto done;
+ }
+
+ /*
+ * This usually means a configuration error
+ * We use RDMA read/write for packet size > rdma_readwrite_threshold
+ * as long as it's properly configured we should never get into this
+ * situation
+ */
+ if (rqst->rq_nvec + rqst->rq_npages > SMBDIRECT_MAX_SGE) {
+ log_write(ERR, "maximum send segment %x exceeding %x\n",
+ rqst->rq_nvec + rqst->rq_npages, SMBDIRECT_MAX_SGE);
+ rc = -EINVAL;
+ goto done;
+ }
+
+ /*
+ * Remove the RFC1002 length defined in MS-SMB2 section 2.1
+ * It is used only for TCP transport
+ * In future we may want to add a transport layer under protocol
+ * layer so this will only be issued to TCP transport
+ */
+ iov[0].iov_base = (char *)rqst->rq_iov[0].iov_base + 4;
+ iov[0].iov_len = rqst->rq_iov[0].iov_len - 4;
+ buflen += iov[0].iov_len;
+
+ /* total up iov array first */
+ for (i = 1; i < rqst->rq_nvec; i++) {
+ iov[i].iov_base = rqst->rq_iov[i].iov_base;
+ iov[i].iov_len = rqst->rq_iov[i].iov_len;
+ buflen += iov[i].iov_len;
+ }
+
+ /* add in the page array if there is one */
+ if (rqst->rq_npages) {
+ buflen += rqst->rq_pagesz * (rqst->rq_npages - 1);
+ buflen += rqst->rq_tailsz;
+ }
+
+ if (buflen + sizeof(struct smbd_data_transfer) >
+ info->max_fragmented_send_size) {
+ log_write(ERR, "payload size %d > max size %d\n",
+ buflen, info->max_fragmented_send_size);
+ rc = -EINVAL;
+ goto done;
+ }
+
+ remaining_data_length = buflen;
+
+ log_write(INFO, "rqst->rq_nvec=%d rqst->rq_npages=%d rq_pagesz=%d "
+ "rq_tailsz=%d buflen=%d\n",
+ rqst->rq_nvec, rqst->rq_npages, rqst->rq_pagesz,
+ rqst->rq_tailsz, buflen);
+
+ start = i = iov[0].iov_len ? 0 : 1;
+ buflen = 0;
+ while (true) {
+ buflen += iov[i].iov_len;
+ if (buflen > max_iov_size) {
+ if (i > start) {
+ remaining_data_length -=
+ (buflen-iov[i].iov_len);
+ log_write(INFO, "sending iov[] from start=%d "
+ "i=%d nvecs=%d "
+ "remaining_data_length=%d\n",
+ start, i, i-start,
+ remaining_data_length);
+ rc = smbd_post_send_data(
+ info, &iov[start], i-start,
+ remaining_data_length);
+ if (rc)
+ goto done;
+ } else {
+ /* iov[start] is too big, break it */
+ nvecs = (buflen+max_iov_size-1)/max_iov_size;
+ log_write(INFO, "iov[%d] iov_base=%p buflen=%d"
+ " break to %d vectors\n",
+ start, iov[start].iov_base,
+ buflen, nvecs);
+ for (j = 0; j < nvecs; j++) {
+ vec.iov_base =
+ (char *)iov[start].iov_base +
+ j*max_iov_size;
+ vec.iov_len = max_iov_size;
+ if (j == nvecs-1)
+ vec.iov_len =
+ buflen -
+ max_iov_size*(nvecs-1);
+ remaining_data_length -= vec.iov_len;
+ log_write(INFO,
+ "sending vec j=%d iov_base=%p"
+ " iov_len=%lu "
+ "remaining_data_length=%d\n",
+ j, vec.iov_base, vec.iov_len,
+ remaining_data_length);
+ rc = smbd_post_send_data(
+ info, &vec, 1,
+ remaining_data_length);
+ if (rc)
+ goto done;
+ }
+ i++;
+ }
+ start = i;
+ buflen = 0;
+ } else {
+ i++;
+ if (i == rqst->rq_nvec) {
+ /* send out all remaining vecs */
+ remaining_data_length -= buflen;
+ log_write(INFO,
+ "sending iov[] from start=%d i=%d "
+ "nvecs=%d remaining_data_length=%d\n",
+ start, i, i-start,
+ remaining_data_length);
+ rc = smbd_post_send_data(info, &iov[start],
+ i-start, remaining_data_length);
+ if (rc)
+ goto done;
+ break;
+ }
+ }
+ log_write(INFO, "looping i=%d buflen=%d\n", i, buflen);
+ }
+
+ /* now sending pages if there are any */
+ for (i = 0; i < rqst->rq_npages; i++) {
+ buflen = (i == rqst->rq_npages-1) ?
+ rqst->rq_tailsz : rqst->rq_pagesz;
+ nvecs = (buflen + max_iov_size - 1) / max_iov_size;
+ log_write(INFO, "sending pages buflen=%d nvecs=%d\n",
+ buflen, nvecs);
+ for (j = 0; j < nvecs; j++) {
+ size = max_iov_size;
+ if (j == nvecs-1)
+ size = buflen - j*max_iov_size;
+ remaining_data_length -= size;
+ log_write(INFO, "sending pages i=%d offset=%d size=%d"
+ " remaining_data_length=%d\n",
+ i, j*max_iov_size, size, remaining_data_length);
+ rc = smbd_post_send_page(
+ info, rqst->rq_pages[i], j*max_iov_size,
+ size, remaining_data_length);
+ if (rc)
+ goto done;
+ }
+ }
+
+done:
+ /*
+ * As an optimization, we don't wait for individual I/O to finish
+ * before sending the next one.
+ * Send them all and wait for pending send count to get to 0
+ * that means all the I/Os have been out and we are good to return
+ */
+
+ wait_event(info->wait_send_payload_pending,
+ atomic_read(&info->send_payload_pending) == 0);
+
+ info->smbd_send_pending--;
+ wake_up(&info->wait_smbd_send_pending);
+ profiling_add_histogram(rdtsc()-t1, info->smbd_write_cycles);
+
+ return rc;
+}
+
+static void register_mr_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ struct smbd_mr *mr;
+ struct ib_cqe *cqe;
+
+ if (wc->status) {
+ log_rdma_mr(ERR, "status=%d\n", wc->status);
+ cqe = wc->wr_cqe;
+ mr = container_of(cqe, struct smbd_mr, cqe);
+ smbd_disconnect_rdma_connection(mr->conn);
+ }
+}
+
+/*
+ * The work queue function that recovers MRs
+ * We need to call ib_dereg_mr() and ib_alloc_mr() before this MR can be used
+ * again. Both calls are slow, so finish them in a workqueue. This will not
+ * block I/O path.
+ * There is one workqueue that recovers MRs, there is no need to lock as the
+ * I/O requests calling smbd_register_mr will never update the links in the
+ * mr_list.
+ */
+static void smbd_mr_recovery_work(struct work_struct *work)
+{
+ struct smbd_connection *info =
+ container_of(work, struct smbd_connection, mr_recovery_work);
+ struct smbd_mr *smbdirect_mr;
+ 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 faield rc=%x\n",
+ rc);
+ smbd_disconnect_rdma_connection(info);
+ }
+
+ 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);
+ smbd_disconnect_rdma_connection(info);
+ }
+
+ 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);
+ }
+ }
+}
+
+static void destroy_mr_list(struct smbd_connection *info)
+{
+ struct smbd_mr *mr, *tmp;
+
+ cancel_work_sync(&info->mr_recovery_work);
+ list_for_each_entry_safe(mr, tmp, &info->mr_list, list) {
+ if (mr->state == MR_INVALIDATED)
+ ib_dma_unmap_sg(info->id->device, mr->sgl,
+ mr->sgl_count, mr->dir);
+ ib_dereg_mr(mr->mr);
+ kfree(mr->sgl);
+ kfree(mr);
+ }
+}
+
+/*
+ * Allocate MRs used for RDMA read/write
+ * The number of MRs will not exceed hardware capability in responder_resources
+ * All MRs are kept in mr_list. The MR can be recovered after it's used
+ * Recovery is done in smbd_mr_recovery_work. The content of list entry changes
+ * as MRs are used and recovered for I/O, but the list links will not change
+ */
+static int allocate_mr_list(struct smbd_connection *info)
+{
+ int i;
+ struct smbd_mr *smbdirect_mr, *tmp;
+
+ INIT_LIST_HEAD(&info->mr_list);
+ init_waitqueue_head(&info->wait_mr);
+ spin_lock_init(&info->mr_list_lock);
+ atomic_set(&info->mr_ready_count, 0);
+ atomic_set(&info->mr_used_count, 0);
+ init_waitqueue_head(&info->wait_for_mr_cleanup);
+ for (i = 0; i < info->responder_resources; i++) {
+ smbdirect_mr = kzalloc(sizeof(*smbdirect_mr), GFP_KERNEL);
+ if (!smbdirect_mr)
+ goto out;
+ 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);
+ goto out;
+ }
+ smbdirect_mr->sgl = kcalloc(
+ info->max_frmr_depth,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!smbdirect_mr->sgl) {
+ log_rdma_mr(ERR, "failed to allocate sgl\n");
+ ib_dereg_mr(smbdirect_mr->mr);
+ goto out;
+ }
+ smbdirect_mr->state = MR_READY;
+ smbdirect_mr->conn = info;
+
+ list_add_tail(&smbdirect_mr->list, &info->mr_list);
+ atomic_inc(&info->mr_ready_count);
+ }
+ INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work);
+ return 0;
+
+out:
+ kfree(smbdirect_mr);
+
+ list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) {
+ ib_dereg_mr(smbdirect_mr->mr);
+ kfree(smbdirect_mr->sgl);
+ kfree(smbdirect_mr);
+ }
+ return -ENOMEM;
+}
+
+/*
+ * Get a MR from mr_list. This function waits until there is at least one
+ * MR available in the list. It may access the list while the
+ * smbd_mr_recovery_work is recovering the MR list. This doesn't need a lock
+ * as they never modify the same places. However, there may be several CPUs
+ * issueing I/O trying to get MR at the same time, mr_list_lock is used to
+ * protect this situation.
+ */
+static struct smbd_mr *get_mr(struct smbd_connection *info)
+{
+ struct smbd_mr *ret;
+ int rc;
+again:
+ rc = wait_event_interruptible(info->wait_mr,
+ atomic_read(&info->mr_ready_count) ||
+ info->transport_status != SMBD_CONNECTED);
+ if (rc) {
+ log_rdma_mr(ERR, "wait_event_interruptible rc=%x\n", rc);
+ return NULL;
+ }
+
+ if (info->transport_status != SMBD_CONNECTED) {
+ log_rdma_mr(ERR, "info->transport_status=%x\n",
+ info->transport_status);
+ return NULL;
+ }
+
+ spin_lock(&info->mr_list_lock);
+ list_for_each_entry(ret, &info->mr_list, list) {
+ if (ret->state == MR_READY) {
+ ret->state = MR_REGISTERED;
+ atomic_dec(&info->mr_ready_count);
+ spin_unlock(&info->mr_list_lock);
+ atomic_inc(&info->mr_used_count);
+ return ret;
+ }
+ }
+
+ spin_unlock(&info->mr_list_lock);
+ /*
+ * It is possible that we can get a MR because other processes may try
+ * to acquire a MR at the same time. If this is the case, retry it.
+ */
+ goto again;
+}
+
+/*
+ * Register memory for RDMA read/write
+ * pages[]: the list of pages to register memory with
+ * num_pages: the number of pages to register
+ * tailsz: if non-zero, the bytes to register in the last page
+ * writing: true if this is a RDMA write (SMB read), false for RDMA read
+ * need_invalidate: true if this MR needs to be locally invalidated after I/O
+ * return value: the MR registered, NULL if failed.
+ */
+struct smbd_mr *smbd_register_mr(
+ struct smbd_connection *info, struct page *pages[], int num_pages,
+ int tailsz, bool writing, bool need_invalidate)
+{
+ struct smbd_mr *smbdirect_mr;
+ int rc, i;
+ enum dma_data_direction dir;
+ struct ib_reg_wr *reg_wr;
+ struct ib_send_wr *bad_wr;
+ unsigned long long t1 = rdtsc();
+
+ if (num_pages > info->max_frmr_depth) {
+ log_rdma_mr(ERR, "num_pages=%d max_frmr_depth=%d\n",
+ num_pages, info->max_frmr_depth);
+ return NULL;
+ }
+
+ smbdirect_mr = get_mr(info);
+ if (!smbdirect_mr) {
+ log_rdma_mr(ERR, "get_mr returning NULL\n");
+ return NULL;
+ }
+ smbdirect_mr->need_invalidate = need_invalidate;
+ smbdirect_mr->sgl_count = num_pages;
+ sg_init_table(smbdirect_mr->sgl, num_pages);
+
+ for (i = 0; i < num_pages - 1; i++)
+ sg_set_page(&smbdirect_mr->sgl[i], pages[i], PAGE_SIZE, 0);
+ sg_set_page(&smbdirect_mr->sgl[i], pages[i],
+ tailsz ? tailsz : PAGE_SIZE, 0);
+
+ dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+ smbdirect_mr->dir = dir;
+ rc = ib_dma_map_sg(info->id->device, smbdirect_mr->sgl, num_pages, dir);
+ if (!rc) {
+ log_rdma_mr(INFO, "ib_dma_map_sg num_pages=%x dir=%x rc=%x\n",
+ num_pages, dir, rc);
+ goto dma_map_error;
+ }
+
+ rc = ib_map_mr_sg(smbdirect_mr->mr, smbdirect_mr->sgl, num_pages,
+ NULL, PAGE_SIZE);
+ if (rc != num_pages) {
+ log_rdma_mr(INFO,
+ "ib_map_mr_sg failed rc = %x num_pages = %x\n",
+ rc, num_pages);
+ goto map_mr_error;
+ }
+
+ ib_update_fast_reg_key(smbdirect_mr->mr,
+ ib_inc_rkey(smbdirect_mr->mr->rkey));
+ reg_wr = &smbdirect_mr->wr;
+ reg_wr->wr.opcode = IB_WR_REG_MR;
+ smbdirect_mr->cqe.done = register_mr_done;
+ reg_wr->wr.wr_cqe = &smbdirect_mr->cqe;
+ reg_wr->wr.num_sge = 0;
+ reg_wr->wr.send_flags = IB_SEND_SIGNALED;
+ reg_wr->mr = smbdirect_mr->mr;
+ reg_wr->key = smbdirect_mr->mr->rkey;
+ reg_wr->access = writing ?
+ IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+ IB_ACCESS_REMOTE_READ;
+
+ /*
+ * There is no need for waiting for complemtion on ib_post_send
+ * on IB_WR_REG_MR. Hardware enforces a barrier and order of execution
+ * on the next ib_post_send when we actaully send I/O to remote peer
+ */
+ rc = ib_post_send(info->id->qp, ®_wr->wr, &bad_wr);
+ if (!rc) {
+ profiling_add_histogram(
+ rdtsc()-t1, info->smbd_register_mr_cycles);
+ return smbdirect_mr;
+ }
+
+ log_rdma_mr(ERR, "ib_post_send failed rc=%x reg_wr->key=%x\n",
+ rc, reg_wr->key);
+
+ /* If all failed, attempt to recover this MR by setting it MR_ERROR*/
+map_mr_error:
+ ib_dma_unmap_sg(info->id->device, smbdirect_mr->sgl,
+ smbdirect_mr->sgl_count, smbdirect_mr->dir);
+
+dma_map_error:
+ smbdirect_mr->state = MR_ERROR;
+ if (atomic_dec_and_test(&info->mr_used_count))
+ wake_up(&info->wait_for_mr_cleanup);
+
+ return NULL;
+}
+
+static void local_inv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ struct smbd_mr *smbdirect_mr;
+ struct ib_cqe *cqe;
+
+ cqe = wc->wr_cqe;
+ smbdirect_mr = container_of(cqe, struct smbd_mr, cqe);
+ smbdirect_mr->state = MR_INVALIDATED;
+ if (wc->status != IB_WC_SUCCESS) {
+ log_rdma_mr(ERR, "invalidate failed status=%x\n", wc->status);
+ smbdirect_mr->state = MR_ERROR;
+ }
+ complete(&smbdirect_mr->invalidate_done);
+}
+
+/*
+ * Deregister a MR after I/O is done
+ * This function may wait if remote invalidation is not used
+ * and we have to locally invalidate the buffer to prevent data is being
+ * modified by remote peer after upper layer consumes it
+ */
+int smbd_deregister_mr(struct smbd_mr *smbdirect_mr)
+{
+ struct ib_send_wr *wr, *bad_wr;
+ struct smbd_connection *info = smbdirect_mr->conn;
+ int rc = 0;
+ unsigned long long t1 = rdtsc();
+
+ if (smbdirect_mr->need_invalidate) {
+ /* Need to finish local invalidation before returning */
+ wr = &smbdirect_mr->inv_wr;
+ wr->opcode = IB_WR_LOCAL_INV;
+ smbdirect_mr->cqe.done = local_inv_done;
+ wr->wr_cqe = &smbdirect_mr->cqe;
+ wr->num_sge = 0;
+ wr->ex.invalidate_rkey = smbdirect_mr->mr->rkey;
+ wr->send_flags = IB_SEND_SIGNALED;
+
+ init_completion(&smbdirect_mr->invalidate_done);
+ rc = ib_post_send(info->id->qp, wr, &bad_wr);
+ if (rc) {
+ log_rdma_mr(ERR, "ib_post_send failed rc=%x\n", rc);
+ smbd_disconnect_rdma_connection(info);
+ goto done;
+ }
+ wait_for_completion(&smbdirect_mr->invalidate_done);
+ smbdirect_mr->need_invalidate = false;
+ } else
+ /*
+ * For remote invalidation, just set it to MR_INVALIDATED
+ * and defer to mr_recovery_work to recover the MR for next use
+ */
+ smbdirect_mr->state = MR_INVALIDATED;
+
+ /*
+ * Schedule the work to do MR recovery for future I/Os
+ * MR recovery is slow and we don't want it to block the current I/O
+ */
+ queue_work(info->workqueue, &info->mr_recovery_work);
+
+ profiling_add_histogram(rdtsc()-t1, info->smbd_deregister_mr_cycles);
+
+done:
+ if (atomic_dec_and_test(&info->mr_used_count))
+ wake_up(&info->wait_for_mr_cleanup);
+
+ return rc;
+}
diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h
index 06eeb0b..30730ec 100644
--- a/fs/cifs/smbdirect.h
+++ b/fs/cifs/smbdirect.h
@@ -16,5 +16,309 @@
#ifndef _SMBDIRECT_H
#define _SMBDIRECT_H
+#include "cifsglob.h"
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <linux/mempool.h>
+
+enum keep_alive_status {
+ KEEP_ALIVE_NONE,
+ KEEP_ALIVE_PENDING,
+ KEEP_ALIVE_SENT,
+};
+
+enum smbd_connection_status {
+ SMBD_CREATED,
+ SMBD_CONNECTING,
+ SMBD_CONNECTED,
+ SMBD_NEGOTIATE_FAILED,
+ SMBD_DISCONNECTING,
+ SMBD_DISCONNECTED,
+ SMBD_DESTROYED
+};
+
+/*
+ * The context for the SMBDirect transport
+ * Everything related to the transport is here. It has several logical parts
+ * 1. RDMA related structures
+ * 2. SMBDirect connection parameters
+ * 3. Memory registrations
+ * 4. Receive and reassembly queues for data receive path
+ * 5. mempools for allocating packets
+ */
+struct smbd_connection {
+ enum smbd_connection_status transport_status;
+
+ /* RDMA related */
+ struct rdma_cm_id *id;
+ struct ib_qp_init_attr qp_attr;
+ struct ib_pd *pd;
+ struct ib_cq *send_cq, *recv_cq;
+ struct ib_device_attr dev_attr;
+ int ri_rc;
+ struct completion ri_done;
+ wait_queue_head_t conn_wait;
+ wait_queue_head_t wait_destroy;
+
+ struct completion negotiate_completion;
+ bool negotiate_done;
+
+ struct work_struct destroy_work;
+ struct work_struct disconnect_work;
+ struct work_struct recv_done_work;
+ struct work_struct post_send_credits_work;
+
+ spinlock_t lock_new_credits_offered;
+ int new_credits_offered;
+
+ /* Connection parameters defined in [MS-SMBD] 3.1.1.1 */
+ int receive_credit_max;
+ int send_credit_target;
+ int max_send_size;
+ int max_fragmented_recv_size;
+ int max_fragmented_send_size;
+ int max_receive_size;
+ int keep_alive_interval;
+ int max_readwrite_size;
+ enum keep_alive_status keep_alive_requested;
+ int protocol;
+ atomic_t send_credits;
+ atomic_t receive_credits;
+ int receive_credit_target;
+ int fragment_reassembly_remaining;
+
+ /* Memory registrations */
+ /* Maximum number of RDMA read/write outstanding on this connection */
+ int responder_resources;
+ /* Maximum number of SGEs in a RDMA write/read */
+ int max_frmr_depth;
+ /*
+ * If payload is less than or equal to the threshold,
+ * use RDMA send/recv to send upper layer I/O.
+ * If payload is more than the threshold,
+ * use RDMA read/write through memory registration for I/O.
+ */
+ int rdma_readwrite_threshold;
+ enum ib_mr_type mr_type;
+ struct list_head mr_list;
+ spinlock_t mr_list_lock;
+ /* The number of available MRs ready for memory registration */
+ atomic_t mr_ready_count;
+ atomic_t mr_used_count;
+ wait_queue_head_t wait_mr;
+ struct work_struct mr_recovery_work;
+ /* Used by transport to wait until all MRs are returned */
+ wait_queue_head_t wait_for_mr_cleanup;
+
+ /* Activity accoutning */
+ /* Pending reqeusts issued from upper layer */
+ int smbd_send_pending;
+ wait_queue_head_t wait_smbd_send_pending;
+
+ int smbd_recv_pending;
+ wait_queue_head_t wait_smbd_recv_pending;
+
+ atomic_t send_pending;
+ wait_queue_head_t wait_send_pending;
+ atomic_t send_payload_pending;
+ wait_queue_head_t wait_send_payload_pending;
+
+ /* Receive queue */
+ struct list_head receive_queue;
+ int count_receive_queue;
+ spinlock_t receive_queue_lock;
+
+ struct list_head empty_packet_queue;
+ int count_empty_packet_queue;
+ spinlock_t empty_packet_queue_lock;
+
+ wait_queue_head_t wait_receive_queues;
+
+ /* Reassembly queue */
+ struct list_head reassembly_queue;
+ spinlock_t reassembly_queue_lock;
+ wait_queue_head_t wait_reassembly_queue;
+
+ /* total data length of reassembly queue */
+ int reassembly_data_length;
+ int reassembly_queue_length;
+ /* the offset to first buffer in reassembly queue */
+ int first_entry_offset;
+
+ bool send_immediate;
+
+ wait_queue_head_t wait_send_queue;
+
+ /*
+ * Indicate if we have received a full packet on the connection
+ * This is used to identify the first SMBD packet of a assembled
+ * payload (SMB packet) in reassembly queue so we can return a
+ * RFC1002 length to upper layer to indicate the length of the SMB
+ * packet received
+ */
+ bool full_packet_received;
+
+ struct workqueue_struct *workqueue;
+ struct delayed_work idle_timer_work;
+ struct delayed_work send_immediate_work;
+
+ /* Memory pool for preallocating buffers */
+ /* request pool for RDMA send */
+ struct kmem_cache *request_cache;
+ mempool_t *request_mempool;
+
+ /* response pool for RDMA receive */
+ struct kmem_cache *response_cache;
+ mempool_t *response_mempool;
+
+ /* for debug purposes */
+ unsigned int count_get_receive_buffer;
+ unsigned int count_put_receive_buffer;
+ unsigned int count_reassembly_queue;
+ unsigned int count_enqueue_reassembly_queue;
+ unsigned int count_dequeue_reassembly_queue;
+ unsigned int count_send_empty;
+
+#define SIZE_LONG_LONG 64
+ unsigned long long smbd_register_mr_cycles[SIZE_LONG_LONG];
+ unsigned long long smbd_deregister_mr_cycles[SIZE_LONG_LONG];
+ unsigned long long smbd_write_cycles[SIZE_LONG_LONG];
+ unsigned long long smbd_recv_cycles[SIZE_LONG_LONG];
+ unsigned long long recv_done_cycles[SIZE_LONG_LONG];
+};
+
+enum smbd_message_type {
+ SMBD_NEGOTIATE_RESP,
+ SMBD_TRANSFER_DATA,
+};
+
+#define SMB_DIRECT_RESPONSE_REQUESTED 0x0001
+
+/* SMBD negotiation request packet [MS-SMBD] 2.2.1 */
+struct smbd_negotiate_req {
+ __le16 min_version;
+ __le16 max_version;
+ __le16 reserved;
+ __le16 credits_requested;
+ __le32 preferred_send_size;
+ __le32 max_receive_size;
+ __le32 max_fragmented_size;
+} __packed;
+
+/* SMBD negotiation response packet [MS-SMBD] 2.2.2 */
+struct smbd_negotiate_resp {
+ __le16 min_version;
+ __le16 max_version;
+ __le16 negotiated_version;
+ __le16 reserved;
+ __le16 credits_requested;
+ __le16 credits_granted;
+ __le32 status;
+ __le32 max_readwrite_size;
+ __le32 preferred_send_size;
+ __le32 max_receive_size;
+ __le32 max_fragmented_size;
+} __packed;
+
+/* SMBD data transfer packet with payload [MS-SMBD] 2.2.3 */
+struct smbd_data_transfer {
+ __le16 credits_requested;
+ __le16 credits_granted;
+ __le16 flags;
+ __le16 reserved;
+ __le32 remaining_data_length;
+ __le32 data_offset;
+ __le32 data_length;
+ __le32 padding;
+ __u8 buffer[];
+} __packed;
+
+/* The packet fields for a registered RDMA buffer */
+struct smbd_buffer_descriptor_v1 {
+ __le64 offset;
+ __le32 token;
+ __le32 length;
+} __packed;
+
#define SMBDIRECT_MAX_SGE 16
+/* The context for a SMBD request */
+struct smbd_request {
+ struct smbd_connection *info;
+ struct ib_cqe cqe;
+
+ /* true if this request carries upper layer payload */
+ bool has_payload;
+
+ /* the SGE entries for this packet */
+ struct ib_sge sge[SMBDIRECT_MAX_SGE];
+ int num_sge;
+
+ /* SMBD packet header follows this structure */
+ u8 packet[];
+};
+
+/* The context for a SMBD response */
+struct smbd_response {
+ struct smbd_connection *info;
+ struct ib_cqe cqe;
+ struct ib_sge sge;
+
+ enum smbd_message_type type;
+
+ /* Link to receive queue or reassembly queue */
+ struct list_head list;
+
+ /* Indicate if this is the 1st packet of a payload */
+ bool first_segment;
+
+ /* SMBD packet header and payload follows this structure */
+ u8 packet[];
+};
+
+/* Create a SMBDirect session */
+struct smbd_connection *smbd_get_connection(
+ struct TCP_Server_Info *server, struct sockaddr *dstaddr);
+
+/* Reconnect SMBDirect session */
+int smbd_reconnect(struct TCP_Server_Info *server);
+
+/* Destroy SMBDirect session */
+void smbd_destroy(struct smbd_connection *info);
+
+/* Interface for carrying upper layer I/O through send/recv */
+int smbd_recv(struct smbd_connection *info, struct msghdr *msg);
+int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst);
+
+enum mr_state {
+ MR_READY,
+ MR_REGISTERED,
+ MR_INVALIDATED,
+ MR_ERROR
+};
+
+struct smbd_mr {
+ struct smbd_connection *conn;
+ struct list_head list;
+ enum mr_state state;
+ struct ib_mr *mr;
+ struct scatterlist *sgl;
+ int sgl_count;
+ enum dma_data_direction dir;
+ union {
+ struct ib_reg_wr wr;
+ struct ib_send_wr inv_wr;
+ };
+ struct ib_cqe cqe;
+ bool need_invalidate;
+ struct completion invalidate_done;
+};
+
+/* Interfaces to register and deregister MR for RDMA read/write */
+struct smbd_mr *smbd_register_mr(
+ struct smbd_connection *info, struct page *pages[], int num_pages,
+ int tailsz, bool writing, bool need_invalidate);
+int smbd_deregister_mr(struct smbd_mr *mr);
+
+void profiling_display_histogram(
+ struct seq_file *m, unsigned long long array[]);
#endif
--
2.7.4
2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> Add "rdma" to CIFS mount options to connect to SMB Direct.
> Add checks to validate this is used on SMB 3.X dialects.
>
> To connect to SMBDirect, use "mount.cifs -o rdma,vers=3.x".
> At the time of this patch, 3.x can be 3.0, 3.02 or 3.1.1.
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/cifs_debug.c | 2 ++
> fs/cifs/cifsfs.c | 2 ++
> fs/cifs/cifsglob.h | 3 +++
> fs/cifs/connect.c | 15 ++++++++++++++-
> 4 files changed, 21 insertions(+), 1 deletion(-)
>
> diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
> index 9727e1d..ba0870d 100644
> --- a/fs/cifs/cifs_debug.c
> +++ b/fs/cifs/cifs_debug.c
> @@ -171,6 +171,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
> ses->ses_count, ses->serverOS, ses->serverNOS,
> ses->capabilities, ses->status);
> }
> + if (server->rdma)
> + seq_printf(m, "RDMA\n\t");
> seq_printf(m, "TCP status: %d\n\tLocal Users To "
> "Server: %d SecMode: 0x%x Req On Wire: %d",
> server->tcpStatus, server->srv_count,
> diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
> index fe0c8dc..a628800 100644
> --- a/fs/cifs/cifsfs.c
> +++ b/fs/cifs/cifsfs.c
> @@ -330,6 +330,8 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
> default:
> seq_puts(s, "(unknown)");
> }
> + if (server->rdma)
> + seq_puts(s, ",rdma");
> }
>
> static void
> diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
> index 8289f95..703c2fb 100644
> --- a/fs/cifs/cifsglob.h
> +++ b/fs/cifs/cifsglob.h
> @@ -531,6 +531,7 @@ struct smb_vol {
> bool nopersistent:1;
> bool resilient:1; /* noresilient not required since not fored for CA */
> bool domainauto:1;
> + bool rdma:1;
> unsigned int rsize;
> unsigned int wsize;
> bool sockopt_tcp_nodelay:1;
> @@ -649,6 +650,8 @@ struct TCP_Server_Info {
> bool sec_kerberos; /* supports plain Kerberos */
> bool sec_mskerberos; /* supports legacy MS Kerberos */
> bool large_buf; /* is current buffer large? */
> + /* use SMBD connection instead of socket */
> + bool rdma;
> struct delayed_work echo; /* echo ping workqueue job */
> char *smallbuf; /* pointer to current "small" buffer */
> char *bigbuf; /* pointer to current "big" buffer */
> diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
> index 2eeaac6..19fdca8 100644
> --- a/fs/cifs/connect.c
> +++ b/fs/cifs/connect.c
> @@ -94,7 +94,7 @@ enum {
> Opt_multiuser, Opt_sloppy, Opt_nosharesock,
> Opt_persistent, Opt_nopersistent,
> Opt_resilient, Opt_noresilient,
> - Opt_domainauto,
> + Opt_domainauto, Opt_rdma,
>
> /* Mount options which take numeric value */
> Opt_backupuid, Opt_backupgid, Opt_uid,
> @@ -185,6 +185,7 @@ static const match_table_t cifs_mount_option_tokens = {
> { Opt_resilient, "resilienthandles"},
> { Opt_noresilient, "noresilienthandles"},
> { Opt_domainauto, "domainauto"},
> + { Opt_rdma, "rdma"},
>
> { Opt_backupuid, "backupuid=%s" },
> { Opt_backupgid, "backupgid=%s" },
> @@ -1541,6 +1542,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
> case Opt_domainauto:
> vol->domainauto = true;
> break;
> + case Opt_rdma:
> + vol->rdma = true;
> + break;
>
> /* Numeric Values */
> case Opt_backupuid:
> @@ -1931,6 +1935,11 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
> goto cifs_parse_mount_err;
> }
>
> + if (vol->rdma && vol->vals->protocol_id < SMB30_PROT_ID) {
> + cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
> + goto cifs_parse_mount_err;
> + }
> +
> #ifndef CONFIG_KEYS
> /* Muliuser mounts require CONFIG_KEYS support */
> if (vol->multiuser) {
> @@ -2134,6 +2143,9 @@ static int match_server(struct TCP_Server_Info *server, struct smb_vol *vol)
> if (server->echo_interval != vol->echo_interval * HZ)
> return 0;
>
> + if (server->rdma != vol->rdma)
> + return 0;
> +
> return 1;
> }
>
> @@ -2234,6 +2246,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
> tcp_ses->noblocksnd = volume_info->noblocksnd;
> tcp_ses->noautotune = volume_info->noautotune;
> tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay;
> + tcp_ses->rdma = volume_info->rdma;
> tcp_ses->in_flight = 0;
> tcp_ses->credits = 1;
> init_waitqueue_head(&tcp_ses->response_q);
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
It is better to introduce a mount option after the functional changes
not before them. In this case we do not result in having the mount
option that does nothing if we break the patchset.
--
Best regards,
Pavel Shilovsky
2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> To prepare for protocol implementation, add constants and user-configurable
> values in the SMBDirect protocol.
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/smbdirect.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++++
> fs/cifs/smbdirect.h | 20 ++++++++++++++
> 2 files changed, 98 insertions(+)
> create mode 100644 fs/cifs/smbdirect.c
> create mode 100644 fs/cifs/smbdirect.h
>
> diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
> new file mode 100644
> index 0000000..d785bc1
> --- /dev/null
> +++ b/fs/cifs/smbdirect.c
> @@ -0,0 +1,78 @@
> +/*
> + * Copyright (C) 2017, Microsoft Corporation.
> + *
> + * Author(s): Long Li <[email protected]>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
> + * the GNU General Public License for more details.
> + */
> +#include <linux/module.h>
> +#include "smbdirect.h"
> +#include "cifs_debug.h"
> +
> +/* SMBD version number */
> +#define SMBD_V1 0x0100
> +
> +/* Port numbers for SMBD transport */
> +#define SMB_PORT 445
> +#define SMBD_PORT 5445
> +
> +/* Address lookup and resolve timeout in ms */
> +#define RDMA_RESOLVE_TIMEOUT 5000
> +
> +/* SMBD negotiation timeout in seconds */
> +#define SMBD_NEGOTIATE_TIMEOUT 120
> +
> +/* SMBD minimum receive size and fragmented sized defined in [MS-SMBD] */
> +#define SMBD_MIN_RECEIVE_SIZE 128
> +#define SMBD_MIN_FRAGMENTED_SIZE 131072
> +
> +/*
> + * Default maximum number of RDMA read/write outstanding on this connection
> + * This value is possibly decreased during QP creation on hardware limit
> + */
> +#define SMBD_CM_RESPONDER_RESOURCES 32
> +
> +/* Maximum number of retries on data transfer operations */
> +#define SMBD_CM_RETRY 6
> +/* No need to retry on Receiver Not Ready since SMBD manages credits */
> +#define SMBD_CM_RNR_RETRY 0
> +
> +/*
> + * User configurable initial values per SMBD transport connection
> + * as defined in [MS-SMBD] 3.1.1.1
> + * Those may change after a SMBD negotiation
> + */
Since these value are per transport connection, why they are global?
Shouldn't they be inside a some structure that is created for a
particular connection? Also the constants below should be defines.
> +/* The local peer's maximum number of credits to grant to the peer */
> +static int receive_credit_max = 255;
> +/* The remote peer's credit request of local peer */
> +static int send_credit_target = 255;
> +/* The maximum single message size can be sent to remote peer */
> +static int max_send_size = 1364;
> +/* The maximum fragmented upper-layer payload receive size supported */
> +static int max_fragmented_recv_size = 1024 * 1024;
> +/* The maximum single-message size which can be received */
> +static int max_receive_size = 8192;
> +
> +/* The timeout to initiate send of a keepalive message on idle */
> +static int keep_alive_interval = 120;
> +
> +/*
> + * User configurable initial values for RDMA transport
> + * The actual values used may be lower and are limited to hardware capabilities
> + */
> +/* Default maximum number of SGEs in a RDMA send/recv */
> +static int max_send_sge = SMBDIRECT_MAX_SGE;
> +static int max_recv_sge = SMBDIRECT_MAX_SGE;
> +/* Default maximum number of SGEs in a RDMA write/read */
> +static int max_frmr_depth = 2048;
> +
> +/* If payload is less than this byte, use RDMA send/recv not read/write */
> +static int rdma_readwrite_threshold = 4096;
> diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h
> new file mode 100644
> index 0000000..06eeb0b
> --- /dev/null
> +++ b/fs/cifs/smbdirect.h
> @@ -0,0 +1,20 @@
> +/*
> + * Copyright (C) 2017, Microsoft Corporation.
> + *
> + * Author(s): Long Li <[email protected]>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
> + * the GNU General Public License for more details.
> + */
> +#ifndef _SMBDIRECT_H
> +#define _SMBDIRECT_H
> +
> +#define SMBDIRECT_MAX_SGE 16
> +#endif
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 3:37 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 01/19] CIFS: Add rdma mount option
>
> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > Add "rdma" to CIFS mount options to connect to SMB Direct.
> > Add checks to validate this is used on SMB 3.X dialects.
> >
> > To connect to SMBDirect, use "mount.cifs -o rdma,vers=3.x".
> > At the time of this patch, 3.x can be 3.0, 3.02 or 3.1.1.
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/cifs_debug.c | 2 ++
> > fs/cifs/cifsfs.c | 2 ++
> > fs/cifs/cifsglob.h | 3 +++
> > fs/cifs/connect.c | 15 ++++++++++++++-
> > 4 files changed, 21 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index
> > 9727e1d..ba0870d 100644
> > --- a/fs/cifs/cifs_debug.c
> > +++ b/fs/cifs/cifs_debug.c
> > @@ -171,6 +171,8 @@ static int cifs_debug_data_proc_show(struct
> seq_file *m, void *v)
> > ses->ses_count, ses->serverOS, ses->serverNOS,
> > ses->capabilities, ses->status);
> > }
> > + if (server->rdma)
> > + seq_printf(m, "RDMA\n\t");
> > seq_printf(m, "TCP status: %d\n\tLocal Users To "
> > "Server: %d SecMode: 0x%x Req On Wire: %d",
> > server->tcpStatus,
> > server->srv_count, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
> > index fe0c8dc..a628800 100644
> > --- a/fs/cifs/cifsfs.c
> > +++ b/fs/cifs/cifsfs.c
> > @@ -330,6 +330,8 @@ cifs_show_address(struct seq_file *s, struct
> TCP_Server_Info *server)
> > default:
> > seq_puts(s, "(unknown)");
> > }
> > + if (server->rdma)
> > + seq_puts(s, ",rdma");
> > }
> >
> > static void
> > diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index
> > 8289f95..703c2fb 100644
> > --- a/fs/cifs/cifsglob.h
> > +++ b/fs/cifs/cifsglob.h
> > @@ -531,6 +531,7 @@ struct smb_vol {
> > bool nopersistent:1;
> > bool resilient:1; /* noresilient not required since not fored for CA */
> > bool domainauto:1;
> > + bool rdma:1;
> > unsigned int rsize;
> > unsigned int wsize;
> > bool sockopt_tcp_nodelay:1;
> > @@ -649,6 +650,8 @@ struct TCP_Server_Info {
> > bool sec_kerberos; /* supports plain Kerberos */
> > bool sec_mskerberos; /* supports legacy MS Kerberos */
> > bool large_buf; /* is current buffer large? */
> > + /* use SMBD connection instead of socket */
> > + bool rdma;
> > struct delayed_work echo; /* echo ping workqueue job */
> > char *smallbuf; /* pointer to current "small" buffer */
> > char *bigbuf; /* pointer to current "big" buffer */
> > diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index
> > 2eeaac6..19fdca8 100644
> > --- a/fs/cifs/connect.c
> > +++ b/fs/cifs/connect.c
> > @@ -94,7 +94,7 @@ enum {
> > Opt_multiuser, Opt_sloppy, Opt_nosharesock,
> > Opt_persistent, Opt_nopersistent,
> > Opt_resilient, Opt_noresilient,
> > - Opt_domainauto,
> > + Opt_domainauto, Opt_rdma,
> >
> > /* Mount options which take numeric value */
> > Opt_backupuid, Opt_backupgid, Opt_uid, @@ -185,6 +185,7 @@
> > static const match_table_t cifs_mount_option_tokens = {
> > { Opt_resilient, "resilienthandles"},
> > { Opt_noresilient, "noresilienthandles"},
> > { Opt_domainauto, "domainauto"},
> > + { Opt_rdma, "rdma"},
> >
> > { Opt_backupuid, "backupuid=%s" },
> > { Opt_backupgid, "backupgid=%s" }, @@ -1541,6 +1542,9 @@
> > cifs_parse_mount_options(const char *mountdata, const char *devname,
> > case Opt_domainauto:
> > vol->domainauto = true;
> > break;
> > + case Opt_rdma:
> > + vol->rdma = true;
> > + break;
> >
> > /* Numeric Values */
> > case Opt_backupuid:
> > @@ -1931,6 +1935,11 @@ cifs_parse_mount_options(const char
> *mountdata, const char *devname,
> > goto cifs_parse_mount_err;
> > }
> >
> > + if (vol->rdma && vol->vals->protocol_id < SMB30_PROT_ID) {
> > + cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
> > + goto cifs_parse_mount_err;
> > + }
> > +
> > #ifndef CONFIG_KEYS
> > /* Muliuser mounts require CONFIG_KEYS support */
> > if (vol->multiuser) {
> > @@ -2134,6 +2143,9 @@ static int match_server(struct TCP_Server_Info
> *server, struct smb_vol *vol)
> > if (server->echo_interval != vol->echo_interval * HZ)
> > return 0;
> >
> > + if (server->rdma != vol->rdma)
> > + return 0;
> > +
> > return 1;
> > }
> >
> > @@ -2234,6 +2246,7 @@ cifs_get_tcp_session(struct smb_vol
> *volume_info)
> > tcp_ses->noblocksnd = volume_info->noblocksnd;
> > tcp_ses->noautotune = volume_info->noautotune;
> > tcp_ses->tcp_nodelay = volume_info->sockopt_tcp_nodelay;
> > + tcp_ses->rdma = volume_info->rdma;
> > tcp_ses->in_flight = 0;
> > tcp_ses->credits = 1;
> > init_waitqueue_head(&tcp_ses->response_q);
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C4e70338e15204a407fd908d4ef2e855c%7C72f988bf86f141af91ab2d7cd011d
> b47%
> >
> 7C1%7C0%7C636396430465385563&sdata=FX0HbkzueGC4ene2wItN6iCiIRqZk
> 71OzY7
> > d%2FXX6rPM%3D&reserved=0
>
> It is better to introduce a mount option after the functional changes not
> before them. In this case we do not result in having the mount option that
> does nothing if we break the patchset.
I can move this patch to later.
However it doesn’t break the build, just does nothing at all.
>
> --
> Best regards,
> Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 3:45 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
> transport constants
>
> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > To prepare for protocol implementation, add constants and
> > user-configurable values in the SMBDirect protocol.
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/smbdirect.c | 78
> > +++++++++++++++++++++++++++++++++++++++++++++++++++++
> > fs/cifs/smbdirect.h | 20 ++++++++++++++
> > 2 files changed, 98 insertions(+)
> > create mode 100644 fs/cifs/smbdirect.c create mode 100644
> > fs/cifs/smbdirect.h
> >
> > diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c new file mode
> > 100644 index 0000000..d785bc1
> > --- /dev/null
> > +++ b/fs/cifs/smbdirect.c
> > @@ -0,0 +1,78 @@
> > +/*
> > + * Copyright (C) 2017, Microsoft Corporation.
> > + *
> > + * Author(s): Long Li <[email protected]>
> > + *
> > + * This program is free software; you can redistribute it and/or modify
> > + * it under the terms of the GNU General Public License as published by
> > + * the Free Software Foundation; either version 2 of the License, or
> > + * (at your option) any later version.
> > + *
> > + * This program is distributed in the hope that it will be useful,
> > + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
> > + * the GNU General Public License for more details.
> > + */
> > +#include <linux/module.h>
> > +#include "smbdirect.h"
> > +#include "cifs_debug.h"
> > +
> > +/* SMBD version number */
> > +#define SMBD_V1 0x0100
> > +
> > +/* Port numbers for SMBD transport */
> > +#define SMB_PORT 445
> > +#define SMBD_PORT 5445
> > +
> > +/* Address lookup and resolve timeout in ms */
> > +#define RDMA_RESOLVE_TIMEOUT 5000
> > +
> > +/* SMBD negotiation timeout in seconds */ #define
> > +SMBD_NEGOTIATE_TIMEOUT 120
> > +
> > +/* SMBD minimum receive size and fragmented sized defined in [MS-
> SMBD] */
> > +#define SMBD_MIN_RECEIVE_SIZE 128
> > +#define SMBD_MIN_FRAGMENTED_SIZE 131072
> > +
> > +/*
> > + * Default maximum number of RDMA read/write outstanding on this
> > +connection
> > + * This value is possibly decreased during QP creation on hardware
> > +limit */
> > +#define SMBD_CM_RESPONDER_RESOURCES 32
> > +
> > +/* Maximum number of retries on data transfer operations */
> > +#define SMBD_CM_RETRY 6
> > +/* No need to retry on Receiver Not Ready since SMBD manages credits
> */
> > +#define SMBD_CM_RNR_RETRY 0
> > +
> > +/*
> > + * User configurable initial values per SMBD transport connection
> > + * as defined in [MS-SMBD] 3.1.1.1
> > + * Those may change after a SMBD negotiation */
>
> Since these value are per transport connection, why they are global?
> Shouldn't they be inside a some structure that is created for a particular
> connection? Also the constants below should be defines.
Those are configurable initial values (default values) for all connections.
Each connection has its own values based on those initial values. But connection-based values can change after negotiation is done, or after RDMA hardware capabilities are probed.
>
> > +/* The local peer's maximum number of credits to grant to the peer */
> > +static int receive_credit_max = 255;
> > +/* The remote peer's credit request of local peer */ static int
> > +send_credit_target = 255;
> > +/* The maximum single message size can be sent to remote peer */
> > +static int max_send_size = 1364;
> > +/* The maximum fragmented upper-layer payload receive size supported
> > +*/ static int max_fragmented_recv_size = 1024 * 1024;
> > +/* The maximum single-message size which can be received */ static
> > +int max_receive_size = 8192;
> > +
> > +/* The timeout to initiate send of a keepalive message on idle */
> > +static int keep_alive_interval = 120;
> > +
> > +/*
> > + * User configurable initial values for RDMA transport
> > + * The actual values used may be lower and are limited to hardware
> > +capabilities */
> > +/* Default maximum number of SGEs in a RDMA send/recv */ static int
> > +max_send_sge = SMBDIRECT_MAX_SGE; static int max_recv_sge =
> > +SMBDIRECT_MAX_SGE;
> > +/* Default maximum number of SGEs in a RDMA write/read */ static int
> > +max_frmr_depth = 2048;
> > +
> > +/* If payload is less than this byte, use RDMA send/recv not
> > +read/write */ static int rdma_readwrite_threshold = 4096;
> > diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h new file mode
> > 100644 index 0000000..06eeb0b
> > --- /dev/null
> > +++ b/fs/cifs/smbdirect.h
> > @@ -0,0 +1,20 @@
> > +/*
> > + * Copyright (C) 2017, Microsoft Corporation.
> > + *
> > + * Author(s): Long Li <[email protected]>
> > + *
> > + * This program is free software; you can redistribute it and/or modify
> > + * it under the terms of the GNU General Public License as published by
> > + * the Free Software Foundation; either version 2 of the License, or
> > + * (at your option) any later version.
> > + *
> > + * This program is distributed in the hope that it will be useful,
> > + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
> > + * the GNU General Public License for more details.
> > + */
> > +#ifndef _SMBDIRECT_H
> > +#define _SMBDIRECT_H
> > +
> > +#define SMBDIRECT_MAX_SGE 16
> > +#endif
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C048aaa90c05748ee36a808d4ef2f9564%7C72f988bf86f141af91ab2d7cd011d
> b47%
> >
> 7C1%7C0%7C636396435035660594&sdata=qdY4CwjZ74W7AdqTVklpo8XlWFI6
> fxZ9y3i
> > fPyPQ%2Fcg%3D&reserved=0
>
>
>
> --
> Best regards,
> Pavel Shilovsky
2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> Add SMBDirect as an optional connection to the SMB session structure in CIFS.
> When SMB session is connected through SMBDirect, upper layer uses this
> connection to carry payloads.
>
> With the transport code hooked up to upper layer, add SMBDirect code to
> Makefile.
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/Makefile | 2 +-
> fs/cifs/cifsglob.h | 2 ++
> 2 files changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
> index eed7eb0..6bb9863 100644
> --- a/fs/cifs/Makefile
> +++ b/fs/cifs/Makefile
> @@ -18,4 +18,4 @@ cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o
> cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o
>
> cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o smb2maperror.o smb2transport.o \
> - smb2misc.o smb2pdu.o smb2inode.o smb2file.o
> + smb2misc.o smb2pdu.o smb2inode.o smb2file.o smbdirect.o
> diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
> index 703c2fb..dc5404d 100644
> --- a/fs/cifs/cifsglob.h
> +++ b/fs/cifs/cifsglob.h
> @@ -652,6 +652,8 @@ struct TCP_Server_Info {
> bool large_buf; /* is current buffer large? */
> /* use SMBD connection instead of socket */
> bool rdma;
> + /* point to the SMBD connection if RDMA is used instead of socket */
> + struct smbd_connection *smbd_conn;
> struct delayed_work echo; /* echo ping workqueue job */
> char *smallbuf; /* pointer to current "small" buffer */
> char *bigbuf; /* pointer to current "big" buffer */
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
It is better to split the current patch into 2 and merge the Makefile
part to #3 and cifsglob.h part to #5.
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 4:12 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 04/19] CIFS: SMBD: Add SMBDirect transport to SMB
> connection and Makefile
>
> 2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > Add SMBDirect as an optional connection to the SMB session structure in
> CIFS.
> > When SMB session is connected through SMBDirect, upper layer uses this
> > connection to carry payloads.
> >
> > With the transport code hooked up to upper layer, add SMBDirect code
> > to Makefile.
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/Makefile | 2 +-
> > fs/cifs/cifsglob.h | 2 ++
> > 2 files changed, 3 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index
> > eed7eb0..6bb9863 100644
> > --- a/fs/cifs/Makefile
> > +++ b/fs/cifs/Makefile
> > @@ -18,4 +18,4 @@ cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o
> > cifs_dfs_ref.o
> > cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o
> >
> > cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o smb2maperror.o
> smb2transport.o \
> > - smb2misc.o smb2pdu.o smb2inode.o smb2file.o
> > + smb2misc.o smb2pdu.o smb2inode.o
> > + smb2file.o smbdirect.o
> > diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index
> > 703c2fb..dc5404d 100644
> > --- a/fs/cifs/cifsglob.h
> > +++ b/fs/cifs/cifsglob.h
> > @@ -652,6 +652,8 @@ struct TCP_Server_Info {
> > bool large_buf; /* is current buffer large? */
> > /* use SMBD connection instead of socket */
> > bool rdma;
> > + /* point to the SMBD connection if RDMA is used instead of socket */
> > + struct smbd_connection *smbd_conn;
> > struct delayed_work echo; /* echo ping workqueue job */
> > char *smallbuf; /* pointer to current "small" buffer */
> > char *bigbuf; /* pointer to current "big" buffer */
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C74a459a67c6440f88d4308d4ef3358c5%7C72f988bf86f141af91ab2d7cd011db
> 47%
> >
> 7C1%7C0%7C636396451192818334&sdata=nIFmV5wvnL1xMm6tCnfdAgLMt%
> 2BFKJU6oh
> > hNhEXO8ZJs%3D&reserved=0
>
> It is better to split the current patch into 2 and merge the Makefile part to #3
> and cifsglob.h part to #5.
Sure, will make the change.
>
> --
> Best regards,
> Pavel Shilovsky
2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> Do a reconnect on SMBDirect when it is used as the connection. Reconnect can
> happen for many reasons and it's mostly the decision of upper layer SMB2 not
> SMBDirect.
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/connect.c | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
> index 43b4d54..341a3fd 100644
> --- a/fs/cifs/connect.c
> +++ b/fs/cifs/connect.c
> @@ -409,7 +409,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
>
> /* we should try only the port we connected to before */
> mutex_lock(&server->srv_mutex);
> - rc = generic_ip_connect(server);
> + if (server->rdma)
> + rc = smbd_reconnect(server);
> + else
> + rc = generic_ip_connect(server);
> +
> if (rc) {
> cifs_dbg(FYI, "reconnect error %d\n", rc);
> mutex_unlock(&server->srv_mutex);
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
It is a easier to follow the logic if the definition is introduced
together with using of this function in the existing code. I suggest
to add smbd_reconnect() definition in this patch.
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 4:15 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 06/19] CIFS: SMBD: Reconnect to SMBDirect session
>
> 2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > Do a reconnect on SMBDirect when it is used as the connection.
> > Reconnect can happen for many reasons and it's mostly the decision of
> > upper layer SMB2 not SMBDirect.
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/connect.c | 6 +++++-
> > 1 file changed, 5 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index
> > 43b4d54..341a3fd 100644
> > --- a/fs/cifs/connect.c
> > +++ b/fs/cifs/connect.c
> > @@ -409,7 +409,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
> >
> > /* we should try only the port we connected to before */
> > mutex_lock(&server->srv_mutex);
> > - rc = generic_ip_connect(server);
> > + if (server->rdma)
> > + rc = smbd_reconnect(server);
> > + else
> > + rc = generic_ip_connect(server);
> > +
> > if (rc) {
> > cifs_dbg(FYI, "reconnect error %d\n", rc);
> > mutex_unlock(&server->srv_mutex);
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C192678645752449a875b08d4ef33d874%7C72f988bf86f141af91ab2d7cd011d
> b47%
> >
> 7C1%7C0%7C636396453334398562&sdata=i5dZUoUU91foFGipTsgQBnmYJeU
> aeWww2QI
> > xoP9BSO4%3D&reserved=0
>
> It is a easier to follow the logic if the definition is introduced together with
> using of this function in the existing code. I suggest to add smbd_reconnect()
> definition in this patch.
I will do this in v4.
> --
> Best regards,
> Pavel Shilovsky
2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> To prepare for RDMA read/write using memory registration, add memory
> registartion pointers to upper layer data I/O context.
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/cifsglob.h | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
> index dc5404d..dcd2b63 100644
> --- a/fs/cifs/cifsglob.h
> +++ b/fs/cifs/cifsglob.h
> @@ -1166,6 +1166,7 @@ struct cifs_readdata {
> struct cifs_readdata *rdata,
> struct iov_iter *iter);
> struct kvec iov[2];
> + struct smbd_mr *mr;
> unsigned int pagesz;
> unsigned int tailsz;
> unsigned int credits;
> @@ -1188,6 +1189,7 @@ struct cifs_writedata {
> pid_t pid;
> unsigned int bytes;
> int result;
> + struct smbd_mr *mr;
> unsigned int pagesz;
> unsigned int tailsz;
> unsigned int credits;
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
The same thing: let's not add structure fields that the code doesn't
do anything with.
--
Best regards,
Pavel Shilovsky
2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> From: Long Li <[email protected]>
>
> The channel value for requesting server remote invalidating local memory
> registration should be 0x00000002
>
> Signed-off-by: Long Li <[email protected]>
> ---
> fs/cifs/smb2pdu.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
> index 18700fd..0417a36 100644
> --- a/fs/cifs/smb2pdu.h
> +++ b/fs/cifs/smb2pdu.h
> @@ -832,7 +832,7 @@ struct smb2_flush_rsp {
> /* Channel field for read and write: exactly one of following flags can be set*/
> #define SMB2_CHANNEL_NONE 0x00000000
> #define SMB2_CHANNEL_RDMA_V1 0x00000001 /* SMB3 or later */
> -#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */
> +#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000002 /* SMB3.02 or later */
>
> /* SMB2 read request without RFC1001 length at the beginning */
> struct smb2_read_plain_req {
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-cifs" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
If this is a bug in the existing code, this patch should go at the
very beginning of the series.
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 5:50 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 12/19] CIFS: SMBD: Fix the definition for
> SMB2_CHANNEL_RDMA_V1_INVALIDATE
>
> 2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > The channel value for requesting server remote invalidating local
> > memory registration should be 0x00000002
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/smb2pdu.h | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index
> > 18700fd..0417a36 100644
> > --- a/fs/cifs/smb2pdu.h
> > +++ b/fs/cifs/smb2pdu.h
> > @@ -832,7 +832,7 @@ struct smb2_flush_rsp {
> > /* Channel field for read and write: exactly one of following flags can be
> set*/
> > #define SMB2_CHANNEL_NONE 0x00000000
> > #define SMB2_CHANNEL_RDMA_V1 0x00000001 /* SMB3 or later */
> > -#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02
> or
> > later */
> > +#define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000002 /*
> SMB3.02 or
> > +later */
> >
> > /* SMB2 read request without RFC1001 length at the beginning */
> > struct smb2_read_plain_req {
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C9a11066a2c3b402da09f08d4ef411927%7C72f988bf86f141af91ab2d7cd011d
> b47%
> >
> 7C1%7C0%7C636396510253376659&sdata=0fLwHcdbOLSOsbKj5PZ2yrJap%2B
> N0ZB%2B
> > TGbFimPMqcx4%3D&reserved=0
>
> If this is a bug in the existing code, this patch should go at the very beginning
> of the series.
Okay, I will reorder the patch.
>
> --
> Best regards,
> Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 5:49 PM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>;
> Long Li <[email protected]>
> Subject: Re: [Patch v3 11/19] CIFS: SMBD: Define memory registration for I/O
> data
>
> 2017-08-29 12:29 GMT-07:00 Long Li <[email protected]>:
> > From: Long Li <[email protected]>
> >
> > To prepare for RDMA read/write using memory registration, add memory
> > registartion pointers to upper layer data I/O context.
> >
> > Signed-off-by: Long Li <[email protected]>
> > ---
> > fs/cifs/cifsglob.h | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index
> > dc5404d..dcd2b63 100644
> > --- a/fs/cifs/cifsglob.h
> > +++ b/fs/cifs/cifsglob.h
> > @@ -1166,6 +1166,7 @@ struct cifs_readdata {
> > struct cifs_readdata *rdata,
> > struct iov_iter *iter);
> > struct kvec iov[2];
> > + struct smbd_mr *mr;
> > unsigned int pagesz;
> > unsigned int tailsz;
> > unsigned int credits;
> > @@ -1188,6 +1189,7 @@ struct cifs_writedata {
> > pid_t pid;
> > unsigned int bytes;
> > int result;
> > + struct smbd_mr *mr;
> > unsigned int pagesz;
> > unsigned int tailsz;
> > unsigned int credits;
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-cifs"
> > in the body of a message to [email protected] More
> majordomo
> > info at
> >
> https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fvger.k
> > ernel.org%2Fmajordomo-
> info.html&data=02%7C01%7Clongli%40microsoft.com%
> >
> 7C1a02c615906e4648835c08d4ef40e655%7C72f988bf86f141af91ab2d7cd011d
> b47%
> >
> 7C1%7C0%7C636396509394018449&sdata=yjvt3xPYPMmBp8nRiAC%2FYUOOs
> ganvPd%2
> > Ff6Y1uZtbqGU%3D&reserved=0
>
> The same thing: let's not add structure fields that the code doesn't do
> anything with.
Okay. I will fold the patch into relevant patches.
>
> --
> Best regards,
> Pavel Shilovsky
2017-08-29 16:00 GMT-07:00 Long Li <[email protected]>:
>> -----Original Message-----
>> From: Pavel Shilovsky [mailto:[email protected]]
>> Sent: Tuesday, August 29, 2017 3:45 PM
>> To: Long Li <[email protected]>
>> Cc: Steve French <[email protected]>; linux-cifs <linux-
>> [email protected]>; samba-technical <[email protected]>;
>> Kernel Mailing List <[email protected]>; linux-
>> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
>> <[email protected]>; Matthew Wilcox <[email protected]>;
>> Long Li <[email protected]>
>> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
>> transport constants
>>
>> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
>> > From: Long Li <[email protected]>
>> >
>> > To prepare for protocol implementation, add constants and
>> > user-configurable values in the SMBDirect protocol.
>> >
>> > Signed-off-by: Long Li <[email protected]>
>> > ---
>> > fs/cifs/smbdirect.c | 78
>> > +++++++++++++++++++++++++++++++++++++++++++++++++++++
>> > fs/cifs/smbdirect.h | 20 ++++++++++++++
>> > 2 files changed, 98 insertions(+)
>> > create mode 100644 fs/cifs/smbdirect.c create mode 100644
>> > fs/cifs/smbdirect.h
>> >
>> > diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c new file mode
>> > 100644 index 0000000..d785bc1
>> > --- /dev/null
>> > +++ b/fs/cifs/smbdirect.c
>> > @@ -0,0 +1,78 @@
>> > +/*
>> > + * Copyright (C) 2017, Microsoft Corporation.
>> > + *
>> > + * Author(s): Long Li <[email protected]>
>> > + *
>> > + * This program is free software; you can redistribute it and/or modify
>> > + * it under the terms of the GNU General Public License as published by
>> > + * the Free Software Foundation; either version 2 of the License, or
>> > + * (at your option) any later version.
>> > + *
>> > + * This program is distributed in the hope that it will be useful,
>> > + * but WITHOUT ANY WARRANTY; without even the implied warranty of
>> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
>> > + * the GNU General Public License for more details.
>> > + */
>> > +#include <linux/module.h>
>> > +#include "smbdirect.h"
>> > +#include "cifs_debug.h"
>> > +
>> > +/* SMBD version number */
>> > +#define SMBD_V1 0x0100
>> > +
>> > +/* Port numbers for SMBD transport */
>> > +#define SMB_PORT 445
>> > +#define SMBD_PORT 5445
>> > +
>> > +/* Address lookup and resolve timeout in ms */
>> > +#define RDMA_RESOLVE_TIMEOUT 5000
>> > +
>> > +/* SMBD negotiation timeout in seconds */ #define
>> > +SMBD_NEGOTIATE_TIMEOUT 120
>> > +
>> > +/* SMBD minimum receive size and fragmented sized defined in [MS-
>> SMBD] */
>> > +#define SMBD_MIN_RECEIVE_SIZE 128
>> > +#define SMBD_MIN_FRAGMENTED_SIZE 131072
>> > +
>> > +/*
>> > + * Default maximum number of RDMA read/write outstanding on this
>> > +connection
>> > + * This value is possibly decreased during QP creation on hardware
>> > +limit */
>> > +#define SMBD_CM_RESPONDER_RESOURCES 32
>> > +
>> > +/* Maximum number of retries on data transfer operations */
>> > +#define SMBD_CM_RETRY 6
>> > +/* No need to retry on Receiver Not Ready since SMBD manages credits
>> */
>> > +#define SMBD_CM_RNR_RETRY 0
>> > +
>> > +/*
>> > + * User configurable initial values per SMBD transport connection
>> > + * as defined in [MS-SMBD] 3.1.1.1
>> > + * Those may change after a SMBD negotiation */
>>
>> Since these value are per transport connection, why they are global?
>> Shouldn't they be inside a some structure that is created for a particular
>> connection? Also the constants below should be defines.
>
> Those are configurable initial values (default values) for all connections.
>
> Each connection has its own values based on those initial values. But connection-based values can change after negotiation is done, or after RDMA hardware capabilities are probed.
If these are configurable values, let's add a way to actually
configure them. Through /proc?
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Pavel Shilovsky [mailto:[email protected]]
> Sent: Wednesday, August 30, 2017 11:19 AM
> To: Long Li <[email protected]>
> Cc: Steve French <[email protected]>; linux-cifs <linux-
> [email protected]>; samba-technical <[email protected]>;
> Kernel Mailing List <[email protected]>; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>
> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
> transport constants
>
> 2017-08-29 16:00 GMT-07:00 Long Li <[email protected]>:
> >> -----Original Message-----
> >> From: Pavel Shilovsky [mailto:[email protected]]
> >> Sent: Tuesday, August 29, 2017 3:45 PM
> >> To: Long Li <[email protected]>
> >> Cc: Steve French <[email protected]>; linux-cifs <linux-
> >> [email protected]>; samba-technical
> >> <[email protected]>;
> >> Kernel Mailing List <[email protected]>; linux-
> >> [email protected]; Christoph Hellwig <[email protected]>; Tom
> >> Talpey <[email protected]>; Matthew Wilcox
> >> <[email protected]>; Long Li <[email protected]>
> >> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
> >> transport constants
> >>
> >> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
> >> > From: Long Li <[email protected]>
> >> >
> >> > To prepare for protocol implementation, add constants and
> >> > user-configurable values in the SMBDirect protocol.
> >> >
> >> > Signed-off-by: Long Li <[email protected]>
> >> > ---
> >> > fs/cifs/smbdirect.c | 78
> >> > +++++++++++++++++++++++++++++++++++++++++++++++++++++
> >> > fs/cifs/smbdirect.h | 20 ++++++++++++++
> >> > 2 files changed, 98 insertions(+)
> >> > create mode 100644 fs/cifs/smbdirect.c create mode 100644
> >> > fs/cifs/smbdirect.h
> >> >
> >> > diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c new file
> >> > mode
> >> > 100644 index 0000000..d785bc1
> >> > --- /dev/null
> >> > +++ b/fs/cifs/smbdirect.c
> >> > @@ -0,0 +1,78 @@
> >> > +/*
> >> > + * Copyright (C) 2017, Microsoft Corporation.
> >> > + *
> >> > + * Author(s): Long Li <[email protected]>
> >> > + *
> >> > + * This program is free software; you can redistribute it and/or modify
> >> > + * it under the terms of the GNU General Public License as published
> by
> >> > + * the Free Software Foundation; either version 2 of the License, or
> >> > + * (at your option) any later version.
> >> > + *
> >> > + * This program is distributed in the hope that it will be useful,
> >> > + * but WITHOUT ANY WARRANTY; without even the implied warranty
> of
> >> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
> >> > + * the GNU General Public License for more details.
> >> > + */
> >> > +#include <linux/module.h>
> >> > +#include "smbdirect.h"
> >> > +#include "cifs_debug.h"
> >> > +
> >> > +/* SMBD version number */
> >> > +#define SMBD_V1 0x0100
> >> > +
> >> > +/* Port numbers for SMBD transport */
> >> > +#define SMB_PORT 445
> >> > +#define SMBD_PORT 5445
> >> > +
> >> > +/* Address lookup and resolve timeout in ms */
> >> > +#define RDMA_RESOLVE_TIMEOUT 5000
> >> > +
> >> > +/* SMBD negotiation timeout in seconds */ #define
> >> > +SMBD_NEGOTIATE_TIMEOUT 120
> >> > +
> >> > +/* SMBD minimum receive size and fragmented sized defined in [MS-
> >> SMBD] */
> >> > +#define SMBD_MIN_RECEIVE_SIZE 128
> >> > +#define SMBD_MIN_FRAGMENTED_SIZE 131072
> >> > +
> >> > +/*
> >> > + * Default maximum number of RDMA read/write outstanding on this
> >> > +connection
> >> > + * This value is possibly decreased during QP creation on hardware
> >> > +limit */
> >> > +#define SMBD_CM_RESPONDER_RESOURCES 32
> >> > +
> >> > +/* Maximum number of retries on data transfer operations */
> >> > +#define SMBD_CM_RETRY 6
> >> > +/* No need to retry on Receiver Not Ready since SMBD manages
> >> > +credits
> >> */
> >> > +#define SMBD_CM_RNR_RETRY 0
> >> > +
> >> > +/*
> >> > + * User configurable initial values per SMBD transport connection
> >> > + * as defined in [MS-SMBD] 3.1.1.1
> >> > + * Those may change after a SMBD negotiation */
> >>
> >> Since these value are per transport connection, why they are global?
> >> Shouldn't they be inside a some structure that is created for a
> >> particular connection? Also the constants below should be defines.
> >
> > Those are configurable initial values (default values) for all connections.
> >
> > Each connection has its own values based on those initial values. But
> connection-based values can change after negotiation is done, or after
> RDMA hardware capabilities are probed.
>
> If these are configurable values, let's add a way to actually configure them.
> Through /proc?
You mean putting them in /proc/fs/cifs?
Or how about module_param?
>
> --
> Best regards,
> Pavel Shilovsky
2017-08-30 11:24 GMT-07:00 Long Li <[email protected]>:
>> -----Original Message-----
>> From: Pavel Shilovsky [mailto:[email protected]]
>> Sent: Wednesday, August 30, 2017 11:19 AM
>> To: Long Li <[email protected]>
>> Cc: Steve French <[email protected]>; linux-cifs <linux-
>> [email protected]>; samba-technical <[email protected]>;
>> Kernel Mailing List <[email protected]>; linux-
>> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
>> <[email protected]>; Matthew Wilcox <[email protected]>
>> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
>> transport constants
>>
>> 2017-08-29 16:00 GMT-07:00 Long Li <[email protected]>:
>> >> -----Original Message-----
>> >> From: Pavel Shilovsky [mailto:[email protected]]
>> >> Sent: Tuesday, August 29, 2017 3:45 PM
>> >> To: Long Li <[email protected]>
>> >> Cc: Steve French <[email protected]>; linux-cifs <linux-
>> >> [email protected]>; samba-technical
>> >> <[email protected]>;
>> >> Kernel Mailing List <[email protected]>; linux-
>> >> [email protected]; Christoph Hellwig <[email protected]>; Tom
>> >> Talpey <[email protected]>; Matthew Wilcox
>> >> <[email protected]>; Long Li <[email protected]>
>> >> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
>> >> transport constants
>> >>
>> >> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
>> >> > From: Long Li <[email protected]>
>> >> >
>> >> > To prepare for protocol implementation, add constants and
>> >> > user-configurable values in the SMBDirect protocol.
>> >> >
>> >> > Signed-off-by: Long Li <[email protected]>
>> >> > ---
>> >> > fs/cifs/smbdirect.c | 78
>> >> > +++++++++++++++++++++++++++++++++++++++++++++++++++++
>> >> > fs/cifs/smbdirect.h | 20 ++++++++++++++
>> >> > 2 files changed, 98 insertions(+)
>> >> > create mode 100644 fs/cifs/smbdirect.c create mode 100644
>> >> > fs/cifs/smbdirect.h
>> >> >
>> >> > diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c new file
>> >> > mode
>> >> > 100644 index 0000000..d785bc1
>> >> > --- /dev/null
>> >> > +++ b/fs/cifs/smbdirect.c
>> >> > @@ -0,0 +1,78 @@
>> >> > +/*
>> >> > + * Copyright (C) 2017, Microsoft Corporation.
>> >> > + *
>> >> > + * Author(s): Long Li <[email protected]>
>> >> > + *
>> >> > + * This program is free software; you can redistribute it and/or modify
>> >> > + * it under the terms of the GNU General Public License as published
>> by
>> >> > + * the Free Software Foundation; either version 2 of the License, or
>> >> > + * (at your option) any later version.
>> >> > + *
>> >> > + * This program is distributed in the hope that it will be useful,
>> >> > + * but WITHOUT ANY WARRANTY; without even the implied warranty
>> of
>> >> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
>> >> > + * the GNU General Public License for more details.
>> >> > + */
>> >> > +#include <linux/module.h>
>> >> > +#include "smbdirect.h"
>> >> > +#include "cifs_debug.h"
>> >> > +
>> >> > +/* SMBD version number */
>> >> > +#define SMBD_V1 0x0100
>> >> > +
>> >> > +/* Port numbers for SMBD transport */
>> >> > +#define SMB_PORT 445
>> >> > +#define SMBD_PORT 5445
>> >> > +
>> >> > +/* Address lookup and resolve timeout in ms */
>> >> > +#define RDMA_RESOLVE_TIMEOUT 5000
>> >> > +
>> >> > +/* SMBD negotiation timeout in seconds */ #define
>> >> > +SMBD_NEGOTIATE_TIMEOUT 120
>> >> > +
>> >> > +/* SMBD minimum receive size and fragmented sized defined in [MS-
>> >> SMBD] */
>> >> > +#define SMBD_MIN_RECEIVE_SIZE 128
>> >> > +#define SMBD_MIN_FRAGMENTED_SIZE 131072
>> >> > +
>> >> > +/*
>> >> > + * Default maximum number of RDMA read/write outstanding on this
>> >> > +connection
>> >> > + * This value is possibly decreased during QP creation on hardware
>> >> > +limit */
>> >> > +#define SMBD_CM_RESPONDER_RESOURCES 32
>> >> > +
>> >> > +/* Maximum number of retries on data transfer operations */
>> >> > +#define SMBD_CM_RETRY 6
>> >> > +/* No need to retry on Receiver Not Ready since SMBD manages
>> >> > +credits
>> >> */
>> >> > +#define SMBD_CM_RNR_RETRY 0
>> >> > +
>> >> > +/*
>> >> > + * User configurable initial values per SMBD transport connection
>> >> > + * as defined in [MS-SMBD] 3.1.1.1
>> >> > + * Those may change after a SMBD negotiation */
>> >>
>> >> Since these value are per transport connection, why they are global?
>> >> Shouldn't they be inside a some structure that is created for a
>> >> particular connection? Also the constants below should be defines.
>> >
>> > Those are configurable initial values (default values) for all connections.
>> >
>> > Each connection has its own values based on those initial values. But
>> connection-based values can change after negotiation is done, or after
>> RDMA hardware capabilities are probed.
>>
>> If these are configurable values, let's add a way to actually configure them.
>> Through /proc?
>
> You mean putting them in /proc/fs/cifs?
>
> Or how about module_param?
I am ok with either way. If it is safe to change them without
reloading the module let's do /proc/fs/cifs which would make it easier
to use. Otherwise - module_param is also good.
--
Best regards,
Pavel Shilovsky
> -----Original Message-----
> From: Long Li [mailto:[email protected]]
> Sent: Tuesday, August 29, 2017 12:29 PM
> To: Steve French <[email protected]>; [email protected]; samba-
> [email protected]; [email protected]; linux-
> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
> <[email protected]>; Matthew Wilcox <[email protected]>
> Cc: Long Li <[email protected]>
> Subject: [Patch v3 00/19] CIFS: Implement SMB Direct
>
> From: Long Li <[email protected]>
>
> Starting with SMB2 dialect 3.0, Microsoft introduced SMBDirect transport
> protocol for transferring upper layer (SMB2) payload over RDMA via
> Infiniband, RoCE or iWARP. The prococol is published in [MS-SMBD]
> (https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmsdn
> .microsoft.com%2Fen-
> us%2Flibrary%2Fhh536346.aspx&data=02%7C01%7Clongli%40microsoft.com
> %7C73e721d48ac0402f414208d4ef1470f2%7C72f988bf86f141af91ab2d7cd011
> db47%7C1%7C0%7C636396318489728526&sdata=3ES4XY3qXqUVEJ37YUHlMJ
> QWuxFeljzOEMhGXhmO2i0%3D&reserved=0).
>
> Patch v2 added RDMA read/write via memory registration, and addressed
> feedbacks on v1.
>
> Patch v3 improved performance by introducing an additional queue for
> handling empty packets and reducing lock contention on IRQ path. Also
> added light weight profiling by reading TSC and addressed feedbacks on v2.
I received some requests about testing the patch. Thank you for help testing.
A snapshot of the development kernel with the patch set is at:
https://github.com/longlimsft/linux-next/tree/patch_v3
During development, it is tested on Infiniband with Mellanox ConnectX-3.
>
> Long Li (19):
> CIFS: Add rdma mount option
> CIFS: SMBD: Add SMBDirect protocol and transport constants
> CIFS: SMBD: Implement SMBDirect transport
> CIFS: SMBD: Add SMBDirect transport to SMB connection and Makefile
> CIFS: SMBD: Connect to SMBDirect session
> CIFS: SMBD: Reconnect to SMBDirect session
> CIFS: SMBD: Destroy SMBDirect session on shutdown or umount
> CIFS: SMBD: Set SMBDirect maximum read or write size for I/O
> CIFS: SMBD: Receive data from SMBDirect
> CIFS: SMBD: Send data through SMBDirect
> CIFS: SMBD: Define memory registration for I/O data
> CIFS: SMBD: Fix the definition for SMB2_CHANNEL_RDMA_V1_INVALIDATE
> CIFS: SMBD: Implement SMB write via RDMA read through memory
> registration
> CIFS: SMBD: Deregister memory on finishing SMB write
> CIFS: SMBD: Add parameter rdata to smb2_new_read_req
> CIFS: SMBD: Read correct returned data length for RDMA write (SMB
> read) I/O
> CIFS: SMBD: Implement SMB read via RDMA write through memory
> registration
> CIFS: SMBD: Deregister memory when finishing SMB read
> CIFS: SMBD: Add SMBDirect debug counters
>
> fs/cifs/Makefile | 2 +-
> fs/cifs/cifs_debug.c | 84 ++
> fs/cifs/cifsfs.c | 2 +
> fs/cifs/cifsglob.h | 17 +-
> fs/cifs/cifssmb.c | 10 +-
> fs/cifs/connect.c | 46 +-
> fs/cifs/file.c | 10 +
> fs/cifs/smb1ops.c | 2 +-
> fs/cifs/smb2ops.c | 21 +-
> fs/cifs/smb2pdu.c | 114 ++-
> fs/cifs/smb2pdu.h | 2 +-
> fs/cifs/smbdirect.c | 2639
> ++++++++++++++++++++++++++++++++++++++++++++++++++
> fs/cifs/smbdirect.h | 324 +++++++
> fs/cifs/transport.c | 7 +
> 14 files changed, 3260 insertions(+), 20 deletions(-) create mode 100644
> fs/cifs/smbdirect.c create mode 100644 fs/cifs/smbdirect.h
>
> --
> 2.7.4
Probably easier to configure in /proc/fs/cifs than as module param
On Wed, Aug 30, 2017 at 1:30 PM, Pavel Shilovsky via samba-technical
<[email protected]> wrote:
> 2017-08-30 11:24 GMT-07:00 Long Li <[email protected]>:
>>> -----Original Message-----
>>> From: Pavel Shilovsky [mailto:[email protected]]
>>> Sent: Wednesday, August 30, 2017 11:19 AM
>>> To: Long Li <[email protected]>
>>> Cc: Steve French <[email protected]>; linux-cifs <linux-
>>> [email protected]>; samba-technical <[email protected]>;
>>> Kernel Mailing List <[email protected]>; linux-
>>> [email protected]; Christoph Hellwig <[email protected]>; Tom Talpey
>>> <[email protected]>; Matthew Wilcox <[email protected]>
>>> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
>>> transport constants
>>>
>>> 2017-08-29 16:00 GMT-07:00 Long Li <[email protected]>:
>>> >> -----Original Message-----
>>> >> From: Pavel Shilovsky [mailto:[email protected]]
>>> >> Sent: Tuesday, August 29, 2017 3:45 PM
>>> >> To: Long Li <[email protected]>
>>> >> Cc: Steve French <[email protected]>; linux-cifs <linux-
>>> >> [email protected]>; samba-technical
>>> >> <[email protected]>;
>>> >> Kernel Mailing List <[email protected]>; linux-
>>> >> [email protected]; Christoph Hellwig <[email protected]>; Tom
>>> >> Talpey <[email protected]>; Matthew Wilcox
>>> >> <[email protected]>; Long Li <[email protected]>
>>> >> Subject: Re: [Patch v3 02/19] CIFS: SMBD: Add SMBDirect protocol and
>>> >> transport constants
>>> >>
>>> >> 2017-08-29 12:28 GMT-07:00 Long Li <[email protected]>:
>>> >> > From: Long Li <[email protected]>
>>> >> >
>>> >> > To prepare for protocol implementation, add constants and
>>> >> > user-configurable values in the SMBDirect protocol.
>>> >> >
>>> >> > Signed-off-by: Long Li <[email protected]>
>>> >> > ---
>>> >> > fs/cifs/smbdirect.c | 78
>>> >> > +++++++++++++++++++++++++++++++++++++++++++++++++++++
>>> >> > fs/cifs/smbdirect.h | 20 ++++++++++++++
>>> >> > 2 files changed, 98 insertions(+)
>>> >> > create mode 100644 fs/cifs/smbdirect.c create mode 100644
>>> >> > fs/cifs/smbdirect.h
>>> >> >
>>> >> > diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c new file
>>> >> > mode
>>> >> > 100644 index 0000000..d785bc1
>>> >> > --- /dev/null
>>> >> > +++ b/fs/cifs/smbdirect.c
>>> >> > @@ -0,0 +1,78 @@
>>> >> > +/*
>>> >> > + * Copyright (C) 2017, Microsoft Corporation.
>>> >> > + *
>>> >> > + * Author(s): Long Li <[email protected]>
>>> >> > + *
>>> >> > + * This program is free software; you can redistribute it and/or modify
>>> >> > + * it under the terms of the GNU General Public License as published
>>> by
>>> >> > + * the Free Software Foundation; either version 2 of the License, or
>>> >> > + * (at your option) any later version.
>>> >> > + *
>>> >> > + * This program is distributed in the hope that it will be useful,
>>> >> > + * but WITHOUT ANY WARRANTY; without even the implied warranty
>>> of
>>> >> > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
>>> >> > + * the GNU General Public License for more details.
>>> >> > + */
>>> >> > +#include <linux/module.h>
>>> >> > +#include "smbdirect.h"
>>> >> > +#include "cifs_debug.h"
>>> >> > +
>>> >> > +/* SMBD version number */
>>> >> > +#define SMBD_V1 0x0100
>>> >> > +
>>> >> > +/* Port numbers for SMBD transport */
>>> >> > +#define SMB_PORT 445
>>> >> > +#define SMBD_PORT 5445
>>> >> > +
>>> >> > +/* Address lookup and resolve timeout in ms */
>>> >> > +#define RDMA_RESOLVE_TIMEOUT 5000
>>> >> > +
>>> >> > +/* SMBD negotiation timeout in seconds */ #define
>>> >> > +SMBD_NEGOTIATE_TIMEOUT 120
>>> >> > +
>>> >> > +/* SMBD minimum receive size and fragmented sized defined in [MS-
>>> >> SMBD] */
>>> >> > +#define SMBD_MIN_RECEIVE_SIZE 128
>>> >> > +#define SMBD_MIN_FRAGMENTED_SIZE 131072
>>> >> > +
>>> >> > +/*
>>> >> > + * Default maximum number of RDMA read/write outstanding on this
>>> >> > +connection
>>> >> > + * This value is possibly decreased during QP creation on hardware
>>> >> > +limit */
>>> >> > +#define SMBD_CM_RESPONDER_RESOURCES 32
>>> >> > +
>>> >> > +/* Maximum number of retries on data transfer operations */
>>> >> > +#define SMBD_CM_RETRY 6
>>> >> > +/* No need to retry on Receiver Not Ready since SMBD manages
>>> >> > +credits
>>> >> */
>>> >> > +#define SMBD_CM_RNR_RETRY 0
>>> >> > +
>>> >> > +/*
>>> >> > + * User configurable initial values per SMBD transport connection
>>> >> > + * as defined in [MS-SMBD] 3.1.1.1
>>> >> > + * Those may change after a SMBD negotiation */
>>> >>
>>> >> Since these value are per transport connection, why they are global?
>>> >> Shouldn't they be inside a some structure that is created for a
>>> >> particular connection? Also the constants below should be defines.
>>> >
>>> > Those are configurable initial values (default values) for all connections.
>>> >
>>> > Each connection has its own values based on those initial values. But
>>> connection-based values can change after negotiation is done, or after
>>> RDMA hardware capabilities are probed.
>>>
>>> If these are configurable values, let's add a way to actually configure them.
>>> Through /proc?
>>
>> You mean putting them in /proc/fs/cifs?
>>
>> Or how about module_param?
>
> I am ok with either way. If it is safe to change them without
> reloading the module let's do /proc/fs/cifs which would make it easier
> to use. Otherwise - module_param is also good.
>
> --
> Best regards,
> Pavel Shilovsky
>
--
Thanks,
Steve