Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
RDMA/hfi1: Remove opa_vnic
OPA Vnic has been abandoned and left to rot. Time to excise.
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://patch.msgid.link/177308912950.1280237.15051663328388849915.stgit@awdrv-04.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
authored by
Dennis Dalessandro
and committed by
Leon Romanovsky
1b50f420
2afa8b9f
+20
-4976
-15
Documentation/driver-api/infiniband.rst
-15
Documentation/driver-api/infiniband.rst
···
92
92
.. kernel-doc:: drivers/infiniband/ulp/iser/iser_verbs.c
93
93
:internal:
94
94
95
-
Omni-Path (OPA) Virtual NIC support
96
-
-----------------------------------
97
-
98
-
.. kernel-doc:: drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h
99
-
:internal:
100
-
101
-
.. kernel-doc:: drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
102
-
:internal:
103
-
104
-
.. kernel-doc:: drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c
105
-
:internal:
106
-
107
-
.. kernel-doc:: drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
108
-
:internal:
109
-
110
95
InfiniBand SCSI RDMA protocol target support
111
96
--------------------------------------------
112
97
-1
Documentation/infiniband/index.rst
-1
Documentation/infiniband/index.rst
-159
Documentation/infiniband/opa_vnic.rst
-159
Documentation/infiniband/opa_vnic.rst
···
1
-
=================================================================
2
-
Intel Omni-Path (OPA) Virtual Network Interface Controller (VNIC)
3
-
=================================================================
4
-
5
-
Intel Omni-Path (OPA) Virtual Network Interface Controller (VNIC) feature
6
-
supports Ethernet functionality over Omni-Path fabric by encapsulating
7
-
the Ethernet packets between HFI nodes.
8
-
9
-
Architecture
10
-
=============
11
-
The patterns of exchanges of Omni-Path encapsulated Ethernet packets
12
-
involves one or more virtual Ethernet switches overlaid on the Omni-Path
13
-
fabric topology. A subset of HFI nodes on the Omni-Path fabric are
14
-
permitted to exchange encapsulated Ethernet packets across a particular
15
-
virtual Ethernet switch. The virtual Ethernet switches are logical
16
-
abstractions achieved by configuring the HFI nodes on the fabric for
17
-
header generation and processing. In the simplest configuration all HFI
18
-
nodes across the fabric exchange encapsulated Ethernet packets over a
19
-
single virtual Ethernet switch. A virtual Ethernet switch, is effectively
20
-
an independent Ethernet network. The configuration is performed by an
21
-
Ethernet Manager (EM) which is part of the trusted Fabric Manager (FM)
22
-
application. HFI nodes can have multiple VNICs each connected to a
23
-
different virtual Ethernet switch. The below diagram presents a case
24
-
of two virtual Ethernet switches with two HFI nodes::
25
-
26
-
+-------------------+
27
-
| Subnet/ |
28
-
| Ethernet |
29
-
| Manager |
30
-
+-------------------+
31
-
/ /
32
-
/ /
33
-
/ /
34
-
/ /
35
-
+-----------------------------+ +------------------------------+
36
-
| Virtual Ethernet Switch | | Virtual Ethernet Switch |
37
-
| +---------+ +---------+ | | +---------+ +---------+ |
38
-
| | VPORT | | VPORT | | | | VPORT | | VPORT | |
39
-
+--+---------+----+---------+-+ +-+---------+----+---------+---+
40
-
| \ / |
41
-
| \ / |
42
-
| \/ |
43
-
| / \ |
44
-
| / \ |
45
-
+-----------+------------+ +-----------+------------+
46
-
| VNIC | VNIC | | VNIC | VNIC |
47
-
+-----------+------------+ +-----------+------------+
48
-
| HFI | | HFI |
49
-
+------------------------+ +------------------------+
50
-
51
-
52
-
The Omni-Path encapsulated Ethernet packet format is as described below.
53
-
54
-
==================== ================================
55
-
Bits Field
56
-
==================== ================================
57
-
Quad Word 0:
58
-
0-19 SLID (lower 20 bits)
59
-
20-30 Length (in Quad Words)
60
-
31 BECN bit
61
-
32-51 DLID (lower 20 bits)
62
-
52-56 SC (Service Class)
63
-
57-59 RC (Routing Control)
64
-
60 FECN bit
65
-
61-62 L2 (=10, 16B format)
66
-
63 LT (=1, Link Transfer Head Flit)
67
-
68
-
Quad Word 1:
69
-
0-7 L4 type (=0x78 ETHERNET)
70
-
8-11 SLID[23:20]
71
-
12-15 DLID[23:20]
72
-
16-31 PKEY
73
-
32-47 Entropy
74
-
48-63 Reserved
75
-
76
-
Quad Word 2:
77
-
0-15 Reserved
78
-
16-31 L4 header
79
-
32-63 Ethernet Packet
80
-
81
-
Quad Words 3 to N-1:
82
-
0-63 Ethernet packet (pad extended)
83
-
84
-
Quad Word N (last):
85
-
0-23 Ethernet packet (pad extended)
86
-
24-55 ICRC
87
-
56-61 Tail
88
-
62-63 LT (=01, Link Transfer Tail Flit)
89
-
==================== ================================
90
-
91
-
Ethernet packet is padded on the transmit side to ensure that the VNIC OPA
92
-
packet is quad word aligned. The 'Tail' field contains the number of bytes
93
-
padded. On the receive side the 'Tail' field is read and the padding is
94
-
removed (along with ICRC, Tail and OPA header) before passing packet up
95
-
the network stack.
96
-
97
-
The L4 header field contains the virtual Ethernet switch id the VNIC port
98
-
belongs to. On the receive side, this field is used to de-multiplex the
99
-
received VNIC packets to different VNIC ports.
100
-
101
-
Driver Design
102
-
==============
103
-
Intel OPA VNIC software design is presented in the below diagram.
104
-
OPA VNIC functionality has a HW dependent component and a HW
105
-
independent component.
106
-
107
-
The support has been added for IB device to allocate and free the RDMA
108
-
netdev devices. The RDMA netdev supports interfacing with the network
109
-
stack thus creating standard network interfaces. OPA_VNIC is an RDMA
110
-
netdev device type.
111
-
112
-
The HW dependent VNIC functionality is part of the HFI1 driver. It
113
-
implements the verbs to allocate and free the OPA_VNIC RDMA netdev.
114
-
It involves HW resource allocation/management for VNIC functionality.
115
-
It interfaces with the network stack and implements the required
116
-
net_device_ops functions. It expects Omni-Path encapsulated Ethernet
117
-
packets in the transmit path and provides HW access to them. It strips
118
-
the Omni-Path header from the received packets before passing them up
119
-
the network stack. It also implements the RDMA netdev control operations.
120
-
121
-
The OPA VNIC module implements the HW independent VNIC functionality.
122
-
It consists of two parts. The VNIC Ethernet Management Agent (VEMA)
123
-
registers itself with IB core as an IB client and interfaces with the
124
-
IB MAD stack. It exchanges the management information with the Ethernet
125
-
Manager (EM) and the VNIC netdev. The VNIC netdev part allocates and frees
126
-
the OPA_VNIC RDMA netdev devices. It overrides the net_device_ops functions
127
-
set by HW dependent VNIC driver where required to accommodate any control
128
-
operation. It also handles the encapsulation of Ethernet packets with an
129
-
Omni-Path header in the transmit path. For each VNIC interface, the
130
-
information required for encapsulation is configured by the EM via VEMA MAD
131
-
interface. It also passes any control information to the HW dependent driver
132
-
by invoking the RDMA netdev control operations::
133
-
134
-
+-------------------+ +----------------------+
135
-
| | | Linux |
136
-
| IB MAD | | Network |
137
-
| | | Stack |
138
-
+-------------------+ +----------------------+
139
-
| | |
140
-
| | |
141
-
+----------------------------+ |
142
-
| | |
143
-
| OPA VNIC Module | |
144
-
| (OPA VNIC RDMA Netdev | |
145
-
| & EMA functions) | |
146
-
| | |
147
-
+----------------------------+ |
148
-
| |
149
-
| |
150
-
+------------------+ |
151
-
| IB core | |
152
-
+------------------+ |
153
-
| |
154
-
| |
155
-
+--------------------------------------------+
156
-
| |
157
-
| HFI1 Driver with VNIC support |
158
-
| |
159
-
+--------------------------------------------+
-1
Documentation/translations/zh_CN/infiniband/index.rst
-1
Documentation/translations/zh_CN/infiniband/index.rst
-156
Documentation/translations/zh_CN/infiniband/opa_vnic.rst
-156
Documentation/translations/zh_CN/infiniband/opa_vnic.rst
···
1
-
.. include:: ../disclaimer-zh_CN.rst
2
-
3
-
:Original: Documentation/infiniband/opa_vnic.rst
4
-
5
-
:翻译:
6
-
7
-
司延腾 Yanteng Si <siyanteng@loongson.cn>
8
-
9
-
:校译:
10
-
11
-
王普宇 Puyu Wang <realpuyuwang@gmail.com>
12
-
时奎亮 Alex Shi <alexs@kernel.org>
13
-
14
-
.. _cn_infiniband_opa_vnic:
15
-
16
-
=============================================
17
-
英特尔全路径（OPA）虚拟网络接口控制器（VNIC）
18
-
=============================================
19
-
20
-
英特尔全路径（OPA）虚拟网络接口控制器（VNIC）功能通过封装HFI节点之间的以
21
-
太网数据包，支持Omni-Path结构上的以太网功能。
22
-
23
-
体系结构
24
-
========
25
-
26
-
Omni-Path封装的以太网数据包的交换模式涉及Omni-Path结构拓扑上覆盖的一个或
27
-
多个虚拟以太网交换机。Omni-Path结构上的HFI节点的一个子集被允许在特定的虚
28
-
拟以太网交换机上交换封装的以太网数据包。虚拟以太网交换机是通过配置结构上的
29
-
HFI节点实现的逻辑抽象，用于生成和处理报头。在最简单的配置中，整个结构的所有
30
-
HFI节点通过一个虚拟以太网交换机交换封装的以太网数据包。一个虚拟以太网交换机，
31
-
实际上是一个独立的以太网网络。该配置由以太网管理器（EM）执行，它是可信的结
32
-
构管理器（FM）应用程序的一部分。HFI节点可以有多个VNIC，每个连接到不同的虚
33
-
拟以太网交换机。下图介绍了两个虚拟以太网交换机与两个HFI节点的情况::
34
-
35
-
+-------------------+
36
-
| 子网/ |
37
-
| 以太网 |
38
-
| 管理 |
39
-
+-------------------+
40
-
/ /
41
-
/ /
42
-
/ /
43
-
/ /
44
-
+-----------------------------+ +------------------------------+
45
-
| 虚拟以太网切换 | | 虚拟以太网切换 |
46
-
| +---------+ +---------+ | | +---------+ +---------+ |
47
-
| | VPORT | | VPORT | | | | VPORT | | VPORT | |
48
-
+--+---------+----+---------+-+ +-+---------+----+---------+---+
49
-
| \ / |
50
-
| \ / |
51
-
| \/ |
52
-
| / \ |
53
-
| / \ |
54
-
+-----------+------------+ +-----------+------------+
55
-
| VNIC | VNIC | | VNIC | VNIC |
56
-
+-----------+------------+ +-----------+------------+
57
-
| HFI | | HFI |
58
-
+------------------------+ +------------------------+
59
-
60
-
61
-
Omni-Path封装的以太网数据包格式如下所述。
62
-
63
-
==================== ================================
64
-
位 域
65
-
==================== ================================
66
-
Quad Word 0:
67
-
0-19 SLID (低20位)
68
-
20-30 长度 (以四字为单位)
69
-
31 BECN 位
70
-
32-51 DLID (低20位)
71
-
52-56 SC (服务级别)
72
-
57-59 RC (路由控制)
73
-
60 FECN 位
74
-
61-62 L2 (=10, 16B 格式)
75
-
63 LT (=1, 链路传输头 Flit)
76
-
77
-
Quad Word 1:
78
-
0-7 L4 type (=0x78 ETHERNET)
79
-
8-11 SLID[23:20]
80
-
12-15 DLID[23:20]
81
-
16-31 PKEY
82
-
32-47 熵
83
-
48-63 保留
84
-
85
-
Quad Word 2:
86
-
0-15 保留
87
-
16-31 L4 头
88
-
32-63 以太网数据包
89
-
90
-
Quad Words 3 to N-1:
91
-
0-63 以太网数据包 (pad拓展)
92
-
93
-
Quad Word N (last):
94
-
0-23 以太网数据包 (pad拓展)
95
-
24-55 ICRC
96
-
56-61 尾
97
-
62-63 LT (=01, 链路传输尾 Flit)
98
-
==================== ================================
99
-
100
-
以太网数据包在传输端被填充，以确保VNIC OPA数据包是四字对齐的。“尾”字段
101
-
包含填充的字节数。在接收端，“尾”字段被读取，在将数据包向上传递到网络堆
102
-
栈之前，填充物被移除（与ICRC、尾和OPA头一起）。
103
-
104
-
L4头字段包含VNIC端口所属的虚拟以太网交换机ID。在接收端，该字段用于将收
105
-
到的VNIC数据包去多路复用到不同的VNIC端口。
106
-
107
-
驱动设计
108
-
========
109
-
110
-
英特尔OPA VNIC的软件设计如下图所示。OPA VNIC功能有一个依赖于硬件的部分
111
-
和一个独立于硬件的部分。
112
-
113
-
对IB设备分配和释放RDMA netdev设备的支持已经被加入。RDMA netdev支持与
114
-
网络堆栈的对接，从而创建标准的网络接口。OPA_VNIC是一个RDMA netdev设备
115
-
类型。
116
-
117
-
依赖于HW的VNIC功能是HFI1驱动的一部分。它实现了分配和释放OPA_VNIC RDMA
118
-
netdev的动作。它涉及VNIC功能的HW资源分配/管理。它与网络堆栈接口并实现所
119
-
需的net_device_ops功能。它在传输路径中期待Omni-Path封装的以太网数据包，
120
-
并提供对它们的HW访问。在将数据包向上传递到网络堆栈之前，它把Omni-Path头
121
-
从接收的数据包中剥离。它还实现了RDMA netdev控制操作。
122
-
123
-
OPA VNIC模块实现了独立于硬件的VNIC功能。它由两部分组成。VNIC以太网管理
124
-
代理（VEMA）作为一个IB客户端向IB核心注册，并与IB MAD栈接口。它与以太网
125
-
管理器（EM）和VNIC netdev交换管理信息。VNIC netdev部分分配和释放OPA_VNIC
126
-
RDMA netdev设备。它在需要时覆盖由依赖HW的VNIC驱动设置的net_device_ops函数，
127
-
以适应任何控制操作。它还处理以太网数据包的封装，在传输路径中使用Omni-Path头。
128
-
对于每个VNIC接口，封装所需的信息是由EM通过VEMA MAD接口配置的。它还通过调用
129
-
RDMA netdev控制操作将任何控制信息传递给依赖于HW的驱动程序::
130
-
131
-
+-------------------+ +----------------------+
132
-
| | | Linux |
133
-
| IB MAD | | 网络 |
134
-
| | | 栈 |
135
-
+-------------------+ +----------------------+
136
-
| | |
137
-
| | |
138
-
+----------------------------+ |
139
-
| | |
140
-
| OPA VNIC 模块 | |
141
-
| (OPA VNIC RDMA Netdev | |
142
-
| & EMA 函数) | |
143
-
| | |
144
-
+----------------------------+ |
145
-
| |
146
-
| |
147
-
+------------------+ |
148
-
| IB 核心 | |
149
-
+------------------+ |
150
-
| |
151
-
| |
152
-
+--------------------------------------------+
153
-
| |
154
-
| HFI1 驱动和 VNIC 支持 |
155
-
| |
156
-
+--------------------------------------------+
-6
MAINTAINERS
-6
MAINTAINERS
···
19764
19764
S: Maintained
19765
19765
F: drivers/rtc/rtc-optee.c
19766
19766
19767
-
OPA-VNIC DRIVER
19768
-
M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
19769
-
L: linux-rdma@vger.kernel.org
19770
-
S: Supported
19771
-
F: drivers/infiniband/ulp/opa_vnic
19772
-
19773
19767
OPEN ALLIANCE 10BASE-T1S MACPHY SERIAL INTERFACE FRAMEWORK
19774
19768
M: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
19775
19769
L: netdev@vger.kernel.org
-2
drivers/infiniband/Kconfig
-2
drivers/infiniband/Kconfig
+1
-3
drivers/infiniband/hw/hfi1/Makefile
+1
-3
drivers/infiniband/hw/hfi1/Makefile
+1
-1
drivers/infiniband/hw/hfi1/aspm.c
+1
-1
drivers/infiniband/hw/hfi1/aspm.c
+7
-47
drivers/infiniband/hw/hfi1/chip.c
+7
-47
drivers/infiniband/hw/hfi1/chip.c
···
85
85
/*
86
86
* RSM instance allocation
87
87
* 0 - User Fecn Handling
88
-
* 1 - Vnic
88
+
* 1 - Deprecated
89
89
* 2 - AIP
90
90
* 3 - Verbs
91
91
*/
92
92
#define RSM_INS_FECN 0
93
-
#define RSM_INS_VNIC 1
93
+
#define RSM_INS_DEPRECATED 1
94
94
#define RSM_INS_AIP 2
95
95
#define RSM_INS_VERBS 3
96
96
···
151
151
#define DETH_AIP_SQPN_OFFSET(off) ((DETH_AIP_SQPN_QW << QW_SHIFT) | (off))
152
152
#define DETH_AIP_SQPN_SELECT_OFFSET \
153
153
DETH_AIP_SQPN_OFFSET(DETH_AIP_SQPN_BIT_OFFSET)
154
-
155
-
/* RSM fields for Vnic */
156
-
/* L2_TYPE: QW 0, OFFSET 61 - for match */
157
-
#define L2_TYPE_QW 0ull
158
-
#define L2_TYPE_BIT_OFFSET 61ull
159
-
#define L2_TYPE_OFFSET(off) ((L2_TYPE_QW << QW_SHIFT) | (off))
160
-
#define L2_TYPE_MATCH_OFFSET L2_TYPE_OFFSET(L2_TYPE_BIT_OFFSET)
161
-
#define L2_TYPE_MASK 3ull
162
-
#define L2_16B_VALUE 2ull
163
154
164
155
/* L4_TYPE QW 1, OFFSET 0 - for match */
165
156
#define L4_TYPE_QW 1ull
···
6835
6844
for (i = 0; i < dd->num_rcv_contexts; i++) {
6836
6845
rcd = hfi1_rcd_get_by_index(dd, i);
6837
6846
6838
-
/* Ensure all non-user contexts(including vnic) are enabled */
6847
+
/* Ensure all non-user contexts are enabled */
6839
6848
if (!rcd ||
6840
-
(i >= dd->first_dyn_alloc_ctxt && !rcd->is_vnic)) {
6849
+
(i >= dd->first_dyn_alloc_ctxt)) {
6841
6850
hfi1_rcd_put(rcd);
6842
6851
continue;
6843
6852
}
···
8458
8467
return work_done;
8459
8468
}
8460
8469
8461
-
/* Receive packet napi handler for netdevs VNIC and AIP */
8470
+
/* Receive packet napi handler for netdevs AIP */
8462
8471
irqreturn_t receive_context_interrupt_napi(int irq, void *data)
8463
8472
{
8464
8473
struct hfi1_ctxtdata *rcd = data;
···
14497
14506
int ctxt_count = hfi1_netdev_ctxt_count(dd);
14498
14507
14499
14508
/* We already have contexts mapped in RMT */
14500
-
if (has_rsm_rule(dd, RSM_INS_VNIC) || has_rsm_rule(dd, RSM_INS_AIP)) {
14509
+
if (has_rsm_rule(dd, RSM_INS_AIP)) {
14501
14510
dd_dev_info(dd, "Contexts are already mapped in RMT\n");
14502
14511
return true;
14503
14512
}
···
14576
14585
14577
14586
hfi1_enable_rsm_rule(dd, RSM_INS_AIP, &rrd);
14578
14587
}
14579
-
}
14580
-
14581
-
/* Initialize RSM for VNIC */
14582
-
void hfi1_init_vnic_rsm(struct hfi1_devdata *dd)
14583
-
{
14584
-
int rmt_start = hfi1_netdev_get_free_rmt_idx(dd);
14585
-
struct rsm_rule_data rrd = {
14586
-
/* Add rule for vnic */
14587
-
.offset = rmt_start,
14588
-
.pkt_type = 4,
14589
-
/* Match 16B packets */
14590
-
.field1_off = L2_TYPE_MATCH_OFFSET,
14591
-
.mask1 = L2_TYPE_MASK,
14592
-
.value1 = L2_16B_VALUE,
14593
-
/* Match ETH L4 packets */
14594
-
.field2_off = L4_TYPE_MATCH_OFFSET,
14595
-
.mask2 = L4_16B_TYPE_MASK,
14596
-
.value2 = L4_16B_ETH_VALUE,
14597
-
/* Calc context from veswid and entropy */
14598
-
.index1_off = L4_16B_HDR_VESWID_OFFSET,
14599
-
.index1_width = ilog2(NUM_NETDEV_MAP_ENTRIES),
14600
-
.index2_off = L2_16B_ENTROPY_OFFSET,
14601
-
.index2_width = ilog2(NUM_NETDEV_MAP_ENTRIES)
14602
-
};
14603
-
14604
-
hfi1_enable_rsm_rule(dd, RSM_INS_VNIC, &rrd);
14605
-
}
14606
-
14607
-
void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd)
14608
-
{
14609
-
clear_rsm_rule(dd, RSM_INS_VNIC);
14610
14588
}
14611
14589
14612
14590
void hfi1_deinit_aip_rsm(struct hfi1_devdata *dd)
···
15155
15195
(dd->revision >> CCE_REVISION_SW_SHIFT)
15156
15196
& CCE_REVISION_SW_MASK);
15157
15197
15158
-
/* alloc VNIC/AIP rx data */
15198
+
/* alloc AIP rx data */
15159
15199
ret = hfi1_alloc_rx(dd);
15160
15200
if (ret)
15161
15201
goto bail_cleanup;
-2
drivers/infiniband/hw/hfi1/chip.h
-2
drivers/infiniband/hw/hfi1/chip.h
···
1392
1392
u16 pkey);
1393
1393
int hfi1_clear_ctxt_pkey(struct hfi1_devdata *dd, struct hfi1_ctxtdata *ctxt);
1394
1394
void hfi1_read_link_quality(struct hfi1_devdata *dd, u8 *link_quality);
1395
-
void hfi1_init_vnic_rsm(struct hfi1_devdata *dd);
1396
-
void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd);
1397
1395
1398
1396
irqreturn_t general_interrupt(int irq, void *data);
1399
1397
irqreturn_t sdma_interrupt(int irq, void *data);
+6
-7
drivers/infiniband/hw/hfi1/driver.c
+6
-7
drivers/infiniband/hw/hfi1/driver.c
···
20
20
#include "qp.h"
21
21
#include "sdma.h"
22
22
#include "debugfs.h"
23
-
#include "vnic.h"
24
23
#include "fault.h"
25
24
26
25
#include "ipoib.h"
···
908
909
u16 i;
909
910
910
911
/*
911
-
* For dynamically allocated kernel contexts (like vnic) switch
912
+
* For dynamically allocated kernel contexts switch
912
913
* interrupt handler only for that context. Otherwise, switch
913
914
* interrupt handler for all statically allocated kernel contexts.
914
915
*/
915
-
if (rcd->ctxt >= dd->first_dyn_alloc_ctxt && !rcd->is_vnic) {
916
+
if (rcd->ctxt >= dd->first_dyn_alloc_ctxt) {
916
917
hfi1_rcd_get(rcd);
917
918
hfi1_set_fast(rcd);
918
919
hfi1_rcd_put(rcd);
···
921
922
922
923
for (i = HFI1_CTRL_CTXT + 1; i < dd->num_rcv_contexts; i++) {
923
924
rcd = hfi1_rcd_get_by_index(dd, i);
924
-
if (rcd && (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic))
925
+
if (rcd && (i < dd->first_dyn_alloc_ctxt))
925
926
hfi1_set_fast(rcd);
926
927
hfi1_rcd_put(rcd);
927
928
}
···
937
938
rcd = hfi1_rcd_get_by_index(dd, i);
938
939
if (!rcd)
939
940
continue;
940
-
if (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic)
941
+
if (i < dd->first_dyn_alloc_ctxt)
941
942
rcd->do_interrupt = rcd->slow_handler;
942
943
943
944
hfi1_rcd_put(rcd);
···
1399
1400
goto bail;
1400
1401
}
1401
1402
1402
-
/* If there are any user/vnic contexts, we cannot reset */
1403
+
/* If there are any user contexts, we cannot reset */
1403
1404
mutex_lock(&hfi1_mutex);
1404
1405
if (dd->rcd)
1405
1406
if (hfi1_stats.sps_ctxts) {
···
1898
1899
[RHF_RCV_TYPE_EAGER] = process_receive_invalid,
1899
1900
[RHF_RCV_TYPE_IB] = hfi1_ipoib_ib_rcv,
1900
1901
[RHF_RCV_TYPE_ERROR] = process_receive_error,
1901
-
[RHF_RCV_TYPE_BYPASS] = hfi1_vnic_bypass_rcv,
1902
+
[RHF_RCV_TYPE_BYPASS] = process_receive_invalid,
1902
1903
[RHF_RCV_TYPE_INVALID5] = process_receive_invalid,
1903
1904
[RHF_RCV_TYPE_INVALID6] = process_receive_invalid,
1904
1905
[RHF_RCV_TYPE_INVALID7] = process_receive_invalid,
-20
drivers/infiniband/hw/hfi1/hfi.h
-20
drivers/infiniband/hw/hfi1/hfi.h
···
212
212
u8 rhf_offset;
213
213
/* dynamic receive available interrupt timeout */
214
214
u8 rcvavail_timeout;
215
-
/* Indicates that this is vnic context */
216
-
bool is_vnic;
217
-
/* vnic queue index this context is mapped to */
218
-
u8 vnic_q_idx;
219
215
/* Is ASPM interrupt supported for this context */
220
216
bool aspm_intr_supported;
221
217
/* ASPM state (enabled/disabled) for this context */
···
398
402
#define OPA_16B_L4_FM 0x08
399
403
#define OPA_16B_L4_IB_LOCAL 0x09
400
404
#define OPA_16B_L4_IB_GLOBAL 0x0A
401
-
#define OPA_16B_L4_ETHR OPA_VNIC_L4_ETHR
402
405
403
406
/*
404
407
* OPA 16B Management
···
992
997
#define NUM_MAP_ENTRIES 256
993
998
#define NUM_MAP_REGS 32
994
999
995
-
/* Virtual NIC information */
996
-
struct hfi1_vnic_data {
997
-
struct kmem_cache *txreq_cache;
998
-
u8 num_vports;
999
-
};
1000
-
1001
-
struct hfi1_vnic_vport_info;
1002
-
1003
1000
/* device data struct now contains only "general per-device" info.
1004
1001
* fields related to a physical IB port are in a hfi1_pportdata struct.
1005
1002
*/
···
1285
1298
send_routine process_dma_send;
1286
1299
void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf,
1287
1300
u64 pbc, const void *from, size_t count);
1288
-
int (*process_vnic_dma_send)(struct hfi1_devdata *dd, u8 q_idx,
1289
-
struct hfi1_vnic_vport_info *vinfo,
1290
-
struct sk_buff *skb, u64 pbc, u8 plen);
1291
1301
/* hfi1_pportdata, points to array of (physical) port-specific
1292
1302
* data structs, indexed by pidx (0..n-1)
1293
1303
*/
···
1298
1314
u16 flags;
1299
1315
/* Number of physical ports available */
1300
1316
u8 num_pports;
1301
-
/* Lowest context number which can be used by user processes or VNIC */
1302
1317
u8 first_dyn_alloc_ctxt;
1303
1318
/* adding a new field here would make it part of this cacheline */
1304
1319
···
1336
1353
bool aspm_enabled; /* ASPM state: enabled/disabled */
1337
1354
struct rhashtable *sdma_rht;
1338
1355
1339
-
/* vnic data */
1340
-
struct hfi1_vnic_data vnic;
1341
1356
/* Lock to protect IRQ SRC register access */
1342
1357
spinlock_t irq_src_lock;
1343
-
int vnic_num_vports;
1344
1358
struct hfi1_netdev_rx *netdev_rx;
1345
1359
struct hfi1_affinity_node *affinity_entry;
1346
1360
+1
-3
drivers/infiniband/hw/hfi1/init.c
+1
-3
drivers/infiniband/hw/hfi1/init.c
···
26
26
#include "verbs.h"
27
27
#include "aspm.h"
28
28
#include "affinity.h"
29
-
#include "vnic.h"
30
29
#include "exp_rcv.h"
31
30
#include "netdev.h"
32
31
···
348
349
* We do this here because we have to take into account all
349
350
* the RcvArray entries that previous context would have
350
351
* taken and we have to account for any extra groups assigned
351
-
* to the static (kernel) or dynamic (vnic/user) contexts.
352
+
* to the static (kernel) or dynamic (user) contexts.
352
353
*/
353
354
if (ctxt < dd->first_dyn_alloc_ctxt) {
354
355
if (ctxt < kctxt_ngroups) {
···
850
851
dd->process_pio_send = hfi1_verbs_send_pio;
851
852
dd->process_dma_send = hfi1_verbs_send_dma;
852
853
dd->pio_inline_send = pio_copy;
853
-
dd->process_vnic_dma_send = hfi1_vnic_send_dma;
854
854
855
855
if (is_ax(dd)) {
856
856
atomic_set(&dd->drop_packet, DROP_PACKET_ON);
-1
drivers/infiniband/hw/hfi1/mad.c
-1
drivers/infiniband/hw/hfi1/mad.c
+1
-3
drivers/infiniband/hw/hfi1/msix.c
+1
-3
drivers/infiniband/hw/hfi1/msix.c
···
24
24
* one for the general, "slow path" interrupt
25
25
* one per used SDMA engine
26
26
* one per kernel receive context
27
-
* one for each VNIC context
28
27
* ...any new IRQs should be added here.
29
28
*/
30
29
total = 1 + dd->num_sdma + dd->n_krcv_queues + dd->num_netdev_contexts;
···
126
127
irq_handler_t thread,
127
128
const char *name)
128
129
{
129
-
int nr = msix_request_irq(rcd->dd, rcd, handler, thread,
130
-
rcd->is_vnic ? IRQ_NETDEVCTXT : IRQ_RCVCTXT,
130
+
int nr = msix_request_irq(rcd->dd, rcd, handler, thread, IRQ_RCVCTXT,
131
131
name);
132
132
if (nr < 0)
133
133
return nr;
+2
-6
drivers/infiniband/hw/hfi1/netdev.h
+2
-6
drivers/infiniband/hw/hfi1/netdev.h
···
14
14
15
15
/**
16
16
* struct hfi1_netdev_rxq - Receive Queue for HFI
17
-
* Both IPoIB and VNIC netdevices will be working on the rx abstraction.
17
+
* IPoIB netdevices will be working on the rx abstraction.
18
18
* @napi: napi object
19
19
* @rx: ptr to netdev_rx
20
20
* @rcd: ptr to receive context data
···
25
25
struct hfi1_ctxtdata *rcd;
26
26
};
27
27
28
-
/*
29
-
* Number of netdev contexts used. Ensure it is less than or equal to
30
-
* max queues supported by VNIC (HFI1_VNIC_MAX_QUEUE).
31
-
*/
32
28
#define HFI1_MAX_NETDEV_CTXTS 8
33
29
34
30
/* Number of NETDEV RSM entries */
···
38
42
* @num_rx_q: number of receive queues
39
43
* @rmt_index: first free index in RMT Array
40
44
* @msix_start: first free MSI-X interrupt vector.
41
-
* @dev_tbl: netdev table for unique identifier VNIC and IPoIb VLANs.
45
+
* @dev_tbl: netdev table for unique identifier IPoIb VLANs.
42
46
* @enabled: atomic counter of netdevs enabling receive queues.
43
47
* When 0 NAPI will be disabled.
44
48
* @netdevs: atomic counter of netdevs using dummy netdev.
+1
-2
drivers/infiniband/hw/hfi1/netdev_rx.c
+1
-2
drivers/infiniband/hw/hfi1/netdev_rx.c
···
78
78
uctxt->fast_handler = handle_receive_interrupt_napi_fp;
79
79
uctxt->slow_handler = handle_receive_interrupt_napi_sp;
80
80
hfi1_set_seq_cnt(uctxt, 1);
81
-
uctxt->is_vnic = true;
82
81
83
82
hfi1_stats.sps_ctxts++;
84
83
···
426
427
427
428
/**
428
429
* hfi1_netdev_add_data - Registers data with unique identifier
429
-
* to be requested later this is needed for VNIC and IPoIB VLANs
430
+
* to be requested later this is needed for IPoIB VLANs
430
431
* implementations.
431
432
* This call is protected by mutex idr_lock.
432
433
*
-2
drivers/infiniband/hw/hfi1/verbs.c
-2
drivers/infiniband/hw/hfi1/verbs.c
···
21
21
#include "qp.h"
22
22
#include "verbs_txreq.h"
23
23
#include "debugfs.h"
24
-
#include "vnic.h"
25
24
#include "fault.h"
26
25
#include "affinity.h"
27
26
#include "ipoib.h"
···
1728
1729
1729
1730
.alloc_hw_device_stats = hfi1_alloc_hw_device_stats,
1730
1731
.alloc_hw_port_stats = hfi_alloc_hw_port_stats,
1731
-
.alloc_rdma_netdev = hfi1_vnic_alloc_rn,
1732
1732
.device_group = &ib_hfi1_attr_group,
1733
1733
.get_dev_fw_str = hfi1_get_dev_fw_str,
1734
1734
.get_hw_stats = get_hw_stats,
-126
drivers/infiniband/hw/hfi1/vnic.h
-126
drivers/infiniband/hw/hfi1/vnic.h
···
1
-
/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
2
-
/*
3
-
* Copyright(c) 2017 - 2020 Intel Corporation.
4
-
*/
5
-
6
-
#ifndef _HFI1_VNIC_H
7
-
#define _HFI1_VNIC_H
8
-
#include <rdma/opa_vnic.h>
9
-
#include "hfi.h"
10
-
#include "sdma.h"
11
-
12
-
#define HFI1_VNIC_MAX_TXQ 16
13
-
#define HFI1_VNIC_MAX_PAD 12
14
-
15
-
/* L4 header definitions */
16
-
#define HFI1_VNIC_L4_HDR_OFFSET OPA_VNIC_L2_HDR_LEN
17
-
18
-
#define HFI1_VNIC_GET_L4_HDR(data) \
19
-
(*((u16 *)((u8 *)(data) + HFI1_VNIC_L4_HDR_OFFSET)))
20
-
21
-
#define HFI1_VNIC_GET_VESWID(data) \
22
-
(HFI1_VNIC_GET_L4_HDR(data) & 0xFFF)
23
-
24
-
/* Service class */
25
-
#define HFI1_VNIC_SC_OFFSET_LOW 6
26
-
#define HFI1_VNIC_SC_OFFSET_HI 7
27
-
#define HFI1_VNIC_SC_SHIFT 4
28
-
29
-
#define HFI1_VNIC_MAX_QUEUE 16
30
-
#define HFI1_NUM_VNIC_CTXT 8
31
-
32
-
/**
33
-
* struct hfi1_vnic_sdma - VNIC per Tx ring SDMA information
34
-
* @dd - device data pointer
35
-
* @sde - sdma engine
36
-
* @vinfo - vnic info pointer
37
-
* @wait - iowait structure
38
-
* @stx - sdma tx request
39
-
* @state - vnic Tx ring SDMA state
40
-
* @q_idx - vnic Tx queue index
41
-
*/
42
-
struct hfi1_vnic_sdma {
43
-
struct hfi1_devdata *dd;
44
-
struct sdma_engine *sde;
45
-
struct hfi1_vnic_vport_info *vinfo;
46
-
struct iowait wait;
47
-
struct sdma_txreq stx;
48
-
unsigned int state;
49
-
u8 q_idx;
50
-
bool pkts_sent;
51
-
};
52
-
53
-
/**
54
-
* struct hfi1_vnic_rx_queue - HFI1 VNIC receive queue
55
-
* @idx: queue index
56
-
* @vinfo: pointer to vport information
57
-
* @netdev: network device
58
-
* @napi: netdev napi structure
59
-
* @skbq: queue of received socket buffers
60
-
*/
61
-
struct hfi1_vnic_rx_queue {
62
-
u8 idx;
63
-
struct hfi1_vnic_vport_info *vinfo;
64
-
struct net_device *netdev;
65
-
struct napi_struct napi;
66
-
};
67
-
68
-
/**
69
-
* struct hfi1_vnic_vport_info - HFI1 VNIC virtual port information
70
-
* @dd: device data pointer
71
-
* @netdev: net device pointer
72
-
* @flags: state flags
73
-
* @lock: vport lock
74
-
* @num_tx_q: number of transmit queues
75
-
* @num_rx_q: number of receive queues
76
-
* @vesw_id: virtual switch id
77
-
* @rxq: Array of receive queues
78
-
* @stats: per queue stats
79
-
* @sdma: VNIC SDMA structure per TXQ
80
-
*/
81
-
struct hfi1_vnic_vport_info {
82
-
struct hfi1_devdata *dd;
83
-
struct net_device *netdev;
84
-
unsigned long flags;
85
-
86
-
/* Lock used around state updates */
87
-
struct mutex lock;
88
-
89
-
u8 num_tx_q;
90
-
u8 num_rx_q;
91
-
u16 vesw_id;
92
-
struct hfi1_vnic_rx_queue rxq[HFI1_NUM_VNIC_CTXT];
93
-
94
-
struct opa_vnic_stats stats[HFI1_VNIC_MAX_QUEUE];
95
-
struct hfi1_vnic_sdma sdma[HFI1_VNIC_MAX_TXQ];
96
-
};
97
-
98
-
#define v_dbg(format, arg...) \
99
-
netdev_dbg(vinfo->netdev, format, ## arg)
100
-
#define v_err(format, arg...) \
101
-
netdev_err(vinfo->netdev, format, ## arg)
102
-
#define v_info(format, arg...) \
103
-
netdev_info(vinfo->netdev, format, ## arg)
104
-
105
-
/* vnic hfi1 internal functions */
106
-
void hfi1_vnic_setup(struct hfi1_devdata *dd);
107
-
int hfi1_vnic_txreq_init(struct hfi1_devdata *dd);
108
-
void hfi1_vnic_txreq_deinit(struct hfi1_devdata *dd);
109
-
110
-
void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet);
111
-
void hfi1_vnic_sdma_init(struct hfi1_vnic_vport_info *vinfo);
112
-
bool hfi1_vnic_sdma_write_avail(struct hfi1_vnic_vport_info *vinfo,
113
-
u8 q_idx);
114
-
115
-
/* vnic rdma netdev operations */
116
-
struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
117
-
u32 port_num,
118
-
enum rdma_netdev_t type,
119
-
const char *name,
120
-
unsigned char name_assign_type,
121
-
void (*setup)(struct net_device *));
122
-
int hfi1_vnic_send_dma(struct hfi1_devdata *dd, u8 q_idx,
123
-
struct hfi1_vnic_vport_info *vinfo,
124
-
struct sk_buff *skb, u64 pbc, u8 plen);
125
-
126
-
#endif /* _HFI1_VNIC_H */
-615
drivers/infiniband/hw/hfi1/vnic_main.c
-615
drivers/infiniband/hw/hfi1/vnic_main.c
···
1
-
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
2
-
/*
3
-
* Copyright(c) 2017 - 2020 Intel Corporation.
4
-
*/
5
-
6
-
/*
7
-
* This file contains HFI1 support for VNIC functionality
8
-
*/
9
-
10
-
#include <linux/io.h>
11
-
#include <linux/if_vlan.h>
12
-
13
-
#include "vnic.h"
14
-
#include "netdev.h"
15
-
16
-
#define HFI_TX_TIMEOUT_MS 1000
17
-
18
-
#define HFI1_VNIC_RCV_Q_SIZE 1024
19
-
20
-
#define HFI1_VNIC_UP 0
21
-
22
-
static DEFINE_SPINLOCK(vport_cntr_lock);
23
-
24
-
#define SUM_GRP_COUNTERS(stats, qstats, x_grp) do { \
25
-
u64 *src64, *dst64; \
26
-
for (src64 = &qstats->x_grp.unicast, \
27
-
dst64 = &stats->x_grp.unicast; \
28
-
dst64 <= &stats->x_grp.s_1519_max;) { \
29
-
*dst64++ += *src64++; \
30
-
} \
31
-
} while (0)
32
-
33
-
#define VNIC_MASK (0xFF)
34
-
#define VNIC_ID(val) ((1ull << 24) | ((val) & VNIC_MASK))
35
-
36
-
/* hfi1_vnic_update_stats - update statistics */
37
-
static void hfi1_vnic_update_stats(struct hfi1_vnic_vport_info *vinfo,
38
-
struct opa_vnic_stats *stats)
39
-
{
40
-
struct net_device *netdev = vinfo->netdev;
41
-
u8 i;
42
-
43
-
/* add tx counters on different queues */
44
-
for (i = 0; i < vinfo->num_tx_q; i++) {
45
-
struct opa_vnic_stats *qstats = &vinfo->stats[i];
46
-
struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
47
-
48
-
stats->netstats.tx_fifo_errors += qnstats->tx_fifo_errors;
49
-
stats->netstats.tx_carrier_errors += qnstats->tx_carrier_errors;
50
-
stats->tx_drop_state += qstats->tx_drop_state;
51
-
stats->tx_dlid_zero += qstats->tx_dlid_zero;
52
-
53
-
SUM_GRP_COUNTERS(stats, qstats, tx_grp);
54
-
stats->netstats.tx_packets += qnstats->tx_packets;
55
-
stats->netstats.tx_bytes += qnstats->tx_bytes;
56
-
}
57
-
58
-
/* add rx counters on different queues */
59
-
for (i = 0; i < vinfo->num_rx_q; i++) {
60
-
struct opa_vnic_stats *qstats = &vinfo->stats[i];
61
-
struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
62
-
63
-
stats->netstats.rx_fifo_errors += qnstats->rx_fifo_errors;
64
-
stats->netstats.rx_nohandler += qnstats->rx_nohandler;
65
-
stats->rx_drop_state += qstats->rx_drop_state;
66
-
stats->rx_oversize += qstats->rx_oversize;
67
-
stats->rx_runt += qstats->rx_runt;
68
-
69
-
SUM_GRP_COUNTERS(stats, qstats, rx_grp);
70
-
stats->netstats.rx_packets += qnstats->rx_packets;
71
-
stats->netstats.rx_bytes += qnstats->rx_bytes;
72
-
}
73
-
74
-
stats->netstats.tx_errors = stats->netstats.tx_fifo_errors +
75
-
stats->netstats.tx_carrier_errors +
76
-
stats->tx_drop_state + stats->tx_dlid_zero;
77
-
stats->netstats.tx_dropped = stats->netstats.tx_errors;
78
-
79
-
stats->netstats.rx_errors = stats->netstats.rx_fifo_errors +
80
-
stats->netstats.rx_nohandler +
81
-
stats->rx_drop_state + stats->rx_oversize +
82
-
stats->rx_runt;
83
-
stats->netstats.rx_dropped = stats->netstats.rx_errors;
84
-
85
-
netdev->stats.tx_packets = stats->netstats.tx_packets;
86
-
netdev->stats.tx_bytes = stats->netstats.tx_bytes;
87
-
netdev->stats.tx_fifo_errors = stats->netstats.tx_fifo_errors;
88
-
netdev->stats.tx_carrier_errors = stats->netstats.tx_carrier_errors;
89
-
netdev->stats.tx_errors = stats->netstats.tx_errors;
90
-
netdev->stats.tx_dropped = stats->netstats.tx_dropped;
91
-
92
-
netdev->stats.rx_packets = stats->netstats.rx_packets;
93
-
netdev->stats.rx_bytes = stats->netstats.rx_bytes;
94
-
netdev->stats.rx_fifo_errors = stats->netstats.rx_fifo_errors;
95
-
netdev->stats.multicast = stats->rx_grp.mcastbcast;
96
-
netdev->stats.rx_length_errors = stats->rx_oversize + stats->rx_runt;
97
-
netdev->stats.rx_errors = stats->netstats.rx_errors;
98
-
netdev->stats.rx_dropped = stats->netstats.rx_dropped;
99
-
}
100
-
101
-
/* update_len_counters - update pkt's len histogram counters */
102
-
static inline void update_len_counters(struct opa_vnic_grp_stats *grp,
103
-
int len)
104
-
{
105
-
/* account for 4 byte FCS */
106
-
if (len >= 1515)
107
-
grp->s_1519_max++;
108
-
else if (len >= 1020)
109
-
grp->s_1024_1518++;
110
-
else if (len >= 508)
111
-
grp->s_512_1023++;
112
-
else if (len >= 252)
113
-
grp->s_256_511++;
114
-
else if (len >= 124)
115
-
grp->s_128_255++;
116
-
else if (len >= 61)
117
-
grp->s_65_127++;
118
-
else
119
-
grp->s_64++;
120
-
}
121
-
122
-
/* hfi1_vnic_update_tx_counters - update transmit counters */
123
-
static void hfi1_vnic_update_tx_counters(struct hfi1_vnic_vport_info *vinfo,
124
-
u8 q_idx, struct sk_buff *skb, int err)
125
-
{
126
-
struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
127
-
struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
128
-
struct opa_vnic_grp_stats *tx_grp = &stats->tx_grp;
129
-
u16 vlan_tci;
130
-
131
-
stats->netstats.tx_packets++;
132
-
stats->netstats.tx_bytes += skb->len + ETH_FCS_LEN;
133
-
134
-
update_len_counters(tx_grp, skb->len);
135
-
136
-
/* rest of the counts are for good packets only */
137
-
if (unlikely(err))
138
-
return;
139
-
140
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
141
-
tx_grp->mcastbcast++;
142
-
else
143
-
tx_grp->unicast++;
144
-
145
-
if (!__vlan_get_tag(skb, &vlan_tci))
146
-
tx_grp->vlan++;
147
-
else
148
-
tx_grp->untagged++;
149
-
}
150
-
151
-
/* hfi1_vnic_update_rx_counters - update receive counters */
152
-
static void hfi1_vnic_update_rx_counters(struct hfi1_vnic_vport_info *vinfo,
153
-
u8 q_idx, struct sk_buff *skb, int err)
154
-
{
155
-
struct ethhdr *mac_hdr = (struct ethhdr *)skb->data;
156
-
struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
157
-
struct opa_vnic_grp_stats *rx_grp = &stats->rx_grp;
158
-
u16 vlan_tci;
159
-
160
-
stats->netstats.rx_packets++;
161
-
stats->netstats.rx_bytes += skb->len + ETH_FCS_LEN;
162
-
163
-
update_len_counters(rx_grp, skb->len);
164
-
165
-
/* rest of the counts are for good packets only */
166
-
if (unlikely(err))
167
-
return;
168
-
169
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
170
-
rx_grp->mcastbcast++;
171
-
else
172
-
rx_grp->unicast++;
173
-
174
-
if (!__vlan_get_tag(skb, &vlan_tci))
175
-
rx_grp->vlan++;
176
-
else
177
-
rx_grp->untagged++;
178
-
}
179
-
180
-
/* This function is overloaded for opa_vnic specific implementation */
181
-
static void hfi1_vnic_get_stats64(struct net_device *netdev,
182
-
struct rtnl_link_stats64 *stats)
183
-
{
184
-
struct opa_vnic_stats *vstats = (struct opa_vnic_stats *)stats;
185
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
186
-
187
-
hfi1_vnic_update_stats(vinfo, vstats);
188
-
}
189
-
190
-
static u64 create_bypass_pbc(u32 vl, u32 dw_len)
191
-
{
192
-
u64 pbc;
193
-
194
-
pbc = ((u64)PBC_IHCRC_NONE << PBC_INSERT_HCRC_SHIFT)
195
-
| PBC_INSERT_BYPASS_ICRC | PBC_CREDIT_RETURN
196
-
| PBC_PACKET_BYPASS
197
-
| ((vl & PBC_VL_MASK) << PBC_VL_SHIFT)
198
-
| (dw_len & PBC_LENGTH_DWS_MASK) << PBC_LENGTH_DWS_SHIFT;
199
-
200
-
return pbc;
201
-
}
202
-
203
-
/* hfi1_vnic_maybe_stop_tx - stop tx queue if required */
204
-
static void hfi1_vnic_maybe_stop_tx(struct hfi1_vnic_vport_info *vinfo,
205
-
u8 q_idx)
206
-
{
207
-
netif_stop_subqueue(vinfo->netdev, q_idx);
208
-
if (!hfi1_vnic_sdma_write_avail(vinfo, q_idx))
209
-
return;
210
-
211
-
netif_start_subqueue(vinfo->netdev, q_idx);
212
-
}
213
-
214
-
static netdev_tx_t hfi1_netdev_start_xmit(struct sk_buff *skb,
215
-
struct net_device *netdev)
216
-
{
217
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
218
-
u8 pad_len, q_idx = skb->queue_mapping;
219
-
struct hfi1_devdata *dd = vinfo->dd;
220
-
struct opa_vnic_skb_mdata *mdata;
221
-
u32 pkt_len, total_len;
222
-
int err = -EINVAL;
223
-
u64 pbc;
224
-
225
-
v_dbg("xmit: queue %d skb len %d\n", q_idx, skb->len);
226
-
if (unlikely(!netif_oper_up(netdev))) {
227
-
vinfo->stats[q_idx].tx_drop_state++;
228
-
goto tx_finish;
229
-
}
230
-
231
-
/* take out meta data */
232
-
mdata = (struct opa_vnic_skb_mdata *)skb->data;
233
-
skb_pull(skb, sizeof(*mdata));
234
-
if (unlikely(mdata->flags & OPA_VNIC_SKB_MDATA_ENCAP_ERR)) {
235
-
vinfo->stats[q_idx].tx_dlid_zero++;
236
-
goto tx_finish;
237
-
}
238
-
239
-
/* add tail padding (for 8 bytes size alignment) and icrc */
240
-
pad_len = -(skb->len + OPA_VNIC_ICRC_TAIL_LEN) & 0x7;
241
-
pad_len += OPA_VNIC_ICRC_TAIL_LEN;
242
-
243
-
/*
244
-
* pkt_len is how much data we have to write, includes header and data.
245
-
* total_len is length of the packet in Dwords plus the PBC should not
246
-
* include the CRC.
247
-
*/
248
-
pkt_len = (skb->len + pad_len) >> 2;
249
-
total_len = pkt_len + 2; /* PBC + packet */
250
-
251
-
pbc = create_bypass_pbc(mdata->vl, total_len);
252
-
253
-
skb_get(skb);
254
-
v_dbg("pbc 0x%016llX len %d pad_len %d\n", pbc, skb->len, pad_len);
255
-
err = dd->process_vnic_dma_send(dd, q_idx, vinfo, skb, pbc, pad_len);
256
-
if (unlikely(err)) {
257
-
if (err == -ENOMEM)
258
-
vinfo->stats[q_idx].netstats.tx_fifo_errors++;
259
-
else if (err != -EBUSY)
260
-
vinfo->stats[q_idx].netstats.tx_carrier_errors++;
261
-
}
262
-
/* remove the header before updating tx counters */
263
-
skb_pull(skb, OPA_VNIC_HDR_LEN);
264
-
265
-
if (unlikely(err == -EBUSY)) {
266
-
hfi1_vnic_maybe_stop_tx(vinfo, q_idx);
267
-
dev_kfree_skb_any(skb);
268
-
return NETDEV_TX_BUSY;
269
-
}
270
-
271
-
tx_finish:
272
-
/* update tx counters */
273
-
hfi1_vnic_update_tx_counters(vinfo, q_idx, skb, err);
274
-
dev_kfree_skb_any(skb);
275
-
return NETDEV_TX_OK;
276
-
}
277
-
278
-
static u16 hfi1_vnic_select_queue(struct net_device *netdev,
279
-
struct sk_buff *skb,
280
-
struct net_device *sb_dev)
281
-
{
282
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
283
-
struct opa_vnic_skb_mdata *mdata;
284
-
struct sdma_engine *sde;
285
-
286
-
mdata = (struct opa_vnic_skb_mdata *)skb->data;
287
-
sde = sdma_select_engine_vl(vinfo->dd, mdata->entropy, mdata->vl);
288
-
return sde->this_idx;
289
-
}
290
-
291
-
/* hfi1_vnic_decap_skb - strip OPA header from the skb (ethernet) packet */
292
-
static inline int hfi1_vnic_decap_skb(struct hfi1_vnic_rx_queue *rxq,
293
-
struct sk_buff *skb)
294
-
{
295
-
struct hfi1_vnic_vport_info *vinfo = rxq->vinfo;
296
-
int max_len = vinfo->netdev->mtu + VLAN_ETH_HLEN;
297
-
int rc = -EFAULT;
298
-
299
-
skb_pull(skb, OPA_VNIC_HDR_LEN);
300
-
301
-
/* Validate Packet length */
302
-
if (unlikely(skb->len > max_len))
303
-
vinfo->stats[rxq->idx].rx_oversize++;
304
-
else if (unlikely(skb->len < ETH_ZLEN))
305
-
vinfo->stats[rxq->idx].rx_runt++;
306
-
else
307
-
rc = 0;
308
-
return rc;
309
-
}
310
-
311
-
static struct hfi1_vnic_vport_info *get_vnic_port(struct hfi1_devdata *dd,
312
-
int vesw_id)
313
-
{
314
-
int vnic_id = VNIC_ID(vesw_id);
315
-
316
-
return hfi1_netdev_get_data(dd, vnic_id);
317
-
}
318
-
319
-
static struct hfi1_vnic_vport_info *get_first_vnic_port(struct hfi1_devdata *dd)
320
-
{
321
-
struct hfi1_vnic_vport_info *vinfo;
322
-
int next_id = VNIC_ID(0);
323
-
324
-
vinfo = hfi1_netdev_get_first_data(dd, &next_id);
325
-
326
-
if (next_id > VNIC_ID(VNIC_MASK))
327
-
return NULL;
328
-
329
-
return vinfo;
330
-
}
331
-
332
-
void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
333
-
{
334
-
struct hfi1_devdata *dd = packet->rcd->dd;
335
-
struct hfi1_vnic_vport_info *vinfo = NULL;
336
-
struct hfi1_vnic_rx_queue *rxq;
337
-
struct sk_buff *skb;
338
-
int l4_type, vesw_id = -1, rc;
339
-
u8 q_idx;
340
-
unsigned char *pad_info;
341
-
342
-
l4_type = hfi1_16B_get_l4(packet->ebuf);
343
-
if (likely(l4_type == OPA_16B_L4_ETHR)) {
344
-
vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
345
-
vinfo = get_vnic_port(dd, vesw_id);
346
-
347
-
/*
348
-
* In case of invalid vesw id, count the error on
349
-
* the first available vport.
350
-
*/
351
-
if (unlikely(!vinfo)) {
352
-
struct hfi1_vnic_vport_info *vinfo_tmp;
353
-
354
-
vinfo_tmp = get_first_vnic_port(dd);
355
-
if (vinfo_tmp) {
356
-
spin_lock(&vport_cntr_lock);
357
-
vinfo_tmp->stats[0].netstats.rx_nohandler++;
358
-
spin_unlock(&vport_cntr_lock);
359
-
}
360
-
}
361
-
}
362
-
363
-
if (unlikely(!vinfo)) {
364
-
dd_dev_warn(dd, "vnic rcv err: l4 %d vesw id %d ctx %d\n",
365
-
l4_type, vesw_id, packet->rcd->ctxt);
366
-
return;
367
-
}
368
-
369
-
q_idx = packet->rcd->vnic_q_idx;
370
-
rxq = &vinfo->rxq[q_idx];
371
-
if (unlikely(!netif_oper_up(vinfo->netdev))) {
372
-
vinfo->stats[q_idx].rx_drop_state++;
373
-
return;
374
-
}
375
-
376
-
skb = netdev_alloc_skb(vinfo->netdev, packet->tlen);
377
-
if (unlikely(!skb)) {
378
-
vinfo->stats[q_idx].netstats.rx_fifo_errors++;
379
-
return;
380
-
}
381
-
382
-
memcpy(skb->data, packet->ebuf, packet->tlen);
383
-
skb_put(skb, packet->tlen);
384
-
385
-
pad_info = skb->data + skb->len - 1;
386
-
skb_trim(skb, (skb->len - OPA_VNIC_ICRC_TAIL_LEN -
387
-
((*pad_info) & 0x7)));
388
-
389
-
rc = hfi1_vnic_decap_skb(rxq, skb);
390
-
391
-
/* update rx counters */
392
-
hfi1_vnic_update_rx_counters(vinfo, rxq->idx, skb, rc);
393
-
if (unlikely(rc)) {
394
-
dev_kfree_skb_any(skb);
395
-
return;
396
-
}
397
-
398
-
skb_checksum_none_assert(skb);
399
-
skb->protocol = eth_type_trans(skb, rxq->netdev);
400
-
401
-
napi_gro_receive(&rxq->napi, skb);
402
-
}
403
-
404
-
static int hfi1_vnic_up(struct hfi1_vnic_vport_info *vinfo)
405
-
{
406
-
struct hfi1_devdata *dd = vinfo->dd;
407
-
struct net_device *netdev = vinfo->netdev;
408
-
int rc;
409
-
410
-
/* ensure virtual eth switch id is valid */
411
-
if (!vinfo->vesw_id)
412
-
return -EINVAL;
413
-
414
-
rc = hfi1_netdev_add_data(dd, VNIC_ID(vinfo->vesw_id), vinfo);
415
-
if (rc < 0)
416
-
return rc;
417
-
418
-
rc = hfi1_netdev_rx_init(dd);
419
-
if (rc)
420
-
goto err_remove;
421
-
422
-
netif_carrier_on(netdev);
423
-
netif_tx_start_all_queues(netdev);
424
-
set_bit(HFI1_VNIC_UP, &vinfo->flags);
425
-
426
-
return 0;
427
-
428
-
err_remove:
429
-
hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
430
-
return rc;
431
-
}
432
-
433
-
static void hfi1_vnic_down(struct hfi1_vnic_vport_info *vinfo)
434
-
{
435
-
struct hfi1_devdata *dd = vinfo->dd;
436
-
437
-
clear_bit(HFI1_VNIC_UP, &vinfo->flags);
438
-
netif_carrier_off(vinfo->netdev);
439
-
netif_tx_disable(vinfo->netdev);
440
-
hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
441
-
442
-
hfi1_netdev_rx_destroy(dd);
443
-
}
444
-
445
-
static int hfi1_netdev_open(struct net_device *netdev)
446
-
{
447
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
448
-
int rc;
449
-
450
-
mutex_lock(&vinfo->lock);
451
-
rc = hfi1_vnic_up(vinfo);
452
-
mutex_unlock(&vinfo->lock);
453
-
return rc;
454
-
}
455
-
456
-
static int hfi1_netdev_close(struct net_device *netdev)
457
-
{
458
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
459
-
460
-
mutex_lock(&vinfo->lock);
461
-
if (test_bit(HFI1_VNIC_UP, &vinfo->flags))
462
-
hfi1_vnic_down(vinfo);
463
-
mutex_unlock(&vinfo->lock);
464
-
return 0;
465
-
}
466
-
467
-
static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
468
-
{
469
-
struct hfi1_devdata *dd = vinfo->dd;
470
-
int rc = 0;
471
-
472
-
mutex_lock(&hfi1_mutex);
473
-
if (!dd->vnic_num_vports) {
474
-
rc = hfi1_vnic_txreq_init(dd);
475
-
if (rc)
476
-
goto txreq_fail;
477
-
}
478
-
479
-
rc = hfi1_netdev_rx_init(dd);
480
-
if (rc) {
481
-
dd_dev_err(dd, "Unable to initialize netdev contexts\n");
482
-
goto alloc_fail;
483
-
}
484
-
485
-
hfi1_init_vnic_rsm(dd);
486
-
487
-
dd->vnic_num_vports++;
488
-
hfi1_vnic_sdma_init(vinfo);
489
-
490
-
alloc_fail:
491
-
if (!dd->vnic_num_vports)
492
-
hfi1_vnic_txreq_deinit(dd);
493
-
txreq_fail:
494
-
mutex_unlock(&hfi1_mutex);
495
-
return rc;
496
-
}
497
-
498
-
static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo)
499
-
{
500
-
struct hfi1_devdata *dd = vinfo->dd;
501
-
502
-
mutex_lock(&hfi1_mutex);
503
-
if (--dd->vnic_num_vports == 0) {
504
-
hfi1_deinit_vnic_rsm(dd);
505
-
hfi1_vnic_txreq_deinit(dd);
506
-
}
507
-
mutex_unlock(&hfi1_mutex);
508
-
hfi1_netdev_rx_destroy(dd);
509
-
}
510
-
511
-
static void hfi1_vnic_set_vesw_id(struct net_device *netdev, int id)
512
-
{
513
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
514
-
bool reopen = false;
515
-
516
-
/*
517
-
* If vesw_id is being changed, and if the vnic port is up,
518
-
* reset the vnic port to ensure new vesw_id gets picked up
519
-
*/
520
-
if (id != vinfo->vesw_id) {
521
-
mutex_lock(&vinfo->lock);
522
-
if (test_bit(HFI1_VNIC_UP, &vinfo->flags)) {
523
-
hfi1_vnic_down(vinfo);
524
-
reopen = true;
525
-
}
526
-
527
-
vinfo->vesw_id = id;
528
-
if (reopen)
529
-
hfi1_vnic_up(vinfo);
530
-
531
-
mutex_unlock(&vinfo->lock);
532
-
}
533
-
}
534
-
535
-
/* netdev ops */
536
-
static const struct net_device_ops hfi1_netdev_ops = {
537
-
.ndo_open = hfi1_netdev_open,
538
-
.ndo_stop = hfi1_netdev_close,
539
-
.ndo_start_xmit = hfi1_netdev_start_xmit,
540
-
.ndo_select_queue = hfi1_vnic_select_queue,
541
-
.ndo_get_stats64 = hfi1_vnic_get_stats64,
542
-
};
543
-
544
-
static void hfi1_vnic_free_rn(struct net_device *netdev)
545
-
{
546
-
struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
547
-
548
-
hfi1_vnic_deinit(vinfo);
549
-
mutex_destroy(&vinfo->lock);
550
-
free_netdev(netdev);
551
-
}
552
-
553
-
struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
554
-
u32 port_num,
555
-
enum rdma_netdev_t type,
556
-
const char *name,
557
-
unsigned char name_assign_type,
558
-
void (*setup)(struct net_device *))
559
-
{
560
-
struct hfi1_devdata *dd = dd_from_ibdev(device);
561
-
struct hfi1_vnic_vport_info *vinfo;
562
-
struct net_device *netdev;
563
-
struct rdma_netdev *rn;
564
-
int i, size, rc;
565
-
566
-
if (!dd->num_netdev_contexts)
567
-
return ERR_PTR(-ENOMEM);
568
-
569
-
if (!port_num || (port_num > dd->num_pports))
570
-
return ERR_PTR(-EINVAL);
571
-
572
-
if (type != RDMA_NETDEV_OPA_VNIC)
573
-
return ERR_PTR(-EOPNOTSUPP);
574
-
575
-
size = sizeof(struct opa_vnic_rdma_netdev) + sizeof(*vinfo);
576
-
netdev = alloc_netdev_mqs(size, name, name_assign_type, setup,
577
-
chip_sdma_engines(dd),
578
-
dd->num_netdev_contexts);
579
-
if (!netdev)
580
-
return ERR_PTR(-ENOMEM);
581
-
582
-
rn = netdev_priv(netdev);
583
-
vinfo = opa_vnic_dev_priv(netdev);
584
-
vinfo->dd = dd;
585
-
vinfo->num_tx_q = chip_sdma_engines(dd);
586
-
vinfo->num_rx_q = dd->num_netdev_contexts;
587
-
vinfo->netdev = netdev;
588
-
rn->free_rdma_netdev = hfi1_vnic_free_rn;
589
-
rn->set_id = hfi1_vnic_set_vesw_id;
590
-
591
-
netdev->features = NETIF_F_HIGHDMA | NETIF_F_SG;
592
-
netdev->hw_features = netdev->features;
593
-
netdev->vlan_features = netdev->features;
594
-
netdev->watchdog_timeo = msecs_to_jiffies(HFI_TX_TIMEOUT_MS);
595
-
netdev->netdev_ops = &hfi1_netdev_ops;
596
-
mutex_init(&vinfo->lock);
597
-
598
-
for (i = 0; i < vinfo->num_rx_q; i++) {
599
-
struct hfi1_vnic_rx_queue *rxq = &vinfo->rxq[i];
600
-
601
-
rxq->idx = i;
602
-
rxq->vinfo = vinfo;
603
-
rxq->netdev = netdev;
604
-
}
605
-
606
-
rc = hfi1_vnic_init(vinfo);
607
-
if (rc)
608
-
goto init_fail;
609
-
610
-
return netdev;
611
-
init_fail:
612
-
mutex_destroy(&vinfo->lock);
613
-
free_netdev(netdev);
614
-
return ERR_PTR(rc);
615
-
}
-282
drivers/infiniband/hw/hfi1/vnic_sdma.c
-282
drivers/infiniband/hw/hfi1/vnic_sdma.c
···
1
-
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
2
-
/*
3
-
* Copyright(c) 2017 - 2018 Intel Corporation.
4
-
*/
5
-
6
-
/*
7
-
* This file contains HFI1 support for VNIC SDMA functionality
8
-
*/
9
-
10
-
#include "sdma.h"
11
-
#include "vnic.h"
12
-
13
-
#define HFI1_VNIC_SDMA_Q_ACTIVE BIT(0)
14
-
#define HFI1_VNIC_SDMA_Q_DEFERRED BIT(1)
15
-
16
-
#define HFI1_VNIC_TXREQ_NAME_LEN 32
17
-
#define HFI1_VNIC_SDMA_DESC_WTRMRK 64
18
-
19
-
/*
20
-
* struct vnic_txreq - VNIC transmit descriptor
21
-
* @txreq: sdma transmit request
22
-
* @sdma: vnic sdma pointer
23
-
* @skb: skb to send
24
-
* @pad: pad buffer
25
-
* @plen: pad length
26
-
* @pbc_val: pbc value
27
-
*/
28
-
struct vnic_txreq {
29
-
struct sdma_txreq txreq;
30
-
struct hfi1_vnic_sdma *sdma;
31
-
32
-
struct sk_buff *skb;
33
-
unsigned char pad[HFI1_VNIC_MAX_PAD];
34
-
u16 plen;
35
-
__le64 pbc_val;
36
-
};
37
-
38
-
static void vnic_sdma_complete(struct sdma_txreq *txreq,
39
-
int status)
40
-
{
41
-
struct vnic_txreq *tx = container_of(txreq, struct vnic_txreq, txreq);
42
-
struct hfi1_vnic_sdma *vnic_sdma = tx->sdma;
43
-
44
-
sdma_txclean(vnic_sdma->dd, txreq);
45
-
dev_kfree_skb_any(tx->skb);
46
-
kmem_cache_free(vnic_sdma->dd->vnic.txreq_cache, tx);
47
-
}
48
-
49
-
static noinline int build_vnic_ulp_payload(struct sdma_engine *sde,
50
-
struct vnic_txreq *tx)
51
-
{
52
-
int i, ret = 0;
53
-
54
-
ret = sdma_txadd_kvaddr(
55
-
sde->dd,
56
-
&tx->txreq,
57
-
tx->skb->data,
58
-
skb_headlen(tx->skb));
59
-
if (unlikely(ret))
60
-
goto bail_txadd;
61
-
62
-
for (i = 0; i < skb_shinfo(tx->skb)->nr_frags; i++) {
63
-
skb_frag_t *frag = &skb_shinfo(tx->skb)->frags[i];
64
-
65
-
/* combine physically continuous fragments later? */
66
-
ret = sdma_txadd_page(sde->dd,
67
-
&tx->txreq,
68
-
skb_frag_page(frag),
69
-
skb_frag_off(frag),
70
-
skb_frag_size(frag),
71
-
NULL, NULL, NULL);
72
-
if (unlikely(ret))
73
-
goto bail_txadd;
74
-
}
75
-
76
-
if (tx->plen)
77
-
ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
78
-
tx->pad + HFI1_VNIC_MAX_PAD - tx->plen,
79
-
tx->plen);
80
-
81
-
bail_txadd:
82
-
return ret;
83
-
}
84
-
85
-
static int build_vnic_tx_desc(struct sdma_engine *sde,
86
-
struct vnic_txreq *tx,
87
-
u64 pbc)
88
-
{
89
-
int ret = 0;
90
-
u16 hdrbytes = 2 << 2; /* PBC */
91
-
92
-
ret = sdma_txinit_ahg(
93
-
&tx->txreq,
94
-
0,
95
-
hdrbytes + tx->skb->len + tx->plen,
96
-
0,
97
-
0,
98
-
NULL,
99
-
0,
100
-
vnic_sdma_complete);
101
-
if (unlikely(ret))
102
-
goto bail_txadd;
103
-
104
-
/* add pbc */
105
-
tx->pbc_val = cpu_to_le64(pbc);
106
-
ret = sdma_txadd_kvaddr(
107
-
sde->dd,
108
-
&tx->txreq,
109
-
&tx->pbc_val,
110
-
hdrbytes);
111
-
if (unlikely(ret))
112
-
goto bail_txadd;
113
-
114
-
/* add the ulp payload */
115
-
ret = build_vnic_ulp_payload(sde, tx);
116
-
bail_txadd:
117
-
return ret;
118
-
}
119
-
120
-
/* setup the last plen bypes of pad */
121
-
static inline void hfi1_vnic_update_pad(unsigned char *pad, u8 plen)
122
-
{
123
-
pad[HFI1_VNIC_MAX_PAD - 1] = plen - OPA_VNIC_ICRC_TAIL_LEN;
124
-
}
125
-
126
-
int hfi1_vnic_send_dma(struct hfi1_devdata *dd, u8 q_idx,
127
-
struct hfi1_vnic_vport_info *vinfo,
128
-
struct sk_buff *skb, u64 pbc, u8 plen)
129
-
{
130
-
struct hfi1_vnic_sdma *vnic_sdma = &vinfo->sdma[q_idx];
131
-
struct sdma_engine *sde = vnic_sdma->sde;
132
-
struct vnic_txreq *tx;
133
-
int ret = -ECOMM;
134
-
135
-
if (unlikely(READ_ONCE(vnic_sdma->state) != HFI1_VNIC_SDMA_Q_ACTIVE))
136
-
goto tx_err;
137
-
138
-
if (unlikely(!sde || !sdma_running(sde)))
139
-
goto tx_err;
140
-
141
-
tx = kmem_cache_alloc(dd->vnic.txreq_cache, GFP_ATOMIC);
142
-
if (unlikely(!tx)) {
143
-
ret = -ENOMEM;
144
-
goto tx_err;
145
-
}
146
-
147
-
tx->sdma = vnic_sdma;
148
-
tx->skb = skb;
149
-
hfi1_vnic_update_pad(tx->pad, plen);
150
-
tx->plen = plen;
151
-
ret = build_vnic_tx_desc(sde, tx, pbc);
152
-
if (unlikely(ret))
153
-
goto free_desc;
154
-
155
-
ret = sdma_send_txreq(sde, iowait_get_ib_work(&vnic_sdma->wait),
156
-
&tx->txreq, vnic_sdma->pkts_sent);
157
-
/* When -ECOMM, sdma callback will be called with ABORT status */
158
-
if (unlikely(ret && unlikely(ret != -ECOMM)))
159
-
goto free_desc;
160
-
161
-
if (!ret) {
162
-
vnic_sdma->pkts_sent = true;
163
-
iowait_starve_clear(vnic_sdma->pkts_sent, &vnic_sdma->wait);
164
-
}
165
-
return ret;
166
-
167
-
free_desc:
168
-
sdma_txclean(dd, &tx->txreq);
169
-
kmem_cache_free(dd->vnic.txreq_cache, tx);
170
-
tx_err:
171
-
if (ret != -EBUSY)
172
-
dev_kfree_skb_any(skb);
173
-
else
174
-
vnic_sdma->pkts_sent = false;
175
-
return ret;
176
-
}
177
-
178
-
/*
179
-
* hfi1_vnic_sdma_sleep - vnic sdma sleep function
180
-
*
181
-
* This function gets called from sdma_send_txreq() when there are not enough
182
-
* sdma descriptors available to send the packet. It adds Tx queue's wait
183
-
* structure to sdma engine's dmawait list to be woken up when descriptors
184
-
* become available.
185
-
*/
186
-
static int hfi1_vnic_sdma_sleep(struct sdma_engine *sde,
187
-
struct iowait_work *wait,
188
-
struct sdma_txreq *txreq,
189
-
uint seq,
190
-
bool pkts_sent)
191
-
{
192
-
struct hfi1_vnic_sdma *vnic_sdma =
193
-
container_of(wait->iow, struct hfi1_vnic_sdma, wait);
194
-
195
-
write_seqlock(&sde->waitlock);
196
-
if (sdma_progress(sde, seq, txreq)) {
197
-
write_sequnlock(&sde->waitlock);
198
-
return -EAGAIN;
199
-
}
200
-
201
-
vnic_sdma->state = HFI1_VNIC_SDMA_Q_DEFERRED;
202
-
if (list_empty(&vnic_sdma->wait.list)) {
203
-
iowait_get_priority(wait->iow);
204
-
iowait_queue(pkts_sent, wait->iow, &sde->dmawait);
205
-
}
206
-
write_sequnlock(&sde->waitlock);
207
-
return -EBUSY;
208
-
}
209
-
210
-
/*
211
-
* hfi1_vnic_sdma_wakeup - vnic sdma wakeup function
212
-
*
213
-
* This function gets called when SDMA descriptors becomes available and Tx
214
-
* queue's wait structure was previously added to sdma engine's dmawait list.
215
-
* It notifies the upper driver about Tx queue wakeup.
216
-
*/
217
-
static void hfi1_vnic_sdma_wakeup(struct iowait *wait, int reason)
218
-
{
219
-
struct hfi1_vnic_sdma *vnic_sdma =
220
-
container_of(wait, struct hfi1_vnic_sdma, wait);
221
-
struct hfi1_vnic_vport_info *vinfo = vnic_sdma->vinfo;
222
-
223
-
vnic_sdma->state = HFI1_VNIC_SDMA_Q_ACTIVE;
224
-
if (__netif_subqueue_stopped(vinfo->netdev, vnic_sdma->q_idx))
225
-
netif_wake_subqueue(vinfo->netdev, vnic_sdma->q_idx);
226
-
};
227
-
228
-
inline bool hfi1_vnic_sdma_write_avail(struct hfi1_vnic_vport_info *vinfo,
229
-
u8 q_idx)
230
-
{
231
-
struct hfi1_vnic_sdma *vnic_sdma = &vinfo->sdma[q_idx];
232
-
233
-
return (READ_ONCE(vnic_sdma->state) == HFI1_VNIC_SDMA_Q_ACTIVE);
234
-
}
235
-
236
-
void hfi1_vnic_sdma_init(struct hfi1_vnic_vport_info *vinfo)
237
-
{
238
-
int i;
239
-
240
-
for (i = 0; i < vinfo->num_tx_q; i++) {
241
-
struct hfi1_vnic_sdma *vnic_sdma = &vinfo->sdma[i];
242
-
243
-
iowait_init(&vnic_sdma->wait, 0, NULL, NULL,
244
-
hfi1_vnic_sdma_sleep,
245
-
hfi1_vnic_sdma_wakeup, NULL, NULL);
246
-
vnic_sdma->sde = &vinfo->dd->per_sdma[i];
247
-
vnic_sdma->dd = vinfo->dd;
248
-
vnic_sdma->vinfo = vinfo;
249
-
vnic_sdma->q_idx = i;
250
-
vnic_sdma->state = HFI1_VNIC_SDMA_Q_ACTIVE;
251
-
252
-
/* Add a free descriptor watermark for wakeups */
253
-
if (vnic_sdma->sde->descq_cnt > HFI1_VNIC_SDMA_DESC_WTRMRK) {
254
-
struct iowait_work *work;
255
-
256
-
INIT_LIST_HEAD(&vnic_sdma->stx.list);
257
-
vnic_sdma->stx.num_desc = HFI1_VNIC_SDMA_DESC_WTRMRK;
258
-
work = iowait_get_ib_work(&vnic_sdma->wait);
259
-
list_add_tail(&vnic_sdma->stx.list, &work->tx_head);
260
-
}
261
-
}
262
-
}
263
-
264
-
int hfi1_vnic_txreq_init(struct hfi1_devdata *dd)
265
-
{
266
-
char buf[HFI1_VNIC_TXREQ_NAME_LEN];
267
-
268
-
snprintf(buf, sizeof(buf), "hfi1_%u_vnic_txreq_cache", dd->unit);
269
-
dd->vnic.txreq_cache = kmem_cache_create(buf,
270
-
sizeof(struct vnic_txreq),
271
-
0, SLAB_HWCACHE_ALIGN,
272
-
NULL);
273
-
if (!dd->vnic.txreq_cache)
274
-
return -ENOMEM;
275
-
return 0;
276
-
}
277
-
278
-
void hfi1_vnic_txreq_deinit(struct hfi1_devdata *dd)
279
-
{
280
-
kmem_cache_destroy(dd->vnic.txreq_cache);
281
-
dd->vnic.txreq_cache = NULL;
282
-
}
-1
drivers/infiniband/ulp/Makefile
-1
drivers/infiniband/ulp/Makefile
-9
drivers/infiniband/ulp/opa_vnic/Kconfig
-9
drivers/infiniband/ulp/opa_vnic/Kconfig
···
1
-
# SPDX-License-Identifier: GPL-2.0-only
2
-
config INFINIBAND_OPA_VNIC
3
-
tristate "Cornelis OPX VNIC support"
4
-
depends on X86_64 && INFINIBAND
5
-
help
6
-
This is Omni-Path Express (OPX) Virtual Network Interface Controller (VNIC)
7
-
driver for Ethernet over Omni-Path feature. It implements the HW
8
-
independent VNIC functionality. It interfaces with Linux stack for
9
-
data path and IB MAD for the control path.
-9
drivers/infiniband/ulp/opa_vnic/Makefile
-9
drivers/infiniband/ulp/opa_vnic/Makefile
···
1
-
# SPDX-License-Identifier: GPL-2.0-only
2
-
# Makefile - Cornelis Omni-Path Express Virtual Network Controller driver
3
-
# Copyright(c) 2017, Intel Corporation.
4
-
# Copyright(c) 2021, Cornelis Networks.
5
-
#
6
-
obj-$(CONFIG_INFINIBAND_OPA_VNIC) += opa_vnic.o
7
-
8
-
opa_vnic-y := opa_vnic_netdev.o opa_vnic_encap.o opa_vnic_ethtool.o \
9
-
opa_vnic_vema.o opa_vnic_vema_iface.o
-513
drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
-513
drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c
···
1
-
/*
2
-
* Copyright(c) 2017 Intel Corporation.
3
-
*
4
-
* This file is provided under a dual BSD/GPLv2 license. When using or
5
-
* redistributing this file, you may do so under either license.
6
-
*
7
-
* GPL LICENSE SUMMARY
8
-
*
9
-
* This program is free software; you can redistribute it and/or modify
10
-
* it under the terms of version 2 of the GNU General Public License as
11
-
* published by the Free Software Foundation.
12
-
*
13
-
* This program is distributed in the hope that it will be useful, but
14
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
15
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16
-
* General Public License for more details.
17
-
*
18
-
* BSD LICENSE
19
-
*
20
-
* Redistribution and use in source and binary forms, with or without
21
-
* modification, are permitted provided that the following conditions
22
-
* are met:
23
-
*
24
-
* - Redistributions of source code must retain the above copyright
25
-
* notice, this list of conditions and the following disclaimer.
26
-
* - Redistributions in binary form must reproduce the above copyright
27
-
* notice, this list of conditions and the following disclaimer in
28
-
* the documentation and/or other materials provided with the
29
-
* distribution.
30
-
* - Neither the name of Intel Corporation nor the names of its
31
-
* contributors may be used to endorse or promote products derived
32
-
* from this software without specific prior written permission.
33
-
*
34
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45
-
*
46
-
*/
47
-
48
-
/*
49
-
* This file contains OPA VNIC encapsulation/decapsulation function.
50
-
*/
51
-
52
-
#include <linux/if_ether.h>
53
-
#include <linux/if_vlan.h>
54
-
55
-
#include "opa_vnic_internal.h"
56
-
57
-
/* OPA 16B Header fields */
58
-
#define OPA_16B_LID_MASK 0xFFFFFull
59
-
#define OPA_16B_SLID_HIGH_SHFT 8
60
-
#define OPA_16B_SLID_MASK 0xF00ull
61
-
#define OPA_16B_DLID_MASK 0xF000ull
62
-
#define OPA_16B_DLID_HIGH_SHFT 12
63
-
#define OPA_16B_LEN_SHFT 20
64
-
#define OPA_16B_SC_SHFT 20
65
-
#define OPA_16B_RC_SHFT 25
66
-
#define OPA_16B_PKEY_SHFT 16
67
-
68
-
#define OPA_VNIC_L4_HDR_SHFT 16
69
-
70
-
/* L2+L4 hdr len is 20 bytes (5 quad words) */
71
-
#define OPA_VNIC_HDR_QW_LEN 5
72
-
73
-
static inline void opa_vnic_make_header(u8 *hdr, u32 slid, u32 dlid, u16 len,
74
-
u16 pkey, u16 entropy, u8 sc, u8 rc,
75
-
u8 l4_type, u16 l4_hdr)
76
-
{
77
-
/* h[1]: LT=1, 16B L2=10 */
78
-
u32 h[OPA_VNIC_HDR_QW_LEN] = {0, 0xc0000000, 0, 0, 0};
79
-
80
-
h[2] = l4_type;
81
-
h[3] = entropy;
82
-
h[4] = l4_hdr << OPA_VNIC_L4_HDR_SHFT;
83
-
84
-
/* Extract and set 4 upper bits and 20 lower bits of the lids */
85
-
h[0] |= (slid & OPA_16B_LID_MASK);
86
-
h[2] |= ((slid >> (20 - OPA_16B_SLID_HIGH_SHFT)) & OPA_16B_SLID_MASK);
87
-
88
-
h[1] |= (dlid & OPA_16B_LID_MASK);
89
-
h[2] |= ((dlid >> (20 - OPA_16B_DLID_HIGH_SHFT)) & OPA_16B_DLID_MASK);
90
-
91
-
h[0] |= (len << OPA_16B_LEN_SHFT);
92
-
h[1] |= (rc << OPA_16B_RC_SHFT);
93
-
h[1] |= (sc << OPA_16B_SC_SHFT);
94
-
h[2] |= ((u32)pkey << OPA_16B_PKEY_SHFT);
95
-
96
-
memcpy(hdr, h, OPA_VNIC_HDR_LEN);
97
-
}
98
-
99
-
/*
100
-
* Using a simple hash table for mac table implementation with the last octet
101
-
* of mac address as a key.
102
-
*/
103
-
static void opa_vnic_free_mac_tbl(struct hlist_head *mactbl)
104
-
{
105
-
struct opa_vnic_mac_tbl_node *node;
106
-
struct hlist_node *tmp;
107
-
int bkt;
108
-
109
-
if (!mactbl)
110
-
return;
111
-
112
-
vnic_hash_for_each_safe(mactbl, bkt, tmp, node, hlist) {
113
-
hash_del(&node->hlist);
114
-
kfree(node);
115
-
}
116
-
kfree(mactbl);
117
-
}
118
-
119
-
static struct hlist_head *opa_vnic_alloc_mac_tbl(void)
120
-
{
121
-
u32 size = sizeof(struct hlist_head) * OPA_VNIC_MAC_TBL_SIZE;
122
-
struct hlist_head *mactbl;
123
-
124
-
mactbl = kzalloc(size, GFP_KERNEL);
125
-
if (!mactbl)
126
-
return ERR_PTR(-ENOMEM);
127
-
128
-
vnic_hash_init(mactbl);
129
-
return mactbl;
130
-
}
131
-
132
-
/* opa_vnic_release_mac_tbl - empty and free the mac table */
133
-
void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter)
134
-
{
135
-
struct hlist_head *mactbl;
136
-
137
-
mutex_lock(&adapter->mactbl_lock);
138
-
mactbl = rcu_access_pointer(adapter->mactbl);
139
-
rcu_assign_pointer(adapter->mactbl, NULL);
140
-
synchronize_rcu();
141
-
opa_vnic_free_mac_tbl(mactbl);
142
-
adapter->info.vport.mac_tbl_digest = 0;
143
-
mutex_unlock(&adapter->mactbl_lock);
144
-
}
145
-
146
-
/*
147
-
* opa_vnic_query_mac_tbl - query the mac table for a section
148
-
*
149
-
* This function implements query of specific function of the mac table.
150
-
* The function also expects the requested range to be valid.
151
-
*/
152
-
void opa_vnic_query_mac_tbl(struct opa_vnic_adapter *adapter,
153
-
struct opa_veswport_mactable *tbl)
154
-
{
155
-
struct opa_vnic_mac_tbl_node *node;
156
-
struct hlist_head *mactbl;
157
-
int bkt;
158
-
u16 loffset, lnum_entries;
159
-
160
-
rcu_read_lock();
161
-
mactbl = rcu_dereference(adapter->mactbl);
162
-
if (!mactbl)
163
-
goto get_mac_done;
164
-
165
-
loffset = be16_to_cpu(tbl->offset);
166
-
lnum_entries = be16_to_cpu(tbl->num_entries);
167
-
168
-
vnic_hash_for_each(mactbl, bkt, node, hlist) {
169
-
struct __opa_vnic_mactable_entry *nentry = &node->entry;
170
-
struct opa_veswport_mactable_entry *entry;
171
-
172
-
if ((node->index < loffset) ||
173
-
(node->index >= (loffset + lnum_entries)))
174
-
continue;
175
-
176
-
/* populate entry in the tbl corresponding to the index */
177
-
entry = &tbl->tbl_entries[node->index - loffset];
178
-
memcpy(entry->mac_addr, nentry->mac_addr,
179
-
ARRAY_SIZE(entry->mac_addr));
180
-
memcpy(entry->mac_addr_mask, nentry->mac_addr_mask,
181
-
ARRAY_SIZE(entry->mac_addr_mask));
182
-
entry->dlid_sd = cpu_to_be32(nentry->dlid_sd);
183
-
}
184
-
tbl->mac_tbl_digest = cpu_to_be32(adapter->info.vport.mac_tbl_digest);
185
-
get_mac_done:
186
-
rcu_read_unlock();
187
-
}
188
-
189
-
/*
190
-
* opa_vnic_update_mac_tbl - update mac table section
191
-
*
192
-
* This function updates the specified section of the mac table.
193
-
* The procedure includes following steps.
194
-
* - Allocate a new mac (hash) table.
195
-
* - Add the specified entries to the new table.
196
-
* (except the ones that are requested to be deleted).
197
-
* - Add all the other entries from the old mac table.
198
-
* - If there is a failure, free the new table and return.
199
-
* - Switch to the new table.
200
-
* - Free the old table and return.
201
-
*
202
-
* The function also expects the requested range to be valid.
203
-
*/
204
-
int opa_vnic_update_mac_tbl(struct opa_vnic_adapter *adapter,
205
-
struct opa_veswport_mactable *tbl)
206
-
{
207
-
struct opa_vnic_mac_tbl_node *node, *new_node;
208
-
struct hlist_head *new_mactbl, *old_mactbl;
209
-
int i, bkt, rc = 0;
210
-
u8 key;
211
-
u16 loffset, lnum_entries;
212
-
213
-
mutex_lock(&adapter->mactbl_lock);
214
-
/* allocate new mac table */
215
-
new_mactbl = opa_vnic_alloc_mac_tbl();
216
-
if (IS_ERR(new_mactbl)) {
217
-
mutex_unlock(&adapter->mactbl_lock);
218
-
return PTR_ERR(new_mactbl);
219
-
}
220
-
221
-
loffset = be16_to_cpu(tbl->offset);
222
-
lnum_entries = be16_to_cpu(tbl->num_entries);
223
-
224
-
/* add updated entries to the new mac table */
225
-
for (i = 0; i < lnum_entries; i++) {
226
-
struct __opa_vnic_mactable_entry *nentry;
227
-
struct opa_veswport_mactable_entry *entry =
228
-
&tbl->tbl_entries[i];
229
-
u8 *mac_addr = entry->mac_addr;
230
-
u8 empty_mac[ETH_ALEN] = { 0 };
231
-
232
-
v_dbg("new mac entry %4d: %02x:%02x:%02x:%02x:%02x:%02x %x\n",
233
-
loffset + i, mac_addr[0], mac_addr[1], mac_addr[2],
234
-
mac_addr[3], mac_addr[4], mac_addr[5],
235
-
entry->dlid_sd);
236
-
237
-
/* if the entry is being removed, do not add it */
238
-
if (!memcmp(mac_addr, empty_mac, ARRAY_SIZE(empty_mac)))
239
-
continue;
240
-
241
-
node = kzalloc_obj(*node);
242
-
if (!node) {
243
-
rc = -ENOMEM;
244
-
goto updt_done;
245
-
}
246
-
247
-
node->index = loffset + i;
248
-
nentry = &node->entry;
249
-
memcpy(nentry->mac_addr, entry->mac_addr,
250
-
ARRAY_SIZE(nentry->mac_addr));
251
-
memcpy(nentry->mac_addr_mask, entry->mac_addr_mask,
252
-
ARRAY_SIZE(nentry->mac_addr_mask));
253
-
nentry->dlid_sd = be32_to_cpu(entry->dlid_sd);
254
-
key = node->entry.mac_addr[OPA_VNIC_MAC_HASH_IDX];
255
-
vnic_hash_add(new_mactbl, &node->hlist, key);
256
-
}
257
-
258
-
/* add other entries from current mac table to new mac table */
259
-
old_mactbl = rcu_access_pointer(adapter->mactbl);
260
-
if (!old_mactbl)
261
-
goto switch_tbl;
262
-
263
-
vnic_hash_for_each(old_mactbl, bkt, node, hlist) {
264
-
if ((node->index >= loffset) &&
265
-
(node->index < (loffset + lnum_entries)))
266
-
continue;
267
-
268
-
new_node = kzalloc_obj(*new_node);
269
-
if (!new_node) {
270
-
rc = -ENOMEM;
271
-
goto updt_done;
272
-
}
273
-
274
-
new_node->index = node->index;
275
-
memcpy(&new_node->entry, &node->entry, sizeof(node->entry));
276
-
key = new_node->entry.mac_addr[OPA_VNIC_MAC_HASH_IDX];
277
-
vnic_hash_add(new_mactbl, &new_node->hlist, key);
278
-
}
279
-
280
-
switch_tbl:
281
-
/* switch to new table */
282
-
rcu_assign_pointer(adapter->mactbl, new_mactbl);
283
-
synchronize_rcu();
284
-
285
-
adapter->info.vport.mac_tbl_digest = be32_to_cpu(tbl->mac_tbl_digest);
286
-
updt_done:
287
-
/* upon failure, free the new table; otherwise, free the old table */
288
-
if (rc)
289
-
opa_vnic_free_mac_tbl(new_mactbl);
290
-
else
291
-
opa_vnic_free_mac_tbl(old_mactbl);
292
-
293
-
mutex_unlock(&adapter->mactbl_lock);
294
-
return rc;
295
-
}
296
-
297
-
/* opa_vnic_chk_mac_tbl - check mac table for dlid */
298
-
static uint32_t opa_vnic_chk_mac_tbl(struct opa_vnic_adapter *adapter,
299
-
struct ethhdr *mac_hdr)
300
-
{
301
-
struct opa_vnic_mac_tbl_node *node;
302
-
struct hlist_head *mactbl;
303
-
u32 dlid = 0;
304
-
u8 key;
305
-
306
-
rcu_read_lock();
307
-
mactbl = rcu_dereference(adapter->mactbl);
308
-
if (unlikely(!mactbl))
309
-
goto chk_done;
310
-
311
-
key = mac_hdr->h_dest[OPA_VNIC_MAC_HASH_IDX];
312
-
vnic_hash_for_each_possible(mactbl, node, hlist, key) {
313
-
struct __opa_vnic_mactable_entry *entry = &node->entry;
314
-
315
-
/* if related to source mac, skip */
316
-
if (unlikely(OPA_VNIC_DLID_SD_IS_SRC_MAC(entry->dlid_sd)))
317
-
continue;
318
-
319
-
if (!memcmp(node->entry.mac_addr, mac_hdr->h_dest,
320
-
ARRAY_SIZE(node->entry.mac_addr))) {
321
-
/* mac address found */
322
-
dlid = OPA_VNIC_DLID_SD_GET_DLID(node->entry.dlid_sd);
323
-
break;
324
-
}
325
-
}
326
-
327
-
chk_done:
328
-
rcu_read_unlock();
329
-
return dlid;
330
-
}
331
-
332
-
/* opa_vnic_get_dlid - find and return the DLID */
333
-
static uint32_t opa_vnic_get_dlid(struct opa_vnic_adapter *adapter,
334
-
struct sk_buff *skb, u8 def_port)
335
-
{
336
-
struct __opa_veswport_info *info = &adapter->info;
337
-
struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
338
-
u32 dlid;
339
-
340
-
dlid = opa_vnic_chk_mac_tbl(adapter, mac_hdr);
341
-
if (dlid)
342
-
return dlid;
343
-
344
-
if (is_multicast_ether_addr(mac_hdr->h_dest)) {
345
-
dlid = info->vesw.u_mcast_dlid;
346
-
} else {
347
-
if (is_local_ether_addr(mac_hdr->h_dest)) {
348
-
dlid = ((uint32_t)mac_hdr->h_dest[5] << 16) |
349
-
((uint32_t)mac_hdr->h_dest[4] << 8) |
350
-
mac_hdr->h_dest[3];
351
-
if (unlikely(!dlid))
352
-
v_warn("Null dlid in MAC address\n");
353
-
} else if (def_port != OPA_VNIC_INVALID_PORT) {
354
-
if (def_port < OPA_VESW_MAX_NUM_DEF_PORT)
355
-
dlid = info->vesw.u_ucast_dlid[def_port];
356
-
}
357
-
}
358
-
359
-
return dlid;
360
-
}
361
-
362
-
/* opa_vnic_get_sc - return the service class */
363
-
static u8 opa_vnic_get_sc(struct __opa_veswport_info *info,
364
-
struct sk_buff *skb)
365
-
{
366
-
struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
367
-
u16 vlan_tci;
368
-
u8 sc;
369
-
370
-
if (!__vlan_get_tag(skb, &vlan_tci)) {
371
-
u8 pcp = OPA_VNIC_VLAN_PCP(vlan_tci);
372
-
373
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
374
-
sc = info->vport.pcp_to_sc_mc[pcp];
375
-
else
376
-
sc = info->vport.pcp_to_sc_uc[pcp];
377
-
} else {
378
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
379
-
sc = info->vport.non_vlan_sc_mc;
380
-
else
381
-
sc = info->vport.non_vlan_sc_uc;
382
-
}
383
-
384
-
return sc;
385
-
}
386
-
387
-
u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb)
388
-
{
389
-
struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
390
-
struct __opa_veswport_info *info = &adapter->info;
391
-
u8 vl;
392
-
393
-
if (skb_vlan_tag_present(skb)) {
394
-
u8 pcp = skb_vlan_tag_get(skb) >> VLAN_PRIO_SHIFT;
395
-
396
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
397
-
vl = info->vport.pcp_to_vl_mc[pcp];
398
-
else
399
-
vl = info->vport.pcp_to_vl_uc[pcp];
400
-
} else {
401
-
if (is_multicast_ether_addr(mac_hdr->h_dest))
402
-
vl = info->vport.non_vlan_vl_mc;
403
-
else
404
-
vl = info->vport.non_vlan_vl_uc;
405
-
}
406
-
407
-
return vl;
408
-
}
409
-
410
-
/* opa_vnic_get_rc - return the routing control */
411
-
static u8 opa_vnic_get_rc(struct __opa_veswport_info *info,
412
-
struct sk_buff *skb)
413
-
{
414
-
u8 proto, rout_ctrl;
415
-
416
-
switch (vlan_get_protocol(skb)) {
417
-
case htons(ETH_P_IPV6):
418
-
proto = ipv6_hdr(skb)->nexthdr;
419
-
if (proto == IPPROTO_TCP)
420
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
421
-
IPV6_TCP);
422
-
else if (proto == IPPROTO_UDP)
423
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
424
-
IPV6_UDP);
425
-
else
426
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV6);
427
-
break;
428
-
case htons(ETH_P_IP):
429
-
proto = ip_hdr(skb)->protocol;
430
-
if (proto == IPPROTO_TCP)
431
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
432
-
IPV4_TCP);
433
-
else if (proto == IPPROTO_UDP)
434
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc,
435
-
IPV4_UDP);
436
-
else
437
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, IPV4);
438
-
break;
439
-
default:
440
-
rout_ctrl = OPA_VNIC_ENCAP_RC_EXT(info->vesw.rc, DEFAULT);
441
-
}
442
-
443
-
return rout_ctrl;
444
-
}
445
-
446
-
/* opa_vnic_calc_entropy - calculate the packet entropy */
447
-
u8 opa_vnic_calc_entropy(struct sk_buff *skb)
448
-
{
449
-
u32 hash = skb_get_hash(skb);
450
-
451
-
/* store XOR of all bytes in lower 8 bits */
452
-
hash ^= hash >> 8;
453
-
hash ^= hash >> 16;
454
-
455
-
/* return lower 8 bits as entropy */
456
-
return (u8)(hash & 0xFF);
457
-
}
458
-
459
-
/* opa_vnic_get_def_port - get default port based on entropy */
460
-
static inline u8 opa_vnic_get_def_port(struct opa_vnic_adapter *adapter,
461
-
u8 entropy)
462
-
{
463
-
u8 flow_id;
464
-
465
-
/* Add the upper and lower 4-bits of entropy to get the flow id */
466
-
flow_id = ((entropy & 0xf) + (entropy >> 4));
467
-
return adapter->flow_tbl[flow_id & (OPA_VNIC_FLOW_TBL_SIZE - 1)];
468
-
}
469
-
470
-
/* Calculate packet length including OPA header, crc and padding */
471
-
static inline int opa_vnic_wire_length(struct sk_buff *skb)
472
-
{
473
-
u32 pad_len;
474
-
475
-
/* padding for 8 bytes size alignment */
476
-
pad_len = -(skb->len + OPA_VNIC_ICRC_TAIL_LEN) & 0x7;
477
-
pad_len += OPA_VNIC_ICRC_TAIL_LEN;
478
-
479
-
return (skb->len + pad_len) >> 3;
480
-
}
481
-
482
-
/* opa_vnic_encap_skb - encapsulate skb packet with OPA header and meta data */
483
-
void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb)
484
-
{
485
-
struct __opa_veswport_info *info = &adapter->info;
486
-
struct opa_vnic_skb_mdata *mdata;
487
-
u8 def_port, sc, rc, entropy, *hdr;
488
-
u16 len, l4_hdr;
489
-
u32 dlid;
490
-
491
-
hdr = skb_push(skb, OPA_VNIC_HDR_LEN);
492
-
493
-
entropy = opa_vnic_calc_entropy(skb);
494
-
def_port = opa_vnic_get_def_port(adapter, entropy);
495
-
len = opa_vnic_wire_length(skb);
496
-
dlid = opa_vnic_get_dlid(adapter, skb, def_port);
497
-
sc = opa_vnic_get_sc(info, skb);
498
-
rc = opa_vnic_get_rc(info, skb);
499
-
l4_hdr = info->vesw.vesw_id;
500
-
501
-
mdata = skb_push(skb, sizeof(*mdata));
502
-
mdata->vl = opa_vnic_get_vl(adapter, skb);
503
-
mdata->entropy = entropy;
504
-
mdata->flags = 0;
505
-
if (unlikely(!dlid)) {
506
-
mdata->flags = OPA_VNIC_SKB_MDATA_ENCAP_ERR;
507
-
return;
508
-
}
509
-
510
-
opa_vnic_make_header(hdr, info->vport.encap_slid, dlid, len,
511
-
info->vesw.pkey, entropy, sc, rc,
512
-
OPA_VNIC_L4_ETHR, l4_hdr);
513
-
}
-524
drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
-524
drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
···
1
-
#ifndef _OPA_VNIC_ENCAP_H
2
-
#define _OPA_VNIC_ENCAP_H
3
-
/*
4
-
* Copyright(c) 2017 Intel Corporation.
5
-
*
6
-
* This file is provided under a dual BSD/GPLv2 license. When using or
7
-
* redistributing this file, you may do so under either license.
8
-
*
9
-
* GPL LICENSE SUMMARY
10
-
*
11
-
* This program is free software; you can redistribute it and/or modify
12
-
* it under the terms of version 2 of the GNU General Public License as
13
-
* published by the Free Software Foundation.
14
-
*
15
-
* This program is distributed in the hope that it will be useful, but
16
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
17
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18
-
* General Public License for more details.
19
-
*
20
-
* BSD LICENSE
21
-
*
22
-
* Redistribution and use in source and binary forms, with or without
23
-
* modification, are permitted provided that the following conditions
24
-
* are met:
25
-
*
26
-
* - Redistributions of source code must retain the above copyright
27
-
* notice, this list of conditions and the following disclaimer.
28
-
* - Redistributions in binary form must reproduce the above copyright
29
-
* notice, this list of conditions and the following disclaimer in
30
-
* the documentation and/or other materials provided with the
31
-
* distribution.
32
-
* - Neither the name of Intel Corporation nor the names of its
33
-
* contributors may be used to endorse or promote products derived
34
-
* from this software without specific prior written permission.
35
-
*
36
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
37
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
38
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
39
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
40
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
41
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
42
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
43
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
44
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
45
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
46
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
47
-
*
48
-
*/
49
-
50
-
/*
51
-
* This file contains all OPA VNIC declaration required for encapsulation
52
-
* and decapsulation of Ethernet packets
53
-
*/
54
-
55
-
#include <linux/types.h>
56
-
#include <rdma/ib_mad.h>
57
-
58
-
/* EMA class version */
59
-
#define OPA_EMA_CLASS_VERSION 0x80
60
-
61
-
/*
62
-
* Define the Intel vendor management class for OPA
63
-
* ETHERNET MANAGEMENT
64
-
*/
65
-
#define OPA_MGMT_CLASS_INTEL_EMA 0x34
66
-
67
-
/* EM attribute IDs */
68
-
#define OPA_EM_ATTR_CLASS_PORT_INFO 0x0001
69
-
#define OPA_EM_ATTR_VESWPORT_INFO 0x0011
70
-
#define OPA_EM_ATTR_VESWPORT_MAC_ENTRIES 0x0012
71
-
#define OPA_EM_ATTR_IFACE_UCAST_MACS 0x0013
72
-
#define OPA_EM_ATTR_IFACE_MCAST_MACS 0x0014
73
-
#define OPA_EM_ATTR_DELETE_VESW 0x0015
74
-
#define OPA_EM_ATTR_VESWPORT_SUMMARY_COUNTERS 0x0020
75
-
#define OPA_EM_ATTR_VESWPORT_ERROR_COUNTERS 0x0022
76
-
77
-
/* VNIC configured and operational state values */
78
-
#define OPA_VNIC_STATE_DROP_ALL 0x1
79
-
#define OPA_VNIC_STATE_FORWARDING 0x3
80
-
81
-
#define OPA_VESW_MAX_NUM_DEF_PORT 16
82
-
#define OPA_VNIC_MAX_NUM_PCP 8
83
-
84
-
#define OPA_VNIC_EMA_DATA (OPA_MGMT_MAD_SIZE - IB_MGMT_VENDOR_HDR)
85
-
86
-
/* Defines for vendor specific notice(trap) attributes */
87
-
#define OPA_INTEL_EMA_NOTICE_TYPE_INFO 0x04
88
-
89
-
/* INTEL OUI */
90
-
#define INTEL_OUI_1 0x00
91
-
#define INTEL_OUI_2 0x06
92
-
#define INTEL_OUI_3 0x6a
93
-
94
-
/* Trap opcodes sent from VNIC */
95
-
#define OPA_VESWPORT_TRAP_IFACE_UCAST_MAC_CHANGE 0x1
96
-
#define OPA_VESWPORT_TRAP_IFACE_MCAST_MAC_CHANGE 0x2
97
-
#define OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE 0x3
98
-
99
-
#define OPA_VNIC_DLID_SD_IS_SRC_MAC(dlid_sd) (!!((dlid_sd) & 0x20))
100
-
#define OPA_VNIC_DLID_SD_GET_DLID(dlid_sd) ((dlid_sd) >> 8)
101
-
102
-
/* VNIC Ethernet link status */
103
-
#define OPA_VNIC_ETH_LINK_UP 1
104
-
#define OPA_VNIC_ETH_LINK_DOWN 2
105
-
106
-
/* routing control */
107
-
#define OPA_VNIC_ENCAP_RC_DEFAULT 0
108
-
#define OPA_VNIC_ENCAP_RC_IPV4 4
109
-
#define OPA_VNIC_ENCAP_RC_IPV4_UDP 8
110
-
#define OPA_VNIC_ENCAP_RC_IPV4_TCP 12
111
-
#define OPA_VNIC_ENCAP_RC_IPV6 16
112
-
#define OPA_VNIC_ENCAP_RC_IPV6_TCP 20
113
-
#define OPA_VNIC_ENCAP_RC_IPV6_UDP 24
114
-
115
-
#define OPA_VNIC_ENCAP_RC_EXT(w, b) (((w) >> OPA_VNIC_ENCAP_RC_ ## b) & 0x7)
116
-
117
-
/**
118
-
* struct opa_vesw_info - OPA vnic switch information
119
-
* @fabric_id: 10-bit fabric id
120
-
* @vesw_id: 12-bit virtual ethernet switch id
121
-
* @rsvd0: reserved bytes
122
-
* @def_port_mask: bitmask of default ports
123
-
* @rsvd1: reserved bytes
124
-
* @pkey: partition key
125
-
* @rsvd2: reserved bytes
126
-
* @u_mcast_dlid: unknown multicast dlid
127
-
* @u_ucast_dlid: array of unknown unicast dlids
128
-
* @rsvd3: reserved bytes
129
-
* @rc: routing control
130
-
* @eth_mtu: Ethernet MTU
131
-
* @rsvd4: reserved bytes
132
-
*/
133
-
struct opa_vesw_info {
134
-
__be16 fabric_id;
135
-
__be16 vesw_id;
136
-
137
-
u8 rsvd0[6];
138
-
__be16 def_port_mask;
139
-
140
-
u8 rsvd1[2];
141
-
__be16 pkey;
142
-
143
-
u8 rsvd2[4];
144
-
__be32 u_mcast_dlid;
145
-
__be32 u_ucast_dlid[OPA_VESW_MAX_NUM_DEF_PORT];
146
-
147
-
__be32 rc;
148
-
149
-
u8 rsvd3[56];
150
-
__be16 eth_mtu;
151
-
u8 rsvd4[2];
152
-
} __packed;
153
-
154
-
/**
155
-
* struct opa_per_veswport_info - OPA vnic per port information
156
-
* @port_num: port number
157
-
* @eth_link_status: current ethernet link state
158
-
* @rsvd0: reserved bytes
159
-
* @base_mac_addr: base mac address
160
-
* @config_state: configured port state
161
-
* @oper_state: operational port state
162
-
* @max_mac_tbl_ent: max number of mac table entries
163
-
* @max_smac_ent: max smac entries in mac table
164
-
* @mac_tbl_digest: mac table digest
165
-
* @rsvd1: reserved bytes
166
-
* @encap_slid: base slid for the port
167
-
* @pcp_to_sc_uc: sc by pcp index for unicast ethernet packets
168
-
* @pcp_to_vl_uc: vl by pcp index for unicast ethernet packets
169
-
* @pcp_to_sc_mc: sc by pcp index for multicast ethernet packets
170
-
* @pcp_to_vl_mc: vl by pcp index for multicast ethernet packets
171
-
* @non_vlan_sc_uc: sc for non-vlan unicast ethernet packets
172
-
* @non_vlan_vl_uc: vl for non-vlan unicast ethernet packets
173
-
* @non_vlan_sc_mc: sc for non-vlan multicast ethernet packets
174
-
* @non_vlan_vl_mc: vl for non-vlan multicast ethernet packets
175
-
* @rsvd2: reserved bytes
176
-
* @uc_macs_gen_count: generation count for unicast macs list
177
-
* @mc_macs_gen_count: generation count for multicast macs list
178
-
* @rsvd3: reserved bytes
179
-
*/
180
-
struct opa_per_veswport_info {
181
-
__be32 port_num;
182
-
183
-
u8 eth_link_status;
184
-
u8 rsvd0[3];
185
-
186
-
u8 base_mac_addr[ETH_ALEN];
187
-
u8 config_state;
188
-
u8 oper_state;
189
-
190
-
__be16 max_mac_tbl_ent;
191
-
__be16 max_smac_ent;
192
-
__be32 mac_tbl_digest;
193
-
u8 rsvd1[4];
194
-
195
-
__be32 encap_slid;
196
-
197
-
u8 pcp_to_sc_uc[OPA_VNIC_MAX_NUM_PCP];
198
-
u8 pcp_to_vl_uc[OPA_VNIC_MAX_NUM_PCP];
199
-
u8 pcp_to_sc_mc[OPA_VNIC_MAX_NUM_PCP];
200
-
u8 pcp_to_vl_mc[OPA_VNIC_MAX_NUM_PCP];
201
-
202
-
u8 non_vlan_sc_uc;
203
-
u8 non_vlan_vl_uc;
204
-
u8 non_vlan_sc_mc;
205
-
u8 non_vlan_vl_mc;
206
-
207
-
u8 rsvd2[48];
208
-
209
-
__be16 uc_macs_gen_count;
210
-
__be16 mc_macs_gen_count;
211
-
212
-
u8 rsvd3[8];
213
-
} __packed;
214
-
215
-
/**
216
-
* struct opa_veswport_info - OPA vnic port information
217
-
* @vesw: OPA vnic switch information
218
-
* @vport: OPA vnic per port information
219
-
*
220
-
* On host, each of the virtual ethernet ports belongs
221
-
* to a different virtual ethernet switches.
222
-
*/
223
-
struct opa_veswport_info {
224
-
struct opa_vesw_info vesw;
225
-
struct opa_per_veswport_info vport;
226
-
};
227
-
228
-
/**
229
-
* struct opa_veswport_mactable_entry - single entry in the forwarding table
230
-
* @mac_addr: MAC address
231
-
* @mac_addr_mask: MAC address bit mask
232
-
* @dlid_sd: Matching DLID and side data
233
-
*
234
-
* On the host each virtual ethernet port will have
235
-
* a forwarding table. These tables are used to
236
-
* map a MAC to a LID and other data. For more
237
-
* details see struct opa_veswport_mactable_entries.
238
-
* This is the structure of a single mactable entry
239
-
*/
240
-
struct opa_veswport_mactable_entry {
241
-
u8 mac_addr[ETH_ALEN];
242
-
u8 mac_addr_mask[ETH_ALEN];
243
-
__be32 dlid_sd;
244
-
} __packed;
245
-
246
-
/**
247
-
* struct opa_veswport_mactable - Forwarding table array
248
-
* @offset: mac table starting offset
249
-
* @num_entries: Number of entries to get or set
250
-
* @mac_tbl_digest: mac table digest
251
-
* @tbl_entries: Array of table entries
252
-
*
253
-
* The EM sends down this structure in a MAD indicating
254
-
* the starting offset in the forwarding table that this
255
-
* entry is to be loaded into and the number of entries
256
-
* that that this MAD instance contains
257
-
* The mac_tbl_digest has been added to this MAD structure. It will be set by
258
-
* the EM and it will be used by the EM to check if there are any
259
-
* discrepancies with this value and the value
260
-
* maintained by the EM in the case of VNIC port being deleted or unloaded
261
-
* A new instantiation of a VNIC will always have a value of zero.
262
-
* This value is stored as part of the vnic adapter structure and will be
263
-
* accessed by the GET and SET routines for both the mactable entries and the
264
-
* veswport info.
265
-
*/
266
-
struct opa_veswport_mactable {
267
-
__be16 offset;
268
-
__be16 num_entries;
269
-
__be32 mac_tbl_digest;
270
-
struct opa_veswport_mactable_entry tbl_entries[];
271
-
} __packed;
272
-
273
-
/**
274
-
* struct opa_veswport_summary_counters - summary counters
275
-
* @vp_instance: vport instance on the OPA port
276
-
* @vesw_id: virtual ethernet switch id
277
-
* @veswport_num: virtual ethernet switch port number
278
-
* @tx_errors: transmit errors
279
-
* @rx_errors: receive errors
280
-
* @tx_packets: transmit packets
281
-
* @rx_packets: receive packets
282
-
* @tx_bytes: transmit bytes
283
-
* @rx_bytes: receive bytes
284
-
* @tx_unicast: unicast packets transmitted
285
-
* @tx_mcastbcast: multicast/broadcast packets transmitted
286
-
* @tx_untagged: non-vlan packets transmitted
287
-
* @tx_vlan: vlan packets transmitted
288
-
* @tx_64_size: transmit packet length is 64 bytes
289
-
* @tx_65_127: transmit packet length is >=65 and < 127 bytes
290
-
* @tx_128_255: transmit packet length is >=128 and < 255 bytes
291
-
* @tx_256_511: transmit packet length is >=256 and < 511 bytes
292
-
* @tx_512_1023: transmit packet length is >=512 and < 1023 bytes
293
-
* @tx_1024_1518: transmit packet length is >=1024 and < 1518 bytes
294
-
* @tx_1519_max: transmit packet length >= 1519 bytes
295
-
* @rx_unicast: unicast packets received
296
-
* @rx_mcastbcast: multicast/broadcast packets received
297
-
* @rx_untagged: non-vlan packets received
298
-
* @rx_vlan: vlan packets received
299
-
* @rx_64_size: received packet length is 64 bytes
300
-
* @rx_65_127: received packet length is >=65 and < 127 bytes
301
-
* @rx_128_255: received packet length is >=128 and < 255 bytes
302
-
* @rx_256_511: received packet length is >=256 and < 511 bytes
303
-
* @rx_512_1023: received packet length is >=512 and < 1023 bytes
304
-
* @rx_1024_1518: received packet length is >=1024 and < 1518 bytes
305
-
* @rx_1519_max: received packet length >= 1519 bytes
306
-
* @reserved: reserved bytes
307
-
*
308
-
* All the above are counters of corresponding conditions.
309
-
*/
310
-
struct opa_veswport_summary_counters {
311
-
__be16 vp_instance;
312
-
__be16 vesw_id;
313
-
__be32 veswport_num;
314
-
315
-
__be64 tx_errors;
316
-
__be64 rx_errors;
317
-
__be64 tx_packets;
318
-
__be64 rx_packets;
319
-
__be64 tx_bytes;
320
-
__be64 rx_bytes;
321
-
322
-
__be64 tx_unicast;
323
-
__be64 tx_mcastbcast;
324
-
325
-
__be64 tx_untagged;
326
-
__be64 tx_vlan;
327
-
328
-
__be64 tx_64_size;
329
-
__be64 tx_65_127;
330
-
__be64 tx_128_255;
331
-
__be64 tx_256_511;
332
-
__be64 tx_512_1023;
333
-
__be64 tx_1024_1518;
334
-
__be64 tx_1519_max;
335
-
336
-
__be64 rx_unicast;
337
-
__be64 rx_mcastbcast;
338
-
339
-
__be64 rx_untagged;
340
-
__be64 rx_vlan;
341
-
342
-
__be64 rx_64_size;
343
-
__be64 rx_65_127;
344
-
__be64 rx_128_255;
345
-
__be64 rx_256_511;
346
-
__be64 rx_512_1023;
347
-
__be64 rx_1024_1518;
348
-
__be64 rx_1519_max;
349
-
350
-
__be64 reserved[16];
351
-
} __packed;
352
-
353
-
/**
354
-
* struct opa_veswport_error_counters - error counters
355
-
* @vp_instance: vport instance on the OPA port
356
-
* @vesw_id: virtual ethernet switch id
357
-
* @veswport_num: virtual ethernet switch port number
358
-
* @tx_errors: transmit errors
359
-
* @rx_errors: receive errors
360
-
* @rsvd0: reserved bytes
361
-
* @tx_smac_filt: smac filter errors
362
-
* @rsvd1: reserved bytes
363
-
* @rsvd2: reserved bytes
364
-
* @rsvd3: reserved bytes
365
-
* @tx_dlid_zero: transmit packets with invalid dlid
366
-
* @rsvd4: reserved bytes
367
-
* @tx_logic: other transmit errors
368
-
* @rsvd5: reserved bytes
369
-
* @tx_drop_state: packet tansmission in non-forward port state
370
-
* @rx_bad_veswid: received packet with invalid vesw id
371
-
* @rsvd6: reserved bytes
372
-
* @rx_runt: received ethernet packet with length < 64 bytes
373
-
* @rx_oversize: received ethernet packet with length > MTU size
374
-
* @rsvd7: reserved bytes
375
-
* @rx_eth_down: received packets when interface is down
376
-
* @rx_drop_state: received packets in non-forwarding port state
377
-
* @rx_logic: other receive errors
378
-
* @rsvd8: reserved bytes
379
-
* @rsvd9: reserved bytes
380
-
*
381
-
* All the above are counters of corresponding error conditions.
382
-
*/
383
-
struct opa_veswport_error_counters {
384
-
__be16 vp_instance;
385
-
__be16 vesw_id;
386
-
__be32 veswport_num;
387
-
388
-
__be64 tx_errors;
389
-
__be64 rx_errors;
390
-
391
-
__be64 rsvd0;
392
-
__be64 tx_smac_filt;
393
-
__be64 rsvd1;
394
-
__be64 rsvd2;
395
-
__be64 rsvd3;
396
-
__be64 tx_dlid_zero;
397
-
__be64 rsvd4;
398
-
__be64 tx_logic;
399
-
__be64 rsvd5;
400
-
__be64 tx_drop_state;
401
-
402
-
__be64 rx_bad_veswid;
403
-
__be64 rsvd6;
404
-
__be64 rx_runt;
405
-
__be64 rx_oversize;
406
-
__be64 rsvd7;
407
-
__be64 rx_eth_down;
408
-
__be64 rx_drop_state;
409
-
__be64 rx_logic;
410
-
__be64 rsvd8;
411
-
412
-
__be64 rsvd9[16];
413
-
} __packed;
414
-
415
-
/**
416
-
* struct opa_veswport_trap - Trap message sent to EM by VNIC
417
-
* @fabric_id: 10 bit fabric id
418
-
* @veswid: 12 bit virtual ethernet switch id
419
-
* @veswportnum: logical port number on the Virtual switch
420
-
* @opaportnum: physical port num (redundant on host)
421
-
* @veswportindex: switch port index on opa port 0 based
422
-
* @opcode: operation
423
-
* @reserved: 32 bit for alignment
424
-
*
425
-
* The VNIC will send trap messages to the Ethernet manager to
426
-
* inform it about changes to the VNIC config, behaviour etc.
427
-
* This is the format of the trap payload.
428
-
*/
429
-
struct opa_veswport_trap {
430
-
__be16 fabric_id;
431
-
__be16 veswid;
432
-
__be32 veswportnum;
433
-
__be16 opaportnum;
434
-
u8 veswportindex;
435
-
u8 opcode;
436
-
__be32 reserved;
437
-
} __packed;
438
-
439
-
/**
440
-
* struct opa_vnic_iface_mac_entry - single entry in the mac list
441
-
* @mac_addr: MAC address
442
-
*/
443
-
struct opa_vnic_iface_mac_entry {
444
-
u8 mac_addr[ETH_ALEN];
445
-
};
446
-
447
-
/**
448
-
* struct opa_veswport_iface_macs - Msg to set globally administered MAC
449
-
* @start_idx: position of first entry (0 based)
450
-
* @num_macs_in_msg: number of MACs in this message
451
-
* @tot_macs_in_lst: The total number of MACs the agent has
452
-
* @gen_count: gen_count to indicate change
453
-
* @entry: The mac list entry
454
-
*
455
-
* Same attribute IDS and attribute modifiers as in locally administered
456
-
* addresses used to set globally administered addresses
457
-
*/
458
-
struct opa_veswport_iface_macs {
459
-
__be16 start_idx;
460
-
__be16 num_macs_in_msg;
461
-
__be16 tot_macs_in_lst;
462
-
__be16 gen_count;
463
-
struct opa_vnic_iface_mac_entry entry[];
464
-
} __packed;
465
-
466
-
/**
467
-
* struct opa_vnic_vema_mad - Generic VEMA MAD
468
-
* @mad_hdr: Generic MAD header
469
-
* @rmpp_hdr: RMPP header for vendor specific MADs
470
-
* @reserved: reserved bytes
471
-
* @oui: Unique org identifier
472
-
* @data: MAD data
473
-
*/
474
-
struct opa_vnic_vema_mad {
475
-
struct ib_mad_hdr mad_hdr;
476
-
struct ib_rmpp_hdr rmpp_hdr;
477
-
u8 reserved;
478
-
u8 oui[3];
479
-
u8 data[OPA_VNIC_EMA_DATA];
480
-
};
481
-
482
-
/**
483
-
* struct opa_vnic_notice_attr - Generic Notice MAD
484
-
* @gen_type: Generic/Specific bit and type of notice
485
-
* @oui_1: Vendor ID byte 1
486
-
* @oui_2: Vendor ID byte 2
487
-
* @oui_3: Vendor ID byte 3
488
-
* @trap_num: Trap number
489
-
* @toggle_count: Notice toggle bit and count value
490
-
* @issuer_lid: Trap issuer's lid
491
-
* @reserved: reserved bytes
492
-
* @issuer_gid: Issuer GID (only if Report method)
493
-
* @raw_data: Trap message body
494
-
*/
495
-
struct opa_vnic_notice_attr {
496
-
u8 gen_type;
497
-
u8 oui_1;
498
-
u8 oui_2;
499
-
u8 oui_3;
500
-
__be16 trap_num;
501
-
__be16 toggle_count;
502
-
__be32 issuer_lid;
503
-
__be32 reserved;
504
-
u8 issuer_gid[16];
505
-
u8 raw_data[64];
506
-
} __packed;
507
-
508
-
/**
509
-
* struct opa_vnic_vema_mad_trap - Generic VEMA MAD Trap
510
-
* @mad_hdr: Generic MAD header
511
-
* @rmpp_hdr: RMPP header for vendor specific MADs
512
-
* @reserved: reserved bytes
513
-
* @oui: Unique org identifier
514
-
* @notice: Notice structure
515
-
*/
516
-
struct opa_vnic_vema_mad_trap {
517
-
struct ib_mad_hdr mad_hdr;
518
-
struct ib_rmpp_hdr rmpp_hdr;
519
-
u8 reserved;
520
-
u8 oui[3];
521
-
struct opa_vnic_notice_attr notice;
522
-
};
523
-
524
-
#endif /* _OPA_VNIC_ENCAP_H */
-183
drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c
-183
drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c
···
1
-
/*
2
-
* Copyright(c) 2017 Intel Corporation.
3
-
*
4
-
* This file is provided under a dual BSD/GPLv2 license. When using or
5
-
* redistributing this file, you may do so under either license.
6
-
*
7
-
* GPL LICENSE SUMMARY
8
-
*
9
-
* This program is free software; you can redistribute it and/or modify
10
-
* it under the terms of version 2 of the GNU General Public License as
11
-
* published by the Free Software Foundation.
12
-
*
13
-
* This program is distributed in the hope that it will be useful, but
14
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
15
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16
-
* General Public License for more details.
17
-
*
18
-
* BSD LICENSE
19
-
*
20
-
* Redistribution and use in source and binary forms, with or without
21
-
* modification, are permitted provided that the following conditions
22
-
* are met:
23
-
*
24
-
* - Redistributions of source code must retain the above copyright
25
-
* notice, this list of conditions and the following disclaimer.
26
-
* - Redistributions in binary form must reproduce the above copyright
27
-
* notice, this list of conditions and the following disclaimer in
28
-
* the documentation and/or other materials provided with the
29
-
* distribution.
30
-
* - Neither the name of Intel Corporation nor the names of its
31
-
* contributors may be used to endorse or promote products derived
32
-
* from this software without specific prior written permission.
33
-
*
34
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45
-
*
46
-
*/
47
-
48
-
/*
49
-
* This file contains OPA VNIC ethtool functions
50
-
*/
51
-
52
-
#include <linux/ethtool.h>
53
-
54
-
#include "opa_vnic_internal.h"
55
-
56
-
enum {NETDEV_STATS, VNIC_STATS};
57
-
58
-
struct vnic_stats {
59
-
char stat_string[ETH_GSTRING_LEN];
60
-
struct {
61
-
int sizeof_stat;
62
-
int stat_offset;
63
-
};
64
-
};
65
-
66
-
#define VNIC_STAT(m) { sizeof_field(struct opa_vnic_stats, m), \
67
-
offsetof(struct opa_vnic_stats, m) }
68
-
69
-
static struct vnic_stats vnic_gstrings_stats[] = {
70
-
/* NETDEV stats */
71
-
{"rx_packets", VNIC_STAT(netstats.rx_packets)},
72
-
{"tx_packets", VNIC_STAT(netstats.tx_packets)},
73
-
{"rx_bytes", VNIC_STAT(netstats.rx_bytes)},
74
-
{"tx_bytes", VNIC_STAT(netstats.tx_bytes)},
75
-
{"rx_errors", VNIC_STAT(netstats.rx_errors)},
76
-
{"tx_errors", VNIC_STAT(netstats.tx_errors)},
77
-
{"rx_dropped", VNIC_STAT(netstats.rx_dropped)},
78
-
{"tx_dropped", VNIC_STAT(netstats.tx_dropped)},
79
-
80
-
/* SUMMARY counters */
81
-
{"tx_unicast", VNIC_STAT(tx_grp.unicast)},
82
-
{"tx_mcastbcast", VNIC_STAT(tx_grp.mcastbcast)},
83
-
{"tx_untagged", VNIC_STAT(tx_grp.untagged)},
84
-
{"tx_vlan", VNIC_STAT(tx_grp.vlan)},
85
-
86
-
{"tx_64_size", VNIC_STAT(tx_grp.s_64)},
87
-
{"tx_65_127", VNIC_STAT(tx_grp.s_65_127)},
88
-
{"tx_128_255", VNIC_STAT(tx_grp.s_128_255)},
89
-
{"tx_256_511", VNIC_STAT(tx_grp.s_256_511)},
90
-
{"tx_512_1023", VNIC_STAT(tx_grp.s_512_1023)},
91
-
{"tx_1024_1518", VNIC_STAT(tx_grp.s_1024_1518)},
92
-
{"tx_1519_max", VNIC_STAT(tx_grp.s_1519_max)},
93
-
94
-
{"rx_unicast", VNIC_STAT(rx_grp.unicast)},
95
-
{"rx_mcastbcast", VNIC_STAT(rx_grp.mcastbcast)},
96
-
{"rx_untagged", VNIC_STAT(rx_grp.untagged)},
97
-
{"rx_vlan", VNIC_STAT(rx_grp.vlan)},
98
-
99
-
{"rx_64_size", VNIC_STAT(rx_grp.s_64)},
100
-
{"rx_65_127", VNIC_STAT(rx_grp.s_65_127)},
101
-
{"rx_128_255", VNIC_STAT(rx_grp.s_128_255)},
102
-
{"rx_256_511", VNIC_STAT(rx_grp.s_256_511)},
103
-
{"rx_512_1023", VNIC_STAT(rx_grp.s_512_1023)},
104
-
{"rx_1024_1518", VNIC_STAT(rx_grp.s_1024_1518)},
105
-
{"rx_1519_max", VNIC_STAT(rx_grp.s_1519_max)},
106
-
107
-
/* ERROR counters */
108
-
{"rx_fifo_errors", VNIC_STAT(netstats.rx_fifo_errors)},
109
-
{"rx_length_errors", VNIC_STAT(netstats.rx_length_errors)},
110
-
111
-
{"tx_fifo_errors", VNIC_STAT(netstats.tx_fifo_errors)},
112
-
{"tx_carrier_errors", VNIC_STAT(netstats.tx_carrier_errors)},
113
-
114
-
{"tx_dlid_zero", VNIC_STAT(tx_dlid_zero)},
115
-
{"tx_drop_state", VNIC_STAT(tx_drop_state)},
116
-
{"rx_drop_state", VNIC_STAT(rx_drop_state)},
117
-
{"rx_oversize", VNIC_STAT(rx_oversize)},
118
-
{"rx_runt", VNIC_STAT(rx_runt)},
119
-
};
120
-
121
-
#define VNIC_STATS_LEN ARRAY_SIZE(vnic_gstrings_stats)
122
-
123
-
/* vnic_get_drvinfo - get driver info */
124
-
static void vnic_get_drvinfo(struct net_device *netdev,
125
-
struct ethtool_drvinfo *drvinfo)
126
-
{
127
-
strscpy(drvinfo->driver, opa_vnic_driver_name, sizeof(drvinfo->driver));
128
-
strscpy(drvinfo->bus_info, dev_name(netdev->dev.parent),
129
-
sizeof(drvinfo->bus_info));
130
-
}
131
-
132
-
/* vnic_get_sset_count - get string set count */
133
-
static int vnic_get_sset_count(struct net_device *netdev, int sset)
134
-
{
135
-
return (sset == ETH_SS_STATS) ? VNIC_STATS_LEN : -EOPNOTSUPP;
136
-
}
137
-
138
-
/* vnic_get_ethtool_stats - get statistics */
139
-
static void vnic_get_ethtool_stats(struct net_device *netdev,
140
-
struct ethtool_stats *stats, u64 *data)
141
-
{
142
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
143
-
struct opa_vnic_stats vstats;
144
-
int i;
145
-
146
-
memset(&vstats, 0, sizeof(vstats));
147
-
spin_lock(&adapter->stats_lock);
148
-
adapter->rn_ops->ndo_get_stats64(netdev, &vstats.netstats);
149
-
spin_unlock(&adapter->stats_lock);
150
-
for (i = 0; i < VNIC_STATS_LEN; i++) {
151
-
char *p = (char *)&vstats + vnic_gstrings_stats[i].stat_offset;
152
-
153
-
data[i] = (vnic_gstrings_stats[i].sizeof_stat ==
154
-
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
155
-
}
156
-
}
157
-
158
-
/* vnic_get_strings - get strings */
159
-
static void vnic_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
160
-
{
161
-
int i;
162
-
163
-
if (stringset != ETH_SS_STATS)
164
-
return;
165
-
166
-
for (i = 0; i < VNIC_STATS_LEN; i++)
167
-
ethtool_puts(&data, vnic_gstrings_stats[i].stat_string);
168
-
}
169
-
170
-
/* ethtool ops */
171
-
static const struct ethtool_ops opa_vnic_ethtool_ops = {
172
-
.get_drvinfo = vnic_get_drvinfo,
173
-
.get_link = ethtool_op_get_link,
174
-
.get_strings = vnic_get_strings,
175
-
.get_sset_count = vnic_get_sset_count,
176
-
.get_ethtool_stats = vnic_get_ethtool_stats,
177
-
};
178
-
179
-
/* opa_vnic_set_ethtool_ops - set ethtool ops */
180
-
void opa_vnic_set_ethtool_ops(struct net_device *netdev)
181
-
{
182
-
netdev->ethtool_ops = &opa_vnic_ethtool_ops;
183
-
}
-329
drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h
-329
drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h
···
1
-
#ifndef _OPA_VNIC_INTERNAL_H
2
-
#define _OPA_VNIC_INTERNAL_H
3
-
/*
4
-
* Copyright(c) 2017 Intel Corporation.
5
-
*
6
-
* This file is provided under a dual BSD/GPLv2 license. When using or
7
-
* redistributing this file, you may do so under either license.
8
-
*
9
-
* GPL LICENSE SUMMARY
10
-
*
11
-
* This program is free software; you can redistribute it and/or modify
12
-
* it under the terms of version 2 of the GNU General Public License as
13
-
* published by the Free Software Foundation.
14
-
*
15
-
* This program is distributed in the hope that it will be useful, but
16
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
17
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18
-
* General Public License for more details.
19
-
*
20
-
* BSD LICENSE
21
-
*
22
-
* Redistribution and use in source and binary forms, with or without
23
-
* modification, are permitted provided that the following conditions
24
-
* are met:
25
-
*
26
-
* - Redistributions of source code must retain the above copyright
27
-
* notice, this list of conditions and the following disclaimer.
28
-
* - Redistributions in binary form must reproduce the above copyright
29
-
* notice, this list of conditions and the following disclaimer in
30
-
* the documentation and/or other materials provided with the
31
-
* distribution.
32
-
* - Neither the name of Intel Corporation nor the names of its
33
-
* contributors may be used to endorse or promote products derived
34
-
* from this software without specific prior written permission.
35
-
*
36
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
37
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
38
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
39
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
40
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
41
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
42
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
43
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
44
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
45
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
46
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
47
-
*
48
-
*/
49
-
50
-
/*
51
-
* This file contains OPA VNIC driver internal declarations
52
-
*/
53
-
54
-
#include <linux/bitops.h>
55
-
#include <linux/etherdevice.h>
56
-
#include <linux/hashtable.h>
57
-
#include <linux/sizes.h>
58
-
#include <rdma/opa_vnic.h>
59
-
60
-
#include "opa_vnic_encap.h"
61
-
62
-
#define OPA_VNIC_VLAN_PCP(vlan_tci) \
63
-
(((vlan_tci) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
64
-
65
-
/* Flow to default port redirection table size */
66
-
#define OPA_VNIC_FLOW_TBL_SIZE 32
67
-
68
-
/* Invalid port number */
69
-
#define OPA_VNIC_INVALID_PORT 0xff
70
-
71
-
struct opa_vnic_adapter;
72
-
73
-
/*
74
-
* struct __opa_vesw_info - OPA vnic virtual switch info
75
-
*
76
-
* Same as opa_vesw_info without bitwise attribute.
77
-
*/
78
-
struct __opa_vesw_info {
79
-
u16 fabric_id;
80
-
u16 vesw_id;
81
-
82
-
u8 rsvd0[6];
83
-
u16 def_port_mask;
84
-
85
-
u8 rsvd1[2];
86
-
u16 pkey;
87
-
88
-
u8 rsvd2[4];
89
-
u32 u_mcast_dlid;
90
-
u32 u_ucast_dlid[OPA_VESW_MAX_NUM_DEF_PORT];
91
-
92
-
u32 rc;
93
-
94
-
u8 rsvd3[56];
95
-
u16 eth_mtu;
96
-
u8 rsvd4[2];
97
-
} __packed;
98
-
99
-
/*
100
-
* struct __opa_per_veswport_info - OPA vnic per port info
101
-
*
102
-
* Same as opa_per_veswport_info without bitwise attribute.
103
-
*/
104
-
struct __opa_per_veswport_info {
105
-
u32 port_num;
106
-
107
-
u8 eth_link_status;
108
-
u8 rsvd0[3];
109
-
110
-
u8 base_mac_addr[ETH_ALEN];
111
-
u8 config_state;
112
-
u8 oper_state;
113
-
114
-
u16 max_mac_tbl_ent;
115
-
u16 max_smac_ent;
116
-
u32 mac_tbl_digest;
117
-
u8 rsvd1[4];
118
-
119
-
u32 encap_slid;
120
-
121
-
u8 pcp_to_sc_uc[OPA_VNIC_MAX_NUM_PCP];
122
-
u8 pcp_to_vl_uc[OPA_VNIC_MAX_NUM_PCP];
123
-
u8 pcp_to_sc_mc[OPA_VNIC_MAX_NUM_PCP];
124
-
u8 pcp_to_vl_mc[OPA_VNIC_MAX_NUM_PCP];
125
-
126
-
u8 non_vlan_sc_uc;
127
-
u8 non_vlan_vl_uc;
128
-
u8 non_vlan_sc_mc;
129
-
u8 non_vlan_vl_mc;
130
-
131
-
u8 rsvd2[48];
132
-
133
-
u16 uc_macs_gen_count;
134
-
u16 mc_macs_gen_count;
135
-
136
-
u8 rsvd3[8];
137
-
} __packed;
138
-
139
-
/*
140
-
* struct __opa_veswport_info - OPA vnic port info
141
-
*
142
-
* Same as opa_veswport_info without bitwise attribute.
143
-
*/
144
-
struct __opa_veswport_info {
145
-
struct __opa_vesw_info vesw;
146
-
struct __opa_per_veswport_info vport;
147
-
};
148
-
149
-
/*
150
-
* struct __opa_veswport_trap - OPA vnic trap info
151
-
*
152
-
* Same as opa_veswport_trap without bitwise attribute.
153
-
*/
154
-
struct __opa_veswport_trap {
155
-
u16 fabric_id;
156
-
u16 veswid;
157
-
u32 veswportnum;
158
-
u16 opaportnum;
159
-
u8 veswportindex;
160
-
u8 opcode;
161
-
u32 reserved;
162
-
} __packed;
163
-
164
-
/**
165
-
* struct opa_vnic_ctrl_port - OPA virtual NIC control port
166
-
* @ibdev: pointer to ib device
167
-
* @ops: opa vnic control operations
168
-
* @num_ports: number of opa ports
169
-
*/
170
-
struct opa_vnic_ctrl_port {
171
-
struct ib_device *ibdev;
172
-
struct opa_vnic_ctrl_ops *ops;
173
-
u8 num_ports;
174
-
};
175
-
176
-
/**
177
-
* struct opa_vnic_adapter - OPA VNIC netdev private data structure
178
-
* @netdev: pointer to associated netdev
179
-
* @ibdev: ib device
180
-
* @cport: pointer to opa vnic control port
181
-
* @rn_ops: rdma netdev's net_device_ops
182
-
* @port_num: OPA port number
183
-
* @vport_num: vesw port number
184
-
* @lock: adapter lock
185
-
* @info: virtual ethernet switch port information
186
-
* @vema_mac_addr: mac address configured by vema
187
-
* @umac_hash: unicast maclist hash
188
-
* @mmac_hash: multicast maclist hash
189
-
* @mactbl: hash table of MAC entries
190
-
* @mactbl_lock: mac table lock
191
-
* @stats_lock: statistics lock
192
-
* @flow_tbl: flow to default port redirection table
193
-
* @trap_timeout: trap timeout
194
-
* @trap_count: no. of traps allowed within timeout period
195
-
*/
196
-
struct opa_vnic_adapter {
197
-
struct net_device *netdev;
198
-
struct ib_device *ibdev;
199
-
struct opa_vnic_ctrl_port *cport;
200
-
const struct net_device_ops *rn_ops;
201
-
202
-
u8 port_num;
203
-
u8 vport_num;
204
-
205
-
/* Lock used around concurrent updates to netdev */
206
-
struct mutex lock;
207
-
208
-
struct __opa_veswport_info info;
209
-
u8 vema_mac_addr[ETH_ALEN];
210
-
u32 umac_hash;
211
-
u32 mmac_hash;
212
-
struct hlist_head __rcu *mactbl;
213
-
214
-
/* Lock used to protect updates to mac table */
215
-
struct mutex mactbl_lock;
216
-
217
-
/* Lock used to protect access to vnic counters */
218
-
spinlock_t stats_lock;
219
-
220
-
u8 flow_tbl[OPA_VNIC_FLOW_TBL_SIZE];
221
-
222
-
unsigned long trap_timeout;
223
-
u8 trap_count;
224
-
};
225
-
226
-
/* Same as opa_veswport_mactable_entry, but without bitwise attribute */
227
-
struct __opa_vnic_mactable_entry {
228
-
u8 mac_addr[ETH_ALEN];
229
-
u8 mac_addr_mask[ETH_ALEN];
230
-
u32 dlid_sd;
231
-
} __packed;
232
-
233
-
/**
234
-
* struct opa_vnic_mac_tbl_node - OPA VNIC mac table node
235
-
* @hlist: hash list handle
236
-
* @index: index of entry in the mac table
237
-
* @entry: entry in the table
238
-
*/
239
-
struct opa_vnic_mac_tbl_node {
240
-
struct hlist_node hlist;
241
-
u16 index;
242
-
struct __opa_vnic_mactable_entry entry;
243
-
};
244
-
245
-
#define v_dbg(format, arg...) \
246
-
netdev_dbg(adapter->netdev, format, ## arg)
247
-
#define v_err(format, arg...) \
248
-
netdev_err(adapter->netdev, format, ## arg)
249
-
#define v_info(format, arg...) \
250
-
netdev_info(adapter->netdev, format, ## arg)
251
-
#define v_warn(format, arg...) \
252
-
netdev_warn(adapter->netdev, format, ## arg)
253
-
254
-
#define c_err(format, arg...) \
255
-
dev_err(&cport->ibdev->dev, format, ## arg)
256
-
#define c_info(format, arg...) \
257
-
dev_info(&cport->ibdev->dev, format, ## arg)
258
-
#define c_dbg(format, arg...) \
259
-
dev_dbg(&cport->ibdev->dev, format, ## arg)
260
-
261
-
/* The maximum allowed entries in the mac table */
262
-
#define OPA_VNIC_MAC_TBL_MAX_ENTRIES 2048
263
-
/* Limit of smac entries in mac table */
264
-
#define OPA_VNIC_MAX_SMAC_LIMIT 256
265
-
266
-
/* The last octet of the MAC address is used as the key to the hash table */
267
-
#define OPA_VNIC_MAC_HASH_IDX 5
268
-
269
-
/* The VNIC MAC hash table is of size 2^8 */
270
-
#define OPA_VNIC_MAC_TBL_HASH_BITS 8
271
-
#define OPA_VNIC_MAC_TBL_SIZE BIT(OPA_VNIC_MAC_TBL_HASH_BITS)
272
-
273
-
/* VNIC HASH MACROS */
274
-
#define vnic_hash_init(hashtable) __hash_init(hashtable, OPA_VNIC_MAC_TBL_SIZE)
275
-
276
-
#define vnic_hash_add(hashtable, node, key) \
277
-
hlist_add_head(node, \
278
-
&hashtable[hash_min(key, ilog2(OPA_VNIC_MAC_TBL_SIZE))])
279
-
280
-
#define vnic_hash_for_each_safe(name, bkt, tmp, obj, member) \
281
-
for ((bkt) = 0, obj = NULL; \
282
-
!obj && (bkt) < OPA_VNIC_MAC_TBL_SIZE; (bkt)++) \
283
-
hlist_for_each_entry_safe(obj, tmp, &name[bkt], member)
284
-
285
-
#define vnic_hash_for_each_possible(name, obj, member, key) \
286
-
hlist_for_each_entry(obj, \
287
-
&name[hash_min(key, ilog2(OPA_VNIC_MAC_TBL_SIZE))], member)
288
-
289
-
#define vnic_hash_for_each(name, bkt, obj, member) \
290
-
for ((bkt) = 0, obj = NULL; \
291
-
!obj && (bkt) < OPA_VNIC_MAC_TBL_SIZE; (bkt)++) \
292
-
hlist_for_each_entry(obj, &name[bkt], member)
293
-
294
-
extern char opa_vnic_driver_name[];
295
-
296
-
struct opa_vnic_adapter *opa_vnic_add_netdev(struct ib_device *ibdev,
297
-
u8 port_num, u8 vport_num);
298
-
void opa_vnic_rem_netdev(struct opa_vnic_adapter *adapter);
299
-
void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb);
300
-
u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb);
301
-
u8 opa_vnic_calc_entropy(struct sk_buff *skb);
302
-
void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter);
303
-
void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter);
304
-
void opa_vnic_query_mac_tbl(struct opa_vnic_adapter *adapter,
305
-
struct opa_veswport_mactable *tbl);
306
-
int opa_vnic_update_mac_tbl(struct opa_vnic_adapter *adapter,
307
-
struct opa_veswport_mactable *tbl);
308
-
void opa_vnic_query_ucast_macs(struct opa_vnic_adapter *adapter,
309
-
struct opa_veswport_iface_macs *macs);
310
-
void opa_vnic_query_mcast_macs(struct opa_vnic_adapter *adapter,
311
-
struct opa_veswport_iface_macs *macs);
312
-
void opa_vnic_get_summary_counters(struct opa_vnic_adapter *adapter,
313
-
struct opa_veswport_summary_counters *cntrs);
314
-
void opa_vnic_get_error_counters(struct opa_vnic_adapter *adapter,
315
-
struct opa_veswport_error_counters *cntrs);
316
-
void opa_vnic_get_vesw_info(struct opa_vnic_adapter *adapter,
317
-
struct opa_vesw_info *info);
318
-
void opa_vnic_set_vesw_info(struct opa_vnic_adapter *adapter,
319
-
struct opa_vesw_info *info);
320
-
void opa_vnic_get_per_veswport_info(struct opa_vnic_adapter *adapter,
321
-
struct opa_per_veswport_info *info);
322
-
void opa_vnic_set_per_veswport_info(struct opa_vnic_adapter *adapter,
323
-
struct opa_per_veswport_info *info);
324
-
void opa_vnic_vema_report_event(struct opa_vnic_adapter *adapter, u8 event);
325
-
void opa_vnic_set_ethtool_ops(struct net_device *netdev);
326
-
void opa_vnic_vema_send_trap(struct opa_vnic_adapter *adapter,
327
-
struct __opa_veswport_trap *data, u32 lid);
328
-
329
-
#endif /* _OPA_VNIC_INTERNAL_H */
-400
drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
-400
drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
···
1
-
/*
2
-
* Copyright(c) 2017 Intel Corporation.
3
-
*
4
-
* This file is provided under a dual BSD/GPLv2 license. When using or
5
-
* redistributing this file, you may do so under either license.
6
-
*
7
-
* GPL LICENSE SUMMARY
8
-
*
9
-
* This program is free software; you can redistribute it and/or modify
10
-
* it under the terms of version 2 of the GNU General Public License as
11
-
* published by the Free Software Foundation.
12
-
*
13
-
* This program is distributed in the hope that it will be useful, but
14
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
15
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16
-
* General Public License for more details.
17
-
*
18
-
* BSD LICENSE
19
-
*
20
-
* Redistribution and use in source and binary forms, with or without
21
-
* modification, are permitted provided that the following conditions
22
-
* are met:
23
-
*
24
-
* - Redistributions of source code must retain the above copyright
25
-
* notice, this list of conditions and the following disclaimer.
26
-
* - Redistributions in binary form must reproduce the above copyright
27
-
* notice, this list of conditions and the following disclaimer in
28
-
* the documentation and/or other materials provided with the
29
-
* distribution.
30
-
* - Neither the name of Intel Corporation nor the names of its
31
-
* contributors may be used to endorse or promote products derived
32
-
* from this software without specific prior written permission.
33
-
*
34
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45
-
*
46
-
*/
47
-
48
-
/*
49
-
* This file contains OPA Virtual Network Interface Controller (VNIC) driver
50
-
* netdev functionality.
51
-
*/
52
-
53
-
#include <linux/if_vlan.h>
54
-
#include <linux/crc32.h>
55
-
56
-
#include "opa_vnic_internal.h"
57
-
58
-
#define OPA_TX_TIMEOUT_MS 1000
59
-
60
-
#define OPA_VNIC_SKB_HEADROOM \
61
-
ALIGN((OPA_VNIC_HDR_LEN + OPA_VNIC_SKB_MDATA_LEN), 8)
62
-
63
-
/* This function is overloaded for opa_vnic specific implementation */
64
-
static void opa_vnic_get_stats64(struct net_device *netdev,
65
-
struct rtnl_link_stats64 *stats)
66
-
{
67
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
68
-
struct opa_vnic_stats vstats;
69
-
70
-
memset(&vstats, 0, sizeof(vstats));
71
-
spin_lock(&adapter->stats_lock);
72
-
adapter->rn_ops->ndo_get_stats64(netdev, &vstats.netstats);
73
-
spin_unlock(&adapter->stats_lock);
74
-
memcpy(stats, &vstats.netstats, sizeof(*stats));
75
-
}
76
-
77
-
/* opa_netdev_start_xmit - transmit function */
78
-
static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb,
79
-
struct net_device *netdev)
80
-
{
81
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
82
-
83
-
v_dbg("xmit: queue %d skb len %d\n", skb->queue_mapping, skb->len);
84
-
/* pad to ensure mininum ethernet packet length */
85
-
if (unlikely(skb->len < ETH_ZLEN)) {
86
-
if (skb_padto(skb, ETH_ZLEN))
87
-
return NETDEV_TX_OK;
88
-
89
-
skb_put(skb, ETH_ZLEN - skb->len);
90
-
}
91
-
92
-
opa_vnic_encap_skb(adapter, skb);
93
-
return adapter->rn_ops->ndo_start_xmit(skb, netdev);
94
-
}
95
-
96
-
static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
97
-
struct net_device *sb_dev)
98
-
{
99
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
100
-
struct opa_vnic_skb_mdata *mdata;
101
-
int rc;
102
-
103
-
/* pass entropy and vl as metadata in skb */
104
-
mdata = skb_push(skb, sizeof(*mdata));
105
-
mdata->entropy = opa_vnic_calc_entropy(skb);
106
-
mdata->vl = opa_vnic_get_vl(adapter, skb);
107
-
rc = adapter->rn_ops->ndo_select_queue(netdev, skb, sb_dev);
108
-
skb_pull(skb, sizeof(*mdata));
109
-
return rc;
110
-
}
111
-
112
-
static void opa_vnic_update_state(struct opa_vnic_adapter *adapter, bool up)
113
-
{
114
-
struct __opa_veswport_info *info = &adapter->info;
115
-
116
-
mutex_lock(&adapter->lock);
117
-
/* Operational state can only be DROP_ALL or FORWARDING */
118
-
if ((info->vport.config_state == OPA_VNIC_STATE_FORWARDING) && up) {
119
-
info->vport.oper_state = OPA_VNIC_STATE_FORWARDING;
120
-
info->vport.eth_link_status = OPA_VNIC_ETH_LINK_UP;
121
-
} else {
122
-
info->vport.oper_state = OPA_VNIC_STATE_DROP_ALL;
123
-
info->vport.eth_link_status = OPA_VNIC_ETH_LINK_DOWN;
124
-
}
125
-
126
-
if (info->vport.config_state == OPA_VNIC_STATE_FORWARDING)
127
-
netif_dormant_off(adapter->netdev);
128
-
else
129
-
netif_dormant_on(adapter->netdev);
130
-
mutex_unlock(&adapter->lock);
131
-
}
132
-
133
-
/* opa_vnic_process_vema_config - process vema configuration updates */
134
-
void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter)
135
-
{
136
-
struct __opa_veswport_info *info = &adapter->info;
137
-
struct rdma_netdev *rn = netdev_priv(adapter->netdev);
138
-
u8 port_num[OPA_VESW_MAX_NUM_DEF_PORT] = { 0 };
139
-
struct net_device *netdev = adapter->netdev;
140
-
u8 i, port_count = 0;
141
-
u16 port_mask;
142
-
143
-
/* If the base_mac_addr is changed, update the interface mac address */
144
-
if (memcmp(info->vport.base_mac_addr, adapter->vema_mac_addr,
145
-
ARRAY_SIZE(info->vport.base_mac_addr))) {
146
-
struct sockaddr saddr;
147
-
148
-
memcpy(saddr.sa_data, info->vport.base_mac_addr,
149
-
ARRAY_SIZE(info->vport.base_mac_addr));
150
-
mutex_lock(&adapter->lock);
151
-
eth_commit_mac_addr_change(netdev, &saddr);
152
-
memcpy(adapter->vema_mac_addr,
153
-
info->vport.base_mac_addr, ETH_ALEN);
154
-
mutex_unlock(&adapter->lock);
155
-
}
156
-
157
-
rn->set_id(netdev, info->vesw.vesw_id);
158
-
159
-
/* Handle MTU limit change */
160
-
rtnl_lock();
161
-
netdev->max_mtu = max_t(unsigned int, info->vesw.eth_mtu,
162
-
netdev->min_mtu);
163
-
if (netdev->mtu > netdev->max_mtu)
164
-
dev_set_mtu(netdev, netdev->max_mtu);
165
-
rtnl_unlock();
166
-
167
-
/* Update flow to default port redirection table */
168
-
port_mask = info->vesw.def_port_mask;
169
-
for (i = 0; i < OPA_VESW_MAX_NUM_DEF_PORT; i++) {
170
-
if (port_mask & 1)
171
-
port_num[port_count++] = i;
172
-
port_mask >>= 1;
173
-
}
174
-
175
-
/*
176
-
* Build the flow table. Flow table is required when destination LID
177
-
* is not available. Up to OPA_VNIC_FLOW_TBL_SIZE flows supported.
178
-
* Each flow need a default port number to get its dlid from the
179
-
* u_ucast_dlid array.
180
-
*/
181
-
for (i = 0; i < OPA_VNIC_FLOW_TBL_SIZE; i++)
182
-
adapter->flow_tbl[i] = port_count ? port_num[i % port_count] :
183
-
OPA_VNIC_INVALID_PORT;
184
-
185
-
/* update state */
186
-
opa_vnic_update_state(adapter, !!(netdev->flags & IFF_UP));
187
-
}
188
-
189
-
/*
190
-
* Set the power on default values in adapter's vema interface structure.
191
-
*/
192
-
static inline void opa_vnic_set_pod_values(struct opa_vnic_adapter *adapter)
193
-
{
194
-
adapter->info.vport.max_mac_tbl_ent = OPA_VNIC_MAC_TBL_MAX_ENTRIES;
195
-
adapter->info.vport.max_smac_ent = OPA_VNIC_MAX_SMAC_LIMIT;
196
-
adapter->info.vport.config_state = OPA_VNIC_STATE_DROP_ALL;
197
-
adapter->info.vport.eth_link_status = OPA_VNIC_ETH_LINK_DOWN;
198
-
adapter->info.vesw.eth_mtu = ETH_DATA_LEN;
199
-
}
200
-
201
-
/* opa_vnic_set_mac_addr - change mac address */
202
-
static int opa_vnic_set_mac_addr(struct net_device *netdev, void *addr)
203
-
{
204
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
205
-
struct sockaddr *sa = addr;
206
-
int rc;
207
-
208
-
if (!memcmp(netdev->dev_addr, sa->sa_data, ETH_ALEN))
209
-
return 0;
210
-
211
-
mutex_lock(&adapter->lock);
212
-
rc = eth_mac_addr(netdev, addr);
213
-
mutex_unlock(&adapter->lock);
214
-
if (rc)
215
-
return rc;
216
-
217
-
adapter->info.vport.uc_macs_gen_count++;
218
-
opa_vnic_vema_report_event(adapter,
219
-
OPA_VESWPORT_TRAP_IFACE_UCAST_MAC_CHANGE);
220
-
return 0;
221
-
}
222
-
223
-
/*
224
-
* opa_vnic_mac_send_event - post event on possible mac list exchange
225
-
* Send trap when digest from uc/mc mac list differs from previous run.
226
-
* Digest is evaluated similar to how cksum does.
227
-
*/
228
-
static void opa_vnic_mac_send_event(struct net_device *netdev, u8 event)
229
-
{
230
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
231
-
struct netdev_hw_addr *ha;
232
-
struct netdev_hw_addr_list *hw_list;
233
-
u32 *ref_crc;
234
-
u32 l, crc = 0;
235
-
236
-
switch (event) {
237
-
case OPA_VESWPORT_TRAP_IFACE_UCAST_MAC_CHANGE:
238
-
hw_list = &netdev->uc;
239
-
adapter->info.vport.uc_macs_gen_count++;
240
-
ref_crc = &adapter->umac_hash;
241
-
break;
242
-
case OPA_VESWPORT_TRAP_IFACE_MCAST_MAC_CHANGE:
243
-
hw_list = &netdev->mc;
244
-
adapter->info.vport.mc_macs_gen_count++;
245
-
ref_crc = &adapter->mmac_hash;
246
-
break;
247
-
default:
248
-
return;
249
-
}
250
-
netdev_hw_addr_list_for_each(ha, hw_list) {
251
-
crc = crc32_le(crc, ha->addr, ETH_ALEN);
252
-
}
253
-
l = netdev_hw_addr_list_count(hw_list) * ETH_ALEN;
254
-
crc = ~crc32_le(crc, (void *)&l, sizeof(l));
255
-
256
-
if (crc != *ref_crc) {
257
-
*ref_crc = crc;
258
-
opa_vnic_vema_report_event(adapter, event);
259
-
}
260
-
}
261
-
262
-
/* opa_vnic_set_rx_mode - handle uc/mc mac list change */
263
-
static void opa_vnic_set_rx_mode(struct net_device *netdev)
264
-
{
265
-
opa_vnic_mac_send_event(netdev,
266
-
OPA_VESWPORT_TRAP_IFACE_UCAST_MAC_CHANGE);
267
-
268
-
opa_vnic_mac_send_event(netdev,
269
-
OPA_VESWPORT_TRAP_IFACE_MCAST_MAC_CHANGE);
270
-
}
271
-
272
-
/* opa_netdev_open - activate network interface */
273
-
static int opa_netdev_open(struct net_device *netdev)
274
-
{
275
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
276
-
int rc;
277
-
278
-
rc = adapter->rn_ops->ndo_open(adapter->netdev);
279
-
if (rc) {
280
-
v_dbg("open failed %d\n", rc);
281
-
return rc;
282
-
}
283
-
284
-
/* Update status and send trap */
285
-
opa_vnic_update_state(adapter, true);
286
-
opa_vnic_vema_report_event(adapter,
287
-
OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE);
288
-
return 0;
289
-
}
290
-
291
-
/* opa_netdev_close - disable network interface */
292
-
static int opa_netdev_close(struct net_device *netdev)
293
-
{
294
-
struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
295
-
int rc;
296
-
297
-
rc = adapter->rn_ops->ndo_stop(adapter->netdev);
298
-
if (rc) {
299
-
v_dbg("close failed %d\n", rc);
300
-
return rc;
301
-
}
302
-
303
-
/* Update status and send trap */
304
-
opa_vnic_update_state(adapter, false);
305
-
opa_vnic_vema_report_event(adapter,
306
-
OPA_VESWPORT_TRAP_ETH_LINK_STATUS_CHANGE);
307
-
return 0;
308
-
}
309
-
310
-
/* netdev ops */
311
-
static const struct net_device_ops opa_netdev_ops = {
312
-
.ndo_open = opa_netdev_open,
313
-
.ndo_stop = opa_netdev_close,
314
-
.ndo_start_xmit = opa_netdev_start_xmit,
315
-
.ndo_get_stats64 = opa_vnic_get_stats64,
316
-
.ndo_set_rx_mode = opa_vnic_set_rx_mode,
317
-
.ndo_select_queue = opa_vnic_select_queue,
318
-
.ndo_set_mac_address = opa_vnic_set_mac_addr,
319
-
};
320
-
321
-
/* opa_vnic_add_netdev - create vnic netdev interface */
322
-
struct opa_vnic_adapter *opa_vnic_add_netdev(struct ib_device *ibdev,
323
-
u8 port_num, u8 vport_num)
324
-
{
325
-
struct opa_vnic_adapter *adapter;
326
-
struct net_device *netdev;
327
-
struct rdma_netdev *rn;
328
-
int rc;
329
-
330
-
netdev = ibdev->ops.alloc_rdma_netdev(ibdev, port_num,
331
-
RDMA_NETDEV_OPA_VNIC,
332
-
"veth%d", NET_NAME_UNKNOWN,
333
-
ether_setup);
334
-
if (!netdev)
335
-
return ERR_PTR(-ENOMEM);
336
-
else if (IS_ERR(netdev))
337
-
return ERR_CAST(netdev);
338
-
339
-
rn = netdev_priv(netdev);
340
-
adapter = kzalloc_obj(*adapter);
341
-
if (!adapter) {
342
-
rc = -ENOMEM;
343
-
goto adapter_err;
344
-
}
345
-
346
-
rn->clnt_priv = adapter;
347
-
rn->hca = ibdev;
348
-
rn->port_num = port_num;
349
-
adapter->netdev = netdev;
350
-
adapter->ibdev = ibdev;
351
-
adapter->port_num = port_num;
352
-
adapter->vport_num = vport_num;
353
-
adapter->rn_ops = netdev->netdev_ops;
354
-
355
-
netdev->netdev_ops = &opa_netdev_ops;
356
-
netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
357
-
netdev->hard_header_len += OPA_VNIC_SKB_HEADROOM;
358
-
mutex_init(&adapter->lock);
359
-
mutex_init(&adapter->mactbl_lock);
360
-
spin_lock_init(&adapter->stats_lock);
361
-
362
-
SET_NETDEV_DEV(netdev, ibdev->dev.parent);
363
-
364
-
opa_vnic_set_ethtool_ops(netdev);
365
-
366
-
opa_vnic_set_pod_values(adapter);
367
-
368
-
rc = register_netdev(netdev);
369
-
if (rc)
370
-
goto netdev_err;
371
-
372
-
netif_carrier_off(netdev);
373
-
netif_dormant_on(netdev);
374
-
v_info("initialized\n");
375
-
376
-
return adapter;
377
-
netdev_err:
378
-
mutex_destroy(&adapter->lock);
379
-
mutex_destroy(&adapter->mactbl_lock);
380
-
kfree(adapter);
381
-
adapter_err:
382
-
rn->free_rdma_netdev(netdev);
383
-
384
-
return ERR_PTR(rc);
385
-
}
386
-
387
-
/* opa_vnic_rem_netdev - remove vnic netdev interface */
388
-
void opa_vnic_rem_netdev(struct opa_vnic_adapter *adapter)
389
-
{
390
-
struct net_device *netdev = adapter->netdev;
391
-
struct rdma_netdev *rn = netdev_priv(netdev);
392
-
393
-
v_info("removing\n");
394
-
unregister_netdev(netdev);
395
-
opa_vnic_release_mac_tbl(adapter);
396
-
mutex_destroy(&adapter->lock);
397
-
mutex_destroy(&adapter->mactbl_lock);
398
-
kfree(adapter);
399
-
rn->free_rdma_netdev(netdev);
400
-
}
-1056
drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
-1056
drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
···
1
-
/*
2
-
* Copyright(c) 2017 Intel Corporation.
3
-
* Copyright(c) 2021 Cornelis Networks.
4
-
*
5
-
* This file is provided under a dual BSD/GPLv2 license. When using or
6
-
* redistributing this file, you may do so under either license.
7
-
*
8
-
* GPL LICENSE SUMMARY
9
-
*
10
-
* This program is free software; you can redistribute it and/or modify
11
-
* it under the terms of version 2 of the GNU General Public License as
12
-
* published by the Free Software Foundation.
13
-
*
14
-
* This program is distributed in the hope that it will be useful, but
15
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
16
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17
-
* General Public License for more details.
18
-
*
19
-
* BSD LICENSE
20
-
*
21
-
* Redistribution and use in source and binary forms, with or without
22
-
* modification, are permitted provided that the following conditions
23
-
* are met:
24
-
*
25
-
* - Redistributions of source code must retain the above copyright
26
-
* notice, this list of conditions and the following disclaimer.
27
-
* - Redistributions in binary form must reproduce the above copyright
28
-
* notice, this list of conditions and the following disclaimer in
29
-
* the documentation and/or other materials provided with the
30
-
* distribution.
31
-
* - Neither the name of Intel Corporation nor the names of its
32
-
* contributors may be used to endorse or promote products derived
33
-
* from this software without specific prior written permission.
34
-
*
35
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
36
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
37
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
38
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
39
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
40
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
41
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
42
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
43
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
44
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
45
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
46
-
*
47
-
*/
48
-
49
-
/*
50
-
* This file contains OPX Virtual Network Interface Controller (VNIC)
51
-
* Ethernet Management Agent (EMA) driver
52
-
*/
53
-
54
-
#include <linux/module.h>
55
-
#include <linux/xarray.h>
56
-
#include <rdma/ib_addr.h>
57
-
#include <rdma/ib_verbs.h>
58
-
#include <rdma/opa_smi.h>
59
-
#include <rdma/opa_port_info.h>
60
-
61
-
#include "opa_vnic_internal.h"
62
-
63
-
char opa_vnic_driver_name[] = "opa_vnic";
64
-
65
-
/*
66
-
* The trap service level is kept in bits 3 to 7 in the trap_sl_rsvd
67
-
* field in the class port info MAD.
68
-
*/
69
-
#define GET_TRAP_SL_FROM_CLASS_PORT_INFO(x) (((x) >> 3) & 0x1f)
70
-
71
-
/* Cap trap bursts to a reasonable limit good for normal cases */
72
-
#define OPA_VNIC_TRAP_BURST_LIMIT 4
73
-
74
-
/*
75
-
* VNIC trap limit timeout.
76
-
* Inverse of cap2_mask response time out (1.0737 secs) = 0.9
77
-
* secs approx IB spec 13.4.6.2.1 PortInfoSubnetTimeout and
78
-
* 13.4.9 Traps.
79
-
*/
80
-
#define OPA_VNIC_TRAP_TIMEOUT ((4096 * (1UL << 18)) / 1000)
81
-
82
-
#define OPA_VNIC_UNSUP_ATTR \
83
-
cpu_to_be16(IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB)
84
-
85
-
#define OPA_VNIC_INVAL_ATTR \
86
-
cpu_to_be16(IB_MGMT_MAD_STATUS_INVALID_ATTRIB_VALUE)
87
-
88
-
#define OPA_VNIC_CLASS_CAP_TRAP 0x1
89
-
90
-
/* Maximum number of VNIC ports supported */
91
-
#define OPA_VNIC_MAX_NUM_VPORT 255
92
-
93
-
/**
94
-
* struct opa_vnic_vema_port -- VNIC VEMA port details
95
-
* @cport: pointer to port
96
-
* @mad_agent: pointer to mad agent for port
97
-
* @class_port_info: Class port info information.
98
-
* @tid: Transaction id
99
-
* @port_num: OPA port number
100
-
* @vports: vnic ports
101
-
* @event_handler: ib event handler
102
-
* @lock: adapter interface lock
103
-
*/
104
-
struct opa_vnic_vema_port {
105
-
struct opa_vnic_ctrl_port *cport;
106
-
struct ib_mad_agent *mad_agent;
107
-
struct opa_class_port_info class_port_info;
108
-
u64 tid;
109
-
u8 port_num;
110
-
struct xarray vports;
111
-
struct ib_event_handler event_handler;
112
-
113
-
/* Lock to query/update network adapter */
114
-
struct mutex lock;
115
-
};
116
-
117
-
static int opa_vnic_vema_add_one(struct ib_device *device);
118
-
static void opa_vnic_vema_rem_one(struct ib_device *device,
119
-
void *client_data);
120
-
121
-
static struct ib_client opa_vnic_client = {
122
-
.name = opa_vnic_driver_name,
123
-
.add = opa_vnic_vema_add_one,
124
-
.remove = opa_vnic_vema_rem_one,
125
-
};
126
-
127
-
/**
128
-
* vema_get_vport_num -- Get the vnic from the mad
129
-
* @recvd_mad: Received mad
130
-
*
131
-
* Return: returns value of the vnic port number
132
-
*/
133
-
static inline u8 vema_get_vport_num(struct opa_vnic_vema_mad *recvd_mad)
134
-
{
135
-
return be32_to_cpu(recvd_mad->mad_hdr.attr_mod) & 0xff;
136
-
}
137
-
138
-
/**
139
-
* vema_get_vport_adapter -- Get vnic port adapter from recvd mad
140
-
* @recvd_mad: received mad
141
-
* @port: ptr to port struct on which MAD was recvd
142
-
*
143
-
* Return: vnic adapter
144
-
*/
145
-
static inline struct opa_vnic_adapter *
146
-
vema_get_vport_adapter(struct opa_vnic_vema_mad *recvd_mad,
147
-
struct opa_vnic_vema_port *port)
148
-
{
149
-
u8 vport_num = vema_get_vport_num(recvd_mad);
150
-
151
-
return xa_load(&port->vports, vport_num);
152
-
}
153
-
154
-
/**
155
-
* vema_mac_tbl_req_ok -- Check if mac request has correct values
156
-
* @mac_tbl: mac table
157
-
*
158
-
* This function checks for the validity of the offset and number of
159
-
* entries required.
160
-
*
161
-
* Return: true if offset and num_entries are valid
162
-
*/
163
-
static inline bool vema_mac_tbl_req_ok(struct opa_veswport_mactable *mac_tbl)
164
-
{
165
-
u16 offset, num_entries;
166
-
u16 req_entries = ((OPA_VNIC_EMA_DATA - sizeof(*mac_tbl)) /
167
-
sizeof(mac_tbl->tbl_entries[0]));
168
-
169
-
offset = be16_to_cpu(mac_tbl->offset);
170
-
num_entries = be16_to_cpu(mac_tbl->num_entries);
171
-
172
-
return ((num_entries <= req_entries) &&
173
-
(offset + num_entries <= OPA_VNIC_MAC_TBL_MAX_ENTRIES));
174
-
}
175
-
176
-
/*
177
-
* Return the power on default values in the port info structure
178
-
* in big endian format as required by MAD.
179
-
*/
180
-
static inline void vema_get_pod_values(struct opa_veswport_info *port_info)
181
-
{
182
-
memset(port_info, 0, sizeof(*port_info));
183
-
port_info->vport.max_mac_tbl_ent =
184
-
cpu_to_be16(OPA_VNIC_MAC_TBL_MAX_ENTRIES);
185
-
port_info->vport.max_smac_ent =
186
-
cpu_to_be16(OPA_VNIC_MAX_SMAC_LIMIT);
187
-
port_info->vport.oper_state = OPA_VNIC_STATE_DROP_ALL;
188
-
port_info->vport.config_state = OPA_VNIC_STATE_DROP_ALL;
189
-
port_info->vesw.eth_mtu = cpu_to_be16(ETH_DATA_LEN);
190
-
}
191
-
192
-
/**
193
-
* vema_add_vport -- Add a new vnic port
194
-
* @port: ptr to opa_vnic_vema_port struct
195
-
* @vport_num: vnic port number (to be added)
196
-
*
197
-
* Return a pointer to the vnic adapter structure
198
-
*/
199
-
static struct opa_vnic_adapter *vema_add_vport(struct opa_vnic_vema_port *port,
200
-
u8 vport_num)
201
-
{
202
-
struct opa_vnic_ctrl_port *cport = port->cport;
203
-
struct opa_vnic_adapter *adapter;
204
-
205
-
adapter = opa_vnic_add_netdev(cport->ibdev, port->port_num, vport_num);
206
-
if (!IS_ERR(adapter)) {
207
-
int rc;
208
-
209
-
adapter->cport = cport;
210
-
rc = xa_insert(&port->vports, vport_num, adapter, GFP_KERNEL);
211
-
if (rc < 0) {
212
-
opa_vnic_rem_netdev(adapter);
213
-
adapter = ERR_PTR(rc);
214
-
}
215
-
}
216
-
217
-
return adapter;
218
-
}
219
-
220
-
/**
221
-
* vema_get_class_port_info -- Get class info for port
222
-
* @port: Port on whic MAD was received
223
-
* @recvd_mad: pointer to the received mad
224
-
* @rsp_mad: pointer to respose mad
225
-
*
226
-
* This function copies the latest class port info value set for the
227
-
* port and stores it for generating traps
228
-
*/
229
-
static void vema_get_class_port_info(struct opa_vnic_vema_port *port,
230
-
struct opa_vnic_vema_mad *recvd_mad,
231
-
struct opa_vnic_vema_mad *rsp_mad)
232
-
{
233
-
struct opa_class_port_info *port_info;
234
-
235
-
port_info = (struct opa_class_port_info *)rsp_mad->data;
236
-
memcpy(port_info, &port->class_port_info, sizeof(*port_info));
237
-
port_info->base_version = OPA_MGMT_BASE_VERSION;
238
-
port_info->class_version = OPA_EMA_CLASS_VERSION;
239
-
240
-
/*
241
-
* Set capability mask bit indicating agent generates traps,
242
-
* and set the maximum number of VNIC ports supported.
243
-
*/
244
-
port_info->cap_mask = cpu_to_be16((OPA_VNIC_CLASS_CAP_TRAP |
245
-
(OPA_VNIC_MAX_NUM_VPORT << 8)));
246
-
247
-
/*
248
-
* Since a get routine is always sent by the EM first we
249
-
* set the expected response time to
250
-
* 4.096 usec * 2^18 == 1.0737 sec here.
251
-
*/
252
-
port_info->cap_mask2_resp_time = cpu_to_be32(18);
253
-
}
254
-
255
-
/**
256
-
* vema_set_class_port_info -- Get class info for port
257
-
* @port: Port on whic MAD was received
258
-
* @recvd_mad: pointer to the received mad
259
-
* @rsp_mad: pointer to respose mad
260
-
*
261
-
* This function updates the port class info for the specific vnic
262
-
* and sets up the response mad data
263
-
*/
264
-
static void vema_set_class_port_info(struct opa_vnic_vema_port *port,
265
-
struct opa_vnic_vema_mad *recvd_mad,
266
-
struct opa_vnic_vema_mad *rsp_mad)
267
-
{
268
-
memcpy(&port->class_port_info, recvd_mad->data,
269
-
sizeof(port->class_port_info));
270
-
271
-
vema_get_class_port_info(port, recvd_mad, rsp_mad);
272
-
}
273
-
274
-
/**
275
-
* vema_get_veswport_info -- Get veswport info
276
-
* @port: source port on which MAD was received
277
-
* @recvd_mad: pointer to the received mad
278
-
* @rsp_mad: pointer to respose mad
279
-
*/
280
-
static void vema_get_veswport_info(struct opa_vnic_vema_port *port,
281
-
struct opa_vnic_vema_mad *recvd_mad,
282
-
struct opa_vnic_vema_mad *rsp_mad)
283
-
{
284
-
struct opa_veswport_info *port_info =
285
-
(struct opa_veswport_info *)rsp_mad->data;
286
-
struct opa_vnic_adapter *adapter;
287
-
288
-
adapter = vema_get_vport_adapter(recvd_mad, port);
289
-
if (adapter) {
290
-
memset(port_info, 0, sizeof(*port_info));
291
-
opa_vnic_get_vesw_info(adapter, &port_info->vesw);
292
-
opa_vnic_get_per_veswport_info(adapter,
293
-
&port_info->vport);
294
-
} else {
295
-
vema_get_pod_values(port_info);
296
-
}
297
-
}
298
-
299
-
/**
300
-
* vema_set_veswport_info -- Set veswport info
301
-
* @port: source port on which MAD was received
302
-
* @recvd_mad: pointer to the received mad
303
-
* @rsp_mad: pointer to respose mad
304
-
*
305
-
* This function gets the port class infor for vnic
306
-
*/
307
-
static void vema_set_veswport_info(struct opa_vnic_vema_port *port,
308
-
struct opa_vnic_vema_mad *recvd_mad,
309
-
struct opa_vnic_vema_mad *rsp_mad)
310
-
{
311
-
struct opa_vnic_ctrl_port *cport = port->cport;
312
-
struct opa_veswport_info *port_info;
313
-
struct opa_vnic_adapter *adapter;
314
-
u8 vport_num;
315
-
316
-
vport_num = vema_get_vport_num(recvd_mad);
317
-
318
-
adapter = vema_get_vport_adapter(recvd_mad, port);
319
-
if (!adapter) {
320
-
adapter = vema_add_vport(port, vport_num);
321
-
if (IS_ERR(adapter)) {
322
-
c_err("failed to add vport %d: %ld\n",
323
-
vport_num, PTR_ERR(adapter));
324
-
goto err_exit;
325
-
}
326
-
}
327
-
328
-
port_info = (struct opa_veswport_info *)recvd_mad->data;
329
-
opa_vnic_set_vesw_info(adapter, &port_info->vesw);
330
-
opa_vnic_set_per_veswport_info(adapter, &port_info->vport);
331
-
332
-
/* Process the new config settings */
333
-
opa_vnic_process_vema_config(adapter);
334
-
335
-
vema_get_veswport_info(port, recvd_mad, rsp_mad);
336
-
return;
337
-
338
-
err_exit:
339
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
340
-
}
341
-
342
-
/**
343
-
* vema_get_mac_entries -- Get MAC entries in VNIC MAC table
344
-
* @port: source port on which MAD was received
345
-
* @recvd_mad: pointer to the received mad
346
-
* @rsp_mad: pointer to respose mad
347
-
*
348
-
* This function gets the MAC entries that are programmed into
349
-
* the VNIC MAC forwarding table. It checks for the validity of
350
-
* the index into the MAC table and the number of entries that
351
-
* are to be retrieved.
352
-
*/
353
-
static void vema_get_mac_entries(struct opa_vnic_vema_port *port,
354
-
struct opa_vnic_vema_mad *recvd_mad,
355
-
struct opa_vnic_vema_mad *rsp_mad)
356
-
{
357
-
struct opa_veswport_mactable *mac_tbl_in, *mac_tbl_out;
358
-
struct opa_vnic_adapter *adapter;
359
-
360
-
adapter = vema_get_vport_adapter(recvd_mad, port);
361
-
if (!adapter) {
362
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
363
-
return;
364
-
}
365
-
366
-
mac_tbl_in = (struct opa_veswport_mactable *)recvd_mad->data;
367
-
mac_tbl_out = (struct opa_veswport_mactable *)rsp_mad->data;
368
-
369
-
if (vema_mac_tbl_req_ok(mac_tbl_in)) {
370
-
mac_tbl_out->offset = mac_tbl_in->offset;
371
-
mac_tbl_out->num_entries = mac_tbl_in->num_entries;
372
-
opa_vnic_query_mac_tbl(adapter, mac_tbl_out);
373
-
} else {
374
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
375
-
}
376
-
}
377
-
378
-
/**
379
-
* vema_set_mac_entries -- Set MAC entries in VNIC MAC table
380
-
* @port: source port on which MAD was received
381
-
* @recvd_mad: pointer to the received mad
382
-
* @rsp_mad: pointer to respose mad
383
-
*
384
-
* This function sets the MAC entries in the VNIC forwarding table
385
-
* It checks for the validity of the index and the number of forwarding
386
-
* table entries to be programmed.
387
-
*/
388
-
static void vema_set_mac_entries(struct opa_vnic_vema_port *port,
389
-
struct opa_vnic_vema_mad *recvd_mad,
390
-
struct opa_vnic_vema_mad *rsp_mad)
391
-
{
392
-
struct opa_veswport_mactable *mac_tbl;
393
-
struct opa_vnic_adapter *adapter;
394
-
395
-
adapter = vema_get_vport_adapter(recvd_mad, port);
396
-
if (!adapter) {
397
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
398
-
return;
399
-
}
400
-
401
-
mac_tbl = (struct opa_veswport_mactable *)recvd_mad->data;
402
-
if (vema_mac_tbl_req_ok(mac_tbl)) {
403
-
if (opa_vnic_update_mac_tbl(adapter, mac_tbl))
404
-
rsp_mad->mad_hdr.status = OPA_VNIC_UNSUP_ATTR;
405
-
} else {
406
-
rsp_mad->mad_hdr.status = OPA_VNIC_UNSUP_ATTR;
407
-
}
408
-
vema_get_mac_entries(port, recvd_mad, rsp_mad);
409
-
}
410
-
411
-
/**
412
-
* vema_set_delete_vesw -- Reset VESW info to POD values
413
-
* @port: source port on which MAD was received
414
-
* @recvd_mad: pointer to the received mad
415
-
* @rsp_mad: pointer to respose mad
416
-
*
417
-
* This function clears all the fields of veswport info for the requested vesw
418
-
* and sets them back to the power-on default values. It does not delete the
419
-
* vesw.
420
-
*/
421
-
static void vema_set_delete_vesw(struct opa_vnic_vema_port *port,
422
-
struct opa_vnic_vema_mad *recvd_mad,
423
-
struct opa_vnic_vema_mad *rsp_mad)
424
-
{
425
-
struct opa_veswport_info *port_info =
426
-
(struct opa_veswport_info *)rsp_mad->data;
427
-
struct opa_vnic_adapter *adapter;
428
-
429
-
adapter = vema_get_vport_adapter(recvd_mad, port);
430
-
if (!adapter) {
431
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
432
-
return;
433
-
}
434
-
435
-
vema_get_pod_values(port_info);
436
-
opa_vnic_set_vesw_info(adapter, &port_info->vesw);
437
-
opa_vnic_set_per_veswport_info(adapter, &port_info->vport);
438
-
439
-
/* Process the new config settings */
440
-
opa_vnic_process_vema_config(adapter);
441
-
442
-
opa_vnic_release_mac_tbl(adapter);
443
-
444
-
vema_get_veswport_info(port, recvd_mad, rsp_mad);
445
-
}
446
-
447
-
/**
448
-
* vema_get_mac_list -- Get the unicast/multicast macs.
449
-
* @port: source port on which MAD was received
450
-
* @recvd_mad: Received mad contains fields to set vnic parameters
451
-
* @rsp_mad: Response mad to be built
452
-
* @attr_id: Attribute ID indicating multicast or unicast mac list
453
-
*/
454
-
static void vema_get_mac_list(struct opa_vnic_vema_port *port,
455
-
struct opa_vnic_vema_mad *recvd_mad,
456
-
struct opa_vnic_vema_mad *rsp_mad,
457
-
u16 attr_id)
458
-
{
459
-
struct opa_veswport_iface_macs *macs_in, *macs_out;
460
-
int max_entries = (OPA_VNIC_EMA_DATA - sizeof(*macs_out)) / ETH_ALEN;
461
-
struct opa_vnic_adapter *adapter;
462
-
463
-
adapter = vema_get_vport_adapter(recvd_mad, port);
464
-
if (!adapter) {
465
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
466
-
return;
467
-
}
468
-
469
-
macs_in = (struct opa_veswport_iface_macs *)recvd_mad->data;
470
-
macs_out = (struct opa_veswport_iface_macs *)rsp_mad->data;
471
-
472
-
macs_out->start_idx = macs_in->start_idx;
473
-
if (macs_in->num_macs_in_msg)
474
-
macs_out->num_macs_in_msg = macs_in->num_macs_in_msg;
475
-
else
476
-
macs_out->num_macs_in_msg = cpu_to_be16(max_entries);
477
-
478
-
if (attr_id == OPA_EM_ATTR_IFACE_MCAST_MACS)
479
-
opa_vnic_query_mcast_macs(adapter, macs_out);
480
-
else
481
-
opa_vnic_query_ucast_macs(adapter, macs_out);
482
-
}
483
-
484
-
/**
485
-
* vema_get_summary_counters -- Gets summary counters.
486
-
* @port: source port on which MAD was received
487
-
* @recvd_mad: Received mad contains fields to set vnic parameters
488
-
* @rsp_mad: Response mad to be built
489
-
*/
490
-
static void vema_get_summary_counters(struct opa_vnic_vema_port *port,
491
-
struct opa_vnic_vema_mad *recvd_mad,
492
-
struct opa_vnic_vema_mad *rsp_mad)
493
-
{
494
-
struct opa_veswport_summary_counters *cntrs;
495
-
struct opa_vnic_adapter *adapter;
496
-
497
-
adapter = vema_get_vport_adapter(recvd_mad, port);
498
-
if (adapter) {
499
-
cntrs = (struct opa_veswport_summary_counters *)rsp_mad->data;
500
-
opa_vnic_get_summary_counters(adapter, cntrs);
501
-
} else {
502
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
503
-
}
504
-
}
505
-
506
-
/**
507
-
* vema_get_error_counters -- Gets summary counters.
508
-
* @port: source port on which MAD was received
509
-
* @recvd_mad: Received mad contains fields to set vnic parameters
510
-
* @rsp_mad: Response mad to be built
511
-
*/
512
-
static void vema_get_error_counters(struct opa_vnic_vema_port *port,
513
-
struct opa_vnic_vema_mad *recvd_mad,
514
-
struct opa_vnic_vema_mad *rsp_mad)
515
-
{
516
-
struct opa_veswport_error_counters *cntrs;
517
-
struct opa_vnic_adapter *adapter;
518
-
519
-
adapter = vema_get_vport_adapter(recvd_mad, port);
520
-
if (adapter) {
521
-
cntrs = (struct opa_veswport_error_counters *)rsp_mad->data;
522
-
opa_vnic_get_error_counters(adapter, cntrs);
523
-
} else {
524
-
rsp_mad->mad_hdr.status = OPA_VNIC_INVAL_ATTR;
525
-
}
526
-
}
527
-
528
-
/**
529
-
* vema_get -- Process received get MAD
530
-
* @port: source port on which MAD was received
531
-
* @recvd_mad: Received mad
532
-
* @rsp_mad: Response mad to be built
533
-
*/
534
-
static void vema_get(struct opa_vnic_vema_port *port,
535
-
struct opa_vnic_vema_mad *recvd_mad,
536
-
struct opa_vnic_vema_mad *rsp_mad)
537
-
{
538
-
u16 attr_id = be16_to_cpu(recvd_mad->mad_hdr.attr_id);
539
-
540
-
switch (attr_id) {
541
-
case OPA_EM_ATTR_CLASS_PORT_INFO:
542
-
vema_get_class_port_info(port, recvd_mad, rsp_mad);
543
-
break;
544
-
case OPA_EM_ATTR_VESWPORT_INFO:
545
-
vema_get_veswport_info(port, recvd_mad, rsp_mad);
546
-
break;
547
-
case OPA_EM_ATTR_VESWPORT_MAC_ENTRIES:
548
-
vema_get_mac_entries(port, recvd_mad, rsp_mad);
549
-
break;
550
-
case OPA_EM_ATTR_IFACE_UCAST_MACS:
551
-
case OPA_EM_ATTR_IFACE_MCAST_MACS:
552
-
vema_get_mac_list(port, recvd_mad, rsp_mad, attr_id);
553
-
break;
554
-
case OPA_EM_ATTR_VESWPORT_SUMMARY_COUNTERS:
555
-
vema_get_summary_counters(port, recvd_mad, rsp_mad);
556
-
break;
557
-
case OPA_EM_ATTR_VESWPORT_ERROR_COUNTERS:
558
-
vema_get_error_counters(port, recvd_mad, rsp_mad);
559
-
break;
560
-
default:
561
-
rsp_mad->mad_hdr.status = OPA_VNIC_UNSUP_ATTR;
562
-
break;
563
-
}
564
-
}
565
-
566
-
/**
567
-
* vema_set -- Process received set MAD
568
-
* @port: source port on which MAD was received
569
-
* @recvd_mad: Received mad contains fields to set vnic parameters
570
-
* @rsp_mad: Response mad to be built
571
-
*/
572
-
static void vema_set(struct opa_vnic_vema_port *port,
573
-
struct opa_vnic_vema_mad *recvd_mad,
574
-
struct opa_vnic_vema_mad *rsp_mad)
575
-
{
576
-
u16 attr_id = be16_to_cpu(recvd_mad->mad_hdr.attr_id);
577
-
578
-
switch (attr_id) {
579
-
case OPA_EM_ATTR_CLASS_PORT_INFO:
580
-
vema_set_class_port_info(port, recvd_mad, rsp_mad);
581
-
break;
582
-
case OPA_EM_ATTR_VESWPORT_INFO:
583
-
vema_set_veswport_info(port, recvd_mad, rsp_mad);
584
-
break;
585
-
case OPA_EM_ATTR_VESWPORT_MAC_ENTRIES:
586
-
vema_set_mac_entries(port, recvd_mad, rsp_mad);
587
-
break;
588
-
case OPA_EM_ATTR_DELETE_VESW:
589
-
vema_set_delete_vesw(port, recvd_mad, rsp_mad);
590
-
break;
591
-
default:
592
-
rsp_mad->mad_hdr.status = OPA_VNIC_UNSUP_ATTR;
593
-
break;
594
-
}
595
-
}
596
-
597
-
/**
598
-
* vema_send -- Send handler for VEMA MAD agent
599
-
* @mad_agent: pointer to the mad agent
600
-
* @mad_wc: pointer to mad send work completion information
601
-
*
602
-
* Free all the data structures associated with the sent MAD
603
-
*/
604
-
static void vema_send(struct ib_mad_agent *mad_agent,
605
-
struct ib_mad_send_wc *mad_wc)
606
-
{
607
-
rdma_destroy_ah(mad_wc->send_buf->ah, RDMA_DESTROY_AH_SLEEPABLE);
608
-
ib_free_send_mad(mad_wc->send_buf);
609
-
}
610
-
611
-
/**
612
-
* vema_recv -- Recv handler for VEMA MAD agent
613
-
* @mad_agent: pointer to the mad agent
614
-
* @send_buf: Send buffer if found, else NULL
615
-
* @mad_wc: pointer to mad send work completion information
616
-
*
617
-
* Handle only set and get methods and respond to other methods
618
-
* as unsupported. Allocate response buffer and address handle
619
-
* for the response MAD.
620
-
*/
621
-
static void vema_recv(struct ib_mad_agent *mad_agent,
622
-
struct ib_mad_send_buf *send_buf,
623
-
struct ib_mad_recv_wc *mad_wc)
624
-
{
625
-
struct opa_vnic_vema_port *port;
626
-
struct ib_ah *ah;
627
-
struct ib_mad_send_buf *rsp;
628
-
struct opa_vnic_vema_mad *vema_mad;
629
-
630
-
if (!mad_wc || !mad_wc->recv_buf.mad)
631
-
return;
632
-
633
-
port = mad_agent->context;
634
-
ah = ib_create_ah_from_wc(mad_agent->qp->pd, mad_wc->wc,
635
-
mad_wc->recv_buf.grh, mad_agent->port_num);
636
-
if (IS_ERR(ah))
637
-
goto free_recv_mad;
638
-
639
-
rsp = ib_create_send_mad(mad_agent, mad_wc->wc->src_qp,
640
-
mad_wc->wc->pkey_index, 0,
641
-
IB_MGMT_VENDOR_HDR, OPA_VNIC_EMA_DATA,
642
-
GFP_KERNEL, OPA_MGMT_BASE_VERSION);
643
-
if (IS_ERR(rsp))
644
-
goto err_rsp;
645
-
646
-
rsp->ah = ah;
647
-
vema_mad = rsp->mad;
648
-
memcpy(vema_mad, mad_wc->recv_buf.mad, IB_MGMT_VENDOR_HDR);
649
-
vema_mad->mad_hdr.method = IB_MGMT_METHOD_GET_RESP;
650
-
vema_mad->mad_hdr.status = 0;
651
-
652
-
/* Lock ensures network adapter is not removed */
653
-
mutex_lock(&port->lock);
654
-
655
-
switch (mad_wc->recv_buf.mad->mad_hdr.method) {
656
-
case IB_MGMT_METHOD_GET:
657
-
vema_get(port, (struct opa_vnic_vema_mad *)mad_wc->recv_buf.mad,
658
-
vema_mad);
659
-
break;
660
-
case IB_MGMT_METHOD_SET:
661
-
vema_set(port, (struct opa_vnic_vema_mad *)mad_wc->recv_buf.mad,
662
-
vema_mad);
663
-
break;
664
-
default:
665
-
vema_mad->mad_hdr.status = OPA_VNIC_UNSUP_ATTR;
666
-
break;
667
-
}
668
-
mutex_unlock(&port->lock);
669
-
670
-
if (!ib_post_send_mad(rsp, NULL)) {
671
-
/*
672
-
* with post send successful ah and send mad
673
-
* will be destroyed in send handler
674
-
*/
675
-
goto free_recv_mad;
676
-
}
677
-
678
-
ib_free_send_mad(rsp);
679
-
680
-
err_rsp:
681
-
rdma_destroy_ah(ah, RDMA_DESTROY_AH_SLEEPABLE);
682
-
free_recv_mad:
683
-
ib_free_recv_mad(mad_wc);
684
-
}
685
-
686
-
/**
687
-
* vema_get_port -- Gets the opa_vnic_vema_port
688
-
* @cport: pointer to control dev
689
-
* @port_num: Port number
690
-
*
691
-
* This function loops through the ports and returns
692
-
* the opa_vnic_vema port structure that is associated
693
-
* with the OPA port number
694
-
*
695
-
* Return: ptr to requested opa_vnic_vema_port strucure
696
-
* if success, NULL if not
697
-
*/
698
-
static struct opa_vnic_vema_port *
699
-
vema_get_port(struct opa_vnic_ctrl_port *cport, u8 port_num)
700
-
{
701
-
struct opa_vnic_vema_port *port = (void *)cport + sizeof(*cport);
702
-
703
-
if (port_num > cport->num_ports)
704
-
return NULL;
705
-
706
-
return port + (port_num - 1);
707
-
}
708
-
709
-
/**
710
-
* opa_vnic_vema_send_trap -- This function sends a trap to the EM
711
-
* @adapter: pointer to vnic adapter
712
-
* @data: pointer to trap data filled by calling function
713
-
* @lid: issuers lid (encap_slid from vesw_port_info)
714
-
*
715
-
* This function is called from the VNIC driver to send a trap if there
716
-
* is somethng the EM should be notified about. These events currently
717
-
* are
718
-
* 1) UNICAST INTERFACE MACADDRESS changes
719
-
* 2) MULTICAST INTERFACE MACADDRESS changes
720
-
* 3) ETHERNET LINK STATUS changes
721
-
* While allocating the send mad the remote site qpn used is 1
722
-
* as this is the well known QP.
723
-
*
724
-
*/
725
-
void opa_vnic_vema_send_trap(struct opa_vnic_adapter *adapter,
726
-
struct __opa_veswport_trap *data, u32 lid)
727
-
{
728
-
struct opa_vnic_ctrl_port *cport = adapter->cport;
729
-
struct ib_mad_send_buf *send_buf;
730
-
struct opa_vnic_vema_port *port;
731
-
struct ib_device *ibp;
732
-
struct opa_vnic_vema_mad_trap *trap_mad;
733
-
struct opa_class_port_info *class;
734
-
struct rdma_ah_attr ah_attr;
735
-
struct ib_ah *ah;
736
-
struct opa_veswport_trap *trap;
737
-
u32 trap_lid;
738
-
u16 pkey_idx;
739
-
740
-
if (!cport)
741
-
goto err_exit;
742
-
ibp = cport->ibdev;
743
-
port = vema_get_port(cport, data->opaportnum);
744
-
if (!port || !port->mad_agent)
745
-
goto err_exit;
746
-
747
-
if (time_before(jiffies, adapter->trap_timeout)) {
748
-
if (adapter->trap_count == OPA_VNIC_TRAP_BURST_LIMIT) {
749
-
v_warn("Trap rate exceeded\n");
750
-
goto err_exit;
751
-
} else {
752
-
adapter->trap_count++;
753
-
}
754
-
} else {
755
-
adapter->trap_count = 0;
756
-
}
757
-
758
-
class = &port->class_port_info;
759
-
/* Set up address handle */
760
-
memset(&ah_attr, 0, sizeof(ah_attr));
761
-
ah_attr.type = rdma_ah_find_type(ibp, port->port_num);
762
-
rdma_ah_set_sl(&ah_attr,
763
-
GET_TRAP_SL_FROM_CLASS_PORT_INFO(class->trap_sl_rsvd));
764
-
rdma_ah_set_port_num(&ah_attr, port->port_num);
765
-
trap_lid = be32_to_cpu(class->trap_lid);
766
-
/*
767
-
* check for trap lid validity, must not be zero
768
-
* The trap sink could change after we fashion the MAD but since traps
769
-
* are not guaranteed we won't use a lock as anyway the change will take
770
-
* place even with locking.
771
-
*/
772
-
if (!trap_lid) {
773
-
c_err("%s: Invalid dlid\n", __func__);
774
-
goto err_exit;
775
-
}
776
-
777
-
rdma_ah_set_dlid(&ah_attr, trap_lid);
778
-
ah = rdma_create_ah(port->mad_agent->qp->pd, &ah_attr, 0);
779
-
if (IS_ERR(ah)) {
780
-
c_err("%s:Couldn't create new AH = %p\n", __func__, ah);
781
-
c_err("%s:dlid = %d, sl = %d, port = %d\n", __func__,
782
-
rdma_ah_get_dlid(&ah_attr), rdma_ah_get_sl(&ah_attr),
783
-
rdma_ah_get_port_num(&ah_attr));
784
-
goto err_exit;
785
-
}
786
-
787
-
if (ib_find_pkey(ibp, data->opaportnum, IB_DEFAULT_PKEY_FULL,
788
-
&pkey_idx) < 0) {
789
-
c_err("%s:full key not found, defaulting to partial\n",
790
-
__func__);
791
-
if (ib_find_pkey(ibp, data->opaportnum, IB_DEFAULT_PKEY_PARTIAL,
792
-
&pkey_idx) < 0)
793
-
pkey_idx = 1;
794
-
}
795
-
796
-
send_buf = ib_create_send_mad(port->mad_agent, 1, pkey_idx, 0,
797
-
IB_MGMT_VENDOR_HDR, IB_MGMT_MAD_DATA,
798
-
GFP_ATOMIC, OPA_MGMT_BASE_VERSION);
799
-
if (IS_ERR(send_buf)) {
800
-
c_err("%s:Couldn't allocate send buf\n", __func__);
801
-
goto err_sndbuf;
802
-
}
803
-
804
-
send_buf->ah = ah;
805
-
806
-
/* Set up common MAD hdr */
807
-
trap_mad = send_buf->mad;
808
-
trap_mad->mad_hdr.base_version = OPA_MGMT_BASE_VERSION;
809
-
trap_mad->mad_hdr.mgmt_class = OPA_MGMT_CLASS_INTEL_EMA;
810
-
trap_mad->mad_hdr.class_version = OPA_EMA_CLASS_VERSION;
811
-
trap_mad->mad_hdr.method = IB_MGMT_METHOD_TRAP;
812
-
port->tid++;
813
-
trap_mad->mad_hdr.tid = cpu_to_be64(port->tid);
814
-
trap_mad->mad_hdr.attr_id = IB_SMP_ATTR_NOTICE;
815
-
816
-
/* Set up vendor OUI */
817
-
trap_mad->oui[0] = INTEL_OUI_1;
818
-
trap_mad->oui[1] = INTEL_OUI_2;
819
-
trap_mad->oui[2] = INTEL_OUI_3;
820
-
821
-
/* Setup notice attribute portion */
822
-
trap_mad->notice.gen_type = OPA_INTEL_EMA_NOTICE_TYPE_INFO << 1;
823
-
trap_mad->notice.oui_1 = INTEL_OUI_1;
824
-
trap_mad->notice.oui_2 = INTEL_OUI_2;
825
-
trap_mad->notice.oui_3 = INTEL_OUI_3;
826
-
trap_mad->notice.issuer_lid = cpu_to_be32(lid);
827
-
828
-
/* copy the actual trap data */
829
-
trap = (struct opa_veswport_trap *)trap_mad->notice.raw_data;
830
-
trap->fabric_id = cpu_to_be16(data->fabric_id);
831
-
trap->veswid = cpu_to_be16(data->veswid);
832
-
trap->veswportnum = cpu_to_be32(data->veswportnum);
833
-
trap->opaportnum = cpu_to_be16(data->opaportnum);
834
-
trap->veswportindex = data->veswportindex;
835
-
trap->opcode = data->opcode;
836
-
837
-
/* If successful send set up rate limit timeout else bail */
838
-
if (ib_post_send_mad(send_buf, NULL)) {
839
-
ib_free_send_mad(send_buf);
840
-
} else {
841
-
if (adapter->trap_count)
842
-
return;
843
-
adapter->trap_timeout = jiffies +
844
-
usecs_to_jiffies(OPA_VNIC_TRAP_TIMEOUT);
845
-
return;
846
-
}
847
-
848
-
err_sndbuf:
849
-
rdma_destroy_ah(ah, 0);
850
-
err_exit:
851
-
v_err("Aborting trap\n");
852
-
}
853
-
854
-
static void opa_vnic_event(struct ib_event_handler *handler,
855
-
struct ib_event *record)
856
-
{
857
-
struct opa_vnic_vema_port *port =
858
-
container_of(handler, struct opa_vnic_vema_port, event_handler);
859
-
struct opa_vnic_ctrl_port *cport = port->cport;
860
-
struct opa_vnic_adapter *adapter;
861
-
unsigned long index;
862
-
863
-
if (record->element.port_num != port->port_num)
864
-
return;
865
-
866
-
c_dbg("OPA_VNIC received event %d on device %s port %d\n",
867
-
record->event, dev_name(&record->device->dev),
868
-
record->element.port_num);
869
-
870
-
if (record->event != IB_EVENT_PORT_ERR &&
871
-
record->event != IB_EVENT_PORT_ACTIVE)
872
-
return;
873
-
874
-
xa_for_each(&port->vports, index, adapter) {
875
-
if (record->event == IB_EVENT_PORT_ACTIVE)
876
-
netif_carrier_on(adapter->netdev);
877
-
else
878
-
netif_carrier_off(adapter->netdev);
879
-
}
880
-
}
881
-
882
-
/**
883
-
* vema_unregister -- Unregisters agent
884
-
* @cport: pointer to control port
885
-
*
886
-
* This deletes the registration by VEMA for MADs
887
-
*/
888
-
static void vema_unregister(struct opa_vnic_ctrl_port *cport)
889
-
{
890
-
struct opa_vnic_adapter *adapter;
891
-
unsigned long index;
892
-
int i;
893
-
894
-
for (i = 1; i <= cport->num_ports; i++) {
895
-
struct opa_vnic_vema_port *port = vema_get_port(cport, i);
896
-
897
-
if (!port->mad_agent)
898
-
continue;
899
-
900
-
/* Lock ensures no MAD is being processed */
901
-
mutex_lock(&port->lock);
902
-
xa_for_each(&port->vports, index, adapter)
903
-
opa_vnic_rem_netdev(adapter);
904
-
mutex_unlock(&port->lock);
905
-
906
-
ib_unregister_mad_agent(port->mad_agent);
907
-
port->mad_agent = NULL;
908
-
mutex_destroy(&port->lock);
909
-
xa_destroy(&port->vports);
910
-
ib_unregister_event_handler(&port->event_handler);
911
-
}
912
-
}
913
-
914
-
/**
915
-
* vema_register -- Registers agent
916
-
* @cport: pointer to control port
917
-
*
918
-
* This function registers the handlers for the VEMA MADs
919
-
*
920
-
* Return: returns 0 on success. non zero otherwise
921
-
*/
922
-
static int vema_register(struct opa_vnic_ctrl_port *cport)
923
-
{
924
-
struct ib_mad_reg_req reg_req = {
925
-
.mgmt_class = OPA_MGMT_CLASS_INTEL_EMA,
926
-
.mgmt_class_version = OPA_MGMT_BASE_VERSION,
927
-
.oui = { INTEL_OUI_1, INTEL_OUI_2, INTEL_OUI_3 }
928
-
};
929
-
int i;
930
-
931
-
set_bit(IB_MGMT_METHOD_GET, reg_req.method_mask);
932
-
set_bit(IB_MGMT_METHOD_SET, reg_req.method_mask);
933
-
934
-
/* register ib event handler and mad agent for each port on dev */
935
-
for (i = 1; i <= cport->num_ports; i++) {
936
-
struct opa_vnic_vema_port *port = vema_get_port(cport, i);
937
-
int ret;
938
-
939
-
port->cport = cport;
940
-
port->port_num = i;
941
-
942
-
INIT_IB_EVENT_HANDLER(&port->event_handler,
943
-
cport->ibdev, opa_vnic_event);
944
-
ib_register_event_handler(&port->event_handler);
945
-
946
-
xa_init(&port->vports);
947
-
mutex_init(&port->lock);
948
-
port->mad_agent = ib_register_mad_agent(cport->ibdev, i,
949
-
IB_QPT_GSI, ®_req,
950
-
IB_MGMT_RMPP_VERSION,
951
-
vema_send, vema_recv,
952
-
port, 0);
953
-
if (IS_ERR(port->mad_agent)) {
954
-
ret = PTR_ERR(port->mad_agent);
955
-
port->mad_agent = NULL;
956
-
mutex_destroy(&port->lock);
957
-
vema_unregister(cport);
958
-
return ret;
959
-
}
960
-
}
961
-
962
-
return 0;
963
-
}
964
-
965
-
/**
966
-
* opa_vnic_ctrl_config_dev -- This function sends a trap to the EM
967
-
* by way of ib_modify_port to indicate support for ethernet on the
968
-
* fabric.
969
-
* @cport: pointer to control port
970
-
* @en: enable or disable ethernet on fabric support
971
-
*/
972
-
static void opa_vnic_ctrl_config_dev(struct opa_vnic_ctrl_port *cport, bool en)
973
-
{
974
-
struct ib_port_modify pm = { 0 };
975
-
int i;
976
-
977
-
if (en)
978
-
pm.set_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported;
979
-
else
980
-
pm.clr_port_cap_mask = OPA_CAP_MASK3_IsEthOnFabricSupported;
981
-
982
-
for (i = 1; i <= cport->num_ports; i++)
983
-
ib_modify_port(cport->ibdev, i, IB_PORT_OPA_MASK_CHG, &pm);
984
-
}
985
-
986
-
/**
987
-
* opa_vnic_vema_add_one -- Handle new ib device
988
-
* @device: ib device pointer
989
-
*
990
-
* Allocate the vnic control port and initialize it.
991
-
*/
992
-
static int opa_vnic_vema_add_one(struct ib_device *device)
993
-
{
994
-
struct opa_vnic_ctrl_port *cport;
995
-
int rc, size = sizeof(*cport);
996
-
997
-
if (!rdma_cap_opa_vnic(device))
998
-
return -EOPNOTSUPP;
999
-
1000
-
size += device->phys_port_cnt * sizeof(struct opa_vnic_vema_port);
1001
-
cport = kzalloc(size, GFP_KERNEL);
1002
-
if (!cport)
1003
-
return -ENOMEM;
1004
-
1005
-
cport->num_ports = device->phys_port_cnt;
1006
-
cport->ibdev = device;
1007
-
1008
-
/* Initialize opa vnic management agent (vema) */
1009
-
rc = vema_register(cport);
1010
-
if (!rc)
1011
-
c_info("VNIC client initialized\n");
1012
-
1013
-
ib_set_client_data(device, &opa_vnic_client, cport);
1014
-
opa_vnic_ctrl_config_dev(cport, true);
1015
-
return 0;
1016
-
}
1017
-
1018
-
/**
1019
-
* opa_vnic_vema_rem_one -- Handle ib device removal
1020
-
* @device: ib device pointer
1021
-
* @client_data: ib client data
1022
-
*
1023
-
* Uninitialize and free the vnic control port.
1024
-
*/
1025
-
static void opa_vnic_vema_rem_one(struct ib_device *device,
1026
-
void *client_data)
1027
-
{
1028
-
struct opa_vnic_ctrl_port *cport = client_data;
1029
-
1030
-
c_info("removing VNIC client\n");
1031
-
opa_vnic_ctrl_config_dev(cport, false);
1032
-
vema_unregister(cport);
1033
-
kfree(cport);
1034
-
}
1035
-
1036
-
static int __init opa_vnic_init(void)
1037
-
{
1038
-
int rc;
1039
-
1040
-
rc = ib_register_client(&opa_vnic_client);
1041
-
if (rc)
1042
-
pr_err("VNIC driver register failed %d\n", rc);
1043
-
1044
-
return rc;
1045
-
}
1046
-
module_init(opa_vnic_init);
1047
-
1048
-
static void opa_vnic_deinit(void)
1049
-
{
1050
-
ib_unregister_client(&opa_vnic_client);
1051
-
}
1052
-
module_exit(opa_vnic_deinit);
1053
-
1054
-
MODULE_LICENSE("Dual BSD/GPL");
1055
-
MODULE_AUTHOR("Cornelis Networks");
1056
-
MODULE_DESCRIPTION("Cornelis OPX Virtual Network driver");
-390
drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c
-390
drivers/infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c
···
1
-
/*
2
-
* Copyright(c) 2017 Intel Corporation.
3
-
*
4
-
* This file is provided under a dual BSD/GPLv2 license. When using or
5
-
* redistributing this file, you may do so under either license.
6
-
*
7
-
* GPL LICENSE SUMMARY
8
-
*
9
-
* This program is free software; you can redistribute it and/or modify
10
-
* it under the terms of version 2 of the GNU General Public License as
11
-
* published by the Free Software Foundation.
12
-
*
13
-
* This program is distributed in the hope that it will be useful, but
14
-
* WITHOUT ANY WARRANTY; without even the implied warranty of
15
-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16
-
* General Public License for more details.
17
-
*
18
-
* BSD LICENSE
19
-
*
20
-
* Redistribution and use in source and binary forms, with or without
21
-
* modification, are permitted provided that the following conditions
22
-
* are met:
23
-
*
24
-
* - Redistributions of source code must retain the above copyright
25
-
* notice, this list of conditions and the following disclaimer.
26
-
* - Redistributions in binary form must reproduce the above copyright
27
-
* notice, this list of conditions and the following disclaimer in
28
-
* the documentation and/or other materials provided with the
29
-
* distribution.
30
-
* - Neither the name of Intel Corporation nor the names of its
31
-
* contributors may be used to endorse or promote products derived
32
-
* from this software without specific prior written permission.
33
-
*
34
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38
-
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39
-
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40
-
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41
-
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42
-
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43
-
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44
-
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45
-
*
46
-
*/
47
-
48
-
/*
49
-
* This file contains OPA VNIC EMA Interface functions.
50
-
*/
51
-
52
-
#include "opa_vnic_internal.h"
53
-
54
-
/**
55
-
* opa_vnic_vema_report_event - sent trap to report the specified event
56
-
* @adapter: vnic port adapter
57
-
* @event: event to be reported
58
-
*
59
-
* This function calls vema api to sent a trap for the given event.
60
-
*/
61
-
void opa_vnic_vema_report_event(struct opa_vnic_adapter *adapter, u8 event)
62
-
{
63
-
struct __opa_veswport_info *info = &adapter->info;
64
-
struct __opa_veswport_trap trap_data;
65
-
66
-
trap_data.fabric_id = info->vesw.fabric_id;
67
-
trap_data.veswid = info->vesw.vesw_id;
68
-
trap_data.veswportnum = info->vport.port_num;
69
-
trap_data.opaportnum = adapter->port_num;
70
-
trap_data.veswportindex = adapter->vport_num;
71
-
trap_data.opcode = event;
72
-
73
-
opa_vnic_vema_send_trap(adapter, &trap_data, info->vport.encap_slid);
74
-
}
75
-
76
-
/**
77
-
* opa_vnic_get_summary_counters - get summary counters
78
-
* @adapter: vnic port adapter
79
-
* @cntrs: pointer to destination summary counters structure
80
-
*
81
-
* This function populates the summary counters that is maintained by the
82
-
* given adapter to destination address provided.
83
-
*/
84
-
void opa_vnic_get_summary_counters(struct opa_vnic_adapter *adapter,
85
-
struct opa_veswport_summary_counters *cntrs)
86
-
{
87
-
struct opa_vnic_stats vstats;
88
-
__be64 *dst;
89
-
u64 *src;
90
-
91
-
memset(&vstats, 0, sizeof(vstats));
92
-
spin_lock(&adapter->stats_lock);
93
-
adapter->rn_ops->ndo_get_stats64(adapter->netdev, &vstats.netstats);
94
-
spin_unlock(&adapter->stats_lock);
95
-
96
-
cntrs->vp_instance = cpu_to_be16(adapter->vport_num);
97
-
cntrs->vesw_id = cpu_to_be16(adapter->info.vesw.vesw_id);
98
-
cntrs->veswport_num = cpu_to_be32(adapter->port_num);
99
-
100
-
cntrs->tx_errors = cpu_to_be64(vstats.netstats.tx_errors);
101
-
cntrs->rx_errors = cpu_to_be64(vstats.netstats.rx_errors);
102
-
cntrs->tx_packets = cpu_to_be64(vstats.netstats.tx_packets);
103
-
cntrs->rx_packets = cpu_to_be64(vstats.netstats.rx_packets);
104
-
cntrs->tx_bytes = cpu_to_be64(vstats.netstats.tx_bytes);
105
-
cntrs->rx_bytes = cpu_to_be64(vstats.netstats.rx_bytes);
106
-
107
-
/*
108
-
* This loop depends on layout of
109
-
* opa_veswport_summary_counters opa_vnic_stats structures.
110
-
*/
111
-
for (dst = &cntrs->tx_unicast, src = &vstats.tx_grp.unicast;
112
-
dst < &cntrs->reserved[0]; dst++, src++) {
113
-
*dst = cpu_to_be64(*src);
114
-
}
115
-
}
116
-
117
-
/**
118
-
* opa_vnic_get_error_counters - get error counters
119
-
* @adapter: vnic port adapter
120
-
* @cntrs: pointer to destination error counters structure
121
-
*
122
-
* This function populates the error counters that is maintained by the
123
-
* given adapter to destination address provided.
124
-
*/
125
-
void opa_vnic_get_error_counters(struct opa_vnic_adapter *adapter,
126
-
struct opa_veswport_error_counters *cntrs)
127
-
{
128
-
struct opa_vnic_stats vstats;
129
-
130
-
memset(&vstats, 0, sizeof(vstats));
131
-
spin_lock(&adapter->stats_lock);
132
-
adapter->rn_ops->ndo_get_stats64(adapter->netdev, &vstats.netstats);
133
-
spin_unlock(&adapter->stats_lock);
134
-
135
-
cntrs->vp_instance = cpu_to_be16(adapter->vport_num);
136
-
cntrs->vesw_id = cpu_to_be16(adapter->info.vesw.vesw_id);
137
-
cntrs->veswport_num = cpu_to_be32(adapter->port_num);
138
-
139
-
cntrs->tx_errors = cpu_to_be64(vstats.netstats.tx_errors);
140
-
cntrs->rx_errors = cpu_to_be64(vstats.netstats.rx_errors);
141
-
cntrs->tx_dlid_zero = cpu_to_be64(vstats.tx_dlid_zero);
142
-
cntrs->tx_drop_state = cpu_to_be64(vstats.tx_drop_state);
143
-
cntrs->tx_logic = cpu_to_be64(vstats.netstats.tx_fifo_errors +
144
-
vstats.netstats.tx_carrier_errors);
145
-
146
-
cntrs->rx_bad_veswid = cpu_to_be64(vstats.netstats.rx_nohandler);
147
-
cntrs->rx_runt = cpu_to_be64(vstats.rx_runt);
148
-
cntrs->rx_oversize = cpu_to_be64(vstats.rx_oversize);
149
-
cntrs->rx_drop_state = cpu_to_be64(vstats.rx_drop_state);
150
-
cntrs->rx_logic = cpu_to_be64(vstats.netstats.rx_fifo_errors);
151
-
}
152
-
153
-
/**
154
-
* opa_vnic_get_vesw_info -- Get the vesw information
155
-
* @adapter: vnic port adapter
156
-
* @info: pointer to destination vesw info structure
157
-
*
158
-
* This function copies the vesw info that is maintained by the
159
-
* given adapter to destination address provided.
160
-
*/
161
-
void opa_vnic_get_vesw_info(struct opa_vnic_adapter *adapter,
162
-
struct opa_vesw_info *info)
163
-
{
164
-
struct __opa_vesw_info *src = &adapter->info.vesw;
165
-
int i;
166
-
167
-
info->fabric_id = cpu_to_be16(src->fabric_id);
168
-
info->vesw_id = cpu_to_be16(src->vesw_id);
169
-
memcpy(info->rsvd0, src->rsvd0, ARRAY_SIZE(src->rsvd0));
170
-
info->def_port_mask = cpu_to_be16(src->def_port_mask);
171
-
memcpy(info->rsvd1, src->rsvd1, ARRAY_SIZE(src->rsvd1));
172
-
info->pkey = cpu_to_be16(src->pkey);
173
-
174
-
memcpy(info->rsvd2, src->rsvd2, ARRAY_SIZE(src->rsvd2));
175
-
info->u_mcast_dlid = cpu_to_be32(src->u_mcast_dlid);
176
-
for (i = 0; i < OPA_VESW_MAX_NUM_DEF_PORT; i++)
177
-
info->u_ucast_dlid[i] = cpu_to_be32(src->u_ucast_dlid[i]);
178
-
179
-
info->rc = cpu_to_be32(src->rc);
180
-
181
-
memcpy(info->rsvd3, src->rsvd3, ARRAY_SIZE(src->rsvd3));
182
-
info->eth_mtu = cpu_to_be16(src->eth_mtu);
183
-
memcpy(info->rsvd4, src->rsvd4, ARRAY_SIZE(src->rsvd4));
184
-
}
185
-
186
-
/**
187
-
* opa_vnic_set_vesw_info -- Set the vesw information
188
-
* @adapter: vnic port adapter
189
-
* @info: pointer to vesw info structure
190
-
*
191
-
* This function updates the vesw info that is maintained by the
192
-
* given adapter with vesw info provided. Reserved fields are stored
193
-
* and returned back to EM as is.
194
-
*/
195
-
void opa_vnic_set_vesw_info(struct opa_vnic_adapter *adapter,
196
-
struct opa_vesw_info *info)
197
-
{
198
-
struct __opa_vesw_info *dst = &adapter->info.vesw;
199
-
int i;
200
-
201
-
dst->fabric_id = be16_to_cpu(info->fabric_id);
202
-
dst->vesw_id = be16_to_cpu(info->vesw_id);
203
-
memcpy(dst->rsvd0, info->rsvd0, ARRAY_SIZE(info->rsvd0));
204
-
dst->def_port_mask = be16_to_cpu(info->def_port_mask);
205
-
memcpy(dst->rsvd1, info->rsvd1, ARRAY_SIZE(info->rsvd1));
206
-
dst->pkey = be16_to_cpu(info->pkey);
207
-
208
-
memcpy(dst->rsvd2, info->rsvd2, ARRAY_SIZE(info->rsvd2));
209
-
dst->u_mcast_dlid = be32_to_cpu(info->u_mcast_dlid);
210
-
for (i = 0; i < OPA_VESW_MAX_NUM_DEF_PORT; i++)
211
-
dst->u_ucast_dlid[i] = be32_to_cpu(info->u_ucast_dlid[i]);
212
-
213
-
dst->rc = be32_to_cpu(info->rc);
214
-
215
-
memcpy(dst->rsvd3, info->rsvd3, ARRAY_SIZE(info->rsvd3));
216
-
dst->eth_mtu = be16_to_cpu(info->eth_mtu);
217
-
memcpy(dst->rsvd4, info->rsvd4, ARRAY_SIZE(info->rsvd4));
218
-
}
219
-
220
-
/**
221
-
* opa_vnic_get_per_veswport_info -- Get the vesw per port information
222
-
* @adapter: vnic port adapter
223
-
* @info: pointer to destination vport info structure
224
-
*
225
-
* This function copies the vesw per port info that is maintained by the
226
-
* given adapter to destination address provided.
227
-
* Note that the read only fields are not copied.
228
-
*/
229
-
void opa_vnic_get_per_veswport_info(struct opa_vnic_adapter *adapter,
230
-
struct opa_per_veswport_info *info)
231
-
{
232
-
struct __opa_per_veswport_info *src = &adapter->info.vport;
233
-
234
-
info->port_num = cpu_to_be32(src->port_num);
235
-
info->eth_link_status = src->eth_link_status;
236
-
memcpy(info->rsvd0, src->rsvd0, ARRAY_SIZE(src->rsvd0));
237
-
238
-
memcpy(info->base_mac_addr, src->base_mac_addr,
239
-
ARRAY_SIZE(info->base_mac_addr));
240
-
info->config_state = src->config_state;
241
-
info->oper_state = src->oper_state;
242
-
info->max_mac_tbl_ent = cpu_to_be16(src->max_mac_tbl_ent);
243
-
info->max_smac_ent = cpu_to_be16(src->max_smac_ent);
244
-
info->mac_tbl_digest = cpu_to_be32(src->mac_tbl_digest);
245
-
memcpy(info->rsvd1, src->rsvd1, ARRAY_SIZE(src->rsvd1));
246
-
247
-
info->encap_slid = cpu_to_be32(src->encap_slid);
248
-
memcpy(info->pcp_to_sc_uc, src->pcp_to_sc_uc,
249
-
ARRAY_SIZE(info->pcp_to_sc_uc));
250
-
memcpy(info->pcp_to_vl_uc, src->pcp_to_vl_uc,
251
-
ARRAY_SIZE(info->pcp_to_vl_uc));
252
-
memcpy(info->pcp_to_sc_mc, src->pcp_to_sc_mc,
253
-
ARRAY_SIZE(info->pcp_to_sc_mc));
254
-
memcpy(info->pcp_to_vl_mc, src->pcp_to_vl_mc,
255
-
ARRAY_SIZE(info->pcp_to_vl_mc));
256
-
info->non_vlan_sc_uc = src->non_vlan_sc_uc;
257
-
info->non_vlan_vl_uc = src->non_vlan_vl_uc;
258
-
info->non_vlan_sc_mc = src->non_vlan_sc_mc;
259
-
info->non_vlan_vl_mc = src->non_vlan_vl_mc;
260
-
memcpy(info->rsvd2, src->rsvd2, ARRAY_SIZE(src->rsvd2));
261
-
262
-
info->uc_macs_gen_count = cpu_to_be16(src->uc_macs_gen_count);
263
-
info->mc_macs_gen_count = cpu_to_be16(src->mc_macs_gen_count);
264
-
memcpy(info->rsvd3, src->rsvd3, ARRAY_SIZE(src->rsvd3));
265
-
}
266
-
267
-
/**
268
-
* opa_vnic_set_per_veswport_info -- Set vesw per port information
269
-
* @adapter: vnic port adapter
270
-
* @info: pointer to vport info structure
271
-
*
272
-
* This function updates the vesw per port info that is maintained by the
273
-
* given adapter with vesw per port info provided. Reserved fields are
274
-
* stored and returned back to EM as is.
275
-
*/
276
-
void opa_vnic_set_per_veswport_info(struct opa_vnic_adapter *adapter,
277
-
struct opa_per_veswport_info *info)
278
-
{
279
-
struct __opa_per_veswport_info *dst = &adapter->info.vport;
280
-
281
-
dst->port_num = be32_to_cpu(info->port_num);
282
-
memcpy(dst->rsvd0, info->rsvd0, ARRAY_SIZE(info->rsvd0));
283
-
284
-
memcpy(dst->base_mac_addr, info->base_mac_addr,
285
-
ARRAY_SIZE(dst->base_mac_addr));
286
-
dst->config_state = info->config_state;
287
-
memcpy(dst->rsvd1, info->rsvd1, ARRAY_SIZE(info->rsvd1));
288
-
289
-
dst->encap_slid = be32_to_cpu(info->encap_slid);
290
-
memcpy(dst->pcp_to_sc_uc, info->pcp_to_sc_uc,
291
-
ARRAY_SIZE(dst->pcp_to_sc_uc));
292
-
memcpy(dst->pcp_to_vl_uc, info->pcp_to_vl_uc,
293
-
ARRAY_SIZE(dst->pcp_to_vl_uc));
294
-
memcpy(dst->pcp_to_sc_mc, info->pcp_to_sc_mc,
295
-
ARRAY_SIZE(dst->pcp_to_sc_mc));
296
-
memcpy(dst->pcp_to_vl_mc, info->pcp_to_vl_mc,
297
-
ARRAY_SIZE(dst->pcp_to_vl_mc));
298
-
dst->non_vlan_sc_uc = info->non_vlan_sc_uc;
299
-
dst->non_vlan_vl_uc = info->non_vlan_vl_uc;
300
-
dst->non_vlan_sc_mc = info->non_vlan_sc_mc;
301
-
dst->non_vlan_vl_mc = info->non_vlan_vl_mc;
302
-
memcpy(dst->rsvd2, info->rsvd2, ARRAY_SIZE(info->rsvd2));
303
-
memcpy(dst->rsvd3, info->rsvd3, ARRAY_SIZE(info->rsvd3));
304
-
}
305
-
306
-
/**
307
-
* opa_vnic_query_mcast_macs - query multicast mac list
308
-
* @adapter: vnic port adapter
309
-
* @macs: pointer mac list
310
-
*
311
-
* This function populates the provided mac list with the configured
312
-
* multicast addresses in the adapter.
313
-
*/
314
-
void opa_vnic_query_mcast_macs(struct opa_vnic_adapter *adapter,
315
-
struct opa_veswport_iface_macs *macs)
316
-
{
317
-
u16 start_idx, num_macs, idx = 0, count = 0;
318
-
struct netdev_hw_addr *ha;
319
-
320
-
start_idx = be16_to_cpu(macs->start_idx);
321
-
num_macs = be16_to_cpu(macs->num_macs_in_msg);
322
-
netdev_for_each_mc_addr(ha, adapter->netdev) {
323
-
struct opa_vnic_iface_mac_entry *entry = &macs->entry[count];
324
-
325
-
if (start_idx > idx++)
326
-
continue;
327
-
else if (num_macs == count)
328
-
break;
329
-
memcpy(entry, ha->addr, sizeof(*entry));
330
-
count++;
331
-
}
332
-
333
-
macs->tot_macs_in_lst = cpu_to_be16(netdev_mc_count(adapter->netdev));
334
-
macs->num_macs_in_msg = cpu_to_be16(count);
335
-
macs->gen_count = cpu_to_be16(adapter->info.vport.mc_macs_gen_count);
336
-
}
337
-
338
-
/**
339
-
* opa_vnic_query_ucast_macs - query unicast mac list
340
-
* @adapter: vnic port adapter
341
-
* @macs: pointer mac list
342
-
*
343
-
* This function populates the provided mac list with the configured
344
-
* unicast addresses in the adapter.
345
-
*/
346
-
void opa_vnic_query_ucast_macs(struct opa_vnic_adapter *adapter,
347
-
struct opa_veswport_iface_macs *macs)
348
-
{
349
-
u16 start_idx, tot_macs, num_macs, idx = 0, count = 0, em_macs = 0;
350
-
struct netdev_hw_addr *ha;
351
-
352
-
start_idx = be16_to_cpu(macs->start_idx);
353
-
num_macs = be16_to_cpu(macs->num_macs_in_msg);
354
-
/* loop through dev_addrs list first */
355
-
for_each_dev_addr(adapter->netdev, ha) {
356
-
struct opa_vnic_iface_mac_entry *entry = &macs->entry[count];
357
-
358
-
/* Do not include EM specified MAC address */
359
-
if (!memcmp(adapter->info.vport.base_mac_addr, ha->addr,
360
-
ARRAY_SIZE(adapter->info.vport.base_mac_addr))) {
361
-
em_macs++;
362
-
continue;
363
-
}
364
-
365
-
if (start_idx > idx++)
366
-
continue;
367
-
else if (num_macs == count)
368
-
break;
369
-
memcpy(entry, ha->addr, sizeof(*entry));
370
-
count++;
371
-
}
372
-
373
-
/* loop through uc list */
374
-
netdev_for_each_uc_addr(ha, adapter->netdev) {
375
-
struct opa_vnic_iface_mac_entry *entry = &macs->entry[count];
376
-
377
-
if (start_idx > idx++)
378
-
continue;
379
-
else if (num_macs == count)
380
-
break;
381
-
memcpy(entry, ha->addr, sizeof(*entry));
382
-
count++;
383
-
}
384
-
385
-
tot_macs = netdev_hw_addr_list_count(&adapter->netdev->dev_addrs) +
386
-
netdev_uc_count(adapter->netdev) - em_macs;
387
-
macs->tot_macs_in_lst = cpu_to_be16(tot_macs);
388
-
macs->num_macs_in_msg = cpu_to_be16(count);
389
-
macs->gen_count = cpu_to_be16(adapter->info.vport.uc_macs_gen_count);
390
-
}
-6
include/rdma/ib_verbs.h
-6
include/rdma/ib_verbs.h
···
2361
2361
2362
2362
/* rdma netdev type - specifies protocol type */
2363
2363
enum rdma_netdev_t {
2364
-
RDMA_NETDEV_OPA_VNIC,
2365
2364
RDMA_NETDEV_IPOIB,
2366
2365
};
2367
2366
···
2374
2375
u32 port_num;
2375
2376
int mtu;
2376
2377
2377
-
/*
2378
-
* cleanup function must be specified.
2379
-
* FIXME: This is only used for OPA_VNIC and that usage should be
2380
-
* removed too.
2381
-
*/
2382
2378
void (*free_rdma_netdev)(struct net_device *netdev);
2383
2379
2384
2380
/* control functions */
-96
include/rdma/opa_vnic.h
-96
include/rdma/opa_vnic.h
···
1
-
/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
2
-
/*
3
-
* Copyright(c) 2017 - 2020 Intel Corporation.
4
-
*/
5
-
6
-
#ifndef _OPA_VNIC_H
7
-
#define _OPA_VNIC_H
8
-
9
-
/*
10
-
* This file contains Intel Omni-Path (OPA) Virtual Network Interface
11
-
* Controller (VNIC) specific declarations.
12
-
*/
13
-
14
-
#include <rdma/ib_verbs.h>
15
-
16
-
/* 16 header bytes + 2 reserved bytes */
17
-
#define OPA_VNIC_L2_HDR_LEN (16 + 2)
18
-
19
-
#define OPA_VNIC_L4_HDR_LEN 2
20
-
21
-
#define OPA_VNIC_HDR_LEN (OPA_VNIC_L2_HDR_LEN + \
22
-
OPA_VNIC_L4_HDR_LEN)
23
-
24
-
#define OPA_VNIC_L4_ETHR 0x78
25
-
26
-
#define OPA_VNIC_ICRC_LEN 4
27
-
#define OPA_VNIC_TAIL_LEN 1
28
-
#define OPA_VNIC_ICRC_TAIL_LEN (OPA_VNIC_ICRC_LEN + OPA_VNIC_TAIL_LEN)
29
-
30
-
#define OPA_VNIC_SKB_MDATA_LEN 4
31
-
#define OPA_VNIC_SKB_MDATA_ENCAP_ERR 0x1
32
-
33
-
/* opa vnic rdma netdev's private data structure */
34
-
struct opa_vnic_rdma_netdev {
35
-
struct rdma_netdev rn; /* keep this first */
36
-
/* followed by device private data */
37
-
char *dev_priv[];
38
-
};
39
-
40
-
static inline void *opa_vnic_priv(const struct net_device *dev)
41
-
{
42
-
struct rdma_netdev *rn = netdev_priv(dev);
43
-
44
-
return rn->clnt_priv;
45
-
}
46
-
47
-
static inline void *opa_vnic_dev_priv(const struct net_device *dev)
48
-
{
49
-
struct opa_vnic_rdma_netdev *oparn = netdev_priv(dev);
50
-
51
-
return oparn->dev_priv;
52
-
}
53
-
54
-
/* opa_vnic skb meta data structure */
55
-
struct opa_vnic_skb_mdata {
56
-
u8 vl;
57
-
u8 entropy;
58
-
u8 flags;
59
-
u8 rsvd;
60
-
} __packed;
61
-
62
-
/* OPA VNIC group statistics */
63
-
struct opa_vnic_grp_stats {
64
-
u64 unicast;
65
-
u64 mcastbcast;
66
-
u64 untagged;
67
-
u64 vlan;
68
-
u64 s_64;
69
-
u64 s_65_127;
70
-
u64 s_128_255;
71
-
u64 s_256_511;
72
-
u64 s_512_1023;
73
-
u64 s_1024_1518;
74
-
u64 s_1519_max;
75
-
};
76
-
77
-
struct opa_vnic_stats {
78
-
/* standard netdev statistics */
79
-
struct rtnl_link_stats64 netstats;
80
-
81
-
/* OPA VNIC statistics */
82
-
struct opa_vnic_grp_stats tx_grp;
83
-
struct opa_vnic_grp_stats rx_grp;
84
-
u64 tx_dlid_zero;
85
-
u64 tx_drop_state;
86
-
u64 rx_drop_state;
87
-
u64 rx_runt;
88
-
u64 rx_oversize;
89
-
};
90
-
91
-
static inline bool rdma_cap_opa_vnic(struct ib_device *device)
92
-
{
93
-
return !!(device->attrs.kernel_cap_flags & IBK_RDMA_NETDEV_OPA);
94
-
}
95
-
96
-
#endif /* _OPA_VNIC_H */