forked from Minki/linux
19fd08b85b
- Fix RDMA uapi headers to actually compile in userspace and be more complete - Three shared with netdev pull requests from Mellanox: * 7 patches, mostly to net with 1 IB related one at the back). This series addresses an IRQ performance issue (patch 1), cleanups related to the fix for the IRQ performance problem (patches 2-6), and then extends the fragmented completion queue support that already exists in the net side of the driver to the ib side of the driver (patch 7). * Mostly IB, with 5 patches to net that are needed to support the remaining 10 patches to the IB subsystem. This series extends the current 'representor' framework when the mlx5 driver is in switchdev mode from being a netdev only construct to being a netdev/IB dev construct. The IB dev is limited to raw Eth queue pairs only, but by having an IB dev of this type attached to the representor for a switchdev port, it enables DPDK to work on the switchdev device. * All net related, but needed as infrastructure for the rdma driver - Updates for the hns, i40iw, bnxt_re, cxgb3, cxgb4, hns drivers - SRP performance updates - IB uverbs write path cleanup patch series from Leon - Add RDMA_CM support to ib_srpt. This is disabled by default. Users need to set the port for ib_srpt to listen on in configfs in order for it to be enabled (/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port) - TSO and Scatter FCS support in mlx4 - Refactor of modify_qp routine to resolve problems seen while working on new code that is forthcoming - More refactoring and updates of RDMA CM for containers support from Parav - mlx5 'fine grained packet pacing', 'ipsec offload' and 'device memory' user API features - Infrastructure updates for the new IOCTL interface, based on increased usage - ABI compatibility bug fixes to fully support 32 bit userspace on 64 bit kernel as was originally intended. See the commit messages for extensive details - Syzkaller bugs and code cleanups motivated by them -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAABCgAGBQJax5Z0AAoJEDht9xV+IJsacCwQAJBIgmLCvVp5fBu2kJcXMMVI y3l2YNzAUJvDDKv1r5yTC9ugBXEkDtgzi/W/C2/5es2yUG/QeT/zzQ3YPrtsnN68 5FkiXQ35Tt7+PBHMr0cacGRmF4M3Td3MeW0X5aJaBKhqlNKwA+aF18pjGWBmpVYx URYCwLb5BZBKVh4+1Leebsk4i0/7jSauAqE5M+9notuAUfBCoY1/Eve3DipEIBBp EyrEnMDIdujYRsg4KHlxFKKJ1EFGItknLQbNL1+SEa0Oe0SnEl5Bd53Yxfz7ekNP oOWQe5csTcs3Yr4Ob0TC+69CzI71zKbz6qPDILTwXmsPFZJ9ipJs4S8D6F7ra8tb D5aT1EdRzh/vAORPC9T3DQ3VsHdvhwpUMG7knnKrVT9X/g7E+gSji1BqaQaTr/xs i40GepHT7lM/TWEuee/6LRpqdhuOhud7vfaRFwn2JGRX9suqTcvwhkBkPUDGV5XX 5RkHcWOb/7KvmpG7S1gaRGK5kO208LgmAZi7REaJFoZB74FqSneMR6NHIH07ha41 Zou7rnxV68CT2bgu27m+72EsprgmBkVDeEzXgKxVI/+PZ1oadUFpgcZ3pRLOPWVx rEqjHu65rlA/YPog4iXQaMfSwt/oRD3cVJS/n8EdJKXi4Qt2RDDGdyOmt74w4prM QuLEdvJIFmwrND1KDoqn =Ku8g -----END PGP SIGNATURE----- Merge tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma Pull rdma updates from Jason Gunthorpe: "Doug and I are at a conference next week so if another PR is sent I expect it to only be bug fixes. Parav noted yesterday that there are some fringe case behavior changes in his work that he would like to fix, and I see that Intel has a number of rc looking patches for HFI1 they posted yesterday. Parav is again the biggest contributor by patch count with his ongoing work to enable container support in the RDMA stack, followed by Leon doing syzkaller inspired cleanups, though most of the actual fixing went to RC. There is one uncomfortable series here fixing the user ABI to actually work as intended in 32 bit mode. There are lots of notes in the commit messages, but the basic summary is we don't think there is an actual 32 bit kernel user of drivers/infiniband for several good reasons. However we are seeing people want to use a 32 bit user space with 64 bit kernel, which didn't completely work today. So in fixing it we required a 32 bit rxe user to upgrade their userspace. rxe users are still already quite rare and we think a 32 bit one is non-existing. - Fix RDMA uapi headers to actually compile in userspace and be more complete - Three shared with netdev pull requests from Mellanox: * 7 patches, mostly to net with 1 IB related one at the back). This series addresses an IRQ performance issue (patch 1), cleanups related to the fix for the IRQ performance problem (patches 2-6), and then extends the fragmented completion queue support that already exists in the net side of the driver to the ib side of the driver (patch 7). * Mostly IB, with 5 patches to net that are needed to support the remaining 10 patches to the IB subsystem. This series extends the current 'representor' framework when the mlx5 driver is in switchdev mode from being a netdev only construct to being a netdev/IB dev construct. The IB dev is limited to raw Eth queue pairs only, but by having an IB dev of this type attached to the representor for a switchdev port, it enables DPDK to work on the switchdev device. * All net related, but needed as infrastructure for the rdma driver - Updates for the hns, i40iw, bnxt_re, cxgb3, cxgb4, hns drivers - SRP performance updates - IB uverbs write path cleanup patch series from Leon - Add RDMA_CM support to ib_srpt. This is disabled by default. Users need to set the port for ib_srpt to listen on in configfs in order for it to be enabled (/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port) - TSO and Scatter FCS support in mlx4 - Refactor of modify_qp routine to resolve problems seen while working on new code that is forthcoming - More refactoring and updates of RDMA CM for containers support from Parav - mlx5 'fine grained packet pacing', 'ipsec offload' and 'device memory' user API features - Infrastructure updates for the new IOCTL interface, based on increased usage - ABI compatibility bug fixes to fully support 32 bit userspace on 64 bit kernel as was originally intended. See the commit messages for extensive details - Syzkaller bugs and code cleanups motivated by them" * tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (199 commits) IB/rxe: Fix for oops in rxe_register_device on ppc64le arch IB/mlx5: Device memory mr registration support net/mlx5: Mkey creation command adjustments IB/mlx5: Device memory support in mlx5_ib net/mlx5: Query device memory capabilities IB/uverbs: Add device memory registration ioctl support IB/uverbs: Add alloc/free dm uverbs ioctl support IB/uverbs: Add device memory capabilities reporting IB/uverbs: Expose device memory capabilities to user RDMA/qedr: Fix wmb usage in qedr IB/rxe: Removed GID add/del dummy routines RDMA/qedr: Zero stack memory before copying to user space IB/mlx5: Add ability to hash by IPSEC_SPI when creating a TIR IB/mlx5: Add information for querying IPsec capabilities IB/mlx5: Add IPsec support for egress and ingress {net,IB}/mlx5: Add ipsec helper IB/mlx5: Add modify_flow_action_esp verb IB/mlx5: Add implementation for create and destroy action_xfrm IB/uverbs: Introduce ESP steering match filter IB/uverbs: Add modify ESP flow_action ...
316 lines
9.3 KiB
C
316 lines
9.3 KiB
C
/*
|
|
* Copyright (c) 2005 Voltaire Inc. All rights reserved.
|
|
* Copyright (c) 2005 Intel Corporation. All rights reserved.
|
|
*
|
|
* This software is available to you under a choice of one of two
|
|
* licenses. You may choose to be licensed under the terms of the GNU
|
|
* General Public License (GPL) Version 2, available from the file
|
|
* COPYING in the main directory of this source tree, or the
|
|
* OpenIB.org BSD license below:
|
|
*
|
|
* Redistribution and use in source and binary forms, with or
|
|
* without modification, are permitted provided that the following
|
|
* conditions are met:
|
|
*
|
|
* - Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer.
|
|
*
|
|
* - Redistributions in binary form must reproduce the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
|
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
|
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*/
|
|
|
|
#if !defined(IB_ADDR_H)
|
|
#define IB_ADDR_H
|
|
|
|
#include <linux/in.h>
|
|
#include <linux/in6.h>
|
|
#include <linux/if_arp.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/inetdevice.h>
|
|
#include <linux/socket.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/if_inet6.h>
|
|
#include <net/ip.h>
|
|
#include <rdma/ib_verbs.h>
|
|
#include <rdma/ib_pack.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/net_namespace.h>
|
|
|
|
struct rdma_addr_client {
|
|
atomic_t refcount;
|
|
struct completion comp;
|
|
};
|
|
|
|
/**
|
|
* rdma_addr_register_client - Register an address client.
|
|
*/
|
|
void rdma_addr_register_client(struct rdma_addr_client *client);
|
|
|
|
/**
|
|
* rdma_addr_unregister_client - Deregister an address client.
|
|
* @client: Client object to deregister.
|
|
*/
|
|
void rdma_addr_unregister_client(struct rdma_addr_client *client);
|
|
|
|
/**
|
|
* struct rdma_dev_addr - Contains resolved RDMA hardware addresses
|
|
* @src_dev_addr: Source MAC address.
|
|
* @dst_dev_addr: Destination MAC address.
|
|
* @broadcast: Broadcast address of the device.
|
|
* @dev_type: The interface hardware type of the device.
|
|
* @bound_dev_if: An optional device interface index.
|
|
* @transport: The transport type used.
|
|
* @net: Network namespace containing the bound_dev_if net_dev.
|
|
*/
|
|
struct rdma_dev_addr {
|
|
unsigned char src_dev_addr[MAX_ADDR_LEN];
|
|
unsigned char dst_dev_addr[MAX_ADDR_LEN];
|
|
unsigned char broadcast[MAX_ADDR_LEN];
|
|
unsigned short dev_type;
|
|
int bound_dev_if;
|
|
enum rdma_transport_type transport;
|
|
struct net *net;
|
|
enum rdma_network_type network;
|
|
int hoplimit;
|
|
};
|
|
|
|
/**
|
|
* rdma_translate_ip - Translate a local IP address to an RDMA hardware
|
|
* address.
|
|
*
|
|
* The dev_addr->net field must be initialized.
|
|
*/
|
|
int rdma_translate_ip(const struct sockaddr *addr,
|
|
struct rdma_dev_addr *dev_addr);
|
|
|
|
/**
|
|
* rdma_resolve_ip - Resolve source and destination IP addresses to
|
|
* RDMA hardware addresses.
|
|
* @client: Address client associated with request.
|
|
* @src_addr: An optional source address to use in the resolution. If a
|
|
* source address is not provided, a usable address will be returned via
|
|
* the callback.
|
|
* @dst_addr: The destination address to resolve.
|
|
* @addr: A reference to a data location that will receive the resolved
|
|
* addresses. The data location must remain valid until the callback has
|
|
* been invoked. The net field of the addr struct must be valid.
|
|
* @timeout_ms: Amount of time to wait for the address resolution to complete.
|
|
* @callback: Call invoked once address resolution has completed, timed out,
|
|
* or been canceled. A status of 0 indicates success.
|
|
* @context: User-specified context associated with the call.
|
|
*/
|
|
int rdma_resolve_ip(struct rdma_addr_client *client,
|
|
struct sockaddr *src_addr, struct sockaddr *dst_addr,
|
|
struct rdma_dev_addr *addr, int timeout_ms,
|
|
void (*callback)(int status, struct sockaddr *src_addr,
|
|
struct rdma_dev_addr *addr, void *context),
|
|
void *context);
|
|
|
|
void rdma_addr_cancel(struct rdma_dev_addr *addr);
|
|
|
|
void rdma_copy_addr(struct rdma_dev_addr *dev_addr,
|
|
const struct net_device *dev,
|
|
const unsigned char *dst_dev_addr);
|
|
|
|
int rdma_addr_size(struct sockaddr *addr);
|
|
int rdma_addr_size_in6(struct sockaddr_in6 *addr);
|
|
int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr);
|
|
|
|
static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
|
|
{
|
|
return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9];
|
|
}
|
|
|
|
static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey)
|
|
{
|
|
dev_addr->broadcast[8] = pkey >> 8;
|
|
dev_addr->broadcast[9] = (unsigned char) pkey;
|
|
}
|
|
|
|
static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr,
|
|
union ib_gid *gid)
|
|
{
|
|
memcpy(gid, dev_addr->broadcast + 4, sizeof *gid);
|
|
}
|
|
|
|
static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
|
|
{
|
|
return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
|
|
}
|
|
|
|
static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
|
|
{
|
|
return is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 0xffff;
|
|
}
|
|
|
|
static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
|
|
{
|
|
switch (addr->sa_family) {
|
|
case AF_INET:
|
|
ipv6_addr_set_v4mapped(((struct sockaddr_in *)
|
|
addr)->sin_addr.s_addr,
|
|
(struct in6_addr *)gid);
|
|
break;
|
|
case AF_INET6:
|
|
*(struct in6_addr *)&gid->raw =
|
|
((struct sockaddr_in6 *)addr)->sin6_addr;
|
|
break;
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
|
|
static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid)
|
|
{
|
|
if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
|
|
struct sockaddr_in *out_in = (struct sockaddr_in *)out;
|
|
memset(out_in, 0, sizeof(*out_in));
|
|
out_in->sin_family = AF_INET;
|
|
memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4);
|
|
} else {
|
|
struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out;
|
|
memset(out_in, 0, sizeof(*out_in));
|
|
out_in->sin6_family = AF_INET6;
|
|
memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp.
|
|
* They are not applicable to RoCE.
|
|
* RoCE GIDs are derived from the IP addresses.
|
|
*/
|
|
static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
|
|
{
|
|
memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr),
|
|
sizeof(*gid));
|
|
}
|
|
|
|
static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
|
|
{
|
|
memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid);
|
|
}
|
|
|
|
static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
|
|
{
|
|
memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid);
|
|
}
|
|
|
|
static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
|
|
{
|
|
memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid);
|
|
}
|
|
|
|
static inline enum ib_mtu iboe_get_mtu(int mtu)
|
|
{
|
|
/*
|
|
* Reduce IB headers from effective IBoE MTU.
|
|
*/
|
|
mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES +
|
|
IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES +
|
|
IB_ICRC_BYTES);
|
|
|
|
if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096))
|
|
return IB_MTU_4096;
|
|
else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048))
|
|
return IB_MTU_2048;
|
|
else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024))
|
|
return IB_MTU_1024;
|
|
else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512))
|
|
return IB_MTU_512;
|
|
else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256))
|
|
return IB_MTU_256;
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
static inline int iboe_get_rate(struct net_device *dev)
|
|
{
|
|
struct ethtool_link_ksettings cmd;
|
|
int err;
|
|
|
|
rtnl_lock();
|
|
err = __ethtool_get_link_ksettings(dev, &cmd);
|
|
rtnl_unlock();
|
|
if (err)
|
|
return IB_RATE_PORT_CURRENT;
|
|
|
|
if (cmd.base.speed >= 40000)
|
|
return IB_RATE_40_GBPS;
|
|
else if (cmd.base.speed >= 30000)
|
|
return IB_RATE_30_GBPS;
|
|
else if (cmd.base.speed >= 20000)
|
|
return IB_RATE_20_GBPS;
|
|
else if (cmd.base.speed >= 10000)
|
|
return IB_RATE_10_GBPS;
|
|
else
|
|
return IB_RATE_PORT_CURRENT;
|
|
}
|
|
|
|
static inline int rdma_link_local_addr(struct in6_addr *addr)
|
|
{
|
|
if (addr->s6_addr32[0] == htonl(0xfe800000) &&
|
|
addr->s6_addr32[1] == 0)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
|
|
{
|
|
memcpy(mac, &addr->s6_addr[8], 3);
|
|
memcpy(mac + 3, &addr->s6_addr[13], 3);
|
|
mac[0] ^= 2;
|
|
}
|
|
|
|
static inline int rdma_is_multicast_addr(struct in6_addr *addr)
|
|
{
|
|
__be32 ipv4_addr;
|
|
|
|
if (addr->s6_addr[0] == 0xff)
|
|
return 1;
|
|
|
|
ipv4_addr = addr->s6_addr32[3];
|
|
return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr));
|
|
}
|
|
|
|
static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
|
|
{
|
|
int i;
|
|
|
|
mac[0] = 0x33;
|
|
mac[1] = 0x33;
|
|
for (i = 2; i < 6; ++i)
|
|
mac[i] = addr->s6_addr[i + 10];
|
|
}
|
|
|
|
static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
|
|
{
|
|
u16 vid;
|
|
|
|
vid = dgid->raw[11] << 8 | dgid->raw[12];
|
|
return vid < 0x1000 ? vid : 0xffff;
|
|
}
|
|
|
|
static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
|
|
{
|
|
return is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : NULL;
|
|
}
|
|
|
|
#endif /* IB_ADDR_H */
|