OpenCloudOS-Kernel/net/rds/iw.c

328 lines
8.7 KiB
C
Raw Normal View History

/*
* Copyright (c) 2006 Oracle. 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.
*
*/
#include <linux/kernel.h>
#include <linux/in.h>
#include <linux/if.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/if_arp.h>
#include <linux/delay.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include "rds.h"
#include "iw.h"
unsigned int fastreg_pool_size = RDS_FASTREG_POOL_SIZE;
unsigned int fastreg_message_size = RDS_FASTREG_SIZE + 1; /* +1 allows for unaligned MRs */
module_param(fastreg_pool_size, int, 0444);
MODULE_PARM_DESC(fastreg_pool_size, " Max number of fastreg MRs per device");
module_param(fastreg_message_size, int, 0444);
MODULE_PARM_DESC(fastreg_message_size, " Max size of a RDMA transfer (fastreg MRs)");
struct list_head rds_iw_devices;
/* NOTE: if also grabbing iwdev lock, grab this first */
DEFINE_SPINLOCK(iw_nodev_conns_lock);
LIST_HEAD(iw_nodev_conns);
void rds_iw_add_one(struct ib_device *device)
{
struct rds_iw_device *rds_iwdev;
struct ib_device_attr *dev_attr;
/* Only handle iwarp devices */
if (device->node_type != RDMA_NODE_RNIC)
return;
dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL);
if (!dev_attr)
return;
if (ib_query_device(device, dev_attr)) {
rdsdebug("Query device failed for %s\n", device->name);
goto free_attr;
}
rds_iwdev = kmalloc(sizeof *rds_iwdev, GFP_KERNEL);
if (!rds_iwdev)
goto free_attr;
spin_lock_init(&rds_iwdev->spinlock);
rds_iwdev->dma_local_lkey = !!(dev_attr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY);
rds_iwdev->max_wrs = dev_attr->max_qp_wr;
rds_iwdev->max_sge = min(dev_attr->max_sge, RDS_IW_MAX_SGE);
rds_iwdev->dev = device;
rds_iwdev->pd = ib_alloc_pd(device);
if (IS_ERR(rds_iwdev->pd))
goto free_dev;
if (!rds_iwdev->dma_local_lkey) {
rds_iwdev->mr = ib_get_dma_mr(rds_iwdev->pd,
IB_ACCESS_REMOTE_READ |
IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_LOCAL_WRITE);
if (IS_ERR(rds_iwdev->mr))
goto err_pd;
} else
rds_iwdev->mr = NULL;
rds_iwdev->mr_pool = rds_iw_create_mr_pool(rds_iwdev);
if (IS_ERR(rds_iwdev->mr_pool)) {
rds_iwdev->mr_pool = NULL;
goto err_mr;
}
INIT_LIST_HEAD(&rds_iwdev->cm_id_list);
INIT_LIST_HEAD(&rds_iwdev->conn_list);
list_add_tail(&rds_iwdev->list, &rds_iw_devices);
ib_set_client_data(device, &rds_iw_client, rds_iwdev);
goto free_attr;
err_mr:
if (rds_iwdev->mr)
ib_dereg_mr(rds_iwdev->mr);
err_pd:
ib_dealloc_pd(rds_iwdev->pd);
free_dev:
kfree(rds_iwdev);
free_attr:
kfree(dev_attr);
}
void rds_iw_remove_one(struct ib_device *device)
{
struct rds_iw_device *rds_iwdev;
struct rds_iw_cm_id *i_cm_id, *next;
rds_iwdev = ib_get_client_data(device, &rds_iw_client);
if (!rds_iwdev)
return;
spin_lock_irq(&rds_iwdev->spinlock);
list_for_each_entry_safe(i_cm_id, next, &rds_iwdev->cm_id_list, list) {
list_del(&i_cm_id->list);
kfree(i_cm_id);
}
spin_unlock_irq(&rds_iwdev->spinlock);
rds_iw_destroy_conns(rds_iwdev);
if (rds_iwdev->mr_pool)
rds_iw_destroy_mr_pool(rds_iwdev->mr_pool);
if (rds_iwdev->mr)
ib_dereg_mr(rds_iwdev->mr);
while (ib_dealloc_pd(rds_iwdev->pd)) {
rdsdebug("Failed to dealloc pd %p\n", rds_iwdev->pd);
msleep(1);
}
list_del(&rds_iwdev->list);
kfree(rds_iwdev);
}
struct ib_client rds_iw_client = {
.name = "rds_iw",
.add = rds_iw_add_one,
.remove = rds_iw_remove_one
};
static int rds_iw_conn_info_visitor(struct rds_connection *conn,
void *buffer)
{
struct rds_info_rdma_connection *iinfo = buffer;
struct rds_iw_connection *ic;
/* We will only ever look at IB transports */
if (conn->c_trans != &rds_iw_transport)
return 0;
iinfo->src_addr = conn->c_laddr;
iinfo->dst_addr = conn->c_faddr;
memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));
if (rds_conn_state(conn) == RDS_CONN_UP) {
struct rds_iw_device *rds_iwdev;
struct rdma_dev_addr *dev_addr;
ic = conn->c_transport_data;
dev_addr = &ic->i_cm_id->route.addr.dev_addr;
RDMA/cm: fix loopback address support The RDMA CM is intended to support the use of a loopback address when establishing a connection; however, the behavior of the CM when loopback addresses are used is confusing and does not always work, depending on whether loopback was specified by the server, the client, or both. The defined behavior of rdma_bind_addr is to associate an RDMA device with an rdma_cm_id, as long as the user specified a non- zero address. (ie they weren't just trying to reserve a port) Currently, if the loopback address is passed to rdam_bind_addr, no device is associated with the rdma_cm_id. Fix this. If a loopback address is specified by the client as the destination address for a connection, it will fail to establish a connection. This is true even if the server is listing across all addresses or on the loopback address itself. The issue is that the server tries to translate the IP address carried in the REQ message to a local net_device address, which fails. The translation is not needed in this case, since the REQ carries the actual HW address that should be used. Finally, cleanup loopback support to be more transport neutral. Replace separate calls to get/set the sgid and dgid from the device address to a single call that behaves correctly depending on the format of the device address. And support both IPv4 and IPv6 address formats. Signed-off-by: Sean Hefty <sean.hefty@intel.com> [ Fixed RDS build by s/ib_addr_get/rdma_addr_get/ - Roland ] Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-11-20 05:26:06 +08:00
rdma_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid);
rdma_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid);
rds_iwdev = ib_get_client_data(ic->i_cm_id->device, &rds_iw_client);
iinfo->max_send_wr = ic->i_send_ring.w_nr;
iinfo->max_recv_wr = ic->i_recv_ring.w_nr;
iinfo->max_send_sge = rds_iwdev->max_sge;
rds_iw_get_mr_info(rds_iwdev, iinfo);
}
return 1;
}
static void rds_iw_ic_info(struct socket *sock, unsigned int len,
struct rds_info_iterator *iter,
struct rds_info_lengths *lens)
{
rds_for_each_conn_info(sock, len, iter, lens,
rds_iw_conn_info_visitor,
sizeof(struct rds_info_rdma_connection));
}
/*
* Early RDS/IB was built to only bind to an address if there is an IPoIB
* device with that address set.
*
* If it were me, I'd advocate for something more flexible. Sending and
* receiving should be device-agnostic. Transports would try and maintain
* connections between peers who have messages queued. Userspace would be
* allowed to influence which paths have priority. We could call userspace
* asserting this policy "routing".
*/
static int rds_iw_laddr_check(__be32 addr)
{
int ret;
struct rdma_cm_id *cm_id;
struct sockaddr_in sin;
/* Create a CMA ID and try to bind it. This catches both
* IB and iWARP capable NICs.
*/
cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP);
if (IS_ERR(cm_id))
return PTR_ERR(cm_id);
memset(&sin, 0, sizeof(sin));
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = addr;
/* rdma_bind_addr will only succeed for IB & iWARP devices */
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
/* due to this, we will claim to support IB devices unless we
check node_type. */
if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
ret = -EADDRNOTAVAIL;
rdsdebug("addr %pI4 ret %d node type %d\n",
&addr, ret,
cm_id->device ? cm_id->device->node_type : -1);
rdma_destroy_id(cm_id);
return ret;
}
void rds_iw_exit(void)
{
rds_info_deregister_func(RDS_INFO_IWARP_CONNECTIONS, rds_iw_ic_info);
rds_iw_destroy_nodev_conns();
ib_unregister_client(&rds_iw_client);
rds_iw_sysctl_exit();
rds_iw_recv_exit();
rds_trans_unregister(&rds_iw_transport);
}
struct rds_transport rds_iw_transport = {
.laddr_check = rds_iw_laddr_check,
.xmit_complete = rds_iw_xmit_complete,
.xmit = rds_iw_xmit,
.xmit_rdma = rds_iw_xmit_rdma,
.recv = rds_iw_recv,
.conn_alloc = rds_iw_conn_alloc,
.conn_free = rds_iw_conn_free,
.conn_connect = rds_iw_conn_connect,
.conn_shutdown = rds_iw_conn_shutdown,
.inc_copy_to_user = rds_iw_inc_copy_to_user,
.inc_free = rds_iw_inc_free,
.cm_initiate_connect = rds_iw_cm_initiate_connect,
.cm_handle_connect = rds_iw_cm_handle_connect,
.cm_connect_complete = rds_iw_cm_connect_complete,
.stats_info_copy = rds_iw_stats_info_copy,
.exit = rds_iw_exit,
.get_mr = rds_iw_get_mr,
.sync_mr = rds_iw_sync_mr,
.free_mr = rds_iw_free_mr,
.flush_mrs = rds_iw_flush_mrs,
.t_owner = THIS_MODULE,
.t_name = "iwarp",
.t_type = RDS_TRANS_IWARP,
.t_prefer_loopback = 1,
};
int __init rds_iw_init(void)
{
int ret;
INIT_LIST_HEAD(&rds_iw_devices);
ret = ib_register_client(&rds_iw_client);
if (ret)
goto out;
ret = rds_iw_sysctl_init();
if (ret)
goto out_ibreg;
ret = rds_iw_recv_init();
if (ret)
goto out_sysctl;
ret = rds_trans_register(&rds_iw_transport);
if (ret)
goto out_recv;
rds_info_register_func(RDS_INFO_IWARP_CONNECTIONS, rds_iw_ic_info);
goto out;
out_recv:
rds_iw_recv_exit();
out_sysctl:
rds_iw_sysctl_exit();
out_ibreg:
ib_unregister_client(&rds_iw_client);
out:
return ret;
}
MODULE_LICENSE("GPL");