linux_dsm_epyc7002/drivers/infiniband/core/addr.c

887 lines
22 KiB
C
Raw Normal View History

/*
* Copyright (c) 2005 Voltaire Inc. All rights reserved.
* Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved.
* Copyright (c) 1999-2005, Mellanox Technologies, 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.
*/
#include <linux/mutex.h>
#include <linux/inetdevice.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/module.h>
#include <net/arp.h>
#include <net/neighbour.h>
#include <net/route.h>
#include <net/netevent.h>
#include <net/ipv6_stubs.h>
#include <net/ip6_route.h>
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_sa.h>
#include <rdma/ib.h>
#include <rdma/rdma_netlink.h>
#include <net/netlink.h>
#include "core_priv.h"
struct addr_req {
struct list_head list;
struct sockaddr_storage src_addr;
struct sockaddr_storage dst_addr;
struct rdma_dev_addr *addr;
void *context;
void (*callback)(int status, struct sockaddr *src_addr,
struct rdma_dev_addr *addr, void *context);
unsigned long timeout;
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
struct delayed_work work;
bool resolve_by_gid_attr; /* Consider gid attr in resolve phase */
int status;
u32 seq;
};
static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(lock);
static LIST_HEAD(req_list);
static struct workqueue_struct *addr_wq;
static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
.len = sizeof(struct rdma_nla_ls_gid)},
};
static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
{
struct nlattr *tb[LS_NLA_TYPE_MAX] = {};
int ret;
if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
return false;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 19:07:28 +07:00
ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
nlmsg_len(nlh), ib_nl_addr_policy, NULL);
if (ret)
return false;
return true;
}
static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
{
const struct nlattr *head, *curr;
union ib_gid gid;
struct addr_req *req;
int len, rem;
int found = 0;
head = (const struct nlattr *)nlmsg_data(nlh);
len = nlmsg_len(nlh);
nla_for_each_attr(curr, head, len, rem) {
if (curr->nla_type == LS_NLA_TYPE_DGID)
memcpy(&gid, nla_data(curr), nla_len(curr));
}
spin_lock_bh(&lock);
list_for_each_entry(req, &req_list, list) {
if (nlh->nlmsg_seq != req->seq)
continue;
/* We set the DGID part, the rest was set earlier */
rdma_addr_set_dgid(req->addr, &gid);
req->status = 0;
found = 1;
break;
}
spin_unlock_bh(&lock);
if (!found)
pr_info("Couldn't find request waiting for DGID: %pI6\n",
&gid);
}
int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
!(NETLINK_CB(skb).sk))
return -EPERM;
if (ib_nl_is_good_ip_resp(nlh))
ib_nl_process_good_ip_rsep(nlh);
return skb->len;
}
static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
const void *daddr,
u32 seq, u16 family)
{
struct sk_buff *skb = NULL;
struct nlmsghdr *nlh;
struct rdma_ls_ip_resolve_header *header;
void *data;
size_t size;
int attrtype;
int len;
if (family == AF_INET) {
size = sizeof(struct in_addr);
attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4;
} else {
size = sizeof(struct in6_addr);
attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6;
}
len = nla_total_size(sizeof(size));
len += NLMSG_ALIGN(sizeof(*header));
skb = nlmsg_new(len, GFP_KERNEL);
if (!skb)
return -ENOMEM;
data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS,
RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST);
if (!data) {
nlmsg_free(skb);
return -ENODATA;
}
/* Construct the family header first */
header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
header->ifindex = dev_addr->bound_dev_if;
nla_put(skb, attrtype, size, daddr);
/* Repair the nlmsg header length */
nlmsg_end(skb, nlh);
rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
/* Make the request retry, so when we get the response from userspace
* we will have something.
*/
return -ENODATA;
}
int rdma_addr_size(const struct sockaddr *addr)
{
switch (addr->sa_family) {
case AF_INET:
return sizeof(struct sockaddr_in);
case AF_INET6:
return sizeof(struct sockaddr_in6);
case AF_IB:
return sizeof(struct sockaddr_ib);
default:
return 0;
}
}
EXPORT_SYMBOL(rdma_addr_size);
int rdma_addr_size_in6(struct sockaddr_in6 *addr)
{
int ret = rdma_addr_size((struct sockaddr *) addr);
return ret <= sizeof(*addr) ? ret : 0;
}
EXPORT_SYMBOL(rdma_addr_size_in6);
int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr)
{
int ret = rdma_addr_size((struct sockaddr *) addr);
return ret <= sizeof(*addr) ? ret : 0;
}
EXPORT_SYMBOL(rdma_addr_size_kss);
/**
* rdma_copy_src_l2_addr - Copy netdevice source addresses
* @dev_addr: Destination address pointer where to copy the addresses
* @dev: Netdevice whose source addresses to copy
*
* rdma_copy_src_l2_addr() copies source addresses from the specified netdevice.
* This includes unicast address, broadcast address, device type and
* interface index.
*/
void rdma_copy_src_l2_addr(struct rdma_dev_addr *dev_addr,
const struct net_device *dev)
{
dev_addr->dev_type = dev->type;
memcpy(dev_addr->src_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
memcpy(dev_addr->broadcast, dev->broadcast, MAX_ADDR_LEN);
dev_addr->bound_dev_if = dev->ifindex;
}
EXPORT_SYMBOL(rdma_copy_src_l2_addr);
static struct net_device *
rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in)
{
struct net_device *dev = NULL;
int ret = -EADDRNOTAVAIL;
switch (src_in->sa_family) {
case AF_INET:
dev = __ip_dev_find(net,
((const struct sockaddr_in *)src_in)->sin_addr.s_addr,
false);
if (dev)
ret = 0;
break;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
for_each_netdev_rcu(net, dev) {
if (ipv6_chk_addr(net,
&((const struct sockaddr_in6 *)src_in)->sin6_addr,
dev, 1)) {
ret = 0;
break;
}
}
break;
#endif
}
return ret ? ERR_PTR(ret) : dev;
}
int rdma_translate_ip(const struct sockaddr *addr,
struct rdma_dev_addr *dev_addr)
{
struct net_device *dev;
if (dev_addr->bound_dev_if) {
dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
if (!dev)
return -ENODEV;
rdma_copy_src_l2_addr(dev_addr, dev);
dev_put(dev);
return 0;
}
rcu_read_lock();
dev = rdma_find_ndev_for_src_ip_rcu(dev_addr->net, addr);
if (!IS_ERR(dev))
rdma_copy_src_l2_addr(dev_addr, dev);
rcu_read_unlock();
return PTR_ERR_OR_ZERO(dev);
}
EXPORT_SYMBOL(rdma_translate_ip);
static void set_timeout(struct addr_req *req, unsigned long time)
{
unsigned long delay;
delay = time - jiffies;
IB/addr: Improve address resolution callback scheduling Address resolution always does a context switch to a work-queue to deliver the address resolution event. When the IP address is already cached in the system ARP table, we're going through the following: chain: rdma_resolve_ip --> addr_resolve (cache hit) --> which ends up with: queue_req --> set_timeout (now) --> mod_delayed_work(,, delay=1) We actually do realize that the timeout should be zero, but the code forces it to a minimum of one jiffie. Using one jiffie as the minimum delay value results in sub-optimal scheduling of executing this work item by the workqueue, which on the below testbed costs about 3-4ms out of 12ms total time. To fix that, we let the minimum delay to be zero. Note that the connect step times change too, as there are address resolution calls from that flow. The results were taken from running both client and server on the same node, over mlx4 RoCE port. before --> step total ms max ms min us us / conn create id : 0.01 0.01 6.00 6.00 resolve addr : 4.02 4.01 4013.00 4016.00 resolve route: 0.18 0.18 182.00 183.00 create qp : 1.15 1.15 1150.00 1150.00 connect : 6.73 6.73 6730.00 6731.00 disconnect : 0.55 0.55 549.00 550.00 destroy : 0.01 0.01 9.00 9.00 after --> step total ms max ms min us us / conn create id : 0.01 0.01 6.00 6.00 resolve addr : 0.05 0.05 49.00 52.00 resolve route: 0.21 0.21 207.00 208.00 create qp : 1.10 1.10 1104.00 1104.00 connect : 1.22 1.22 1220.00 1221.00 disconnect : 0.71 0.71 713.00 713.00 destroy : 0.01 0.01 9.00 9.00 Signed-off-by: Or Kehati <ork@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Acked-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-29 21:32:04 +07:00
if ((long)delay < 0)
delay = 0;
mod_delayed_work(addr_wq, &req->work, delay);
}
static void queue_req(struct addr_req *req)
{
spin_lock_bh(&lock);
list_add_tail(&req->list, &req_list);
set_timeout(req, req->timeout);
spin_unlock_bh(&lock);
}
static int ib_nl_fetch_ha(struct rdma_dev_addr *dev_addr,
const void *daddr, u32 seq, u16 family)
{
if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
return -EADDRNOTAVAIL;
return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
}
static int dst_fetch_ha(const struct dst_entry *dst,
struct rdma_dev_addr *dev_addr,
const void *daddr)
{
struct neighbour *n;
int ret = 0;
n = dst_neigh_lookup(dst, daddr);
if (!n)
return -ENODATA;
if (!(n->nud_state & NUD_VALID)) {
neigh_event_send(n, NULL);
ret = -ENODATA;
} else {
neigh_ha_snapshot(dev_addr->dst_dev_addr, n, dst->dev);
}
neigh_release(n);
return ret;
}
static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
{
struct rtable *rt;
struct rt6_info *rt6;
if (family == AF_INET) {
rt = container_of(dst, struct rtable, dst);
return rt->rt_uses_gateway;
}
rt6 = container_of(dst, struct rt6_info, dst);
return rt6->rt6i_flags & RTF_GATEWAY;
}
static int fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
const struct sockaddr *dst_in, u32 seq)
{
const struct sockaddr_in *dst_in4 =
(const struct sockaddr_in *)dst_in;
const struct sockaddr_in6 *dst_in6 =
(const struct sockaddr_in6 *)dst_in;
const void *daddr = (dst_in->sa_family == AF_INET) ?
(const void *)&dst_in4->sin_addr.s_addr :
(const void *)&dst_in6->sin6_addr;
sa_family_t family = dst_in->sa_family;
/* If we have a gateway in IB mode then it must be an IB network */
if (has_gateway(dst, family) && dev_addr->network == RDMA_NETWORK_IB)
return ib_nl_fetch_ha(dev_addr, daddr, seq, family);
else
return dst_fetch_ha(dst, dev_addr, daddr);
}
static int addr4_resolve(struct sockaddr *src_sock,
const struct sockaddr *dst_sock,
struct rdma_dev_addr *addr,
struct rtable **prt)
{
struct sockaddr_in *src_in = (struct sockaddr_in *)src_sock;
const struct sockaddr_in *dst_in =
(const struct sockaddr_in *)dst_sock;
__be32 src_ip = src_in->sin_addr.s_addr;
__be32 dst_ip = dst_in->sin_addr.s_addr;
struct rtable *rt;
struct flowi4 fl4;
int ret;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst_ip;
fl4.saddr = src_ip;
fl4.flowi4_oif = addr->bound_dev_if;
rt = ip_route_output_key(addr->net, &fl4);
ret = PTR_ERR_OR_ZERO(rt);
if (ret)
return ret;
src_in->sin_addr.s_addr = fl4.saddr;
addr->hoplimit = ip4_dst_hoplimit(&rt->dst);
*prt = rt;
return 0;
}
#if IS_ENABLED(CONFIG_IPV6)
static int addr6_resolve(struct sockaddr *src_sock,
const struct sockaddr *dst_sock,
struct rdma_dev_addr *addr,
struct dst_entry **pdst)
{
struct sockaddr_in6 *src_in = (struct sockaddr_in6 *)src_sock;
const struct sockaddr_in6 *dst_in =
(const struct sockaddr_in6 *)dst_sock;
struct flowi6 fl6;
struct dst_entry *dst;
int ret;
memset(&fl6, 0, sizeof fl6);
fl6.daddr = dst_in->sin6_addr;
fl6.saddr = src_in->sin6_addr;
fl6.flowi6_oif = addr->bound_dev_if;
ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6);
if (ret < 0)
return ret;
if (ipv6_addr_any(&src_in->sin6_addr))
src_in->sin6_addr = fl6.saddr;
addr->hoplimit = ip6_dst_hoplimit(dst);
*pdst = dst;
return 0;
}
#else
static int addr6_resolve(struct sockaddr *src_sock,
const struct sockaddr *dst_sock,
struct rdma_dev_addr *addr,
struct dst_entry **pdst)
{
return -EADDRNOTAVAIL;
}
#endif
static int addr_resolve_neigh(const struct dst_entry *dst,
const struct sockaddr *dst_in,
struct rdma_dev_addr *addr,
unsigned int ndev_flags,
u32 seq)
{
int ret = 0;
if (ndev_flags & IFF_LOOPBACK) {
memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
} else {
if (!(ndev_flags & IFF_NOARP)) {
/* If the device doesn't do ARP internally */
ret = fetch_ha(dst, addr, dst_in, seq);
}
}
return ret;
}
static int copy_src_l2_addr(struct rdma_dev_addr *dev_addr,
const struct sockaddr *dst_in,
const struct dst_entry *dst,
const struct net_device *ndev)
{
int ret = 0;
if (dst->dev->flags & IFF_LOOPBACK)
ret = rdma_translate_ip(dst_in, dev_addr);
else
rdma_copy_src_l2_addr(dev_addr, dst->dev);
/*
* If there's a gateway and type of device not ARPHRD_INFINIBAND,
* we're definitely in RoCE v2 (as RoCE v1 isn't routable) set the
* network type accordingly.
*/
if (has_gateway(dst, dst_in->sa_family) &&
ndev->type != ARPHRD_INFINIBAND)
dev_addr->network = dst_in->sa_family == AF_INET ?
RDMA_NETWORK_IPV4 :
RDMA_NETWORK_IPV6;
else
dev_addr->network = RDMA_NETWORK_IB;
return ret;
}
static int rdma_set_src_addr_rcu(struct rdma_dev_addr *dev_addr,
unsigned int *ndev_flags,
const struct sockaddr *dst_in,
const struct dst_entry *dst)
{
struct net_device *ndev = READ_ONCE(dst->dev);
*ndev_flags = ndev->flags;
/* A physical device must be the RDMA device to use */
if (ndev->flags & IFF_LOOPBACK) {
/*
* RDMA (IB/RoCE, iWarp) doesn't run on lo interface or
* loopback IP address. So if route is resolved to loopback
* interface, translate that to a real ndev based on non
* loopback IP address.
*/
ndev = rdma_find_ndev_for_src_ip_rcu(dev_net(ndev), dst_in);
if (IS_ERR(ndev))
return -ENODEV;
}
return copy_src_l2_addr(dev_addr, dst_in, dst, ndev);
}
static int set_addr_netns_by_gid_rcu(struct rdma_dev_addr *addr)
{
struct net_device *ndev;
ndev = rdma_read_gid_attr_ndev_rcu(addr->sgid_attr);
if (IS_ERR(ndev))
return PTR_ERR(ndev);
/*
* Since we are holding the rcu, reading net and ifindex
* are safe without any additional reference; because
* change_net_namespace() in net/core/dev.c does rcu sync
* after it changes the state to IFF_DOWN and before
* updating netdev fields {net, ifindex}.
*/
addr->net = dev_net(ndev);
addr->bound_dev_if = ndev->ifindex;
return 0;
}
static void rdma_addr_set_net_defaults(struct rdma_dev_addr *addr)
{
addr->net = &init_net;
addr->bound_dev_if = 0;
}
static int addr_resolve(struct sockaddr *src_in,
const struct sockaddr *dst_in,
struct rdma_dev_addr *addr,
bool resolve_neigh,
bool resolve_by_gid_attr,
u32 seq)
{
struct dst_entry *dst = NULL;
unsigned int ndev_flags = 0;
struct rtable *rt = NULL;
int ret;
if (!addr->net) {
pr_warn_ratelimited("%s: missing namespace\n", __func__);
return -EINVAL;
}
rcu_read_lock();
if (resolve_by_gid_attr) {
if (!addr->sgid_attr) {
rcu_read_unlock();
pr_warn_ratelimited("%s: missing gid_attr\n", __func__);
return -EINVAL;
}
/*
* If the request is for a specific gid attribute of the
* rdma_dev_addr, derive net from the netdevice of the
* GID attribute.
*/
ret = set_addr_netns_by_gid_rcu(addr);
if (ret) {
rcu_read_unlock();
return ret;
}
}
if (src_in->sa_family == AF_INET) {
ret = addr4_resolve(src_in, dst_in, addr, &rt);
dst = &rt->dst;
} else {
ret = addr6_resolve(src_in, dst_in, addr, &dst);
}
if (ret) {
rcu_read_unlock();
goto done;
}
ret = rdma_set_src_addr_rcu(addr, &ndev_flags, dst_in, dst);
rcu_read_unlock();
/*
* Resolve neighbor destination address if requested and
* only if src addr translation didn't fail.
*/
if (!ret && resolve_neigh)
ret = addr_resolve_neigh(dst, dst_in, addr, ndev_flags, seq);
if (src_in->sa_family == AF_INET)
ip_rt_put(rt);
else
dst_release(dst);
done:
/*
* Clear the addr net to go back to its original state, only if it was
* derived from GID attribute in this context.
*/
if (resolve_by_gid_attr)
rdma_addr_set_net_defaults(addr);
return ret;
}
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
static void process_one_req(struct work_struct *_work)
{
struct addr_req *req;
struct sockaddr *src_in, *dst_in;
req = container_of(_work, struct addr_req, work.work);
if (req->status == -ENODATA) {
src_in = (struct sockaddr *)&req->src_addr;
dst_in = (struct sockaddr *)&req->dst_addr;
req->status = addr_resolve(src_in, dst_in, req->addr,
true, req->resolve_by_gid_attr,
req->seq);
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
if (req->status && time_after_eq(jiffies, req->timeout)) {
req->status = -ETIMEDOUT;
} else if (req->status == -ENODATA) {
/* requeue the work for retrying again */
spin_lock_bh(&lock);
if (!list_empty(&req->list))
set_timeout(req, req->timeout);
spin_unlock_bh(&lock);
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
return;
}
}
RDMA/rdma_cm: Fix use after free race with process_one_req process_one_req() can race with rdma_addr_cancel(): CPU0 CPU1 ==== ==== process_one_work() debug_work_deactivate(work); process_one_req() rdma_addr_cancel() mutex_lock(&lock); set_timeout(&req->work,..); __queue_work() debug_work_activate(work); mutex_unlock(&lock); mutex_lock(&lock); [..] list_del(&req->list); mutex_unlock(&lock); [..] // ODEBUG explodes since the work is still queued. kfree(req); Causing ODEBUG to detect the use after free: ODEBUG: free active (active state 0) object type: work_struct hint: process_one_req+0x0/0x6c0 include/net/dst.h:165 WARNING: CPU: 0 PID: 79 at lib/debugobjects.c:291 debug_print_object+0x166/0x220 lib/debugobjects.c:288 kvm: emulating exchange as write Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 79 Comm: kworker/u4:3 Not tainted 4.16.0-rc6+ #361 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: ib_addr process_one_req Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x24d lib/dump_stack.c:53 panic+0x1e4/0x41c kernel/panic.c:183 __warn+0x1dc/0x200 kernel/panic.c:547 report_bug+0x1f4/0x2b0 lib/bug.c:186 fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178 fixup_bug arch/x86/kernel/traps.c:247 [inline] do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315 invalid_op+0x1b/0x40 arch/x86/entry/entry_64.S:986 RIP: 0010:debug_print_object+0x166/0x220 lib/debugobjects.c:288 RSP: 0000:ffff8801d966f210 EFLAGS: 00010086 RAX: dffffc0000000008 RBX: 0000000000000003 RCX: ffffffff815acd6e RDX: 0000000000000000 RSI: 1ffff1003b2cddf2 RDI: 0000000000000000 RBP: ffff8801d966f250 R08: 0000000000000000 R09: 1ffff1003b2cddc8 R10: ffffed003b2cde71 R11: ffffffff86f39a98 R12: 0000000000000001 R13: ffffffff86f15540 R14: ffffffff86408700 R15: ffffffff8147c0a0 __debug_check_no_obj_freed lib/debugobjects.c:745 [inline] debug_check_no_obj_freed+0x662/0xf1f lib/debugobjects.c:774 kfree+0xc7/0x260 mm/slab.c:3799 process_one_req+0x2e7/0x6c0 drivers/infiniband/core/addr.c:592 process_one_work+0xc47/0x1bb0 kernel/workqueue.c:2113 worker_thread+0x223/0x1990 kernel/workqueue.c:2247 kthread+0x33c/0x400 kernel/kthread.c:238 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:406 Fixes: 5fff41e1f89d ("IB/core: Fix race condition in resolving IP to MAC") Reported-by: <syzbot+3b4acab09b6463472d0a@syzkaller.appspotmail.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-23 03:04:23 +07:00
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
req->callback(req->status, (struct sockaddr *)&req->src_addr,
req->addr, req->context);
req->callback = NULL;
spin_lock_bh(&lock);
if (!list_empty(&req->list)) {
/*
* Although the work will normally have been canceled by the
* workqueue, it can still be requeued as long as it is on the
* req_list.
*/
cancel_delayed_work(&req->work);
list_del_init(&req->list);
kfree(req);
}
spin_unlock_bh(&lock);
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
}
int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr,
struct rdma_dev_addr *addr, unsigned long timeout_ms,
void (*callback)(int status, struct sockaddr *src_addr,
struct rdma_dev_addr *addr, void *context),
bool resolve_by_gid_attr, void *context)
{
struct sockaddr *src_in, *dst_in;
struct addr_req *req;
int ret = 0;
2007-07-19 15:49:03 +07:00
req = kzalloc(sizeof *req, GFP_KERNEL);
if (!req)
return -ENOMEM;
src_in = (struct sockaddr *) &req->src_addr;
dst_in = (struct sockaddr *) &req->dst_addr;
if (src_addr) {
if (src_addr->sa_family != dst_addr->sa_family) {
ret = -EINVAL;
goto err;
}
memcpy(src_in, src_addr, rdma_addr_size(src_addr));
} else {
src_in->sa_family = dst_addr->sa_family;
}
memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr));
req->addr = addr;
req->callback = callback;
req->context = context;
req->resolve_by_gid_attr = resolve_by_gid_attr;
IB/core: Fix race condition in resolving IP to MAC Currently while resolving IP address to MAC address single delayed work is used for resolving multiple such resolve requests. This singled work is essentially performs two tasks. (a) any retry needed to resolve and (b) it executes the callback function for all completed requests While work is executing callbacks, any new work scheduled on for this workqueue is lost because workqueue has completed looking at all pending requests and now looking at callbacks, but work is still under execution. Any further retry to look at pending requests in process_req() after executing callbacks would lead to similar race condition (may be reduce the probably further but doesn't eliminate it). Retrying to enqueue work that from queue_req() context is not something rest of the kernel modules have followed. Therefore fix in this patch utilizes kernel facility to enqueue multiple work items to a workqueue. This ensures that no such requests gets lost in synchronization. Request list is still maintained so that rdma_cancel_addr() can unlink the request and get the completion with error sooner. Neighbour update event handling continues to be handled in same way as before. Additionally process_req() work entry cancels any pending work for a request that gets completed while processing those requests. Originally ib_addr was ST workqueue, but it became MT work queue with patch of [1]. This patch again makes it similar to ST so that neighbour update events handler work item doesn't race with other work items. In one such below trace, (though on 4.5 based kernel) it can be seen that process_req() never executed the callback, which is likely for an event that was schedule by queue_req() when previous callback was getting executed by workqueue. [<ffffffff816b0dde>] schedule+0x3e/0x90 [<ffffffff816b3c45>] schedule_timeout+0x1b5/0x210 [<ffffffff81618c37>] ? ip_route_output_flow+0x27/0x70 [<ffffffffa027f9c9>] ? addr_resolve+0x149/0x1b0 [ib_addr] [<ffffffff816b228f>] wait_for_completion+0x10f/0x170 [<ffffffff810b6140>] ? try_to_wake_up+0x210/0x210 [<ffffffffa027f220>] ? rdma_copy_addr+0xa0/0xa0 [ib_addr] [<ffffffffa0280120>] rdma_addr_find_l2_eth_by_grh+0x1d0/0x278 [ib_addr] [<ffffffff81321297>] ? sub_alloc+0x77/0x1c0 [<ffffffffa02943b7>] ib_init_ah_from_wc+0x3a7/0x5a0 [ib_core] [<ffffffffa0457aba>] cm_req_handler+0xea/0x580 [ib_cm] [<ffffffff81015982>] ? __switch_to+0x212/0x5e0 [<ffffffffa04582fd>] cm_work_handler+0x6d/0x150 [ib_cm] [<ffffffff810a14c1>] process_one_work+0x151/0x4b0 [<ffffffff810a1940>] worker_thread+0x120/0x480 [<ffffffff816b074b>] ? __schedule+0x30b/0x890 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a1820>] ? process_one_work+0x4b0/0x4b0 [<ffffffff810a6b1e>] kthread+0xce/0xf0 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff816b53a2>] ret_from_fork+0x42/0x70 [<ffffffff810a6a50>] ? kthread_freezable_should_stop+0x70/0x70 INFO: task kworker/u144:1:156520 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u144:1 D ffff883ffe1d7600 0 156520 2 0x00000080 Workqueue: ib_addr process_req [ib_addr] ffff883f446fbbd8 0000000000000046 ffff881f95280000 ffff881ff24de200 ffff883f66120000 ffff883f446f8008 ffff881f95280000 ffff883f6f9208c4 ffff883f6f9208c8 00000000ffffffff ffff883f446fbbf8 ffffffff816b0dde [1] http://lkml.iu.edu/hypermail/linux/kernel/1608.1/05834.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-01 13:41:34 +07:00
INIT_DELAYED_WORK(&req->work, process_one_req);
req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
req->status = addr_resolve(src_in, dst_in, addr, true,
req->resolve_by_gid_attr, req->seq);
switch (req->status) {
case 0:
req->timeout = jiffies;
queue_req(req);
break;
case -ENODATA:
req->timeout = msecs_to_jiffies(timeout_ms) + jiffies;
queue_req(req);
break;
default:
ret = req->status;
goto err;
}
return ret;
err:
kfree(req);
return ret;
}
EXPORT_SYMBOL(rdma_resolve_ip);
int roce_resolve_route_from_path(struct sa_path_rec *rec,
const struct ib_gid_attr *attr)
{
union {
struct sockaddr _sockaddr;
struct sockaddr_in _sockaddr_in;
struct sockaddr_in6 _sockaddr_in6;
} sgid, dgid;
struct rdma_dev_addr dev_addr = {};
int ret;
if (rec->roce.route_resolved)
return 0;
rdma_gid2ip((struct sockaddr *)&sgid, &rec->sgid);
rdma_gid2ip((struct sockaddr *)&dgid, &rec->dgid);
if (sgid._sockaddr.sa_family != dgid._sockaddr.sa_family)
return -EINVAL;
if (!attr || !attr->ndev)
return -EINVAL;
dev_addr.net = &init_net;
dev_addr.sgid_attr = attr;
ret = addr_resolve((struct sockaddr *)&sgid, (struct sockaddr *)&dgid,
&dev_addr, false, true, 0);
if (ret)
return ret;
if ((dev_addr.network == RDMA_NETWORK_IPV4 ||
dev_addr.network == RDMA_NETWORK_IPV6) &&
rec->rec_type != SA_PATH_REC_TYPE_ROCE_V2)
return -EINVAL;
rec->roce.route_resolved = true;
return 0;
}
/**
* rdma_addr_cancel - Cancel resolve ip request
* @addr: Pointer to address structure given previously
* during rdma_resolve_ip().
* rdma_addr_cancel() is synchronous function which cancels any pending
* request if there is any.
*/
void rdma_addr_cancel(struct rdma_dev_addr *addr)
{
struct addr_req *req, *temp_req;
struct addr_req *found = NULL;
spin_lock_bh(&lock);
list_for_each_entry_safe(req, temp_req, &req_list, list) {
if (req->addr == addr) {
/*
* Removing from the list means we take ownership of
* the req
*/
list_del_init(&req->list);
found = req;
break;
}
}
spin_unlock_bh(&lock);
if (!found)
return;
/*
* sync canceling the work after removing it from the req_list
* guarentees no work is running and none will be started.
*/
cancel_delayed_work_sync(&found->work);
kfree(found);
}
EXPORT_SYMBOL(rdma_addr_cancel);
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
struct resolve_cb_context {
struct completion comp;
int status;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
};
static void resolve_cb(int status, struct sockaddr *src_addr,
struct rdma_dev_addr *addr, void *context)
{
((struct resolve_cb_context *)context)->status = status;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
complete(&((struct resolve_cb_context *)context)->comp);
}
int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
const union ib_gid *dgid,
u8 *dmac, const struct ib_gid_attr *sgid_attr,
int *hoplimit)
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
{
struct rdma_dev_addr dev_addr;
struct resolve_cb_context ctx;
union {
struct sockaddr_in _sockaddr_in;
struct sockaddr_in6 _sockaddr_in6;
} sgid_addr, dgid_addr;
IB/{core/cm}: Fix generating a return AH for RoCEE When computing a UD reverse path (return AH) from a WC the code was not doing a route lookup anchored in a specific netdevice. This caused several bugs, including broken IPv6 link-local address support in RoCEv2. [1] This fixes the lookup by determining the GID table entry that the HW matched to the SGID for the WC and then using the netdevice from that entry to perform the route and ND lookup for the 'DGID' to build a return AH. RoCE GID table management ensures that right upper netdevices of the physical netdevices are added. Therefore init_ah_from_wc doesn't need to perform such check. Now that route lookup is done based on the netdevice of the GID entry, simplify code to not have ifindex and vlan pointers. As part of that, refactor to have netdevice as input parameter. This is already discussed at [2]. Finally ib_init_ah_from_wc resolves dmac for unicast GID in similar way as what ib_resolve_eth_dmac() does. So ib_resolve_eth_dmac is refactored to split for unicast and non unicast GIDs, so that it can be reused by ib_init_ah_from_wc. While we are at refactoring ib_resolve_eth_dmac(), it is further simplified (a) to avoid hoplimit as optional parameter, as there is only one user who always queries hoplimit. (b) for empty line. (c) avoided zero initialization of ret. (d) removed as exported symbol as only ib core uses it. For IPv6, this is tested using simple rping test as below. rping -sv -a ::0 rping -c -a fe80::268a:7ff:fe55:4661%ens2f1 -C 1 -v -d [1] https://www.spinics.net/lists/linux-rdma/msg45690.html [2] https://www.spinics.net/lists/linux-rdma/msg45710.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Reported-by: Roland Dreier <roland@purestorage.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2017-11-14 19:51:49 +07:00
int ret;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
rdma_gid2ip((struct sockaddr *)&sgid_addr, sgid);
rdma_gid2ip((struct sockaddr *)&dgid_addr, dgid);
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
memset(&dev_addr, 0, sizeof(dev_addr));
dev_addr.net = &init_net;
dev_addr.sgid_attr = sgid_attr;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
init_completion(&ctx.comp);
ret = rdma_resolve_ip((struct sockaddr *)&sgid_addr,
(struct sockaddr *)&dgid_addr, &dev_addr, 1000,
resolve_cb, true, &ctx);
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
if (ret)
return ret;
wait_for_completion(&ctx.comp);
ret = ctx.status;
if (ret)
return ret;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
IB/{core/cm}: Fix generating a return AH for RoCEE When computing a UD reverse path (return AH) from a WC the code was not doing a route lookup anchored in a specific netdevice. This caused several bugs, including broken IPv6 link-local address support in RoCEv2. [1] This fixes the lookup by determining the GID table entry that the HW matched to the SGID for the WC and then using the netdevice from that entry to perform the route and ND lookup for the 'DGID' to build a return AH. RoCE GID table management ensures that right upper netdevices of the physical netdevices are added. Therefore init_ah_from_wc doesn't need to perform such check. Now that route lookup is done based on the netdevice of the GID entry, simplify code to not have ifindex and vlan pointers. As part of that, refactor to have netdevice as input parameter. This is already discussed at [2]. Finally ib_init_ah_from_wc resolves dmac for unicast GID in similar way as what ib_resolve_eth_dmac() does. So ib_resolve_eth_dmac is refactored to split for unicast and non unicast GIDs, so that it can be reused by ib_init_ah_from_wc. While we are at refactoring ib_resolve_eth_dmac(), it is further simplified (a) to avoid hoplimit as optional parameter, as there is only one user who always queries hoplimit. (b) for empty line. (c) avoided zero initialization of ret. (d) removed as exported symbol as only ib core uses it. For IPv6, this is tested using simple rping test as below. rping -sv -a ::0 rping -c -a fe80::268a:7ff:fe55:4661%ens2f1 -C 1 -v -d [1] https://www.spinics.net/lists/linux-rdma/msg45690.html [2] https://www.spinics.net/lists/linux-rdma/msg45710.html Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Matan Barak <matanb@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Reported-by: Roland Dreier <roland@purestorage.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2017-11-14 19:51:49 +07:00
*hoplimit = dev_addr.hoplimit;
return 0;
IB/core: Ethernet L2 attributes in verbs/cm structures This patch add the support for Ethernet L2 attributes in the verbs/cm/cma structures. When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority in a similar manner that the IB L2 (and the L4 PKEY) attributes are used. Thus, those attributes were added to the following structures: * ib_ah_attr - added dmac * ib_qp_attr - added smac and vlan_id, (sl remains vlan priority) * ib_wc - added smac, vlan_id * ib_sa_path_rec - added smac, dmac, vlan_id * cm_av - added smac and vlan_id For the path record structure, extra care was taken to avoid the new fields when packing it into wire format, so we don't break the IB CM and SA wire protocol. On the active side, the CM fills. its internal structures from the path provided by the ULP. We add there taking the ETH L2 attributes and placing them into the CM Address Handle (struct cm_av). On the passive side, the CM fills its internal structures from the WC associated with the REQ message. We add there taking the ETH L2 attributes from the WC. When the HW driver provides the required ETH L2 attributes in the WC, they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core code checks for the presence of these flags, and in their absence does address resolution from the ib_init_ah_from_wc() helper function. ib_modify_qp_is_ok is also updated to consider the link layer. Some parameters are mandatory for Ethernet link layer, while they are irrelevant for IB. Vendor drivers are modified to support the new function signature. Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-12-12 23:03:11 +07:00
}
static int netevent_callback(struct notifier_block *self, unsigned long event,
void *ctx)
{
struct addr_req *req;
if (event == NETEVENT_NEIGH_UPDATE) {
struct neighbour *neigh = ctx;
if (neigh->nud_state & NUD_VALID) {
spin_lock_bh(&lock);
list_for_each_entry(req, &req_list, list)
set_timeout(req, jiffies);
spin_unlock_bh(&lock);
}
}
return 0;
}
static struct notifier_block nb = {
.notifier_call = netevent_callback
};
int addr_init(void)
{
addr_wq = alloc_ordered_workqueue("ib_addr", 0);
if (!addr_wq)
return -ENOMEM;
register_netevent_notifier(&nb);
return 0;
}
void addr_cleanup(void)
{
unregister_netevent_notifier(&nb);
destroy_workqueue(addr_wq);
WARN_ON(!list_empty(&req_list));
}