* [PATCHv2 net-next 1/3] xfrm: Try to honor policy index if it's supplied by user
From: Fan Du @ 2013-11-07 9:47 UTC (permalink / raw)
To: steffen.klassert, herbert, davem; +Cc: netdev
In-Reply-To: <1383817670-5783-1-git-send-email-fan.du@windriver.com>
xfrm code always searches for unused policy index for
newly created policy regardless whether or not user
space policy index hint supplied.
This patch enables such feature so that using
"ip xfrm ... index=xxx" can be used by user to set
specific policy index.
Currently this beahvior is broken, so this patch make
it happen as expected.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
v2:
-Unchanged
---
net/xfrm/xfrm_policy.c | 16 +++++++++++-----
net/xfrm/xfrm_user.c | 10 +++++++++-
2 files changed, 20 insertions(+), 6 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9a91f74..a5bbdfb 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -538,7 +538,7 @@ static void xfrm_hash_resize(struct work_struct *work)
/* Generate new index... KAME seems to generate them ordered by cost
* of an absolute inpredictability of ordering of rules. This will not pass. */
-static u32 xfrm_gen_index(struct net *net, int dir)
+static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
{
static u32 idx_generator;
@@ -548,8 +548,14 @@ static u32 xfrm_gen_index(struct net *net, int dir)
u32 idx;
int found;
- idx = (idx_generator | dir);
- idx_generator += 8;
+ if (!index) {
+ idx = (idx_generator | dir);
+ idx_generator += 8;
+ } else {
+ idx = index;
+ index = 0;
+ }
+
if (idx == 0)
idx = 8;
list = net->xfrm.policy_byidx + idx_hash(net, idx);
@@ -672,7 +678,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
xfrm_policy_requeue(delpol, policy);
__xfrm_policy_unlink(delpol, dir);
}
- policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
+ policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
policy->curlft.add_time = get_seconds();
policy->curlft.use_time = 0;
@@ -1192,7 +1198,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
sk->sk_policy[dir] = pol;
if (pol) {
pol->curlft.add_time = get_seconds();
- pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
+ pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
}
if (old_pol) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index f964d4c..4e0546e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1189,6 +1189,8 @@ static int verify_policy_type(u8 type)
static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
{
+ int ret;
+
switch (p->share) {
case XFRM_SHARE_ANY:
case XFRM_SHARE_SESSION:
@@ -1224,7 +1226,13 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
return -EINVAL;
}
- return verify_policy_dir(p->dir);
+ ret = verify_policy_dir(p->dir);
+ if (ret)
+ return ret;
+ if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+ return -EINVAL;
+
+ return 0;
}
static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
--
1.7.9.5
^ permalink raw reply related
* [PATCHv2 net-next 3/3] xfrm: Namespacify xfrm state/policy locks
From: Fan Du @ 2013-11-07 9:47 UTC (permalink / raw)
To: steffen.klassert, herbert, davem; +Cc: netdev
In-Reply-To: <1383817670-5783-1-git-send-email-fan.du@windriver.com>
By semantics, xfrm layer is fully name space aware,
so will the locks, e.g. xfrm_state/pocliy_lock.
Ensure exclusive access into state/policy link list
for different name space with one global lock is not
right in terms of semantics aspect at first place,
as they are indeed mutually independent with each
other, but also more seriously causes scalability
problem.
One practical scenario is on a Open Network Stack,
more than hundreds of lxc tenants acts as routers
within one host, a global xfrm_state/policy_lock
becomes the bottleneck. But onces those locks are
decoupled in a per-namespace fashion, locks contend
is just with in specific name space scope, without
causing additional SPD/SAD access delay for other
name space.
Also this patch improve scalability while as without
changing original xfrm behavior.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
v2:
-Use sock_net to access struct net, instead of using sk_net directly.
---
include/net/netns/xfrm.h | 4 ++
include/net/xfrm.h | 11 +++--
net/key/af_key.c | 15 ++++---
net/xfrm/xfrm_policy.c | 104 ++++++++++++++++++++++++----------------------
net/xfrm/xfrm_state.c | 104 ++++++++++++++++++++++++----------------------
net/xfrm/xfrm_user.c | 14 +++++--
6 files changed, 138 insertions(+), 114 deletions(-)
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 5299e69..ea28404 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -59,6 +59,10 @@ struct netns_xfrm {
#if IS_ENABLED(CONFIG_IPV6)
struct dst_ops xfrm6_dst_ops;
#endif
+ spinlock_t xfrm_state_lock;
+ spinlock_t xfrm_policy_sk_bundle_lock;
+ rwlock_t xfrm_policy_lock;
+ struct mutex xfrm_cfg_mutex;
};
#endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 5b522c5..59f5d0a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -53,7 +53,6 @@
#define XFRM_INC_STATS_USER(net, field) ((void)(net))
#endif
-extern struct mutex xfrm_cfg_mutex;
/* Organization of SPD aka "XFRM rules"
------------------------------------
@@ -1409,7 +1408,7 @@ static inline void xfrm_sysctl_fini(struct net *net)
void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*), void *);
-void xfrm_state_walk_done(struct xfrm_state_walk *walk);
+void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net);
struct xfrm_state *xfrm_state_alloc(struct net *net);
struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
@@ -1436,12 +1435,12 @@ struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
unsigned short family);
#ifdef CONFIG_XFRM_SUB_POLICY
int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
- unsigned short family);
+ unsigned short family, struct net *net);
int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
unsigned short family);
#else
static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
- int n, unsigned short family)
+ int n, unsigned short family, struct net *net)
{
return -ENOSYS;
}
@@ -1553,7 +1552,7 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type);
int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
int (*func)(struct xfrm_policy *, int, int, void*),
void *);
-void xfrm_policy_walk_done(struct xfrm_policy_walk *walk);
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net);
int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
u8 type, int dir,
@@ -1576,7 +1575,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
const struct xfrm_migrate *m, int num_bundles,
const struct xfrm_kmaddress *k);
-struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m);
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net);
struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m);
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 33480b3..537a4d4 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1785,7 +1785,9 @@ static int pfkey_dump_sa(struct pfkey_sock *pfk)
static void pfkey_dump_sa_done(struct pfkey_sock *pfk)
{
- xfrm_state_walk_done(&pfk->dump.u.state);
+ struct net *net = sock_net(&pfk->sk);
+
+ xfrm_state_walk_done(&pfk->dump.u.state, net);
}
static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs)
@@ -1861,7 +1863,7 @@ static u32 gen_reqid(struct net *net)
reqid = IPSEC_MANUAL_REQID_MAX+1;
xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN);
rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid);
- xfrm_policy_walk_done(&walk);
+ xfrm_policy_walk_done(&walk, net);
if (rc != -EEXIST)
return reqid;
} while (reqid != start);
@@ -2660,7 +2662,9 @@ static int pfkey_dump_sp(struct pfkey_sock *pfk)
static void pfkey_dump_sp_done(struct pfkey_sock *pfk)
{
- xfrm_policy_walk_done(&pfk->dump.u.policy);
+ struct net *net = sock_net((struct sock *)pfk);
+
+ xfrm_policy_walk_done(&pfk->dump.u.policy, net);
}
static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs)
@@ -3570,6 +3574,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
struct sk_buff *skb = NULL;
struct sadb_msg *hdr = NULL;
int err;
+ struct net *net = sock_net(sk);
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB)
@@ -3592,9 +3597,9 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
if (!hdr)
goto out;
- mutex_lock(&xfrm_cfg_mutex);
+ mutex_lock(&net->xfrm.xfrm_cfg_mutex);
err = pfkey_process(sk, skb, hdr);
- mutex_unlock(&xfrm_cfg_mutex);
+ mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
out:
if (err && hdr && pfkey_error(hdr, err, sk) == 0)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 907fd2f..73b04d3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,12 +39,7 @@
#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
#define XFRM_MAX_QUEUE_LEN 100
-DEFINE_MUTEX(xfrm_cfg_mutex);
-EXPORT_SYMBOL(xfrm_cfg_mutex);
-
-static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
static struct dst_entry *xfrm_policy_sk_bundles;
-static DEFINE_RWLOCK(xfrm_policy_lock);
static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
@@ -438,7 +433,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
if (!ndst)
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
for (i = hmask; i >= 0; i--)
xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
@@ -446,7 +441,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
net->xfrm.policy_bydst[dir].table = ndst;
net->xfrm.policy_bydst[dir].hmask = nhashmask;
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
}
@@ -463,7 +458,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
if (!nidx)
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
for (i = hmask; i >= 0; i--)
xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
@@ -471,7 +466,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
net->xfrm.policy_byidx = nidx;
net->xfrm.policy_idx_hmask = nhashmask;
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
}
@@ -504,7 +499,7 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total)
void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
{
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
@@ -513,7 +508,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
si->spdhcnt = net->xfrm.policy_idx_hmask;
si->spdhmcnt = xfrm_policy_hashmax;
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_spd_getinfo);
@@ -636,7 +631,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
struct hlist_head *chain;
struct hlist_node *newpos;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
delpol = NULL;
newpos = NULL;
@@ -647,7 +642,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
xfrm_sec_ctx_match(pol->security, policy->security) &&
!WARN_ON(delpol)) {
if (excl) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return -EEXIST;
}
delpol = pol;
@@ -685,7 +680,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
if (!mod_timer(&policy->timer, jiffies + HZ))
xfrm_pol_hold(policy);
list_add(&policy->walk.all, &net->xfrm.policy_all);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (delpol)
xfrm_policy_kill(delpol);
@@ -705,7 +700,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
struct hlist_head *chain;
*err = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
@@ -718,7 +713,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
*err = security_xfrm_policy_delete(
pol->security);
if (*err) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
@@ -727,7 +722,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
break;
}
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
@@ -746,7 +741,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
return NULL;
*err = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = net->xfrm.policy_byidx + idx_hash(net, id);
ret = NULL;
hlist_for_each_entry(pol, chain, byidx) {
@@ -757,7 +752,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
*err = security_xfrm_policy_delete(
pol->security);
if (*err) {
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
@@ -766,7 +761,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
break;
}
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
@@ -829,7 +824,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
{
int dir, err = 0, cnt = 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
err = xfrm_policy_flush_secctx_check(net, type, audit_info);
if (err)
@@ -845,7 +840,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
if (pol->type != type)
continue;
__xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
cnt++;
xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
@@ -854,7 +849,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
xfrm_policy_kill(pol);
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again1;
}
@@ -866,7 +861,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
if (pol->type != type)
continue;
__xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
cnt++;
xfrm_audit_policy_delete(pol, 1,
@@ -875,7 +870,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
audit_info->secid);
xfrm_policy_kill(pol);
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again2;
}
}
@@ -884,7 +879,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
if (!cnt)
err = -ESRCH;
out:
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return err;
}
EXPORT_SYMBOL(xfrm_policy_flush);
@@ -904,7 +899,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
if (list_empty(&walk->walk.all) && walk->seq != 0)
return 0;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
if (list_empty(&walk->walk.all))
x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
else
@@ -930,7 +925,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
}
list_del_init(&walk->walk.all);
out:
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
return error;
}
EXPORT_SYMBOL(xfrm_policy_walk);
@@ -944,14 +939,14 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
}
EXPORT_SYMBOL(xfrm_policy_walk_init);
-void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
{
if (list_empty(&walk->walk.all))
return;
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
list_del(&walk->walk.all);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_policy_walk_done);
@@ -996,7 +991,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
if (unlikely(!daddr || !saddr))
return NULL;
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_direct(net, daddr, saddr, family, dir);
ret = NULL;
hlist_for_each_entry(pol, chain, bydst) {
@@ -1032,7 +1027,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
if (ret)
xfrm_pol_hold(ret);
fail:
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return ret;
}
@@ -1109,8 +1104,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
const struct flowi *fl)
{
struct xfrm_policy *pol;
+ struct net *net = sock_net(sk);
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock);
if ((pol = sk->sk_policy[dir]) != NULL) {
bool match = xfrm_selector_match(&pol->selector, fl,
sk->sk_family);
@@ -1134,7 +1130,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
pol = NULL;
}
out:
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
@@ -1172,9 +1168,11 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
{
- write_lock_bh(&xfrm_policy_lock);
+ struct net *net = xp_net(pol);
+
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
pol = __xfrm_policy_unlink(pol, dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (pol) {
xfrm_policy_kill(pol);
return 0;
@@ -1193,7 +1191,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
return -EINVAL;
#endif
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
old_pol = sk->sk_policy[dir];
sk->sk_policy[dir] = pol;
if (pol) {
@@ -1210,7 +1208,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
*/
__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
}
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (old_pol) {
xfrm_policy_kill(old_pol);
@@ -1221,6 +1219,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
{
struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+ struct net *net = xp_net(old);
if (newp) {
newp->selector = old->selector;
@@ -1239,9 +1238,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
newp->type = old->type;
memcpy(newp->xfrm_vec, old->xfrm_vec,
newp->xfrm_nr*sizeof(struct xfrm_tmpl));
- write_lock_bh(&xfrm_policy_lock);
+ write_lock_bh(&net->xfrm.xfrm_policy_lock);
__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
- write_unlock_bh(&xfrm_policy_lock);
+ write_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_pol_put(newp);
}
return newp;
@@ -2112,10 +2111,10 @@ restart:
dst_hold(&xdst->u.dst);
- spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
xdst->u.dst.next = xfrm_policy_sk_bundles;
xfrm_policy_sk_bundles = &xdst->u.dst;
- spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
route = xdst->route;
}
@@ -2440,7 +2439,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
}
xfrm_nr = ti;
if (npols > 1) {
- xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
+ xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
tpp = stp;
}
@@ -2569,10 +2568,10 @@ static void __xfrm_garbage_collect(struct net *net)
{
struct dst_entry *head, *next;
- spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
head = xfrm_policy_sk_bundles;
xfrm_policy_sk_bundles = NULL;
- spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
while (head) {
next = head->next;
@@ -2956,6 +2955,13 @@ static int __net_init xfrm_net_init(struct net *net)
rv = xfrm_sysctl_init(net);
if (rv < 0)
goto out_sysctl;
+
+ /* Initialize the per-net locks here */
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
+ rwlock_init(&net->xfrm.xfrm_policy_lock);
+ spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock);
+ mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
return 0;
out_sysctl:
@@ -3082,7 +3088,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
struct hlist_head *chain;
u32 priority = ~0U;
- read_lock_bh(&xfrm_policy_lock);
+ read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/
chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
hlist_for_each_entry(pol, chain, bydst) {
if (xfrm_migrate_selector_match(sel, &pol->selector) &&
@@ -3105,7 +3111,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
if (ret)
xfrm_pol_hold(ret);
- read_unlock_bh(&xfrm_policy_lock);
+ read_unlock_bh(&net->xfrm.xfrm_policy_lock);
return ret;
}
@@ -3236,7 +3242,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
/* Stage 2 - find and update state(s) */
for (i = 0, mp = m; i < num_migrate; i++, mp++) {
- if ((x = xfrm_migrate_state_find(mp))) {
+ if ((x = xfrm_migrate_state_find(mp, net))) {
x_cur[nx_cur] = x;
nx_cur++;
if ((xc = xfrm_state_migrate(x, mp))) {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 68c2f35..290479d 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -35,8 +35,6 @@
destination/tunnel endpoint. (output)
*/
-static DEFINE_SPINLOCK(xfrm_state_lock);
-
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static inline unsigned int xfrm_dst_hash(struct net *net,
@@ -127,7 +125,7 @@ static void xfrm_hash_resize(struct work_struct *work)
goto out_unlock;
}
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
for (i = net->xfrm.state_hmask; i >= 0; i--)
@@ -144,7 +142,7 @@ static void xfrm_hash_resize(struct work_struct *work)
net->xfrm.state_byspi = nspi;
net->xfrm.state_hmask = nhashmask;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
osize = (ohashmask + 1) * sizeof(struct hlist_head);
xfrm_hash_free(odst, osize);
@@ -535,14 +533,14 @@ int __xfrm_state_delete(struct xfrm_state *x)
if (x->km.state != XFRM_STATE_DEAD) {
x->km.state = XFRM_STATE_DEAD;
- spin_lock(&xfrm_state_lock);
+ spin_lock(&net->xfrm.xfrm_state_lock);
list_del(&x->km.all);
hlist_del(&x->bydst);
hlist_del(&x->bysrc);
if (x->id.spi)
hlist_del(&x->byspi);
net->xfrm.state_num--;
- spin_unlock(&xfrm_state_lock);
+ spin_unlock(&net->xfrm.xfrm_state_lock);
/* All xfrm_state objects are created by xfrm_state_alloc.
* The xfrm_state_alloc call gives a reference, and that
@@ -603,7 +601,7 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info)
{
int i, err = 0, cnt = 0;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_flush_secctx_check(net, proto, audit_info);
if (err)
goto out;
@@ -616,7 +614,7 @@ restart:
if (!xfrm_state_kern(x) &&
xfrm_id_proto_match(x->id.proto, proto)) {
xfrm_state_hold(x);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
@@ -627,7 +625,7 @@ restart:
if (!err)
cnt++;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
goto restart;
}
}
@@ -636,7 +634,7 @@ restart:
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
wake_up(&net->xfrm.km_waitq);
return err;
}
@@ -644,11 +642,11 @@ EXPORT_SYMBOL(xfrm_state_flush);
void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
{
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
si->sadcnt = net->xfrm.state_num;
si->sadhcnt = net->xfrm.state_hmask;
si->sadhmcnt = xfrm_state_hashmax;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_sad_getinfo);
@@ -801,7 +799,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == encap_family &&
@@ -886,7 +884,7 @@ out:
xfrm_state_hold(x);
else
*err = acquire_in_progress ? -EAGAIN : error;
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (to_put)
xfrm_state_put(to_put);
return x;
@@ -900,7 +898,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
unsigned int h;
struct xfrm_state *rx = NULL, *x = NULL;
- spin_lock(&xfrm_state_lock);
+ spin_lock(&net->xfrm.xfrm_state_lock);
h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
@@ -918,7 +916,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
if (rx)
xfrm_state_hold(rx);
- spin_unlock(&xfrm_state_lock);
+ spin_unlock(&net->xfrm.xfrm_state_lock);
return rx;
@@ -957,7 +955,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
xfrm_hash_grow_check(net, x->bydst.next != NULL);
}
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
{
struct net *net = xs_net(xnew);
@@ -980,14 +978,16 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
void xfrm_state_insert(struct xfrm_state *x)
{
- spin_lock_bh(&xfrm_state_lock);
+ struct net *net = xs_net(x);
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
__xfrm_state_bump_genids(x);
__xfrm_state_insert(x);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_insert);
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
static struct xfrm_state *__find_acq_core(struct net *net,
const struct xfrm_mark *m,
unsigned short family, u8 mode,
@@ -1079,7 +1079,7 @@ int xfrm_state_add(struct xfrm_state *x)
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, family);
if (x1) {
@@ -1108,7 +1108,7 @@ int xfrm_state_add(struct xfrm_state *x)
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (x1) {
xfrm_state_delete(x1);
@@ -1203,16 +1203,16 @@ out:
return NULL;
}
-/* xfrm_state_lock is held */
-struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
+/* net->xfrm.xfrm_state_lock is held */
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
{
unsigned int h;
struct xfrm_state *x;
if (m->reqid) {
- h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr,
+ h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
m->reqid, m->old_family);
- hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) {
+ hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
@@ -1227,9 +1227,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
return x;
}
} else {
- h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr,
+ h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
m->old_family);
- hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) {
+ hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
@@ -1283,10 +1283,11 @@ int xfrm_state_update(struct xfrm_state *x)
struct xfrm_state *x1, *to_put;
int err;
int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+ struct net *net = xs_net(x);
to_put = NULL;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x1 = __xfrm_state_locate(x, use_spi, x->props.family);
err = -ESRCH;
@@ -1306,7 +1307,7 @@ int xfrm_state_update(struct xfrm_state *x)
err = 0;
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
if (to_put)
xfrm_state_put(to_put);
@@ -1377,9 +1378,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup);
@@ -1391,9 +1392,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
@@ -1405,9 +1406,9 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
@@ -1416,17 +1417,17 @@ EXPORT_SYMBOL(xfrm_find_acq);
#ifdef CONFIG_XFRM_SUB_POLICY
int
xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
- unsigned short family)
+ unsigned short family, struct net *net)
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
if (!afinfo)
return -EAFNOSUPPORT;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
if (afinfo->tmpl_sort)
err = afinfo->tmpl_sort(dst, src, n);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
@@ -1438,13 +1439,15 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+ struct net *net = xs_net(*dst);
+
if (!afinfo)
return -EAFNOSUPPORT;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (afinfo->state_sort)
err = afinfo->state_sort(dst, src, n);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_put_afinfo(afinfo);
return err;
}
@@ -1476,9 +1479,9 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
{
struct xfrm_state *x;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
x = __xfrm_find_acq_byseq(net, mark, seq);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
EXPORT_SYMBOL(xfrm_find_acq_byseq);
@@ -1536,10 +1539,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
}
}
if (x->id.spi) {
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = 0;
}
@@ -1562,7 +1565,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
if (walk->seq != 0 && list_empty(&walk->all))
return 0;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (list_empty(&walk->all))
x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
else
@@ -1586,7 +1589,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
}
list_del_init(&walk->all);
out:
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return err;
}
EXPORT_SYMBOL(xfrm_state_walk);
@@ -1600,14 +1603,14 @@ void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
}
EXPORT_SYMBOL(xfrm_state_walk_init);
-void xfrm_state_walk_done(struct xfrm_state_walk *walk)
+void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
{
if (list_empty(&walk->all))
return;
- spin_lock_bh(&xfrm_state_lock);
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
list_del(&walk->all);
- spin_unlock_bh(&xfrm_state_lock);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
EXPORT_SYMBOL(xfrm_state_walk_done);
@@ -2026,6 +2029,7 @@ int __net_init xfrm_state_init(struct net *net)
INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
init_waitqueue_head(&net->xfrm.km_waitq);
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
return 0;
out_byspi:
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 840cc8d..16c8460 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -877,7 +877,10 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
static int xfrm_dump_sa_done(struct netlink_callback *cb)
{
struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
- xfrm_state_walk_done(walk);
+ struct sock *sk = cb->skb->sk;
+ struct net *net = sock_net(sk);
+
+ xfrm_state_walk_done(walk, net);
return 0;
}
@@ -1555,8 +1558,9 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
static int xfrm_dump_policy_done(struct netlink_callback *cb)
{
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+ struct net *net = sock_net(cb->skb->sk);
- xfrm_policy_walk_done(walk);
+ xfrm_policy_walk_done(walk, net);
return 0;
}
@@ -2403,9 +2407,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
static void xfrm_netlink_rcv(struct sk_buff *skb)
{
- mutex_lock(&xfrm_cfg_mutex);
+ struct net *net = sock_net(skb->sk);
+
+ mutex_lock(&net->xfrm.xfrm_cfg_mutex);
netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
- mutex_unlock(&xfrm_cfg_mutex);
+ mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
}
static inline size_t xfrm_expire_msgsize(void)
--
1.7.9.5
^ permalink raw reply related
* [PATCHv2 net-next 2/3] xfrm: Using the right namespace to migrate key info
From: Fan Du @ 2013-11-07 9:47 UTC (permalink / raw)
To: steffen.klassert, herbert, davem; +Cc: netdev
In-Reply-To: <1383817670-5783-1-git-send-email-fan.du@windriver.com>
because the home agent could surely be run on a different
net namespace other than init_net. The original behavior
could lead into inconsistent of key info.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
v2:
-Unchanged
---
include/net/xfrm.h | 2 +-
net/key/af_key.c | 3 ++-
net/xfrm/xfrm_policy.c | 10 +++++-----
net/xfrm/xfrm_user.c | 3 ++-
4 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 6b82fdf..5b522c5 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1581,7 +1581,7 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m);
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
struct xfrm_migrate *m, int num_bundles,
- struct xfrm_kmaddress *k);
+ struct xfrm_kmaddress *k, struct net *net);
#endif
int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 911ef03..33480b3 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2485,6 +2485,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
struct xfrm_selector sel;
struct xfrm_migrate m[XFRM_MAX_DEPTH];
struct xfrm_kmaddress k;
+ struct net *net = sock_net(sk);
if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1],
ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) ||
@@ -2558,7 +2559,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
}
return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i,
- kma ? &k : NULL);
+ kma ? &k : NULL, net);
out:
return err;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index a5bbdfb..907fd2f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3076,14 +3076,14 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
}
static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
- u8 dir, u8 type)
+ u8 dir, u8 type, struct net *net)
{
struct xfrm_policy *pol, *ret = NULL;
struct hlist_head *chain;
u32 priority = ~0U;
read_lock_bh(&xfrm_policy_lock);
- chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir);
+ chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
hlist_for_each_entry(pol, chain, bydst) {
if (xfrm_migrate_selector_match(sel, &pol->selector) &&
pol->type == type) {
@@ -3092,7 +3092,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
break;
}
}
- chain = &init_net.xfrm.policy_inexact[dir];
+ chain = &net->xfrm.policy_inexact[dir];
hlist_for_each_entry(pol, chain, bydst) {
if (xfrm_migrate_selector_match(sel, &pol->selector) &&
pol->type == type &&
@@ -3216,7 +3216,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
struct xfrm_migrate *m, int num_migrate,
- struct xfrm_kmaddress *k)
+ struct xfrm_kmaddress *k, struct net *net)
{
int i, err, nx_cur = 0, nx_new = 0;
struct xfrm_policy *pol = NULL;
@@ -3229,7 +3229,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
goto out;
/* Stage 1 - find policy */
- if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) {
+ if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
err = -ENOENT;
goto out;
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 4e0546e..840cc8d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2137,6 +2137,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
u8 type;
int err;
int n = 0;
+ struct net *net = sock_net(skb->sk);
if (attrs[XFRMA_MIGRATE] == NULL)
return -EINVAL;
@@ -2154,7 +2155,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!n)
return 0;
- xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp);
+ xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net);
return 0;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCHv2 net-next 0/3] Small IPsec fix
From: Fan Du @ 2013-11-07 9:47 UTC (permalink / raw)
To: steffen.klassert, herbert, davem; +Cc: netdev
Hi
This patchset made below modifications:
- Fix setting policy index with "ip xfrm ... index=xx"
which is currently broken
- Using correct name space for home agent when migrating
key info.
- Put xfrm locks into per namespace to improve scalability.
Changelog:
v2:
xfrm: Namespacify xfrm state/policy locks
-Fix compile error when CONFIG_NET_NS is unset, thanks for the lovely build robot.
Fan Du (3):
xfrm: Try to honor policy index if it's supplied by user
xfrm: Using the right namespace to migrate key info
xfrm: Namespacify xfrm state/policy locks
include/net/netns/xfrm.h | 4 ++
include/net/xfrm.h | 13 +++--
net/key/af_key.c | 18 ++++---
net/xfrm/xfrm_policy.c | 130 +++++++++++++++++++++++++---------------------
net/xfrm/xfrm_state.c | 104 +++++++++++++++++++------------------
net/xfrm/xfrm_user.c | 27 +++++++---
6 files changed, 168 insertions(+), 128 deletions(-)
--
1.7.9.5
^ permalink raw reply
* [PATCH net-next 0/8] bonding: add more netlink attributes
From: Scott Feldman @ 2013-11-07 9:42 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Following Jiri Pirko's lead, add more bonding netlink attributes. Sending
matching iproute2 patch separately. sysfs access to attributes is
retained.
There are more bonding attributes to add to netlink; I'll save those for a
follow-on patch set.
---
Scott Feldman (8):
bonding: add miimon netlink support
bonding: add updelay netlink support
bonding: add downdelay netlink support
bonding: add use_carrier netlink support
bonding: add arp_interval netlink support
bonding: add arp_ip_target netlink support
bonding: add arp_validate netlink support
bonding: add arp_all_targets netlink support
drivers/net/bonding/bond_netlink.c | 145 +++++++++++++++-
drivers/net/bonding/bond_options.c | 297 ++++++++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 335 ++++++++----------------------------
drivers/net/bonding/bonding.h | 10 +
include/uapi/linux/if_link.h | 8 +
5 files changed, 529 insertions(+), 266 deletions(-)
--
^ permalink raw reply
* [PATCH net-next 2/8] bonding: add updelay netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_UPDELAY to allow get/set of bonding parameter
updelay via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 12 +++++++++++
drivers/net/bonding/bond_options.c | 29 +++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 39 +++++++++---------------------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 53 insertions(+), 29 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 38dd2f1..9ba5431 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -25,6 +25,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_MODE] = { .type = NLA_U8 },
[IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 },
[IFLA_BOND_MIIMON] = { .type = NLA_U32 },
+ [IFLA_BOND_UPDELAY] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -77,6 +78,13 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_UPDELAY]) {
+ int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]);
+
+ err = bond_option_updelay_set(bond, updelay);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -97,6 +105,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
return nla_total_size(sizeof(u8)) + /* IFLA_BOND_MODE */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */
0;
}
@@ -116,6 +125,9 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
goto nla_put_failure;
+ if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index eaafab9..c0fea66 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -182,3 +182,32 @@ int bond_option_miimon_set(struct bonding *bond, int miimon)
}
return 0;
}
+
+int bond_option_updelay_set(struct bonding *bond, int updelay)
+{
+ if (!(bond->params.miimon)) {
+ pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
+ bond->dev->name);
+ return -EPERM;
+ }
+
+ if (updelay < 0) {
+ pr_err("%s: Invalid up delay value %d not in range %d-%d; rejected.\n",
+ bond->dev->name, updelay, 0, INT_MAX);
+ return -EINVAL;
+ } else {
+ if ((updelay % bond->params.miimon) != 0) {
+ pr_warn("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
+ bond->dev->name, updelay,
+ bond->params.miimon,
+ (updelay / bond->params.miimon) *
+ bond->params.miimon);
+ }
+ bond->params.updelay = updelay / bond->params.miimon;
+ pr_info("%s: Setting up delay to %d.\n",
+ bond->dev->name,
+ bond->params.updelay * bond->params.miimon);
+ }
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 2fb9777..1125bef 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -761,42 +761,23 @@ static ssize_t bonding_store_updelay(struct device *d,
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value, ret = count;
+ int new_value, ret;
struct bonding *bond = to_bond(d);
- if (!(bond->params.miimon)) {
- pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
- bond->dev->name);
- ret = -EPERM;
- goto out;
- }
-
if (sscanf(buf, "%d", &new_value) != 1) {
pr_err("%s: no up delay value specified.\n",
bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- if (new_value < 0) {
- pr_err("%s: Invalid up delay value %d not in range %d-%d; rejected.\n",
- bond->dev->name, new_value, 0, INT_MAX);
- ret = -EINVAL;
- goto out;
- } else {
- if ((new_value % bond->params.miimon) != 0) {
- pr_warning("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
- bond->dev->name, new_value,
- bond->params.miimon,
- (new_value / bond->params.miimon) *
- bond->params.miimon);
- }
- bond->params.updelay = new_value / bond->params.miimon;
- pr_info("%s: Setting up delay to %d.\n",
- bond->dev->name,
- bond->params.updelay * bond->params.miimon);
+ return -EINVAL;
}
-out:
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = bond_option_updelay_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 91d7eae..408e6c2 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -429,6 +429,7 @@ void bond_netlink_fini(void);
int bond_option_mode_set(struct bonding *bond, int mode);
int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
int bond_option_miimon_set(struct bonding *bond, int miimon);
+int bond_option_updelay_set(struct bonding *bond, int updelay);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index b38472b..361414e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -332,6 +332,7 @@ enum {
IFLA_BOND_MODE,
IFLA_BOND_ACTIVE_SLAVE,
IFLA_BOND_MIIMON,
+ IFLA_BOND_UPDELAY,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 4/8] bonding: add use_carrier netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_USE_CARRIER to allow get/set of bonding parameter
use_carrier via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 12 ++++++++++++
drivers/net/bonding/bond_options.c | 14 ++++++++++++++
drivers/net/bonding/bond_sysfs.c | 24 +++++++++++-------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 39 insertions(+), 13 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index e684713..4f81d87 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -27,6 +27,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_MIIMON] = { .type = NLA_U32 },
[IFLA_BOND_UPDELAY] = { .type = NLA_U32 },
[IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 },
+ [IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -93,6 +94,13 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_USE_CARRIER]) {
+ int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]);
+
+ err = bond_option_use_carrier_set(bond, use_carrier);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -115,6 +123,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */
+ nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */
0;
}
@@ -140,6 +149,9 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay))
goto nla_put_failure;
+ if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 738be5f..8743d6b 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -240,3 +240,17 @@ int bond_option_downdelay_set(struct bonding *bond, int downdelay)
return 0;
}
+
+int bond_option_use_carrier_set(struct bonding *bond, int use_carrier)
+{
+ if ((use_carrier == 0) || (use_carrier == 1)) {
+ bond->params.use_carrier = use_carrier;
+ pr_info("%s: Setting use_carrier to %d.\n",
+ bond->dev->name, use_carrier);
+ } else {
+ pr_info("%s: Ignoring invalid use_carrier value %d.\n",
+ bond->dev->name, use_carrier);
+ }
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 41a62ac..c74d430 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1114,25 +1114,23 @@ static ssize_t bonding_store_carrier(struct device *d,
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value, ret = count;
+ int new_value, ret;
struct bonding *bond = to_bond(d);
-
if (sscanf(buf, "%d", &new_value) != 1) {
pr_err("%s: no use_carrier value specified.\n",
bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- if ((new_value == 0) || (new_value == 1)) {
- bond->params.use_carrier = new_value;
- pr_info("%s: Setting use_carrier to %d.\n",
- bond->dev->name, new_value);
- } else {
- pr_info("%s: Ignoring invalid use_carrier value %d.\n",
- bond->dev->name, new_value);
+ return -EINVAL;
}
-out:
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = bond_option_use_carrier_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 40987f3..1f3aef6 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -431,6 +431,7 @@ int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_
int bond_option_miimon_set(struct bonding *bond, int miimon);
int bond_option_updelay_set(struct bonding *bond, int updelay);
int bond_option_downdelay_set(struct bonding *bond, int downdelay);
+int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a372831..6101db7 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -334,6 +334,7 @@ enum {
IFLA_BOND_MIIMON,
IFLA_BOND_UPDELAY,
IFLA_BOND_DOWNDELAY,
+ IFLA_BOND_USE_CARRIER,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 3/8] bonding: add downdelay netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_DOWNDELAY to allow get/set of bonding parameter
downdelay via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 12 +++++++++++
drivers/net/bonding/bond_options.c | 29 +++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 38 +++++++++---------------------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 52 insertions(+), 29 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 9ba5431..e684713 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -26,6 +26,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 },
[IFLA_BOND_MIIMON] = { .type = NLA_U32 },
[IFLA_BOND_UPDELAY] = { .type = NLA_U32 },
+ [IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -85,6 +86,13 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_DOWNDELAY]) {
+ int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]);
+
+ err = bond_option_downdelay_set(bond, downdelay);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -106,6 +114,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */
0;
}
@@ -128,6 +137,9 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay))
goto nla_put_failure;
+ if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index c0fea66..738be5f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -211,3 +211,32 @@ int bond_option_updelay_set(struct bonding *bond, int updelay)
return 0;
}
+
+int bond_option_downdelay_set(struct bonding *bond, int downdelay)
+{
+ if (!(bond->params.miimon)) {
+ pr_err("%s: Unable to set down delay as MII monitoring is disabled\n", bond->dev->name);
+ return -EPERM;
+ }
+
+ if (downdelay < 0) {
+ pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n",
+ bond->dev->name, downdelay, 0, INT_MAX);
+ return -EINVAL;
+ } else {
+ if ((downdelay % bond->params.miimon) != 0) {
+ pr_warn("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n",
+ bond->dev->name, downdelay,
+ bond->params.miimon,
+ (downdelay / bond->params.miimon) *
+ bond->params.miimon);
+ }
+ bond->params.downdelay = downdelay / bond->params.miimon;
+ pr_info("%s: Setting down delay to %d.\n",
+ bond->dev->name,
+ bond->params.downdelay * bond->params.miimon);
+
+ }
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 1125bef..41a62ac 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -706,42 +706,22 @@ static ssize_t bonding_store_downdelay(struct device *d,
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value, ret = count;
+ int new_value, ret;
struct bonding *bond = to_bond(d);
- if (!(bond->params.miimon)) {
- pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
- bond->dev->name);
- ret = -EPERM;
- goto out;
- }
-
if (sscanf(buf, "%d", &new_value) != 1) {
pr_err("%s: no down delay value specified.\n", bond->dev->name);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
- if (new_value < 0) {
- pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n",
- bond->dev->name, new_value, 0, INT_MAX);
- ret = -EINVAL;
- goto out;
- } else {
- if ((new_value % bond->params.miimon) != 0) {
- pr_warning("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n",
- bond->dev->name, new_value,
- bond->params.miimon,
- (new_value / bond->params.miimon) *
- bond->params.miimon);
- }
- bond->params.downdelay = new_value / bond->params.miimon;
- pr_info("%s: Setting down delay to %d.\n",
- bond->dev->name,
- bond->params.downdelay * bond->params.miimon);
- }
+ if (!rtnl_trylock())
+ return restart_syscall();
-out:
+ ret = bond_option_downdelay_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 408e6c2..40987f3 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -430,6 +430,7 @@ int bond_option_mode_set(struct bonding *bond, int mode);
int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
int bond_option_miimon_set(struct bonding *bond, int miimon);
int bond_option_updelay_set(struct bonding *bond, int updelay);
+int bond_option_downdelay_set(struct bonding *bond, int downdelay);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 361414e..a372831 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
IFLA_BOND_ACTIVE_SLAVE,
IFLA_BOND_MIIMON,
IFLA_BOND_UPDELAY,
+ IFLA_BOND_DOWNDELAY,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 1/8] bonding: add miimon netlink support
From: Scott Feldman @ 2013-11-07 9:42 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_MIIMON to allow get/set of bonding parameter
miimon via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 32 ++++++++++++++++++----
drivers/net/bonding/bond_options.c | 42 +++++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 53 +++++++-----------------------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 80 insertions(+), 49 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 40e7b1c..38dd2f1 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -1,6 +1,7 @@
/*
* drivers/net/bond/bond_netlink.c - Netlink interface for bonding
* Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -23,6 +24,7 @@
static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_MODE] = { .type = NLA_U8 },
[IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 },
+ [IFLA_BOND_MIIMON] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -42,14 +44,17 @@ static int bond_changelink(struct net_device *bond_dev,
struct bonding *bond = netdev_priv(bond_dev);
int err;
- if (data && data[IFLA_BOND_MODE]) {
+ if (!data)
+ return 0;
+
+ if (data[IFLA_BOND_MODE]) {
int mode = nla_get_u8(data[IFLA_BOND_MODE]);
err = bond_option_mode_set(bond, mode);
if (err)
return err;
}
- if (data && data[IFLA_BOND_ACTIVE_SLAVE]) {
+ if (data[IFLA_BOND_ACTIVE_SLAVE]) {
int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]);
struct net_device *slave_dev;
@@ -65,6 +70,13 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_MIIMON]) {
+ int miimon = nla_get_u32(data[IFLA_BOND_MIIMON]);
+
+ err = bond_option_miimon_set(bond, miimon);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -83,7 +95,9 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
static size_t bond_get_size(const struct net_device *bond_dev)
{
return nla_total_size(sizeof(u8)) + /* IFLA_BOND_MODE */
- nla_total_size(sizeof(u32)); /* IFLA_BOND_ACTIVE_SLAVE */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */
+ 0;
}
static int bond_fill_info(struct sk_buff *skb,
@@ -92,10 +106,16 @@ static int bond_fill_info(struct sk_buff *skb,
struct bonding *bond = netdev_priv(bond_dev);
struct net_device *slave_dev = bond_option_active_slave_get(bond);
- if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode) ||
- (slave_dev &&
- nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex)))
+ if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
goto nla_put_failure;
+
+ if (slave_dev &&
+ nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 9a5223c..eaafab9 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1,6 +1,7 @@
/*
* drivers/net/bond/bond_options.c - bonding options
* Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -140,3 +141,44 @@ int bond_option_active_slave_set(struct bonding *bond,
unblock_netpoll_tx();
return ret;
}
+
+int bond_option_miimon_set(struct bonding *bond, int miimon)
+{
+ if (miimon < 0) {
+ pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n",
+ bond->dev->name, miimon, 0, INT_MAX);
+ return -EINVAL;
+ }
+ pr_info("%s: Setting MII monitoring interval to %d.\n",
+ bond->dev->name, miimon);
+ bond->params.miimon = miimon;
+ if (bond->params.updelay)
+ pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n",
+ bond->dev->name,
+ bond->params.updelay * bond->params.miimon);
+ if (bond->params.downdelay)
+ pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n",
+ bond->dev->name,
+ bond->params.downdelay * bond->params.miimon);
+ if (miimon && bond->params.arp_interval) {
+ pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n",
+ bond->dev->name);
+ bond->params.arp_interval = 0;
+ if (bond->params.arp_validate)
+ bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
+ }
+ if (bond->dev->flags & IFF_UP) {
+ /* If the interface is up, we may need to fire off
+ * the MII timer. If the interface is down, the
+ * timer will get fired off when the open function
+ * is called.
+ */
+ if (!miimon) {
+ cancel_delayed_work_sync(&bond->mii_work);
+ } else {
+ cancel_delayed_work_sync(&bond->arp_work);
+ queue_delayed_work(bond->wq, &bond->mii_work, 0);
+ }
+ }
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 47749c9..2fb9777 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -981,55 +981,22 @@ static ssize_t bonding_store_miimon(struct device *d,
struct device_attribute *attr,
const char *buf, size_t count)
{
- int new_value, ret = count;
+ int new_value, ret;
struct bonding *bond = to_bond(d);
- if (!rtnl_trylock())
- return restart_syscall();
if (sscanf(buf, "%d", &new_value) != 1) {
pr_err("%s: no miimon value specified.\n",
bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- if (new_value < 0) {
- pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n",
- bond->dev->name, new_value, 0, INT_MAX);
- ret = -EINVAL;
- goto out;
- }
- pr_info("%s: Setting MII monitoring interval to %d.\n",
- bond->dev->name, new_value);
- bond->params.miimon = new_value;
- if (bond->params.updelay)
- pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n",
- bond->dev->name,
- bond->params.updelay * bond->params.miimon);
- if (bond->params.downdelay)
- pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n",
- bond->dev->name,
- bond->params.downdelay * bond->params.miimon);
- if (new_value && bond->params.arp_interval) {
- pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n",
- bond->dev->name);
- bond->params.arp_interval = 0;
- if (bond->params.arp_validate)
- bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
- }
- if (bond->dev->flags & IFF_UP) {
- /* If the interface is up, we may need to fire off
- * the MII timer. If the interface is down, the
- * timer will get fired off when the open function
- * is called.
- */
- if (!new_value) {
- cancel_delayed_work_sync(&bond->mii_work);
- } else {
- cancel_delayed_work_sync(&bond->arp_work);
- queue_delayed_work(bond->wq, &bond->mii_work, 0);
- }
+ return -EINVAL;
}
-out:
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = bond_option_miimon_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
rtnl_unlock();
return ret;
}
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 046a605..91d7eae 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -428,6 +428,7 @@ int bond_netlink_init(void);
void bond_netlink_fini(void);
int bond_option_mode_set(struct bonding *bond, int mode);
int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
+int bond_option_miimon_set(struct bonding *bond, int miimon);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index b78566f..b38472b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -331,6 +331,7 @@ enum {
IFLA_BOND_UNSPEC,
IFLA_BOND_MODE,
IFLA_BOND_ACTIVE_SLAVE,
+ IFLA_BOND_MIIMON,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next v3 0/2] net_sched: Fix some checkpatch errors and use pr_*
From: Yang Yingliang @ 2013-11-07 9:51 UTC (permalink / raw)
To: davem, netdev; +Cc: jhs, stephen, dborkman
Fix some checkpatch errors and
replace printk(KERN_DEBUG ...) with pr_debug.
v1 -> v2:
- patch 1/2: return an assignment on seperate line
in tcf_hash_new_index() suggested by Stephen.
v2 -> v3:
- patch 1/2: don't remove global vars' initialization.
- patch 2/2: adjust pr_warn content make more comfortable.
Yang Yingliang (2):
net_sched: fix some checkpatch errors
net_sched: Use pr_debug replace printk(KERN_DEBUG ...)
net/sched/act_api.c | 3 ++-
net/sched/cls_bpf.c | 2 +-
net/sched/cls_u32.c | 2 +-
net/sched/sch_cbq.c | 5 +++--
net/sched/sch_dsmark.c | 2 +-
net/sched/sch_generic.c | 4 ++--
net/sched/sch_gred.c | 4 ++--
net/sched/sch_htb.c | 23 ++++++++++++-----------
net/sched/sch_netem.c | 2 +-
net/sched/sch_sfq.c | 10 ++++++----
10 files changed, 31 insertions(+), 26 deletions(-)
--
1.7.12
^ permalink raw reply
* [PATCH net-next v3 1/2] net_sched: fix some checkpatch errors
From: Yang Yingliang @ 2013-11-07 9:51 UTC (permalink / raw)
To: davem, netdev; +Cc: jhs, stephen, dborkman
In-Reply-To: <1383817918-5156-1-git-send-email-yangyingliang@huawei.com>
There are some checkpatch errors, fix them.
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Suggested-by: Daniel Borkmann <dborkman@redhat.com>
---
net/sched/act_api.c | 3 ++-
net/sched/cls_bpf.c | 2 +-
net/sched/cls_u32.c | 2 +-
net/sched/sch_cbq.c | 3 ++-
net/sched/sch_generic.c | 4 ++--
net/sched/sch_htb.c | 9 +++++----
net/sched/sch_netem.c | 2 +-
net/sched/sch_sfq.c | 10 ++++++----
8 files changed, 20 insertions(+), 15 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fd70728..f874d1f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -191,7 +191,8 @@ u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo)
val = 1;
} while (tcf_hash_lookup(val, hinfo));
- return (*idx_gen = val);
+ *idx_gen = val;
+ return *idx_gen;
}
EXPORT_SYMBOL(tcf_hash_new_index);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 1002a82..d7c72be 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -323,7 +323,7 @@ static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh,
if (nla == NULL)
goto nla_put_failure;
- memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+ memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0)
goto nla_put_failure;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index eb07a1e..59e546c 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -352,7 +352,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n)
return 0;
}
-static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key)
+static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
{
struct tc_u_knode **kp;
struct tc_u_hnode *ht = key->ht_up;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 7a42c81..a8f40f5 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1058,7 +1058,8 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio)
cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/
q->quanta[prio];
}
- if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) {
+ if (cl->quantum <= 0 ||
+ cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) {
pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n",
cl->common.classid, cl->quantum);
cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7fc899a..9421350 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -338,13 +338,13 @@ EXPORT_SYMBOL(netif_carrier_off);
cheaper.
*/
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc)
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
{
kfree_skb(skb);
return NET_XMIT_CN;
}
-static struct sk_buff *noop_dequeue(struct Qdisc * qdisc)
+static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
{
return NULL;
}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0e1e38b..86c45a5 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -846,7 +846,7 @@ next:
break;
qdisc_warn_nonwc("htb", cl->un.leaf.q);
- htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr:
+ htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr :
&q->hlevel[0].hprio[prio].ptr);
cl = htb_lookup_leaf(hprio, prio);
@@ -1276,9 +1276,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
struct Qdisc *new_q = NULL;
int last_child = 0;
- // TODO: why don't allow to delete subtree ? references ? does
- // tc subsys quarantee us that in htb_destroy it holds no class
- // refs so that we can remove children safely there ?
+ /* TODO: why don't allow to delete subtree ? references ? does
+ * tc subsys quarantee us that in htb_destroy it holds no class
+ * refs so that we can remove children safely there ?
+ */
if (cl->children || cl->filter_cnt)
return -EBUSY;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 75c94e5..9765c3f 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -728,7 +728,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
nla_for_each_nested(la, attr, rem) {
u16 type = nla_type(la);
- switch(type) {
+ switch (type) {
case NETEM_LOSS_GI: {
const struct tc_netem_gimodel *gi = nla_data(la);
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index d3a1bc2..76f01e0 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -237,10 +237,12 @@ static inline void sfq_link(struct sfq_sched_data *q, sfq_index x)
}
#define sfq_unlink(q, x, n, p) \
- n = q->slots[x].dep.next; \
- p = q->slots[x].dep.prev; \
- sfq_dep_head(q, p)->next = n; \
- sfq_dep_head(q, n)->prev = p
+ do { \
+ n = q->slots[x].dep.next; \
+ p = q->slots[x].dep.prev; \
+ sfq_dep_head(q, p)->next = n; \
+ sfq_dep_head(q, n)->prev = p; \
+ } while (0)
static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x)
--
1.7.12
^ permalink raw reply related
* [PATCH net-next v3 2/2] net_sched: Use pr_debug replace printk(KERN_DEBUG ...)
From: Yang Yingliang @ 2013-11-07 9:51 UTC (permalink / raw)
To: davem, netdev; +Cc: jhs, stephen, dborkman
In-Reply-To: <1383817918-5156-1-git-send-email-yangyingliang@huawei.com>
Replace printk(KERN_DEBUG ...) with pr_debug() and
replace pr_warning() with pr_warn().
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Suggested-by: Daniel Borkmann <dborkman@redhat.com>
---
net/sched/sch_cbq.c | 2 +-
net/sched/sch_dsmark.c | 2 +-
net/sched/sch_gred.c | 4 ++--
net/sched/sch_htb.c | 14 +++++++-------
4 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index a8f40f5..9e3a9dc 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1060,7 +1060,7 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio)
}
if (cl->quantum <= 0 ||
cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) {
- pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n",
+ pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n",
cl->common.classid, cl->quantum);
cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1;
}
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 3886365..190cf65 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
* and don't need yet another qdisc as a bypass.
*/
if (p->mask[index] != 0xff || p->value[index])
- pr_warning("dsmark_dequeue: unsupported protocol %d\n",
+ pr_warn("dsmark_dequeue: unsupported protocol %d\n",
ntohs(skb->protocol));
break;
}
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index d42234c..19fa4dc 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -370,7 +370,7 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
for (i = table->DPs; i < MAX_DPs; i++) {
if (table->tab[i]) {
- pr_warning("GRED: Warning: Destroying "
+ pr_warn("GRED: Warning: Destroying "
"shadowed VQ 0x%x\n", i);
gred_destroy_vq(table->tab[i]);
table->tab[i] = NULL;
@@ -456,7 +456,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
if (table->tab[table->def])
def_prio = table->tab[table->def]->prio;
- printk(KERN_DEBUG "GRED: DP %u does not have a prio "
+ pr_debug("GRED: DP %u does not have a prio "
"setting default to %d\n", ctl->DP, def_prio);
prio = def_prio;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 86c45a5..5b62ba7 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -712,7 +712,7 @@ static s64 htb_do_events(struct htb_sched *q, const int level,
/* too much load - let's continue after a break for scheduling */
if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) {
- pr_warning("htb: too many events!\n");
+ pr_warn("htb: too many events!\n");
q->warned |= HTB_WARN_TOOMANYEVENTS;
}
@@ -1484,15 +1484,15 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
if (!cl->level) {
cl->quantum = hopt->rate.rate / q->rate2quantum;
if (!hopt->quantum && cl->quantum < 1000) {
- pr_warning(
- "HTB: quantum of class %X is small. Consider r2q change.\n",
- cl->common.classid);
+ pr_warn("HTB: quantum of class %X is small."
+ " Consider r2q change.\n",
+ cl->common.classid);
cl->quantum = 1000;
}
if (!hopt->quantum && cl->quantum > 200000) {
- pr_warning(
- "HTB: quantum of class %X is big. Consider r2q change.\n",
- cl->common.classid);
+ pr_warn("HTB: quantum of class %X is big."
+ " Consider r2q change.\n",
+ cl->common.classid);
cl->quantum = 200000;
}
if (hopt->quantum)
--
1.7.12
^ permalink raw reply related
* [PATCH net-next 5/8] bonding: add arp_interval netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_ARP_INTERVAL to allow get/set of bonding parameter
arp_interval via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 12 +++++++
drivers/net/bonding/bond_options.c | 48 ++++++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 58 ++++++------------------------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 71 insertions(+), 49 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 4f81d87..9c50165 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -28,6 +28,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_UPDELAY] = { .type = NLA_U32 },
[IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 },
[IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 },
+ [IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -101,6 +102,13 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_ARP_INTERVAL]) {
+ int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]);
+
+ err = bond_option_arp_interval_set(bond, arp_interval);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -124,6 +132,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */
nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */
0;
}
@@ -152,6 +161,9 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
goto nla_put_failure;
+ if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 8743d6b..c4b60ad 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -254,3 +254,51 @@ int bond_option_use_carrier_set(struct bonding *bond, int use_carrier)
return 0;
}
+
+int bond_option_arp_interval_set(struct bonding *bond, int arp_interval)
+{
+ if (arp_interval < 0) {
+ pr_err("%s: Invalid arp_interval value %d not in range 0-%d; rejected.\n",
+ bond->dev->name, arp_interval, INT_MAX);
+ return -EINVAL;
+ }
+ if (bond->params.mode == BOND_MODE_ALB ||
+ bond->params.mode == BOND_MODE_TLB) {
+ pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
+ bond->dev->name, bond->dev->name);
+ return -EINVAL;
+ }
+ pr_info("%s: Setting ARP monitoring interval to %d.\n",
+ bond->dev->name, arp_interval);
+ bond->params.arp_interval = arp_interval;
+ if (arp_interval) {
+ if (bond->params.miimon) {
+ pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n",
+ bond->dev->name, bond->dev->name);
+ bond->params.miimon = 0;
+ }
+ if (!bond->params.arp_targets[0])
+ pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n",
+ bond->dev->name);
+ }
+ if (bond->dev->flags & IFF_UP) {
+ /* If the interface is up, we may need to fire off
+ * the ARP timer. If the interface is down, the
+ * timer will get fired off when the open function
+ * is called.
+ */
+ if (!arp_interval) {
+ if (bond->params.arp_validate)
+ bond->recv_probe = NULL;
+ cancel_delayed_work_sync(&bond->arp_work);
+ } else {
+ /* arp_validate can be set only in active-backup mode */
+ if (bond->params.arp_validate)
+ bond->recv_probe = bond_arp_rcv;
+ cancel_delayed_work_sync(&bond->mii_work);
+ queue_delayed_work(bond->wq, &bond->arp_work, 0);
+ }
+ }
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index c74d430..644b745 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -517,59 +517,19 @@ static ssize_t bonding_store_arp_interval(struct device *d,
struct bonding *bond = to_bond(d);
int new_value, ret = count;
- if (!rtnl_trylock())
- return restart_syscall();
if (sscanf(buf, "%d", &new_value) != 1) {
pr_err("%s: no arp_interval value specified.\n",
bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- if (new_value < 0) {
- pr_err("%s: Invalid arp_interval value %d not in range 0-%d; rejected.\n",
- bond->dev->name, new_value, INT_MAX);
- ret = -EINVAL;
- goto out;
- }
- if (bond->params.mode == BOND_MODE_ALB ||
- bond->params.mode == BOND_MODE_TLB) {
- pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
- bond->dev->name, bond->dev->name);
- ret = -EINVAL;
- goto out;
- }
- pr_info("%s: Setting ARP monitoring interval to %d.\n",
- bond->dev->name, new_value);
- bond->params.arp_interval = new_value;
- if (new_value) {
- if (bond->params.miimon) {
- pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n",
- bond->dev->name, bond->dev->name);
- bond->params.miimon = 0;
- }
- if (!bond->params.arp_targets[0])
- pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n",
- bond->dev->name);
- }
- if (bond->dev->flags & IFF_UP) {
- /* If the interface is up, we may need to fire off
- * the ARP timer. If the interface is down, the
- * timer will get fired off when the open function
- * is called.
- */
- if (!new_value) {
- if (bond->params.arp_validate)
- bond->recv_probe = NULL;
- cancel_delayed_work_sync(&bond->arp_work);
- } else {
- /* arp_validate can be set only in active-backup mode */
- if (bond->params.arp_validate)
- bond->recv_probe = bond_arp_rcv;
- cancel_delayed_work_sync(&bond->mii_work);
- queue_delayed_work(bond->wq, &bond->arp_work, 0);
- }
+ return -EINVAL;
}
-out:
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = bond_option_arp_interval_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
rtnl_unlock();
return ret;
}
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 1f3aef6..caaa5e7 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -432,6 +432,7 @@ int bond_option_miimon_set(struct bonding *bond, int miimon);
int bond_option_updelay_set(struct bonding *bond, int updelay);
int bond_option_downdelay_set(struct bonding *bond, int downdelay);
int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
+int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6101db7..858b09e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -335,6 +335,7 @@ enum {
IFLA_BOND_UPDELAY,
IFLA_BOND_DOWNDELAY,
IFLA_BOND_USE_CARRIER,
+ IFLA_BOND_ARP_INTERVAL,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 6/8] bonding: add arp_ip_target netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_ARP_IP_TARGET to allow get/set of bonding parameter
arp_ip_target via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 43 ++++++++++++++-
drivers/net/bonding/bond_options.c | 102 ++++++++++++++++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 77 +++------------------------
drivers/net/bonding/bonding.h | 3 +
include/uapi/linux/if_link.h | 1
5 files changed, 155 insertions(+), 71 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 9c50165..e4673ba 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -29,6 +29,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 },
[IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 },
[IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 },
+ [IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -109,6 +110,21 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_ARP_IP_TARGET]) {
+ struct nlattr *attr;
+ int rem;
+
+ err = bond_option_arp_ip_target_clear_all(bond);
+ if (err)
+ return err;
+
+ nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) {
+ __be32 target = nla_get_u32(attr);
+ err = bond_option_arp_ip_target_set(bond, target);
+ if (err)
+ return err;
+ }
+ }
return 0;
}
@@ -133,6 +149,8 @@ static size_t bond_get_size(const struct net_device *bond_dev)
nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */
nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */
nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */
+ /* IFLA_BOND_ARP_IP_TARGET */
+ nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
0;
}
@@ -141,6 +159,8 @@ static int bond_fill_info(struct sk_buff *skb,
{
struct bonding *bond = netdev_priv(bond_dev);
struct net_device *slave_dev = bond_option_active_slave_get(bond);
+ struct nlattr *targets;
+ int i, targets_added;
if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
goto nla_put_failure;
@@ -152,10 +172,12 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
goto nla_put_failure;
- if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay))
+ if (nla_put_u32(skb, IFLA_BOND_UPDELAY,
+ bond->params.updelay * bond->params.miimon))
goto nla_put_failure;
- if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay))
+ if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY,
+ bond->params.downdelay * bond->params.miimon))
goto nla_put_failure;
if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
@@ -164,6 +186,23 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
goto nla_put_failure;
+ targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET);
+ if (!targets)
+ goto nla_put_failure;
+
+ targets_added = 0;
+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
+ if (bond->params.arp_targets[i]) {
+ nla_put_u32(skb, i, bond->params.arp_targets[i]);
+ targets_added = 1;
+ }
+ }
+
+ if (targets_added)
+ nla_nest_end(skb, targets);
+ else
+ nla_nest_cancel(skb, targets);
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index c4b60ad..f57f113 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -302,3 +302,105 @@ int bond_option_arp_interval_set(struct bonding *bond, int arp_interval)
return 0;
}
+
+int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target)
+{
+ __be32 *targets = bond->params.arp_targets;
+ struct list_head *iter;
+ struct slave *slave;
+ int ind;
+
+ if ((target == 0) || (target == htonl(INADDR_BROADCAST))) {
+ pr_err("%s: invalid ARP target %pI4 specified for addition\n",
+ bond->dev->name, &target);
+ return -EINVAL;
+ }
+
+ if (bond_get_targets_ip(targets, target) != -1) { /* dup */
+ pr_err("%s: ARP target %pI4 is already present\n",
+ bond->dev->name, &target);
+ return -EINVAL;
+ }
+
+ ind = bond_get_targets_ip(targets, 0); /* first free slot */
+ if (ind == -1) {
+ pr_err("%s: ARP target table is full!\n",
+ bond->dev->name);
+ return -EINVAL;
+ }
+
+ pr_info("%s: adding ARP target %pI4.\n", bond->dev->name,
+ &target);
+
+ /* not to race with bond_arp_rcv */
+ write_lock_bh(&bond->lock);
+ bond_for_each_slave(bond, slave, iter)
+ slave->target_last_arp_rx[ind] = jiffies;
+ targets[ind] = target;
+ write_unlock_bh(&bond->lock);
+
+ return 0;
+}
+
+int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target)
+{
+ __be32 *targets = bond->params.arp_targets;
+ struct list_head *iter;
+ struct slave *slave;
+ unsigned long *targets_rx;
+ int ind, i, j;
+
+ if ((target == 0) || (target == htonl(INADDR_BROADCAST))) {
+ pr_err("%s: invalid ARP target %pI4 specified for removal\n",
+ bond->dev->name, &target);
+ return -EINVAL;
+ }
+
+ ind = bond_get_targets_ip(targets, target);
+ if (ind == -1) {
+ pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
+ bond->dev->name, &target);
+ return -EINVAL;
+ }
+
+ if (ind == 0 && !targets[1] && bond->params.arp_interval)
+ pr_warn("%s: removing last arp target with arp_interval on\n",
+ bond->dev->name);
+
+ pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
+ &target);
+
+ write_lock_bh(&bond->lock);
+ bond_for_each_slave(bond, slave, iter) {
+ targets_rx = slave->target_last_arp_rx;
+ j = ind;
+ for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
+ targets_rx[j] = targets_rx[j+1];
+ targets_rx[j] = 0;
+ }
+ for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
+ targets[i] = targets[i+1];
+ targets[i] = 0;
+ write_unlock_bh(&bond->lock);
+
+ return 0;
+}
+
+int bond_option_arp_ip_target_clear_all(struct bonding *bond)
+{
+ __be32 *targets = bond->params.arp_targets;
+ struct list_head *iter;
+ struct slave *slave;
+ int i;
+
+ write_lock_bh(&bond->lock);
+ bond_for_each_slave(bond, slave, iter) {
+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
+ slave->target_last_arp_rx[i] = 0;
+ }
+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
+ targets[i] = 0;
+ write_unlock_bh(&bond->lock);
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 644b745..aa97b12 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -561,88 +561,27 @@ static ssize_t bonding_store_arp_targets(struct device *d,
const char *buf, size_t count)
{
struct bonding *bond = to_bond(d);
- struct list_head *iter;
- struct slave *slave;
- __be32 newtarget, *targets;
- unsigned long *targets_rx;
- int ind, i, j, ret = -EINVAL;
+ __be32 target;
+ int ret;
if (!rtnl_trylock())
return restart_syscall();
- targets = bond->params.arp_targets;
- newtarget = in_aton(buf + 1);
+ target = in_aton(buf + 1);
/* look for adds */
if (buf[0] == '+') {
- if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
- pr_err("%s: invalid ARP target %pI4 specified for addition\n",
- bond->dev->name, &newtarget);
- goto out;
- }
-
- if (bond_get_targets_ip(targets, newtarget) != -1) { /* dup */
- pr_err("%s: ARP target %pI4 is already present\n",
- bond->dev->name, &newtarget);
- goto out;
- }
-
- ind = bond_get_targets_ip(targets, 0); /* first free slot */
- if (ind == -1) {
- pr_err("%s: ARP target table is full!\n",
- bond->dev->name);
- goto out;
- }
-
- pr_info("%s: adding ARP target %pI4.\n", bond->dev->name,
- &newtarget);
- /* not to race with bond_arp_rcv */
- write_lock_bh(&bond->lock);
- bond_for_each_slave(bond, slave, iter)
- slave->target_last_arp_rx[ind] = jiffies;
- targets[ind] = newtarget;
- write_unlock_bh(&bond->lock);
+ ret = bond_option_arp_ip_target_set(bond, target);
} else if (buf[0] == '-') {
- if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
- pr_err("%s: invalid ARP target %pI4 specified for removal\n",
- bond->dev->name, &newtarget);
- goto out;
- }
-
- ind = bond_get_targets_ip(targets, newtarget);
- if (ind == -1) {
- pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
- bond->dev->name, &newtarget);
- goto out;
- }
-
- if (ind == 0 && !targets[1] && bond->params.arp_interval)
- pr_warn("%s: removing last arp target with arp_interval on\n",
- bond->dev->name);
-
- pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
- &newtarget);
-
- write_lock_bh(&bond->lock);
- bond_for_each_slave(bond, slave, iter) {
- targets_rx = slave->target_last_arp_rx;
- j = ind;
- for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
- targets_rx[j] = targets_rx[j+1];
- targets_rx[j] = 0;
- }
- for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
- targets[i] = targets[i+1];
- targets[i] = 0;
- write_unlock_bh(&bond->lock);
+ ret = bond_option_arp_ip_target_unset(bond, target);
} else {
pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n",
bond->dev->name);
ret = -EPERM;
- goto out;
}
- ret = count;
-out:
+ if (!ret)
+ ret = count;
+
rtnl_unlock();
return ret;
}
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index caaa5e7..e5d215d 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -433,6 +433,9 @@ int bond_option_updelay_set(struct bonding *bond, int updelay);
int bond_option_downdelay_set(struct bonding *bond, int downdelay);
int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
+int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target);
+int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target);
+int bond_option_arp_ip_target_clear_all(struct bonding *bond);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 858b09e..58dd318 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -336,6 +336,7 @@ enum {
IFLA_BOND_DOWNDELAY,
IFLA_BOND_USE_CARRIER,
IFLA_BOND_ARP_INTERVAL,
+ IFLA_BOND_ARP_IP_TARGET,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 8/8] bonding: add arp_all_targets netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_ARP_ALL_TARGETS to allow get/set of bonding parameter
arp_all_targets via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
drivers/net/bonding/bond_options.c | 11 +++++++++++
drivers/net/bonding/bond_sysfs.c | 16 ++++++++++------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 37 insertions(+), 6 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index a5ca6e0..818a7ba 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -31,6 +31,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 },
[IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED },
[IFLA_BOND_ARP_VALIDATE] = { .type = NLA_U32 },
+ [IFLA_BOND_ARP_ALL_TARGETS] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -133,6 +134,14 @@ static int bond_changelink(struct net_device *bond_dev,
if (err)
return err;
}
+ if (data[IFLA_BOND_ARP_ALL_TARGETS]) {
+ int arp_all_targets =
+ nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]);
+
+ err = bond_option_arp_all_targets_set(bond, arp_all_targets);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -160,6 +169,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
/* IFLA_BOND_ARP_IP_TARGET */
nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_VALIDATE */
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_ALL_TARGETS */
0;
}
@@ -215,6 +225,10 @@ static int bond_fill_info(struct sk_buff *skb,
if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate))
goto nla_put_failure;
+ if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS,
+ bond->params.arp_all_targets))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 9c36215..543a318 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -426,3 +426,14 @@ int bond_option_arp_validate_set(struct bonding *bond, int arp_validate)
return 0;
}
+
+int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets)
+{
+ pr_info("%s: setting arp_all_targets to %s (%d).\n",
+ bond->dev->name, arp_all_targets_tbl[arp_all_targets].modename,
+ arp_all_targets);
+
+ bond->params.arp_all_targets = arp_all_targets;
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 8a35440..a3cd27e 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -408,7 +408,7 @@ static ssize_t bonding_store_arp_all_targets(struct device *d,
const char *buf, size_t count)
{
struct bonding *bond = to_bond(d);
- int new_value;
+ int new_value, ret;
new_value = bond_parse_parm(buf, arp_all_targets_tbl);
if (new_value < 0) {
@@ -416,13 +416,17 @@ static ssize_t bonding_store_arp_all_targets(struct device *d,
bond->dev->name, buf);
return -EINVAL;
}
- pr_info("%s: setting arp_all_targets to %s (%d).\n",
- bond->dev->name, arp_all_targets_tbl[new_value].modename,
- new_value);
- bond->params.arp_all_targets = new_value;
+ if (!rtnl_trylock())
+ return restart_syscall();
- return count;
+ ret = bond_option_arp_all_targets_set(bond, new_value);
+ if (!ret)
+ ret = count;
+
+ rtnl_unlock();
+
+ return ret;
}
static DEVICE_ATTR(arp_all_targets, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 77bbd71..ed35c8c 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -437,6 +437,7 @@ int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target);
int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target);
int bond_option_arp_ip_target_clear_all(struct bonding *bond);
int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
+int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c17f801..ca01850 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -338,6 +338,7 @@ enum {
IFLA_BOND_ARP_INTERVAL,
IFLA_BOND_ARP_IP_TARGET,
IFLA_BOND_ARP_VALIDATE,
+ IFLA_BOND_ARP_ALL_TARGETS,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* [PATCH net-next 7/8] bonding: add arp_validate netlink support
From: Scott Feldman @ 2013-11-07 9:43 UTC (permalink / raw)
To: vfalico, fubar, andy; +Cc: netdev, shm
Add IFLA_BOND_ARP_VALIDATE to allow get/set of bonding parameter
arp_validate via netlink.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
---
drivers/net/bonding/bond_netlink.c | 12 ++++++++++++
drivers/net/bonding/bond_options.c | 22 ++++++++++++++++++++++
drivers/net/bonding/bond_sysfs.c | 30 ++++++++----------------------
drivers/net/bonding/bonding.h | 1 +
include/uapi/linux/if_link.h | 1 +
5 files changed, 44 insertions(+), 22 deletions(-)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index e4673ba..a5ca6e0 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -30,6 +30,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 },
[IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 },
[IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED },
+ [IFLA_BOND_ARP_VALIDATE] = { .type = NLA_U32 },
};
static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -125,6 +126,13 @@ static int bond_changelink(struct net_device *bond_dev,
return err;
}
}
+ if (data[IFLA_BOND_ARP_VALIDATE]) {
+ int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]);
+
+ err = bond_option_arp_validate_set(bond, arp_validate);
+ if (err)
+ return err;
+ }
return 0;
}
@@ -151,6 +159,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */
/* IFLA_BOND_ARP_IP_TARGET */
nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
+ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_VALIDATE */
0;
}
@@ -203,6 +212,9 @@ static int bond_fill_info(struct sk_buff *skb,
else
nla_nest_cancel(skb, targets);
+ if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index f57f113..9c36215 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -404,3 +404,25 @@ int bond_option_arp_ip_target_clear_all(struct bonding *bond)
return 0;
}
+
+int bond_option_arp_validate_set(struct bonding *bond, int arp_validate)
+{
+ if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+ pr_err("%s: arp_validate only supported in active-backup mode.\n",
+ bond->dev->name);
+ return -EINVAL;
+ }
+ pr_info("%s: setting arp_validate to %s (%d).\n",
+ bond->dev->name, arp_validate_tbl[arp_validate].modename,
+ arp_validate);
+
+ if (bond->dev->flags & IFF_UP) {
+ if (!arp_validate)
+ bond->recv_probe = NULL;
+ else if (bond->params.arp_interval)
+ bond->recv_probe = bond_arp_rcv;
+ }
+ bond->params.arp_validate = arp_validate;
+
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index aa97b12..8a35440 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -367,35 +367,21 @@ static ssize_t bonding_store_arp_validate(struct device *d,
const char *buf, size_t count)
{
struct bonding *bond = to_bond(d);
- int new_value, ret = count;
+ int new_value, ret;
- if (!rtnl_trylock())
- return restart_syscall();
new_value = bond_parse_parm(buf, arp_validate_tbl);
if (new_value < 0) {
pr_err("%s: Ignoring invalid arp_validate value %s\n",
bond->dev->name, buf);
- ret = -EINVAL;
- goto out;
- }
- if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
- pr_err("%s: arp_validate only supported in active-backup mode.\n",
- bond->dev->name);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
- pr_info("%s: setting arp_validate to %s (%d).\n",
- bond->dev->name, arp_validate_tbl[new_value].modename,
- new_value);
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = bond_option_arp_validate_set(bond, new_value);
+ if (!ret)
+ ret = count;
- if (bond->dev->flags & IFF_UP) {
- if (!new_value)
- bond->recv_probe = NULL;
- else if (bond->params.arp_interval)
- bond->recv_probe = bond_arp_rcv;
- }
- bond->params.arp_validate = new_value;
-out:
rtnl_unlock();
return ret;
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index e5d215d..77bbd71 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -436,6 +436,7 @@ int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target);
int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target);
int bond_option_arp_ip_target_clear_all(struct bonding *bond);
+int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 58dd318..c17f801 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -337,6 +337,7 @@ enum {
IFLA_BOND_USE_CARRIER,
IFLA_BOND_ARP_INTERVAL,
IFLA_BOND_ARP_IP_TARGET,
+ IFLA_BOND_ARP_VALIDATE,
__IFLA_BOND_MAX,
};
^ permalink raw reply related
* Re: [PATCH net-next 3/3] net: allow to leave the buffer fragmented in skb_cow_data()
From: Mathias Krause @ 2013-11-07 10:01 UTC (permalink / raw)
To: Herbert Xu; +Cc: David S. Miller, Steffen Klassert, Dmitry Tarnyagin, netdev
In-Reply-To: <20131107090135.GA385@gondor.apana.org.au>
On 07.11.2013 10:01, Herbert Xu wrote:
> On Thu, Nov 07, 2013 at 09:55:34AM +0100, Mathias Krause wrote:
>> Indeed. I want to avoid the costly memcpy() on the CPU serving the NIC
>> interrupt, as that is a bottleneck in my setup. The packet processing --
>> encrypting/decrypting of ESP packets -- gets mostly parallelized via
>> pcrypt, so that's fine. But the initial network processing, i.e. getting
>> to pcrypt, is what's throttling the throughput currently. (RPS only
>> partly solves this problem as for the ESP receive path most traffic ends
>> up on the same flow).
>
> How about this: instead of doing in-place encryption/decryption
> let's allocate a new destination buffer and encrypt/decrypt into
> it. Then we essentially get the copy for free.
>
> So instead of modifying skb_cow_data you can change esp4.c, etc.
That might be another option. But I fear it might affect performance due
to caching or NUMA effects. :/
I'll think about it and will try to investigate both approaches.
Thanks,
Mathias
^ permalink raw reply
* Sie Won $1,000,000.00 USD
From: Qatar Foundation @ 2013-11-07 9:44 UTC (permalink / raw)
Lieber Beg?nstigten,
Hiermit m?chten wir Sie informieren, dass Sie unter den gl?cklichen Empf?nger ausgew?hlt, um diese Spenden award Summe von $ 1.000.000,00 USD erhalten waren, als wohlt?tige Spenden / Hilfe von der Qatar Foundation statt in Doha, Qatar, 7. November 2013, um Ihre gesch?ftlichen und pers?nlichen Interesse zu f?rdern . Bitte zur?ck zu bekommen, um weitere Informationen, wie man behauptet, Ihre Auszeichnung per E-Mail: qatarfoundation631@yahoo.com.hk
Im Namen der Stiftung, sagen wir herzlichen Gl?ckwunsch an Sie.
Mit freundlichen Gr??en,
Dr. Mohammad Fathy Saoud.
Antwort an: qatarfoundation631@yahoo.com.hk
Pr?sident der Qatar Foundation.
WICHTIG: Wenn Sie diese Nachricht in Ihrem Spam-oder Junk erhalten, es ist wegen Ihres Netzbetreibers. Antworten zur?ck zur Spende Anspr?che.
^ permalink raw reply
* Re: [PATCH net-next 6/8] bonding: add arp_ip_target netlink support
From: Jiri Pirko @ 2013-11-07 10:16 UTC (permalink / raw)
To: Scott Feldman; +Cc: vfalico, fubar, andy, netdev, shm
In-Reply-To: <20131107094330.15846.84353.stgit@monster-03.cumulusnetworks.com>
Thu, Nov 07, 2013 at 10:43:30AM CET, sfeldma@cumulusnetworks.com wrote:
>Add IFLA_BOND_ARP_IP_TARGET to allow get/set of bonding parameter
>arp_ip_target via netlink.
>
>Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
>---
> drivers/net/bonding/bond_netlink.c | 43 ++++++++++++++-
> drivers/net/bonding/bond_options.c | 102 ++++++++++++++++++++++++++++++++++++
> drivers/net/bonding/bond_sysfs.c | 77 +++------------------------
> drivers/net/bonding/bonding.h | 3 +
> include/uapi/linux/if_link.h | 1
> 5 files changed, 155 insertions(+), 71 deletions(-)
>
>diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
>index 9c50165..e4673ba 100644
>--- a/drivers/net/bonding/bond_netlink.c
>+++ b/drivers/net/bonding/bond_netlink.c
>@@ -29,6 +29,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
> [IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 },
> [IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 },
> [IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 },
>+ [IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED },
> };
>
> static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
>@@ -109,6 +110,21 @@ static int bond_changelink(struct net_device *bond_dev,
> if (err)
> return err;
> }
>+ if (data[IFLA_BOND_ARP_IP_TARGET]) {
>+ struct nlattr *attr;
>+ int rem;
>+
>+ err = bond_option_arp_ip_target_clear_all(bond);
>+ if (err)
>+ return err;
>+
Hmm. I think this is not correct. I think you should not clear all. They
might be needed to be used but for a brief moment, they disappear.
Just set or unset them one by one.
>+ nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) {
>+ __be32 target = nla_get_u32(attr);
>+ err = bond_option_arp_ip_target_set(bond, target);
>+ if (err)
>+ return err;
>+ }
>+ }
> return 0;
> }
>
>@@ -133,6 +149,8 @@ static size_t bond_get_size(const struct net_device *bond_dev)
> nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */
> nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */
> nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */
>+ /* IFLA_BOND_ARP_IP_TARGET */
>+ nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
> 0;
> }
>
>@@ -141,6 +159,8 @@ static int bond_fill_info(struct sk_buff *skb,
> {
> struct bonding *bond = netdev_priv(bond_dev);
> struct net_device *slave_dev = bond_option_active_slave_get(bond);
>+ struct nlattr *targets;
>+ int i, targets_added;
>
> if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
> goto nla_put_failure;
>@@ -152,10 +172,12 @@ static int bond_fill_info(struct sk_buff *skb,
> if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
> goto nla_put_failure;
>
>- if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay))
>+ if (nla_put_u32(skb, IFLA_BOND_UPDELAY,
>+ bond->params.updelay * bond->params.miimon))
> goto nla_put_failure;
This bit should probably no be here :)
>
>- if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay))
>+ if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY,
>+ bond->params.downdelay * bond->params.miimon))
> goto nla_put_failure;
This as well.
>
> if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
>@@ -164,6 +186,23 @@ static int bond_fill_info(struct sk_buff *skb,
> if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
> goto nla_put_failure;
>
>+ targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET);
>+ if (!targets)
>+ goto nla_put_failure;
>+
>+ targets_added = 0;
>+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
>+ if (bond->params.arp_targets[i]) {
>+ nla_put_u32(skb, i, bond->params.arp_targets[i]);
>+ targets_added = 1;
>+ }
>+ }
>+
>+ if (targets_added)
>+ nla_nest_end(skb, targets);
>+ else
>+ nla_nest_cancel(skb, targets);
>+
> return 0;
>
> nla_put_failure:
>diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
>index c4b60ad..f57f113 100644
>--- a/drivers/net/bonding/bond_options.c
>+++ b/drivers/net/bonding/bond_options.c
>@@ -302,3 +302,105 @@ int bond_option_arp_interval_set(struct bonding *bond, int arp_interval)
>
> return 0;
> }
>+
>+int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target)
>+{
>+ __be32 *targets = bond->params.arp_targets;
>+ struct list_head *iter;
>+ struct slave *slave;
>+ int ind;
>+
>+ if ((target == 0) || (target == htonl(INADDR_BROADCAST))) {
>+ pr_err("%s: invalid ARP target %pI4 specified for addition\n",
>+ bond->dev->name, &target);
>+ return -EINVAL;
>+ }
>+
>+ if (bond_get_targets_ip(targets, target) != -1) { /* dup */
>+ pr_err("%s: ARP target %pI4 is already present\n",
>+ bond->dev->name, &target);
>+ return -EINVAL;
>+ }
>+
>+ ind = bond_get_targets_ip(targets, 0); /* first free slot */
>+ if (ind == -1) {
>+ pr_err("%s: ARP target table is full!\n",
>+ bond->dev->name);
>+ return -EINVAL;
>+ }
>+
>+ pr_info("%s: adding ARP target %pI4.\n", bond->dev->name,
>+ &target);
>+
>+ /* not to race with bond_arp_rcv */
>+ write_lock_bh(&bond->lock);
>+ bond_for_each_slave(bond, slave, iter)
>+ slave->target_last_arp_rx[ind] = jiffies;
>+ targets[ind] = target;
>+ write_unlock_bh(&bond->lock);
>+
>+ return 0;
>+}
>+
>+int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target)
>+{
>+ __be32 *targets = bond->params.arp_targets;
>+ struct list_head *iter;
>+ struct slave *slave;
>+ unsigned long *targets_rx;
>+ int ind, i, j;
>+
>+ if ((target == 0) || (target == htonl(INADDR_BROADCAST))) {
>+ pr_err("%s: invalid ARP target %pI4 specified for removal\n",
>+ bond->dev->name, &target);
>+ return -EINVAL;
>+ }
>+
>+ ind = bond_get_targets_ip(targets, target);
>+ if (ind == -1) {
>+ pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
>+ bond->dev->name, &target);
>+ return -EINVAL;
>+ }
>+
>+ if (ind == 0 && !targets[1] && bond->params.arp_interval)
>+ pr_warn("%s: removing last arp target with arp_interval on\n",
>+ bond->dev->name);
>+
>+ pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
>+ &target);
>+
>+ write_lock_bh(&bond->lock);
>+ bond_for_each_slave(bond, slave, iter) {
>+ targets_rx = slave->target_last_arp_rx;
>+ j = ind;
>+ for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
>+ targets_rx[j] = targets_rx[j+1];
>+ targets_rx[j] = 0;
>+ }
>+ for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
>+ targets[i] = targets[i+1];
>+ targets[i] = 0;
>+ write_unlock_bh(&bond->lock);
>+
>+ return 0;
>+}
>+
>+int bond_option_arp_ip_target_clear_all(struct bonding *bond)
>+{
>+ __be32 *targets = bond->params.arp_targets;
>+ struct list_head *iter;
>+ struct slave *slave;
>+ int i;
>+
>+ write_lock_bh(&bond->lock);
>+ bond_for_each_slave(bond, slave, iter) {
>+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
>+ slave->target_last_arp_rx[i] = 0;
>+ }
>+ for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
>+ targets[i] = 0;
>+ write_unlock_bh(&bond->lock);
>+
>+ return 0;
>+}
>diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
>index 644b745..aa97b12 100644
>--- a/drivers/net/bonding/bond_sysfs.c
>+++ b/drivers/net/bonding/bond_sysfs.c
>@@ -561,88 +561,27 @@ static ssize_t bonding_store_arp_targets(struct device *d,
> const char *buf, size_t count)
> {
> struct bonding *bond = to_bond(d);
>- struct list_head *iter;
>- struct slave *slave;
>- __be32 newtarget, *targets;
>- unsigned long *targets_rx;
>- int ind, i, j, ret = -EINVAL;
>+ __be32 target;
>+ int ret;
>
> if (!rtnl_trylock())
> return restart_syscall();
>
>- targets = bond->params.arp_targets;
>- newtarget = in_aton(buf + 1);
>+ target = in_aton(buf + 1);
> /* look for adds */
> if (buf[0] == '+') {
>- if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
>- pr_err("%s: invalid ARP target %pI4 specified for addition\n",
>- bond->dev->name, &newtarget);
>- goto out;
>- }
>-
>- if (bond_get_targets_ip(targets, newtarget) != -1) { /* dup */
>- pr_err("%s: ARP target %pI4 is already present\n",
>- bond->dev->name, &newtarget);
>- goto out;
>- }
>-
>- ind = bond_get_targets_ip(targets, 0); /* first free slot */
>- if (ind == -1) {
>- pr_err("%s: ARP target table is full!\n",
>- bond->dev->name);
>- goto out;
>- }
>-
>- pr_info("%s: adding ARP target %pI4.\n", bond->dev->name,
>- &newtarget);
>- /* not to race with bond_arp_rcv */
>- write_lock_bh(&bond->lock);
>- bond_for_each_slave(bond, slave, iter)
>- slave->target_last_arp_rx[ind] = jiffies;
>- targets[ind] = newtarget;
>- write_unlock_bh(&bond->lock);
>+ ret = bond_option_arp_ip_target_set(bond, target);
> } else if (buf[0] == '-') {
>- if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
>- pr_err("%s: invalid ARP target %pI4 specified for removal\n",
>- bond->dev->name, &newtarget);
>- goto out;
>- }
>-
>- ind = bond_get_targets_ip(targets, newtarget);
>- if (ind == -1) {
>- pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
>- bond->dev->name, &newtarget);
>- goto out;
>- }
>-
>- if (ind == 0 && !targets[1] && bond->params.arp_interval)
>- pr_warn("%s: removing last arp target with arp_interval on\n",
>- bond->dev->name);
>-
>- pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
>- &newtarget);
>-
>- write_lock_bh(&bond->lock);
>- bond_for_each_slave(bond, slave, iter) {
>- targets_rx = slave->target_last_arp_rx;
>- j = ind;
>- for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
>- targets_rx[j] = targets_rx[j+1];
>- targets_rx[j] = 0;
>- }
>- for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
>- targets[i] = targets[i+1];
>- targets[i] = 0;
>- write_unlock_bh(&bond->lock);
>+ ret = bond_option_arp_ip_target_unset(bond, target);
> } else {
> pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n",
> bond->dev->name);
> ret = -EPERM;
>- goto out;
> }
>
>- ret = count;
>-out:
>+ if (!ret)
>+ ret = count;
>+
> rtnl_unlock();
> return ret;
> }
>diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
>index caaa5e7..e5d215d 100644
>--- a/drivers/net/bonding/bonding.h
>+++ b/drivers/net/bonding/bonding.h
>@@ -433,6 +433,9 @@ int bond_option_updelay_set(struct bonding *bond, int updelay);
> int bond_option_downdelay_set(struct bonding *bond, int downdelay);
> int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
> int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
>+int bond_option_arp_ip_target_set(struct bonding *bond, __be32 target);
>+int bond_option_arp_ip_target_unset(struct bonding *bond, __be32 target);
>+int bond_option_arp_ip_target_clear_all(struct bonding *bond);
> struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
> struct net_device *bond_option_active_slave_get(struct bonding *bond);
>
>diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
>index 858b09e..58dd318 100644
>--- a/include/uapi/linux/if_link.h
>+++ b/include/uapi/linux/if_link.h
>@@ -336,6 +336,7 @@ enum {
> IFLA_BOND_DOWNDELAY,
> IFLA_BOND_USE_CARRIER,
> IFLA_BOND_ARP_INTERVAL,
>+ IFLA_BOND_ARP_IP_TARGET,
> __IFLA_BOND_MAX,
> };
>
>
>--
>To unsubscribe from this list: send the line "unsubscribe netdev" in
>the body of a message to majordomo@vger.kernel.org
>More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net-next 0/6] net/mlx4: Mellanox driver update 07-11-2013
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz
Hi Dave,
This patchset contains some enhancements and bug fixes for the mlx4_* drivers.
Patchset was applied and tested against commit: "9bb8ca8 virtio-net: switch to
use XPS to choose txq"
Thanks,
Amir
Eugenia Emantayev (3):
net/mlx4_en: Datapath resources allocated dynamically
net/mlx4_core: ICM pages are allocated on device NUMA node
net/mlx4_en: Datapath structures are allocated per NUMA node
Eyal Perry (1):
net/mlx4_en: Add RFS support in UDP
Jack Morgenstein (1):
net/mlx4_core: Initialize all mailbox buffers to zero before use
Rony Efraim (1):
net/mlx4_core: Add immediate activate for VGT->VST->VGT
drivers/infiniband/hw/mlx4/main.c | 6 -
drivers/net/ethernet/mellanox/mlx4/cmd.c | 36 +++---
drivers/net/ethernet/mellanox/mlx4/cq.c | 6 -
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 45 +++++--
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 36 +++---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 144 +++++++++++++--------
drivers/net/ethernet/mellanox/mlx4/en_port.c | 17 +--
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 68 +++++++---
drivers/net/ethernet/mellanox/mlx4/en_selftest.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 54 ++++++--
drivers/net/ethernet/mellanox/mlx4/eq.c | 1 -
drivers/net/ethernet/mellanox/mlx4/fw.c | 7 -
drivers/net/ethernet/mellanox/mlx4/icm.c | 42 ++++--
drivers/net/ethernet/mellanox/mlx4/main.c | 1 +
drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 -
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 33 ++---
drivers/net/ethernet/mellanox/mlx4/mr.c | 5 -
drivers/net/ethernet/mellanox/mlx4/pd.c | 11 +-
drivers/net/ethernet/mellanox/mlx4/port.c | 11 --
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 79 +++++++++--
drivers/net/ethernet/mellanox/mlx4/srq.c | 2 -
include/linux/mlx4/device.h | 3 +-
22 files changed, 383 insertions(+), 228 deletions(-)
--
1.8.3.4
^ permalink raw reply
* [PATCH net-next 1/6] net/mlx4_en: Add RFS support in UDP
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz, Eyal Perry
In-Reply-To: <1383819594-24070-1-git-send-email-amirv@mellanox.com>
From: Eyal Perry <eyalpe@mellanox.com>
Modify RFS code to support applying filters for incoming UDP streams.
Signed-off-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 45 +++++++++++++++++++-------
1 file changed, 34 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index b555412..cd61e26 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -102,6 +102,7 @@ struct mlx4_en_filter {
struct list_head next;
struct work_struct work;
+ u8 ip_proto;
__be32 src_ip;
__be32 dst_ip;
__be16 src_port;
@@ -120,14 +121,26 @@ struct mlx4_en_filter {
static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv);
+static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
+{
+ switch (ip_proto) {
+ case IPPROTO_UDP:
+ return MLX4_NET_TRANS_RULE_ID_UDP;
+ case IPPROTO_TCP:
+ return MLX4_NET_TRANS_RULE_ID_TCP;
+ default:
+ return -EPROTONOSUPPORT;
+ }
+};
+
static void mlx4_en_filter_work(struct work_struct *work)
{
struct mlx4_en_filter *filter = container_of(work,
struct mlx4_en_filter,
work);
struct mlx4_en_priv *priv = filter->priv;
- struct mlx4_spec_list spec_tcp = {
- .id = MLX4_NET_TRANS_RULE_ID_TCP,
+ struct mlx4_spec_list spec_tcp_udp = {
+ .id = mlx4_ip_proto_to_trans_rule_id(filter->ip_proto),
{
.tcp_udp = {
.dst_port = filter->dst_port,
@@ -163,9 +176,14 @@ static void mlx4_en_filter_work(struct work_struct *work)
int rc;
__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+ if (spec_tcp_udp.id < 0) {
+ en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
+ filter->ip_proto);
+ goto ignore;
+ }
list_add_tail(&spec_eth.list, &rule.list);
list_add_tail(&spec_ip.list, &rule.list);
- list_add_tail(&spec_tcp.list, &rule.list);
+ list_add_tail(&spec_tcp_udp.list, &rule.list);
rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
@@ -183,6 +201,7 @@ static void mlx4_en_filter_work(struct work_struct *work)
if (rc)
en_err(priv, "Error attaching flow. err = %d\n", rc);
+ignore:
mlx4_en_filter_rfs_expire(priv);
filter->activated = 1;
@@ -206,8 +225,8 @@ filter_hash_bucket(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
static struct mlx4_en_filter *
mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
- __be32 dst_ip, __be16 src_port, __be16 dst_port,
- u32 flow_id)
+ __be32 dst_ip, u8 ip_proto, __be16 src_port,
+ __be16 dst_port, u32 flow_id)
{
struct mlx4_en_filter *filter = NULL;
@@ -221,6 +240,7 @@ mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
filter->src_ip = src_ip;
filter->dst_ip = dst_ip;
+ filter->ip_proto = ip_proto;
filter->src_port = src_port;
filter->dst_port = dst_port;
@@ -252,7 +272,7 @@ static void mlx4_en_filter_free(struct mlx4_en_filter *filter)
static inline struct mlx4_en_filter *
mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
- __be16 src_port, __be16 dst_port)
+ u8 ip_proto, __be16 src_port, __be16 dst_port)
{
struct mlx4_en_filter *filter;
struct mlx4_en_filter *ret = NULL;
@@ -263,6 +283,7 @@ mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
filter_chain) {
if (filter->src_ip == src_ip &&
filter->dst_ip == dst_ip &&
+ filter->ip_proto == ip_proto &&
filter->src_port == src_port &&
filter->dst_port == dst_port) {
ret = filter;
@@ -281,6 +302,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
struct mlx4_en_filter *filter;
const struct iphdr *ip;
const __be16 *ports;
+ u8 ip_proto;
__be32 src_ip;
__be32 dst_ip;
__be16 src_port;
@@ -295,18 +317,19 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
if (ip_is_fragment(ip))
return -EPROTONOSUPPORT;
+ if ((ip->protocol != IPPROTO_TCP) && (ip->protocol != IPPROTO_UDP))
+ return -EPROTONOSUPPORT;
ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
+ ip_proto = ip->protocol;
src_ip = ip->saddr;
dst_ip = ip->daddr;
src_port = ports[0];
dst_port = ports[1];
- if (ip->protocol != IPPROTO_TCP)
- return -EPROTONOSUPPORT;
-
spin_lock_bh(&priv->filters_lock);
- filter = mlx4_en_filter_find(priv, src_ip, dst_ip, src_port, dst_port);
+ filter = mlx4_en_filter_find(priv, src_ip, dst_ip, ip_proto,
+ src_port, dst_port);
if (filter) {
if (filter->rxq_index == rxq_index)
goto out;
@@ -314,7 +337,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
filter->rxq_index = rxq_index;
} else {
filter = mlx4_en_filter_alloc(priv, rxq_index,
- src_ip, dst_ip,
+ src_ip, dst_ip, ip_proto,
src_port, dst_port, flow_id);
if (!filter) {
ret = -ENOMEM;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 2/6] net/mlx4_core: Initialize all mailbox buffers to zero before use
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz,
Jack Morgenstein, Majd Dibbiny
In-Reply-To: <1383819594-24070-1-git-send-email-amirv@mellanox.com>
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
To guarantee that all unused fields in all FW commands for both inboxes
and outboxes are zeroed out, initialize the mailbox buffer to all zeroes.
This is especially important for SRIOV comm-channel virtual commands
(such as QUERY_FUNC_CAP), where if new fields are added to support new
features, the driver can depend on older kernels passing zeroes in these
fields.
In addition to zeroing out the mailbox buffer at allocation time, all
(now unnecessary) calls to memset by the callers of
mlx4_alloc_cmd_mailbox() are removed.
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/infiniband/hw/mlx4/main.c | 6 ------
drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 ++
drivers/net/ethernet/mellanox/mlx4/cq.c | 6 ------
drivers/net/ethernet/mellanox/mlx4/en_port.c | 3 ---
drivers/net/ethernet/mellanox/mlx4/eq.c | 1 -
drivers/net/ethernet/mellanox/mlx4/fw.c | 7 -------
drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 --
drivers/net/ethernet/mellanox/mlx4/mr.c | 5 -----
drivers/net/ethernet/mellanox/mlx4/port.c | 11 -----------
drivers/net/ethernet/mellanox/mlx4/srq.c | 2 --
10 files changed, 2 insertions(+), 43 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 7567437..6a0a0d2 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -526,7 +526,6 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
if (IS_ERR(mailbox))
return 0;
- memset(mailbox->buf, 0, 256);
memcpy(mailbox->buf, props->node_desc, 64);
mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
@@ -547,8 +546,6 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, 256);
-
if (dev->dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
*(u8 *) mailbox->buf = !!reset_qkey_viols << 6;
((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
@@ -879,8 +876,6 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
struct mlx4_ib_dev *mdev = to_mdev(qp->device);
struct mlx4_cmd_mailbox *mailbox;
struct mlx4_net_trans_rule_hw_ctrl *ctrl;
- size_t rule_size = sizeof(struct mlx4_net_trans_rule_hw_ctrl) +
- (sizeof(struct _rule_hw) * flow_attr->num_of_specs);
static const u16 __mlx4_domain[] = {
[IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
@@ -905,7 +900,6 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, rule_size);
ctrl = mailbox->buf;
ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 65d41b76..7207dcd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2199,6 +2199,8 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
return ERR_PTR(-ENOMEM);
}
+ memset(mailbox->buf, 0, MLX4_MAILBOX_SIZE);
+
return mailbox;
}
EXPORT_SYMBOL_GPL(mlx4_alloc_cmd_mailbox);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 004e423..22fcbe7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -128,8 +128,6 @@ int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
return PTR_ERR(mailbox);
cq_context = mailbox->buf;
- memset(cq_context, 0, sizeof *cq_context);
-
cq_context->cq_max_count = cpu_to_be16(count);
cq_context->cq_period = cpu_to_be16(period);
@@ -153,8 +151,6 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
return PTR_ERR(mailbox);
cq_context = mailbox->buf;
- memset(cq_context, 0, sizeof *cq_context);
-
cq_context->logsize_usrpage = cpu_to_be32(ilog2(entries) << 24);
cq_context->log_page_size = mtt->page_shift - 12;
mtt_addr = mlx4_mtt_addr(dev, mtt);
@@ -274,8 +270,6 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
}
cq_context = mailbox->buf;
- memset(cq_context, 0, sizeof *cq_context);
-
cq_context->flags = cpu_to_be32(!!collapsed << 18);
if (timestamp_en)
cq_context->flags |= cpu_to_be32(1 << 19);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 3317914..5f8535e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -56,7 +56,6 @@ int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv)
return PTR_ERR(mailbox);
filter = mailbox->buf;
- memset(filter, 0, sizeof(*filter));
for (i = VLAN_FLTR_SIZE - 1; i >= 0; i--) {
entry = 0;
for (j = 0; j < 32; j++)
@@ -81,7 +80,6 @@ int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port)
mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, sizeof(*qport_context));
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, port, 0,
MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
MLX4_CMD_WRAPPED);
@@ -127,7 +125,6 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, sizeof(*mlx4_en_stats));
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
MLX4_CMD_WRAPPED);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 0416c5b..c9cdb2a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -936,7 +936,6 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
if (err)
goto err_out_free_mtt;
- memset(eq_context, 0, sizeof *eq_context);
eq_context->flags = cpu_to_be32(MLX4_EQ_STATUS_OK |
MLX4_EQ_STATE_ARMED);
eq_context->log_eq_size = ilog2(eq->nent);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index c3e70bc..fda2667 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -159,8 +159,6 @@ int mlx4_MOD_STAT_CFG(struct mlx4_dev *dev, struct mlx4_mod_stat_cfg *cfg)
return PTR_ERR(mailbox);
inbox = mailbox->buf;
- memset(inbox, 0, MOD_STAT_CFG_IN_SIZE);
-
MLX4_PUT(inbox, cfg->log_pg_sz, MOD_STAT_CFG_PG_SZ_OFFSET);
MLX4_PUT(inbox, cfg->log_pg_sz_m, MOD_STAT_CFG_PG_SZ_M_OFFSET);
@@ -967,7 +965,6 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
mailbox = mlx4_alloc_cmd_mailbox(dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, MLX4_MAILBOX_SIZE);
pages = mailbox->buf;
for (mlx4_icm_first(icm, &iter);
@@ -1316,8 +1313,6 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
return PTR_ERR(mailbox);
inbox = mailbox->buf;
- memset(inbox, 0, INIT_HCA_IN_SIZE);
-
*((u8 *) mailbox->buf + INIT_HCA_VERSION_OFFSET) = INIT_HCA_VERSION;
*((u8 *) mailbox->buf + INIT_HCA_CACHELINE_SZ_OFFSET) =
@@ -1616,8 +1611,6 @@ int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
return PTR_ERR(mailbox);
inbox = mailbox->buf;
- memset(inbox, 0, INIT_PORT_IN_SIZE);
-
flags = 0;
flags |= (dev->caps.vl_cap[port] & 0xf) << INIT_PORT_VL_SHIFT;
flags |= (dev->caps.port_width_cap[port] & 0xf) << INIT_PORT_PORT_WIDTH_SHIFT;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 70f0213..acf9d5f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -506,7 +506,6 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
goto out_list;
}
mgm = mailbox->buf;
- memset(mgm, 0, sizeof *mgm);
members_count = 0;
list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
@@ -857,7 +856,6 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, sizeof(struct mlx4_net_trans_rule_hw_ctrl));
trans_rule_ctrl_to_hw(rule, mailbox->buf);
size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 63391a1..b3ee9ba 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -480,9 +480,6 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
goto err_table;
}
mpt_entry = mailbox->buf;
-
- memset(mpt_entry, 0, sizeof *mpt_entry);
-
mpt_entry->flags = cpu_to_be32(MLX4_MPT_FLAG_MIO |
MLX4_MPT_FLAG_REGION |
mr->access);
@@ -695,8 +692,6 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw)
}
mpt_entry = mailbox->buf;
- memset(mpt_entry, 0, sizeof(*mpt_entry));
-
/* Note that the MLX4_MPT_FLAG_REGION bit in mpt_entry->flags is turned
* off, thus creating a memory window and not a memory region.
*/
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index caaa154..97d342f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -469,8 +469,6 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
inbuf = inmailbox->buf;
outbuf = outmailbox->buf;
- memset(inbuf, 0, 256);
- memset(outbuf, 0, 256);
inbuf[0] = 1;
inbuf[1] = 1;
inbuf[2] = 1;
@@ -653,8 +651,6 @@ int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz)
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, 256);
-
((__be32 *) mailbox->buf)[1] = dev->caps.ib_port_def_cap[port];
if (pkey_tbl_sz >= 0 && mlx4_is_master(dev)) {
@@ -692,8 +688,6 @@ int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
context = mailbox->buf;
- memset(context, 0, sizeof *context);
-
context->flags = SET_PORT_GEN_ALL_VALID;
context->mtu = cpu_to_be16(mtu);
context->pptx = (pptx * (!pfctx)) << 7;
@@ -727,8 +721,6 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
context = mailbox->buf;
- memset(context, 0, sizeof *context);
-
context->base_qpn = cpu_to_be32(base_qpn);
context->n_mac = dev->caps.log_num_macs;
context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
@@ -761,8 +753,6 @@ int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc)
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
context = mailbox->buf;
- memset(context, 0, sizeof *context);
-
for (i = 0; i < MLX4_NUM_UP; i += 2)
context->prio2tc[i >> 1] = prio2tc[i] << 4 | prio2tc[i + 1];
@@ -788,7 +778,6 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
context = mailbox->buf;
- memset(context, 0, sizeof *context);
for (i = 0; i < MLX4_NUM_TC; i++) {
struct mlx4_port_scheduler_tc_cfg_be *tc = &context->tc[i];
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index 9e08e35..8fdf237 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -189,8 +189,6 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
}
srq_context = mailbox->buf;
- memset(srq_context, 0, sizeof *srq_context);
-
srq_context->state_logsize_srqn = cpu_to_be32((ilog2(srq->max) << 24) |
srq->srqn);
srq_context->logstride = srq->wqe_shift - 4;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 4/6] net/mlx4_en: Datapath resources allocated dynamically
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz,
Eugenia Emantayev
In-Reply-To: <1383819594-24070-1-git-send-email-amirv@mellanox.com>
From: Eugenia Emantayev <eugenia@mellanox.com>
Currently all TX/RX rings and completion queues are part of the
netdev priv structure and are allocated statically. This patch
will change the priv to hold only arrays of pointers and therefore
all TX/RX rings and completetion queues will be allocated
dynamically. This is in preparation for NUMA aware allocations.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 34 ++++++---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 36 +++++-----
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 87 ++++++++++++++----------
drivers/net/ethernet/mellanox/mlx4/en_port.c | 14 ++--
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 57 ++++++++++------
drivers/net/ethernet/mellanox/mlx4/en_selftest.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 32 ++++++---
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 27 ++++----
8 files changed, 178 insertions(+), 111 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 3e2d504..d203f11 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -44,12 +44,19 @@ static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
int mlx4_en_create_cq(struct mlx4_en_priv *priv,
- struct mlx4_en_cq *cq,
+ struct mlx4_en_cq **pcq,
int entries, int ring, enum cq_type mode)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_cq *cq;
int err;
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq) {
+ en_err(priv, "Failed to allocate CQ structure\n");
+ return -ENOMEM;
+ }
+
cq->size = entries;
cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
@@ -60,14 +67,22 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
cq->buf_size, 2 * PAGE_SIZE);
if (err)
- return err;
+ goto err_cq;
err = mlx4_en_map_buffer(&cq->wqres.buf);
if (err)
- mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
- else
- cq->buf = (struct mlx4_cqe *) cq->wqres.buf.direct.buf;
+ goto err_res;
+
+ cq->buf = (struct mlx4_cqe *)cq->wqres.buf.direct.buf;
+ *pcq = cq;
+ return 0;
+
+err_res:
+ mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
+err_cq:
+ kfree(cq);
+ *pcq = NULL;
return err;
}
@@ -117,12 +132,12 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
struct mlx4_en_cq *rx_cq;
cq_idx = cq_idx % priv->rx_ring_num;
- rx_cq = &priv->rx_cq[cq_idx];
+ rx_cq = priv->rx_cq[cq_idx];
cq->vector = rx_cq->vector;
}
if (!cq->is_tx)
- cq->size = priv->rx_ring[cq->ring].actual_size;
+ cq->size = priv->rx_ring[cq->ring]->actual_size;
if ((cq->is_tx && priv->hwtstamp_config.tx_type) ||
(!cq->is_tx && priv->hwtstamp_config.rx_filter))
@@ -146,9 +161,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
return 0;
}
-void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_cq *cq = *pcq;
mlx4_en_unmap_buffer(&cq->wqres.buf);
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
@@ -157,6 +173,8 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
cq->vector = 0;
cq->buf_size = 0;
cq->buf = NULL;
+ kfree(cq);
+ *pcq = NULL;
}
void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 0c75098..0596f9f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -51,10 +51,10 @@ static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
int err = 0;
for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_cq[i].moder_cnt = priv->tx_frames;
- priv->tx_cq[i].moder_time = priv->tx_usecs;
+ priv->tx_cq[i]->moder_cnt = priv->tx_frames;
+ priv->tx_cq[i]->moder_time = priv->tx_usecs;
if (priv->port_up) {
- err = mlx4_en_set_cq_moder(priv, &priv->tx_cq[i]);
+ err = mlx4_en_set_cq_moder(priv, priv->tx_cq[i]);
if (err)
return err;
}
@@ -64,11 +64,11 @@ static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
return 0;
for (i = 0; i < priv->rx_ring_num; i++) {
- priv->rx_cq[i].moder_cnt = priv->rx_frames;
- priv->rx_cq[i].moder_time = priv->rx_usecs;
+ priv->rx_cq[i]->moder_cnt = priv->rx_frames;
+ priv->rx_cq[i]->moder_time = priv->rx_usecs;
priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
if (priv->port_up) {
- err = mlx4_en_set_cq_moder(priv, &priv->rx_cq[i]);
+ err = mlx4_en_set_cq_moder(priv, priv->rx_cq[i]);
if (err)
return err;
}
@@ -274,16 +274,16 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
}
}
for (i = 0; i < priv->tx_ring_num; i++) {
- data[index++] = priv->tx_ring[i].packets;
- data[index++] = priv->tx_ring[i].bytes;
+ data[index++] = priv->tx_ring[i]->packets;
+ data[index++] = priv->tx_ring[i]->bytes;
}
for (i = 0; i < priv->rx_ring_num; i++) {
- data[index++] = priv->rx_ring[i].packets;
- data[index++] = priv->rx_ring[i].bytes;
+ data[index++] = priv->rx_ring[i]->packets;
+ data[index++] = priv->rx_ring[i]->bytes;
#ifdef CONFIG_NET_RX_BUSY_POLL
- data[index++] = priv->rx_ring[i].yields;
- data[index++] = priv->rx_ring[i].misses;
- data[index++] = priv->rx_ring[i].cleaned;
+ data[index++] = priv->rx_ring[i]->yields;
+ data[index++] = priv->rx_ring[i]->misses;
+ data[index++] = priv->rx_ring[i]->cleaned;
#endif
}
spin_unlock_bh(&priv->stats_lock);
@@ -510,9 +510,9 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
tx_size = max_t(u32, tx_size, MLX4_EN_MIN_TX_SIZE);
tx_size = min_t(u32, tx_size, MLX4_EN_MAX_TX_SIZE);
- if (rx_size == (priv->port_up ? priv->rx_ring[0].actual_size :
- priv->rx_ring[0].size) &&
- tx_size == priv->tx_ring[0].size)
+ if (rx_size == (priv->port_up ? priv->rx_ring[0]->actual_size :
+ priv->rx_ring[0]->size) &&
+ tx_size == priv->tx_ring[0]->size)
return 0;
mutex_lock(&mdev->state_lock);
@@ -553,8 +553,8 @@ static void mlx4_en_get_ringparam(struct net_device *dev,
param->rx_max_pending = MLX4_EN_MAX_RX_SIZE;
param->tx_max_pending = MLX4_EN_MAX_TX_SIZE;
param->rx_pending = priv->port_up ?
- priv->rx_ring[0].actual_size : priv->rx_ring[0].size;
- param->tx_pending = priv->tx_ring[0].size;
+ priv->rx_ring[0]->actual_size : priv->rx_ring[0]->size;
+ param->tx_pending = priv->tx_ring[0]->size;
}
static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index cd61e26..f430788 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -75,7 +75,7 @@ static int mlx4_en_low_latency_recv(struct napi_struct *napi)
struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
struct net_device *dev = cq->dev;
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_rx_ring *rx_ring = &priv->rx_ring[cq->ring];
+ struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
int done;
if (!priv->port_up)
@@ -355,8 +355,7 @@ err:
return ret;
}
-void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *rx_ring)
+void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv)
{
struct mlx4_en_filter *filter, *tmp;
LIST_HEAD(del_list);
@@ -1242,7 +1241,7 @@ static void mlx4_en_netpoll(struct net_device *dev)
int i;
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
+ cq = priv->rx_cq[i];
spin_lock_irqsave(&cq->lock, flags);
napi_synchronize(&cq->napi);
mlx4_en_process_rx_cq(dev, cq, 0);
@@ -1264,8 +1263,8 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
continue;
en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
- i, priv->tx_ring[i].qpn, priv->tx_ring[i].cqn,
- priv->tx_ring[i].cons, priv->tx_ring[i].prod);
+ i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
+ priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
}
priv->port_stats.tx_timeout++;
@@ -1305,7 +1304,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
/* Setup cq moderation params */
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
+ cq = priv->rx_cq[i];
cq->moder_cnt = priv->rx_frames;
cq->moder_time = priv->rx_usecs;
priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
@@ -1314,7 +1313,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
}
for (i = 0; i < priv->tx_ring_num; i++) {
- cq = &priv->tx_cq[i];
+ cq = priv->tx_cq[i];
cq->moder_cnt = priv->tx_frames;
cq->moder_time = priv->tx_usecs;
}
@@ -1348,8 +1347,8 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
for (ring = 0; ring < priv->rx_ring_num; ring++) {
spin_lock_bh(&priv->stats_lock);
- rx_packets = priv->rx_ring[ring].packets;
- rx_bytes = priv->rx_ring[ring].bytes;
+ rx_packets = priv->rx_ring[ring]->packets;
+ rx_bytes = priv->rx_ring[ring]->bytes;
spin_unlock_bh(&priv->stats_lock);
rx_pkt_diff = ((unsigned long) (rx_packets -
@@ -1378,7 +1377,7 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
if (moder_time != priv->last_moder_time[ring]) {
priv->last_moder_time[ring] = moder_time;
- cq = &priv->rx_cq[ring];
+ cq = priv->rx_cq[ring];
cq->moder_time = moder_time;
cq->moder_cnt = priv->rx_frames;
err = mlx4_en_set_cq_moder(priv, cq);
@@ -1501,7 +1500,7 @@ int mlx4_en_start_port(struct net_device *dev)
return err;
}
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
+ cq = priv->rx_cq[i];
mlx4_en_cq_init_lock(cq);
@@ -1519,7 +1518,7 @@ int mlx4_en_start_port(struct net_device *dev)
goto cq_err;
}
mlx4_en_arm_cq(priv, cq);
- priv->rx_ring[i].cqn = cq->mcq.cqn;
+ priv->rx_ring[i]->cqn = cq->mcq.cqn;
++rx_index;
}
@@ -1545,7 +1544,7 @@ int mlx4_en_start_port(struct net_device *dev)
/* Configure tx cq's and rings */
for (i = 0; i < priv->tx_ring_num; i++) {
/* Configure cq */
- cq = &priv->tx_cq[i];
+ cq = priv->tx_cq[i];
err = mlx4_en_activate_cq(priv, cq, i);
if (err) {
en_err(priv, "Failed allocating Tx CQ\n");
@@ -1561,7 +1560,7 @@ int mlx4_en_start_port(struct net_device *dev)
cq->buf->wqe_index = cpu_to_be16(0xffff);
/* Configure ring */
- tx_ring = &priv->tx_ring[i];
+ tx_ring = priv->tx_ring[i];
err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
i / priv->num_tx_rings_p_up);
if (err) {
@@ -1631,8 +1630,8 @@ int mlx4_en_start_port(struct net_device *dev)
tx_err:
while (tx_index--) {
- mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[tx_index]);
- mlx4_en_deactivate_cq(priv, &priv->tx_cq[tx_index]);
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
}
mlx4_en_destroy_drop_qp(priv);
rss_err:
@@ -1641,9 +1640,9 @@ mac_err:
mlx4_en_put_qp(priv);
cq_err:
while (rx_index--)
- mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
+ mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
for (i = 0; i < priv->rx_ring_num; i++)
- mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
+ mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
return err; /* need to close devices */
}
@@ -1739,13 +1738,13 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
/* Free TX Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
- mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[i]);
- mlx4_en_deactivate_cq(priv, &priv->tx_cq[i]);
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
}
msleep(10);
for (i = 0; i < priv->tx_ring_num; i++)
- mlx4_en_free_tx_buf(dev, &priv->tx_ring[i]);
+ mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);
/* Free RSS qps */
mlx4_en_release_rss_steer(priv);
@@ -1757,7 +1756,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
/* Free RX Rings */
for (i = 0; i < priv->rx_ring_num; i++) {
- struct mlx4_en_cq *cq = &priv->rx_cq[i];
+ struct mlx4_en_cq *cq = priv->rx_cq[i];
local_bh_disable();
while (!mlx4_en_cq_lock_napi(cq)) {
@@ -1768,7 +1767,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
while (test_bit(NAPI_STATE_SCHED, &cq->napi.state))
msleep(1);
- mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
+ mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
mlx4_en_deactivate_cq(priv, cq);
}
}
@@ -1806,15 +1805,15 @@ static void mlx4_en_clear_stats(struct net_device *dev)
memset(&priv->port_stats, 0, sizeof(priv->port_stats));
for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_ring[i].bytes = 0;
- priv->tx_ring[i].packets = 0;
- priv->tx_ring[i].tx_csum = 0;
+ priv->tx_ring[i]->bytes = 0;
+ priv->tx_ring[i]->packets = 0;
+ priv->tx_ring[i]->tx_csum = 0;
}
for (i = 0; i < priv->rx_ring_num; i++) {
- priv->rx_ring[i].bytes = 0;
- priv->rx_ring[i].packets = 0;
- priv->rx_ring[i].csum_ok = 0;
- priv->rx_ring[i].csum_none = 0;
+ priv->rx_ring[i]->bytes = 0;
+ priv->rx_ring[i]->packets = 0;
+ priv->rx_ring[i]->csum_ok = 0;
+ priv->rx_ring[i]->csum_none = 0;
}
}
@@ -1871,17 +1870,17 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
#endif
for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring[i].tx_info)
+ if (priv->tx_ring && priv->tx_ring[i])
mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq[i].buf)
+ if (priv->tx_cq && priv->tx_cq[i])
mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
}
for (i = 0; i < priv->rx_ring_num; i++) {
- if (priv->rx_ring[i].rx_info)
+ if (priv->rx_ring[i])
mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
priv->prof->rx_ring_size, priv->stride);
- if (priv->rx_cq[i].buf)
+ if (priv->rx_cq[i])
mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
}
@@ -1937,6 +1936,20 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
err:
en_err(priv, "Failed to allocate NIC resources\n");
+ for (i = 0; i < priv->rx_ring_num; i++) {
+ if (priv->rx_ring[i])
+ mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
+ prof->rx_ring_size,
+ priv->stride);
+ if (priv->rx_cq[i])
+ mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
+ }
+ for (i = 0; i < priv->tx_ring_num; i++) {
+ if (priv->tx_ring[i])
+ mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
+ if (priv->tx_cq[i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ }
return -ENOMEM;
}
@@ -2230,13 +2243,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
priv->tx_ring_num = prof->tx_ring_num;
- priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring) * MAX_TX_RINGS,
+ priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
GFP_KERNEL);
if (!priv->tx_ring) {
err = -ENOMEM;
goto out;
}
- priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq) * MAX_TX_RINGS,
+ priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
GFP_KERNEL);
if (!priv->tx_cq) {
err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 5f8535e..dae1a1f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -140,18 +140,18 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good = 0;
priv->port_stats.rx_chksum_none = 0;
for (i = 0; i < priv->rx_ring_num; i++) {
- stats->rx_packets += priv->rx_ring[i].packets;
- stats->rx_bytes += priv->rx_ring[i].bytes;
- priv->port_stats.rx_chksum_good += priv->rx_ring[i].csum_ok;
- priv->port_stats.rx_chksum_none += priv->rx_ring[i].csum_none;
+ stats->rx_packets += priv->rx_ring[i]->packets;
+ stats->rx_bytes += priv->rx_ring[i]->bytes;
+ priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
+ priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
}
stats->tx_packets = 0;
stats->tx_bytes = 0;
priv->port_stats.tx_chksum_offload = 0;
for (i = 0; i < priv->tx_ring_num; i++) {
- stats->tx_packets += priv->tx_ring[i].packets;
- stats->tx_bytes += priv->tx_ring[i].bytes;
- priv->port_stats.tx_chksum_offload += priv->tx_ring[i].tx_csum;
+ stats->tx_packets += priv->tx_ring[i]->packets;
+ stats->tx_bytes += priv->tx_ring[i]->bytes;
+ priv->port_stats.tx_chksum_offload += priv->tx_ring[i]->tx_csum;
}
stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) +
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index afe2efa..1c45f88 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -264,7 +264,7 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
for (buf_ind = 0; buf_ind < priv->prof->rx_ring_size; buf_ind++) {
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
- ring = &priv->rx_ring[ring_ind];
+ ring = priv->rx_ring[ring_ind];
if (mlx4_en_prepare_rx_desc(priv, ring,
ring->actual_size,
@@ -289,7 +289,7 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
reduce_rings:
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
- ring = &priv->rx_ring[ring_ind];
+ ring = priv->rx_ring[ring_ind];
while (ring->actual_size > new_size) {
ring->actual_size--;
ring->prod--;
@@ -319,12 +319,20 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
}
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring, u32 size, u16 stride)
+ struct mlx4_en_rx_ring **pring,
+ u32 size, u16 stride)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_rx_ring *ring;
int err = -ENOMEM;
int tmp;
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring) {
+ en_err(priv, "Failed to allocate RX ring structure\n");
+ return -ENOMEM;
+ }
+
ring->prod = 0;
ring->cons = 0;
ring->size = size;
@@ -336,8 +344,10 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
sizeof(struct mlx4_en_rx_alloc));
ring->rx_info = vmalloc(tmp);
- if (!ring->rx_info)
- return -ENOMEM;
+ if (!ring->rx_info) {
+ err = -ENOMEM;
+ goto err_ring;
+ }
en_dbg(DRV, priv, "Allocated rx_info ring at addr:%p size:%d\n",
ring->rx_info, tmp);
@@ -345,7 +355,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres,
ring->buf_size, 2 * PAGE_SIZE);
if (err)
- goto err_ring;
+ goto err_info;
err = mlx4_en_map_buffer(&ring->wqres.buf);
if (err) {
@@ -356,13 +366,18 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
ring->hwtstamp_rx_filter = priv->hwtstamp_config.rx_filter;
+ *pring = ring;
return 0;
err_hwq:
mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
-err_ring:
+err_info:
vfree(ring->rx_info);
ring->rx_info = NULL;
+err_ring:
+ kfree(ring);
+ *pring = NULL;
+
return err;
}
@@ -376,12 +391,12 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
DS_SIZE * priv->num_frags);
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
- ring = &priv->rx_ring[ring_ind];
+ ring = priv->rx_ring[ring_ind];
ring->prod = 0;
ring->cons = 0;
ring->actual_size = 0;
- ring->cqn = priv->rx_cq[ring_ind].mcq.cqn;
+ ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn;
ring->stride = stride;
if (ring->stride <= TXBB_SIZE)
@@ -412,7 +427,7 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
goto err_buffers;
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
- ring = &priv->rx_ring[ring_ind];
+ ring = priv->rx_ring[ring_ind];
ring->size_mask = ring->actual_size - 1;
mlx4_en_update_rx_prod_db(ring);
@@ -422,30 +437,34 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
err_buffers:
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++)
- mlx4_en_free_rx_buf(priv, &priv->rx_ring[ring_ind]);
+ mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]);
ring_ind = priv->rx_ring_num - 1;
err_allocator:
while (ring_ind >= 0) {
- if (priv->rx_ring[ring_ind].stride <= TXBB_SIZE)
- priv->rx_ring[ring_ind].buf -= TXBB_SIZE;
- mlx4_en_destroy_allocator(priv, &priv->rx_ring[ring_ind]);
+ if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE)
+ priv->rx_ring[ring_ind]->buf -= TXBB_SIZE;
+ mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]);
ring_ind--;
}
return err;
}
void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring, u32 size, u16 stride)
+ struct mlx4_en_rx_ring **pring,
+ u32 size, u16 stride)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_rx_ring *ring = *pring;
mlx4_en_unmap_buffer(&ring->wqres.buf);
mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
vfree(ring->rx_info);
ring->rx_info = NULL;
+ kfree(ring);
+ *pring = NULL;
#ifdef CONFIG_RFS_ACCEL
- mlx4_en_cleanup_filters(priv, ring);
+ mlx4_en_cleanup_filters(priv);
#endif
}
@@ -592,7 +611,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_cqe *cqe;
- struct mlx4_en_rx_ring *ring = &priv->rx_ring[cq->ring];
+ struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
struct mlx4_en_rx_alloc *frags;
struct mlx4_en_rx_desc *rx_desc;
struct sk_buff *skb;
@@ -991,7 +1010,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
for (i = 0; i < priv->rx_ring_num; i++) {
qpn = rss_map->base_qpn + i;
- err = mlx4_en_config_rss_qp(priv, qpn, &priv->rx_ring[i],
+ err = mlx4_en_config_rss_qp(priv, qpn, priv->rx_ring[i],
&rss_map->state[i],
&rss_map->qps[i]);
if (err)
@@ -1008,7 +1027,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
}
rss_map->indir_qp.event = mlx4_en_sqp_event;
mlx4_en_fill_qp_context(priv, 0, 0, 0, 1, priv->base_qpn,
- priv->rx_ring[0].cqn, -1, &context);
+ priv->rx_ring[0]->cqn, -1, &context);
if (!priv->prof->rss_rings || priv->prof->rss_rings > priv->rx_ring_num)
rss_rings = priv->rx_ring_num;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 2448f0d..4062669 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -156,7 +156,7 @@ retry_tx:
* since we turned the carrier off */
msleep(200);
for (i = 0; i < priv->tx_ring_num && carrier_ok; i++) {
- tx_ring = &priv->tx_ring[i];
+ tx_ring = priv->tx_ring[i];
if (tx_ring->prod != (tx_ring->cons + tx_ring->last_nr_txbb))
goto retry_tx;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0698c82..d4e4cf3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -54,13 +54,20 @@ module_param_named(inline_thold, inline_thold, int, 0444);
MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_tx_ring *ring, int qpn, u32 size,
+ struct mlx4_en_tx_ring **pring, int qpn, u32 size,
u16 stride)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_tx_ring *ring;
int tmp;
int err;
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring) {
+ en_err(priv, "Failed allocating TX ring\n");
+ return -ENOMEM;
+ }
+
ring->size = size;
ring->size_mask = size - 1;
ring->stride = stride;
@@ -69,8 +76,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
tmp = size * sizeof(struct mlx4_en_tx_info);
ring->tx_info = vmalloc(tmp);
- if (!ring->tx_info)
- return -ENOMEM;
+ if (!ring->tx_info) {
+ err = -ENOMEM;
+ goto err_ring;
+ }
en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n",
ring->tx_info, tmp);
@@ -78,7 +87,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
if (!ring->bounce_buf) {
err = -ENOMEM;
- goto err_tx;
+ goto err_info;
}
ring->buf_size = ALIGN(size * ring->stride, MLX4_EN_PAGE_SIZE);
@@ -120,6 +129,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
+ *pring = ring;
return 0;
err_map:
@@ -129,16 +139,20 @@ err_hwq_res:
err_bounce:
kfree(ring->bounce_buf);
ring->bounce_buf = NULL;
-err_tx:
+err_info:
vfree(ring->tx_info);
ring->tx_info = NULL;
+err_ring:
+ kfree(ring);
+ *pring = NULL;
return err;
}
void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_tx_ring *ring)
+ struct mlx4_en_tx_ring **pring)
{
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_tx_ring *ring = *pring;
en_dbg(DRV, priv, "Destroying tx ring, qpn: %d\n", ring->qpn);
if (ring->bf_enabled)
@@ -151,6 +165,8 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
ring->bounce_buf = NULL;
vfree(ring->tx_info);
ring->tx_info = NULL;
+ kfree(ring);
+ *pring = NULL;
}
int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
@@ -330,7 +346,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cq *mcq = &cq->mcq;
- struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
+ struct mlx4_en_tx_ring *ring = priv->tx_ring[cq->ring];
struct mlx4_cqe *cqe;
u16 index;
u16 new_index, ring_index, stamp_index;
@@ -622,7 +638,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
}
tx_ind = skb->queue_mapping;
- ring = &priv->tx_ring[tx_ind];
+ ring = priv->tx_ring[tx_ind];
if (vlan_tx_tag_present(skb))
vlan_tag = vlan_tx_tag_get(skb);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index bf06e36..b2547ae 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -530,10 +530,10 @@ struct mlx4_en_priv {
u16 num_frags;
u16 log_rx_info;
- struct mlx4_en_tx_ring *tx_ring;
- struct mlx4_en_rx_ring rx_ring[MAX_RX_RINGS];
- struct mlx4_en_cq *tx_cq;
- struct mlx4_en_cq rx_cq[MAX_RX_RINGS];
+ struct mlx4_en_tx_ring **tx_ring;
+ struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
+ struct mlx4_en_cq **tx_cq;
+ struct mlx4_en_cq *rx_cq[MAX_RX_RINGS];
struct mlx4_qp drop_qp;
struct work_struct rx_mode_task;
struct work_struct watchdog_task;
@@ -626,7 +626,7 @@ static inline bool mlx4_en_cq_lock_poll(struct mlx4_en_cq *cq)
if ((cq->state & MLX4_CQ_LOCKED)) {
struct net_device *dev = cq->dev;
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_rx_ring *rx_ring = &priv->rx_ring[cq->ring];
+ struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
cq->state |= MLX4_EN_CQ_STATE_POLL_YIELD;
rc = false;
@@ -704,9 +704,9 @@ void mlx4_en_stop_port(struct net_device *dev, int detach);
void mlx4_en_free_resources(struct mlx4_en_priv *priv);
int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
-int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
+int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
int entries, int ring, enum cq_type mode);
-void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq);
int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
int cq_idx);
void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
@@ -717,9 +717,11 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq);
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
-int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring,
+int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
+ struct mlx4_en_tx_ring **pring,
int qpn, u32 size, u16 stride);
-void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring);
+void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
+ struct mlx4_en_tx_ring **pring);
int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
int cq, int user_prio);
@@ -727,10 +729,10 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring);
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring,
+ struct mlx4_en_rx_ring **pring,
u32 size, u16 stride);
void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring,
+ struct mlx4_en_rx_ring **pring,
u32 size, u16 stride);
int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv);
void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
@@ -768,8 +770,7 @@ extern const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops;
int mlx4_en_setup_tc(struct net_device *dev, u8 up);
#ifdef CONFIG_RFS_ACCEL
-void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *rx_ring);
+void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv);
#endif
#define MLX4_EN_NUM_SELF_TEST 5
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 6/6] net/mlx4_en: Datapath structures are allocated per NUMA node
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz,
Eugenia Emantayev
In-Reply-To: <1383819594-24070-1-git-send-email-amirv@mellanox.com>
From: Eugenia Emantayev <eugenia@mellanox.com>
For each RX/TX ring and its CQ, allocation is done on a NUMA node that
corresponds to the core that the data structure should operate on.
The assumption is that the core number is reflected by the ring index.
The affected allocations are the ring/CQ data structures,
the TX/RX info and the shared HW/SW buffer.
For TX rings, each core has rings of all UPs.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 17 ++++++++++---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 12 ++++++---
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 23 +++++++++++------
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 34 +++++++++++++++++---------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 6 ++---
drivers/net/ethernet/mellanox/mlx4/pd.c | 11 ++++++---
include/linux/mlx4/device.h | 2 +-
7 files changed, 71 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index d203f11..3a098cc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -45,16 +45,20 @@ static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
int mlx4_en_create_cq(struct mlx4_en_priv *priv,
struct mlx4_en_cq **pcq,
- int entries, int ring, enum cq_type mode)
+ int entries, int ring, enum cq_type mode,
+ int node)
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_cq *cq;
int err;
- cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, node);
if (!cq) {
- en_err(priv, "Failed to allocate CQ structure\n");
- return -ENOMEM;
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq) {
+ en_err(priv, "Failed to allocate CQ structure\n");
+ return -ENOMEM;
+ }
}
cq->size = entries;
@@ -64,8 +68,13 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
cq->is_tx = mode;
spin_lock_init(&cq->lock);
+ /* Allocate HW buffers on provided NUMA node.
+ * dev->numa_node is used in mtt range allocation flow.
+ */
+ set_dev_node(&mdev->dev->pdev->dev, node);
err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
cq->buf_size, 2 * PAGE_SIZE);
+ set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
if (err)
goto err_cq;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index f430788..e72d8a1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1895,6 +1895,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
struct mlx4_en_port_profile *prof = priv->prof;
int i;
int err;
+ int node;
err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
if (err) {
@@ -1904,23 +1905,26 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
/* Create tx Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
+ node = cpu_to_node(i % num_online_cpus());
if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
- prof->tx_ring_size, i, TX))
+ prof->tx_ring_size, i, TX, node))
goto err;
if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
- prof->tx_ring_size, TXBB_SIZE))
+ prof->tx_ring_size, TXBB_SIZE, node))
goto err;
}
/* Create rx Rings */
for (i = 0; i < priv->rx_ring_num; i++) {
+ node = cpu_to_node(i % num_online_cpus());
if (mlx4_en_create_cq(priv, &priv->rx_cq[i],
- prof->rx_ring_size, i, RX))
+ prof->rx_ring_size, i, RX, node))
goto err;
if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
- prof->rx_ring_size, priv->stride))
+ prof->rx_ring_size, priv->stride,
+ node))
goto err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 1c45f88..07a1d0f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -320,17 +320,20 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
- u32 size, u16 stride)
+ u32 size, u16 stride, int node)
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_rx_ring *ring;
int err = -ENOMEM;
int tmp;
- ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
if (!ring) {
- en_err(priv, "Failed to allocate RX ring structure\n");
- return -ENOMEM;
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring) {
+ en_err(priv, "Failed to allocate RX ring structure\n");
+ return -ENOMEM;
+ }
}
ring->prod = 0;
@@ -343,17 +346,23 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
sizeof(struct mlx4_en_rx_alloc));
- ring->rx_info = vmalloc(tmp);
+ ring->rx_info = vmalloc_node(tmp, node);
if (!ring->rx_info) {
- err = -ENOMEM;
- goto err_ring;
+ ring->rx_info = vmalloc(tmp);
+ if (!ring->rx_info) {
+ err = -ENOMEM;
+ goto err_ring;
+ }
}
en_dbg(DRV, priv, "Allocated rx_info ring at addr:%p size:%d\n",
ring->rx_info, tmp);
+ /* Allocate HW buffers on provided NUMA node */
+ set_dev_node(&mdev->dev->pdev->dev, node);
err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres,
ring->buf_size, 2 * PAGE_SIZE);
+ set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
if (err)
goto err_info;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d4e4cf3..f54ebd5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -55,17 +55,20 @@ MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring, int qpn, u32 size,
- u16 stride)
+ u16 stride, int node)
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_tx_ring *ring;
int tmp;
int err;
- ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
if (!ring) {
- en_err(priv, "Failed allocating TX ring\n");
- return -ENOMEM;
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring) {
+ en_err(priv, "Failed allocating TX ring\n");
+ return -ENOMEM;
+ }
}
ring->size = size;
@@ -75,24 +78,33 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
inline_thold = min(inline_thold, MAX_INLINE);
tmp = size * sizeof(struct mlx4_en_tx_info);
- ring->tx_info = vmalloc(tmp);
+ ring->tx_info = vmalloc_node(tmp, node);
if (!ring->tx_info) {
- err = -ENOMEM;
- goto err_ring;
+ ring->tx_info = vmalloc(tmp);
+ if (!ring->tx_info) {
+ err = -ENOMEM;
+ goto err_ring;
+ }
}
en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n",
ring->tx_info, tmp);
- ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+ ring->bounce_buf = kmalloc_node(MAX_DESC_SIZE, GFP_KERNEL, node);
if (!ring->bounce_buf) {
- err = -ENOMEM;
- goto err_info;
+ ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+ if (!ring->bounce_buf) {
+ err = -ENOMEM;
+ goto err_info;
+ }
}
ring->buf_size = ALIGN(size * ring->stride, MLX4_EN_PAGE_SIZE);
+ /* Allocate HW buffers on provided NUMA node */
+ set_dev_node(&mdev->dev->pdev->dev, node);
err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size,
2 * PAGE_SIZE);
+ set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
if (err) {
en_err(priv, "Failed allocating hwq resources\n");
goto err_bounce;
@@ -118,7 +130,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
}
ring->qp.event = mlx4_en_sqp_event;
- err = mlx4_bf_alloc(mdev->dev, &ring->bf);
+ err = mlx4_bf_alloc(mdev->dev, &ring->bf, node);
if (err) {
en_dbg(DRV, priv, "working without blueflame (%d)", err);
ring->bf.uar = &mdev->priv_uar;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b2547ae..f3758de 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -705,7 +705,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv);
int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
- int entries, int ring, enum cq_type mode);
+ int entries, int ring, enum cq_type mode, int node);
void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq);
int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
int cq_idx);
@@ -719,7 +719,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring,
- int qpn, u32 size, u16 stride);
+ int qpn, u32 size, u16 stride, int node);
void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring);
int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
@@ -730,7 +730,7 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
- u32 size, u16 stride);
+ u32 size, u16 stride, int node);
void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
u32 size, u16 stride);
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 00f223a..84cfb40 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -168,7 +168,7 @@ void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar)
}
EXPORT_SYMBOL_GPL(mlx4_uar_free);
-int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_uar *uar;
@@ -186,10 +186,13 @@ int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
err = -ENOMEM;
goto out;
}
- uar = kmalloc(sizeof *uar, GFP_KERNEL);
+ uar = kmalloc_node(sizeof(*uar), GFP_KERNEL, node);
if (!uar) {
- err = -ENOMEM;
- goto out;
+ uar = kmalloc(sizeof(*uar), GFP_KERNEL);
+ if (!uar) {
+ err = -ENOMEM;
+ goto out;
+ }
}
err = mlx4_uar_alloc(dev, uar);
if (err)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 4cf0b01..7d3a523 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -835,7 +835,7 @@ void mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn);
int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar);
void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar);
-int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf);
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node);
void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf);
int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 5/6] net/mlx4_core: ICM pages are allocated on device NUMA node
From: Amir Vadai @ 2013-11-07 10:19 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Amir Vadai, Yevgeny Petrilin, Or Gerlitz,
Eugenia Emantayev
In-Reply-To: <1383819594-24070-1-git-send-email-amirv@mellanox.com>
From: Eugenia Emantayev <eugenia@mellanox.com>
>From now ICM pages will be allocated on device NUMA node.
This is done to optimize FW/HW access to host memory.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/icm.c | 42 ++++++++++++++++++++++---------
drivers/net/ethernet/mellanox/mlx4/main.c | 1 +
include/linux/mlx4/device.h | 1 +
3 files changed, 32 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 31d0264..5fbf492 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -93,13 +93,17 @@ void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
kfree(icm);
}
-static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order, gfp_t gfp_mask)
+static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order,
+ gfp_t gfp_mask, int node)
{
struct page *page;
- page = alloc_pages(gfp_mask, order);
- if (!page)
- return -ENOMEM;
+ page = alloc_pages_node(node, gfp_mask, order);
+ if (!page) {
+ page = alloc_pages(gfp_mask, order);
+ if (!page)
+ return -ENOMEM;
+ }
sg_set_page(mem, page, PAGE_SIZE << order, 0);
return 0;
@@ -130,9 +134,15 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
/* We use sg_set_buf for coherent allocs, which assumes low memory */
BUG_ON(coherent && (gfp_mask & __GFP_HIGHMEM));
- icm = kmalloc(sizeof *icm, gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
- if (!icm)
- return NULL;
+ icm = kmalloc_node(sizeof(*icm),
+ gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN),
+ dev->numa_node);
+ if (!icm) {
+ icm = kmalloc(sizeof(*icm),
+ gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
+ if (!icm)
+ return NULL;
+ }
icm->refcount = 0;
INIT_LIST_HEAD(&icm->chunk_list);
@@ -141,10 +151,17 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
while (npages > 0) {
if (!chunk) {
- chunk = kmalloc(sizeof *chunk,
- gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
- if (!chunk)
- goto fail;
+ chunk = kmalloc_node(sizeof(*chunk),
+ gfp_mask & ~(__GFP_HIGHMEM |
+ __GFP_NOWARN),
+ dev->numa_node);
+ if (!chunk) {
+ chunk = kmalloc(sizeof(*chunk),
+ gfp_mask & ~(__GFP_HIGHMEM |
+ __GFP_NOWARN));
+ if (!chunk)
+ goto fail;
+ }
sg_init_table(chunk->mem, MLX4_ICM_CHUNK_LEN);
chunk->npages = 0;
@@ -161,7 +178,8 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
cur_order, gfp_mask);
else
ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
- cur_order, gfp_mask);
+ cur_order, gfp_mask,
+ dev->numa_node);
if (ret) {
if (--cur_order < 0)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7d2628d..5789ea2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2191,6 +2191,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
mutex_init(&priv->bf_mutex);
dev->rev_id = pdev->revision;
+ dev->numa_node = dev_to_node(&pdev->dev);
/* Detect if this device is a virtual function */
if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
/* When acting as pf, we normally skip vfs unless explicitly
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f6f5927..4cf0b01 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -662,6 +662,7 @@ struct mlx4_dev {
u8 rev_id;
char board_id[MLX4_BOARD_ID_LEN];
int num_vfs;
+ int numa_node;
int oper_log_mgm_entry_size;
u64 regid_promisc_array[MLX4_MAX_PORTS + 1];
u64 regid_allmulti_array[MLX4_MAX_PORTS + 1];
--
1.8.3.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox