* [PATCH net-next 03/16] ipv6: prepare fib6_remove_prefsrc() for exception table
From: Wei Wang @ 2017-10-06 19:05 UTC (permalink / raw)
To: David Miller, netdev; +Cc: Eric Dumazet, Martin KaFai Lau, Wei Wang
In-Reply-To: <20171006190611.110633-3-tracywwnj@gmail.com>
From: Wei Wang <weiwan@google.com>
After we move cached dst entries into the exception table under its
parent route, current fib6_remove_prefsrc() no longer can access them.
This commit makes fib6_remove_prefsrc() also go through all routes
in the exception table to remove the pref src.
This is a preparation patch in order to move all cached dst into the
exception table.
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/route.c | 29 +++++++++++++++++++++++++++++
1 file changed, 29 insertions(+)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index dc5e70975966..f52ac57dcc99 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1264,6 +1264,12 @@ static int rt6_insert_exception(struct rt6_info *nrt,
if (ort->rt6i_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
+
+ /* Update rt6i_prefsrc as it could be changed
+ * in rt6_remove_prefsrc()
+ */
+ nrt->rt6i_prefsrc = ort->rt6i_prefsrc;
+
rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
src_key);
if (rt6_ex)
@@ -1432,6 +1438,25 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
rcu_read_unlock();
}
+static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
+{
+ struct rt6_exception_bucket *bucket;
+ struct rt6_exception *rt6_ex;
+ int i;
+
+ bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+ lockdep_is_held(&rt6_exception_lock));
+
+ if (bucket) {
+ for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+ hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+ rt6_ex->rt6i->rt6i_prefsrc.plen = 0;
+ }
+ bucket++;
+ }
+ }
+}
+
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6, int flags)
{
@@ -3159,8 +3184,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
if (((void *)rt->dst.dev == dev || !dev) &&
rt != net->ipv6.ip6_null_entry &&
ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+ spin_lock_bh(&rt6_exception_lock);
/* remove prefsrc entry */
rt->rt6i_prefsrc.plen = 0;
+ /* need to update cache as well */
+ rt6_exceptions_remove_prefsrc(rt);
+ spin_unlock_bh(&rt6_exception_lock);
}
return 0;
}
--
2.14.2.920.gcf0c67979c-goog
^ permalink raw reply related
* [PATCH net-next 02/16] ipv6: introduce a hash table to store dst cache
From: Wei Wang @ 2017-10-06 19:05 UTC (permalink / raw)
To: David Miller, netdev; +Cc: Eric Dumazet, Martin KaFai Lau, Wei Wang
In-Reply-To: <20171006190611.110633-2-tracywwnj@gmail.com>
From: Wei Wang <weiwan@google.com>
Add a hash table into struct rt6_info in order to store dst caches
created by pmtu discovery and ip redirect in ipv6 routing code.
APIs to add dst cache, delete dst cache, find dst cache and update
dst cache in the hash table are implemented and will be used in later
commits.
This is a preparation work to move all cache routes into the exception
table instead of getting inserted into the fib6 tree.
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/ip6_fib.h | 19 +++
include/net/ip6_route.h | 3 +
net/ipv6/route.c | 341 ++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 363 insertions(+)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 152b7b14a5a5..c4864c1e8f13 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -98,6 +98,22 @@ struct rt6key {
struct fib6_table;
+struct rt6_exception_bucket {
+ struct hlist_head chain;
+ int depth;
+};
+
+struct rt6_exception {
+ struct hlist_node hlist;
+ struct rt6_info *rt6i;
+ unsigned long stamp;
+ struct rcu_head rcu;
+};
+
+#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10
+#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
+#define FIB6_MAX_DEPTH 5
+
struct rt6_info {
struct dst_entry dst;
@@ -134,12 +150,15 @@ struct rt6_info {
struct inet6_dev *rt6i_idev;
struct rt6_info * __percpu *rt6i_pcpu;
+ struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 rt6i_metric;
u32 rt6i_pmtu;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
+ u8 exception_bucket_flushed:1,
+ unused:7;
};
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index ee96f402cb75..3315605f34c9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -95,6 +95,9 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
int ip6_ins_rt(struct rt6_info *);
int ip6_del_rt(struct rt6_info *);
+void rt6_flush_exceptions(struct rt6_info *rt);
+int rt6_remove_exception_rt(struct rt6_info *rt);
+
static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 26cc9f483b6d..dc5e70975966 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -44,6 +44,7 @@
#include <linux/seq_file.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
+#include <linux/jhash.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
@@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net,
struct in6_addr *dst, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+ struct in6_addr *daddr,
+ struct in6_addr *saddr);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -392,6 +396,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
+ struct rt6_exception_bucket *bucket;
struct dst_entry *from = dst->from;
struct inet6_dev *idev;
@@ -404,6 +409,11 @@ static void ip6_dst_destroy(struct dst_entry *dst)
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
+ bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1);
+ if (bucket) {
+ rt->rt6i_exception_bucket = NULL;
+ kfree(bucket);
+ }
dst->from = NULL;
dst_release(from);
@@ -1091,6 +1101,337 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
return pcpu_rt;
}
+/* exception hash table implementation
+ */
+static DEFINE_SPINLOCK(rt6_exception_lock);
+
+/* Remove rt6_ex from hash table and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
+ struct rt6_exception *rt6_ex)
+{
+ if (!bucket || !rt6_ex)
+ return;
+ rt6_ex->rt6i->rt6i_node = NULL;
+ hlist_del_rcu(&rt6_ex->hlist);
+ rt6_release(rt6_ex->rt6i);
+ kfree_rcu(rt6_ex, rcu);
+ WARN_ON_ONCE(!bucket->depth);
+ bucket->depth--;
+}
+
+/* Remove oldest rt6_ex in bucket and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket)
+{
+ struct rt6_exception *rt6_ex, *oldest = NULL;
+
+ if (!bucket)
+ return;
+
+ hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+ if (!oldest || time_before(rt6_ex->stamp, oldest->stamp))
+ oldest = rt6_ex;
+ }
+ rt6_remove_exception(bucket, oldest);
+}
+
+static u32 rt6_exception_hash(const struct in6_addr *dst,
+ const struct in6_addr *src)
+{
+ static u32 seed __read_mostly;
+ u32 val;
+
+ net_get_random_once(&seed, sizeof(seed));
+ val = jhash(dst, sizeof(*dst), seed);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ if (src)
+ val = jhash(src, sizeof(*src), val);
+#endif
+ return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rt6_exception_lock
+ */
+static struct rt6_exception *
+__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
+{
+ struct rt6_exception *rt6_ex;
+ u32 hval;
+
+ if (!(*bucket) || !daddr)
+ return NULL;
+
+ hval = rt6_exception_hash(daddr, saddr);
+ *bucket += hval;
+
+ hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) {
+ struct rt6_info *rt6 = rt6_ex->rt6i;
+ bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ if (matched && saddr)
+ matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+ if (matched)
+ return rt6_ex;
+ }
+ return NULL;
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rcu_read_lock()
+ */
+static struct rt6_exception *
+__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
+{
+ struct rt6_exception *rt6_ex;
+ u32 hval;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (!(*bucket) || !daddr)
+ return NULL;
+
+ hval = rt6_exception_hash(daddr, saddr);
+ *bucket += hval;
+
+ hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) {
+ struct rt6_info *rt6 = rt6_ex->rt6i;
+ bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ if (matched && saddr)
+ matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+ if (matched)
+ return rt6_ex;
+ }
+ return NULL;
+}
+
+static int rt6_insert_exception(struct rt6_info *nrt,
+ struct rt6_info *ort)
+{
+ struct rt6_exception_bucket *bucket;
+ struct in6_addr *src_key = NULL;
+ struct rt6_exception *rt6_ex;
+ int err = 0;
+
+ /* ort can't be a cache or pcpu route */
+ if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
+ ort = (struct rt6_info *)ort->dst.from;
+ WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
+
+ spin_lock_bh(&rt6_exception_lock);
+
+ if (ort->exception_bucket_flushed) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ bucket = rcu_dereference_protected(ort->rt6i_exception_bucket,
+ lockdep_is_held(&rt6_exception_lock));
+ if (!bucket) {
+ bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
+ GFP_ATOMIC);
+ if (!bucket) {
+ err = -ENOMEM;
+ goto out;
+ }
+ rcu_assign_pointer(ort->rt6i_exception_bucket, bucket);
+ }
+
+#ifdef CONFIG_IPV6_SUBTREES
+ /* rt6i_src.plen != 0 indicates ort is in subtree
+ * and exception table is indexed by a hash of
+ * both rt6i_dst and rt6i_src.
+ * Otherwise, the exception table is indexed by
+ * a hash of only rt6i_dst.
+ */
+ if (ort->rt6i_src.plen)
+ src_key = &nrt->rt6i_src.addr;
+#endif
+ rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
+ src_key);
+ if (rt6_ex)
+ rt6_remove_exception(bucket, rt6_ex);
+
+ rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC);
+ if (!rt6_ex) {
+ err = -ENOMEM;
+ goto out;
+ }
+ rt6_ex->rt6i = nrt;
+ rt6_ex->stamp = jiffies;
+ atomic_inc(&nrt->rt6i_ref);
+ nrt->rt6i_node = ort->rt6i_node;
+ hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
+ bucket->depth++;
+
+ if (bucket->depth > FIB6_MAX_DEPTH)
+ rt6_exception_remove_oldest(bucket);
+
+out:
+ spin_unlock_bh(&rt6_exception_lock);
+
+ /* Update fn->fn_sernum to invalidate all cached dst */
+ if (!err)
+ fib6_update_sernum(ort);
+
+ return err;
+}
+
+void rt6_flush_exceptions(struct rt6_info *rt)
+{
+ struct rt6_exception_bucket *bucket;
+ struct rt6_exception *rt6_ex;
+ struct hlist_node *tmp;
+ int i;
+
+ spin_lock_bh(&rt6_exception_lock);
+ /* Prevent rt6_insert_exception() to recreate the bucket list */
+ rt->exception_bucket_flushed = 1;
+
+ bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+ lockdep_is_held(&rt6_exception_lock));
+ if (!bucket)
+ goto out;
+
+ for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+ hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist)
+ rt6_remove_exception(bucket, rt6_ex);
+ WARN_ON_ONCE(bucket->depth);
+ bucket++;
+ }
+
+out:
+ spin_unlock_bh(&rt6_exception_lock);
+}
+
+/* Find cached rt in the hash table inside passed in rt
+ * Caller has to hold rcu_read_lock()
+ */
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+ struct in6_addr *daddr,
+ struct in6_addr *saddr)
+{
+ struct rt6_exception_bucket *bucket;
+ struct in6_addr *src_key = NULL;
+ struct rt6_exception *rt6_ex;
+ struct rt6_info *res = NULL;
+
+ bucket = rcu_dereference(rt->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ /* rt6i_src.plen != 0 indicates rt is in subtree
+ * and exception table is indexed by a hash of
+ * both rt6i_dst and rt6i_src.
+ * Otherwise, the exception table is indexed by
+ * a hash of only rt6i_dst.
+ */
+ if (rt->rt6i_src.plen)
+ src_key = saddr;
+#endif
+ rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
+
+ if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+ res = rt6_ex->rt6i;
+
+ return res;
+}
+
+/* Remove the passed in cached rt from the hash table that contains it */
+int rt6_remove_exception_rt(struct rt6_info *rt)
+{
+ struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+ struct rt6_exception_bucket *bucket;
+ struct in6_addr *src_key = NULL;
+ struct rt6_exception *rt6_ex;
+ int err;
+
+ if (!from ||
+ !(rt->rt6i_flags | RTF_CACHE))
+ return -EINVAL;
+
+ if (!rcu_access_pointer(from->rt6i_exception_bucket))
+ return -ENOENT;
+
+ spin_lock_bh(&rt6_exception_lock);
+ bucket = rcu_dereference_protected(from->rt6i_exception_bucket,
+ lockdep_is_held(&rt6_exception_lock));
+#ifdef CONFIG_IPV6_SUBTREES
+ /* rt6i_src.plen != 0 indicates 'from' is in subtree
+ * and exception table is indexed by a hash of
+ * both rt6i_dst and rt6i_src.
+ * Otherwise, the exception table is indexed by
+ * a hash of only rt6i_dst.
+ */
+ if (from->rt6i_src.plen)
+ src_key = &rt->rt6i_src.addr;
+#endif
+ rt6_ex = __rt6_find_exception_spinlock(&bucket,
+ &rt->rt6i_dst.addr,
+ src_key);
+ if (rt6_ex) {
+ rt6_remove_exception(bucket, rt6_ex);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+
+ spin_unlock_bh(&rt6_exception_lock);
+ return err;
+}
+
+/* Find rt6_ex which contains the passed in rt cache and
+ * refresh its stamp
+ */
+static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+{
+ struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+ struct rt6_exception_bucket *bucket;
+ struct in6_addr *src_key = NULL;
+ struct rt6_exception *rt6_ex;
+
+ if (!from ||
+ !(rt->rt6i_flags | RTF_CACHE))
+ return;
+
+ rcu_read_lock();
+ bucket = rcu_dereference(from->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ /* rt6i_src.plen != 0 indicates 'from' is in subtree
+ * and exception table is indexed by a hash of
+ * both rt6i_dst and rt6i_src.
+ * Otherwise, the exception table is indexed by
+ * a hash of only rt6i_dst.
+ */
+ if (from->rt6i_src.plen)
+ src_key = &rt->rt6i_src.addr;
+#endif
+ rt6_ex = __rt6_find_exception_rcu(&bucket,
+ &rt->rt6i_dst.addr,
+ src_key);
+ if (rt6_ex)
+ rt6_ex->stamp = jiffies;
+
+ rcu_read_unlock();
+}
+
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6, int flags)
{
--
2.14.2.920.gcf0c67979c-goog
^ permalink raw reply related
* [PATCH net-next 01/16] ipv6: introduce a new function fib6_update_sernum()
From: Wei Wang @ 2017-10-06 19:05 UTC (permalink / raw)
To: David Miller, netdev; +Cc: Eric Dumazet, Martin KaFai Lau, Wei Wang
In-Reply-To: <20171006190611.110633-1-tracywwnj@gmail.com>
From: Wei Wang <weiwan@google.com>
This function takes a route as input and tries to update the sernum in
the fib6_node this route is associated with. It will be used in later
commit when adding a cached route into the exception table under that
route.
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/ip6_fib.h | 2 ++
net/ipv6/ip6_fib.c | 14 ++++++++++++++
2 files changed, 16 insertions(+)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index d060d711a624..152b7b14a5a5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -358,6 +358,8 @@ void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
+void fib6_update_sernum(struct rt6_info *rt);
+
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
int fib6_rules_init(void);
void fib6_rules_cleanup(void);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e5308d7cbd75..0ba4fbb2f855 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -110,6 +110,20 @@ enum {
FIB6_NO_SERNUM_CHANGE = 0,
};
+void fib6_update_sernum(struct rt6_info *rt)
+{
+ struct fib6_table *table = rt->rt6i_table;
+ struct net *net = dev_net(rt->dst.dev);
+ struct fib6_node *fn;
+
+ write_lock_bh(&table->tb6_lock);
+ fn = rcu_dereference_protected(rt->rt6i_node,
+ lockdep_is_held(&table->tb6_lock));
+ if (fn)
+ fn->fn_sernum = fib6_new_sernum(net);
+ write_unlock_bh(&table->tb6_lock);
+}
+
/*
* Auxiliary address test functions for the radix tree.
*
--
2.14.2.920.gcf0c67979c-goog
^ permalink raw reply related
* [PATCH net-next 00/16] ipv6: replace rwlock with rcu and spinlock in fib6 table
From: Wei Wang @ 2017-10-06 19:05 UTC (permalink / raw)
To: David Miller, netdev; +Cc: Eric Dumazet, Martin KaFai Lau, Wei Wang
From: Wei Wang <weiwan@google.com>
Currently, fib6 table is protected by rwlock. During route lookup,
reader lock is taken and during route insertion, deletion or
modification, writer lock is taken. This is a very inefficient
implementation because the fastpath always has to do the operation
to grab the reader lock.
According to my latest syn flood test on an iota ivybridage machine
with 2 10G mlx nics bonded together, each with 8 rx queues on 2 NUMA
nodes, and with the upstream net-next kernel:
ipv4 stack can handle around 4.2Mpps
ipv6 stack can handle around 1.3Mpps
In order to close the gap of the performance number between ipv4
and ipv6 stack, this patch series tries to get rid of the usage of
the rwlock and replace it with rcu and spinlock protection. This will
greatly speed up the fastpath performance as it only needs to hold
rcu which is much less expensive than grabbing the reader lock. It
also makes ipv6 fib implementation more consistent with ipv4.
In order to be able to replace the current rwlock with rcu and
spinlock, some preparation work is needed:
Patch 1-8 introduces a per-route hash table (protected by rcu and a
different spinlock) to store all cached routes created by pmtu and ip
redirect under its main route. This makes the main fib6 tree only
contain static routes.
Patch 9-14 prepares all the reader path to be ready to tolerate
concurrent writer.
Patch 15 finally does the rwlock to rcu and spinlock conversion.
Patch 16 takes care of rt6_stats.
After this patch series, in the same syn flood test,
ipv6 stack can now handle around 3.5Mpps compared to previous 1.3Mpps
in my test setup.
After this patch series, there are still some improvements that should
be done in ipv6 stack:
1. During route lookup, dst_use() is called everytime on the selected
route to update dst->__use and dst->lastuse. This dirties the cacheline
and causes extra cacheline miss and should be avoided.
2. when no route is found in the current table, net->ip6.ipv6_null_entry
is used and refcnt is taken on it. As there is no pcpu cache for this
specific route, frequent change on the refcnt for this route causes
quite some cacheline misses.
And to make things worse, if CONFIG_IPV6_MULTIPLE_TABLES is defined,
output path route lookup always starts with local table first and
guarantees to hit net->ipv6.ip6_null_entry before continuing to do
lookup in the main table.
These operations on net->ipv6.ip6_null_entry could potentially be
avoided.
3. ipv6 input path route lookup grabs refcnt on dst. This is different
from ipv4. We could potentially change this behavior to let ipv6 input
path route lookup not to grab refcnt on dst. However, it does not give
us much performance boost as we currently have pcpu route cache for
input path as well in ipv6. But this work probably is still worth doing
to unify ipv6 and ipv4 route lookup behavior.
The above issues will be addressed separately after this patch series
has been accepted.
This is a joint work with Martin KaFai Lau and Eric Dumazet. And many
many thanks to them for their inspiring ideas and big big code review
efforts.
Wei Wang (16):
ipv6: introduce a new function fib6_update_sernum()
ipv6: introduce a hash table to store dst cache
ipv6: prepare fib6_remove_prefsrc() for exception table
ipv6: prepare rt6_mtu_change() for exception table
ipv6: prepare rt6_clean_tohost() for exception table
ipv6: prepare fib6_age() for exception table
ipv6: prepare fib6_locate() for exception table
ipv6: hook up exception table to store dst cache
ipv6: grab rt->rt6i_ref before allocating pcpu rt
ipv6: don't release rt->rt6i_pcpu memory during rt6_release()
ipv6: replace dst_hold() with dst_hold_safe() in routing code
ipv6: update fn_sernum after route is inserted to tree
ipv6: check fn->leaf before it is used
ipv6: add key length check into rt6_select()
ipv6: replace rwlock with rcu and spinlock in fib6_table
ipv6: take care of rt6_stats
include/net/dst.h | 2 +-
include/net/ip6_fib.h | 79 ++++-
include/net/ip6_route.h | 5 +
net/ipv6/addrconf.c | 17 +-
net/ipv6/ip6_fib.c | 645 ++++++++++++++++++----------------
net/ipv6/route.c | 901 ++++++++++++++++++++++++++++++++++++++++--------
6 files changed, 1179 insertions(+), 470 deletions(-)
--
2.14.2.920.gcf0c67979c-goog
^ permalink raw reply
* Re: [PATCH v2] isdn/gigaset: Convert timers to use timer_setup()
From: Paul Bolle @ 2017-10-06 19:00 UTC (permalink / raw)
To: Kees Cook
Cc: Karsten Keil, David S. Miller, Johan Hovold, linux-kernel,
gigaset307x-common, netdev
In-Reply-To: <20171005193118.GA105874@beast>
On Thu, 2017-10-05 at 12:31 -0700, Kees Cook wrote:
> --- a/drivers/isdn/gigaset/bas-gigaset.c
> +++ b/drivers/isdn/gigaset/bas-gigaset.c
> -static void cmd_in_timeout(unsigned long data)
> +static void cmd_in_timeout(struct timer_list *t)
> {
> - struct cardstate *cs = (struct cardstate *) data;
> - struct bas_cardstate *ucs = cs->hw.bas;
> + struct bas_cardstate *ucs = from_timer(ucs, t, timer_cmd_in);
> + struct urb *urb = ucs->urb_int_in;
> + struct cardstate *cs = urb->context;
This makes me nervous. Are you sure urb->context points to a struct cardstate
here and in the other two places this patch changes?
Anyhow, I'd like to have some time to do my review. So what's your timeframe
here? I do hope I have at least a few weeks. (In other words: I hope gigaset
isn't the only driver where the ability to use random pointers in these timer
callbacks is removed.)
Thanks,
Paul Bolle
^ permalink raw reply
* [PATCH net-next v5 3/3] bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports
From: Roopa Prabhu @ 2017-10-06 18:34 UTC (permalink / raw)
To: davem; +Cc: netdev, nikolay, stephen, makita.toshiaki, bridge
In-Reply-To: <1507314880-16310-1-git-send-email-roopa@cumulusnetworks.com>
From: Roopa Prabhu <roopa@cumulusnetworks.com>
This patch avoids flooding and proxies ndisc packets
for BR_NEIGH_SUPPRESS ports.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
net/bridge/br_arp_nd_proxy.c | 249 +++++++++++++++++++++++++++++++++++++++++++
net/bridge/br_device.c | 11 ++
net/bridge/br_input.c | 11 ++
net/bridge/br_private.h | 3 +
4 files changed, 274 insertions(+)
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index a79c182..6b7440d 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -21,6 +21,9 @@
#include <linux/if_vlan.h>
#include <linux/inetdevice.h>
#include <net/addrconf.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_checksum.h>
+#endif
#include "br_private.h"
@@ -218,3 +221,249 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
}
}
#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg)
+{
+ struct nd_msg *m;
+
+ m = skb_header_pointer(skb, skb_network_offset(skb) +
+ sizeof(struct ipv6hdr), sizeof(*msg), msg);
+ if (!m)
+ return NULL;
+
+ if (m->icmph.icmp6_code != 0 ||
+ (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION &&
+ m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT))
+ return NULL;
+
+ return m;
+}
+
+static void br_nd_send(struct net_bridge_port *p, struct sk_buff *request,
+ struct neighbour *n, __be16 vlan_proto, u16 vlan_tci,
+ struct nd_msg *ns)
+{
+ struct net_device *dev = request->dev;
+ struct sk_buff *reply;
+ struct nd_msg *na;
+ struct ipv6hdr *pip6;
+ u8 *daddr;
+ int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+ int ns_olen;
+ int i, len;
+
+ if (!dev)
+ return;
+
+ len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+ sizeof(*na) + na_olen + dev->needed_tailroom;
+
+ reply = alloc_skb(len, GFP_ATOMIC);
+ if (!reply)
+ return;
+
+ reply->protocol = htons(ETH_P_IPV6);
+ reply->dev = dev;
+ skb_reserve(reply, LL_RESERVED_SPACE(dev));
+ skb_push(reply, sizeof(struct ethhdr));
+ skb_set_mac_header(reply, 0);
+
+ daddr = eth_hdr(request)->h_source;
+
+ /* Do we need option processing ? */
+ ns_olen = request->len - (skb_network_offset(request) +
+ sizeof(struct ipv6hdr)) - sizeof(*ns);
+ for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+ if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+ daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+ break;
+ }
+ }
+
+ /* Ethernet header */
+ ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+ ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+ eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+ reply->protocol = htons(ETH_P_IPV6);
+
+ skb_pull(reply, sizeof(struct ethhdr));
+ skb_set_network_header(reply, 0);
+ skb_put(reply, sizeof(struct ipv6hdr));
+
+ /* IPv6 header */
+ pip6 = ipv6_hdr(reply);
+ memset(pip6, 0, sizeof(struct ipv6hdr));
+ pip6->version = 6;
+ pip6->priority = ipv6_hdr(request)->priority;
+ pip6->nexthdr = IPPROTO_ICMPV6;
+ pip6->hop_limit = 255;
+ pip6->daddr = ipv6_hdr(request)->saddr;
+ pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+ skb_pull(reply, sizeof(struct ipv6hdr));
+ skb_set_transport_header(reply, 0);
+
+ na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+ /* Neighbor Advertisement */
+ memset(na, 0, sizeof(*na) + na_olen);
+ na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */
+ na->icmph.icmp6_override = 1;
+ na->icmph.icmp6_solicited = 1;
+ na->target = ns->target;
+ ether_addr_copy(&na->opt[2], n->ha);
+ na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+ na->opt[1] = na_olen >> 3;
+
+ na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+ &pip6->daddr,
+ sizeof(*na) + na_olen,
+ IPPROTO_ICMPV6,
+ csum_partial(na, sizeof(*na) + na_olen, 0));
+
+ pip6->payload_len = htons(sizeof(*na) + na_olen);
+
+ skb_push(reply, sizeof(struct ipv6hdr));
+ skb_push(reply, sizeof(struct ethhdr));
+
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+ if (p) {
+ struct net_bridge_vlan_group *vg;
+ u16 pvid;
+
+ vg = nbp_vlan_group_rcu(p);
+ pvid = br_get_pvid(vg);
+ if (pvid && pvid == vlan_tci)
+ vlan_tci = 0;
+ }
+
+ if (vlan_tci != 0) {
+ reply = vlan_insert_tag_set_proto(reply, vlan_proto, vlan_tci);
+ if (!reply) {
+ net_err_ratelimited("evpn: failed to insert VLAN tag\n");
+ return;
+ }
+ }
+
+ netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n",
+ dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha);
+
+ dev_queue_xmit(reply);
+}
+
+static int br_chk_addr_ip6(struct net_device *dev, void *data)
+{
+ struct in6_addr *addr = (struct in6_addr *)data;
+
+ if (ipv6_chk_addr(dev_net(dev), addr, dev, 0))
+ return 1;
+
+ return 0;
+}
+
+static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr)
+
+{
+ if (br_chk_addr_ip6(dev, addr))
+ return true;
+
+ /* check if ip is configured on upper dev */
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr))
+ return true;
+
+ return false;
+}
+
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p, struct nd_msg *msg)
+{
+ struct net_device *dev = br->dev;
+ struct net_device *vlandev = NULL;
+ struct in6_addr *saddr, *daddr;
+ struct ipv6hdr *iphdr;
+ struct inet6_dev *in6_dev;
+ struct neighbour *n;
+
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+ if (p && (p->flags & BR_NEIGH_SUPPRESS))
+ return;
+
+ if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
+ !msg->icmph.icmp6_solicited) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
+ return;
+
+ in6_dev = __in6_dev_get(dev);
+ if (!in6_dev)
+ return;
+
+ iphdr = ipv6_hdr(skb);
+ saddr = &iphdr->saddr;
+ daddr = &iphdr->daddr;
+
+ if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ if (vid != 0) {
+ /* build neigh table lookup on the vlan device */
+ vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+ vid);
+ if (!vlandev)
+ return;
+ } else {
+ vlandev = dev;
+ }
+
+ if (br_is_local_ip6(vlandev, &msg->target)) {
+ /* its our own ip, so don't proxy reply
+ * and don't forward to arp suppress ports
+ */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev);
+ if (n) {
+ struct net_bridge_fdb_entry *f;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_release(n);
+ return;
+ }
+
+ f = br_fdb_find_rcu(br, n->ha, vid);
+ if (f) {
+ bool replied = false;
+
+ if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) {
+ if (vid != 0)
+ br_nd_send(p, skb, n, skb->vlan_proto,
+ skb_vlan_tag_get(skb), msg);
+ else
+ br_nd_send(p, skb, n, 0, 0, msg);
+ replied = true;
+ }
+
+ /* If we have replied or as long as we know the
+ * mac, indicate to NEIGH_SUPPRESS ports that we
+ * have replied
+ */
+ if (replied || br->neigh_suppress_enabled)
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ }
+ neigh_release(n);
+ }
+}
+#endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index eb30c6a..28bb221 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -69,6 +69,17 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
eth->h_proto == htons(ETH_P_RARP)) &&
br->neigh_suppress_enabled) {
br_do_proxy_suppress_arp(skb, br, vid, NULL);
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6) &&
+ br->neigh_suppress_enabled &&
+ pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+ sizeof(struct nd_msg)) &&
+ ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+ struct nd_msg *msg, _msg;
+
+ msg = br_is_nd_neigh_msg(skb, &_msg);
+ if (msg)
+ br_do_suppress_nd(skb, br, vid, NULL, msg);
}
dest = eth_hdr(skb)->h_dest;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 4b8d2ec..a096d3e 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -119,6 +119,17 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
(skb->protocol == htons(ETH_P_ARP) ||
skb->protocol == htons(ETH_P_RARP))) {
br_do_proxy_suppress_arp(skb, br, vid, p);
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6) &&
+ br->neigh_suppress_enabled &&
+ pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+ sizeof(struct nd_msg)) &&
+ ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+ struct nd_msg *msg, _msg;
+
+ msg = br_is_nd_neigh_msg(skb, &_msg);
+ if (msg)
+ br_do_suppress_nd(skb, br, vid, p, msg);
}
switch (pkt_type) {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 4e6b25b..fa0039f 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1144,4 +1144,7 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
u16 vid, struct net_bridge_port *p);
+void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p, struct nd_msg *msg);
+struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m);
#endif
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v5 2/3] bridge: suppress arp pkts on BR_NEIGH_SUPPRESS ports
From: Roopa Prabhu @ 2017-10-06 18:34 UTC (permalink / raw)
To: davem; +Cc: netdev, nikolay, stephen, makita.toshiaki, bridge
In-Reply-To: <1507314880-16310-1-git-send-email-roopa@cumulusnetworks.com>
From: Roopa Prabhu <roopa@cumulusnetworks.com>
This patch avoids flooding and proxies arp packets
for BR_NEIGH_SUPPRESS ports.
Moves existing br_do_proxy_arp to br_do_proxy_suppress_arp
to support both proxy arp and neigh suppress.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
net/bridge/br_arp_nd_proxy.c | 188 +++++++++++++++++++++++++++++++++++++++++++
net/bridge/br_device.c | 9 +++
net/bridge/br_input.c | 63 ++-------------
net/bridge/br_private.h | 3 +
4 files changed, 205 insertions(+), 58 deletions(-)
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index f889ad5..a79c182 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -14,6 +14,14 @@
*/
#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
+#include <linux/if_vlan.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+
#include "br_private.h"
void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
@@ -30,3 +38,183 @@ void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
br->neigh_suppress_enabled = neigh_suppress;
}
+
+#if IS_ENABLED(CONFIG_INET)
+static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p,
+ struct net_device *dev, __be32 dest_ip, __be32 src_ip,
+ const unsigned char *dest_hw,
+ const unsigned char *src_hw,
+ const unsigned char *target_hw,
+ __be16 vlan_proto, u16 vlan_tci)
+{
+ struct net_bridge_vlan_group *vg;
+ struct sk_buff *skb;
+ u16 pvid;
+
+ netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n",
+ dev->name, &dest_ip, dest_hw, &src_ip, src_hw);
+
+ if (!vlan_tci) {
+ arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+ dest_hw, src_hw, target_hw);
+ return;
+ }
+
+ skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip,
+ dest_hw, src_hw, target_hw);
+ if (!skb)
+ return;
+
+ if (p)
+ vg = nbp_vlan_group_rcu(p);
+ else
+ vg = br_vlan_group_rcu(br);
+ pvid = br_get_pvid(vg);
+ if (pvid == (vlan_tci & VLAN_VID_MASK))
+ vlan_tci = 0;
+
+ if (vlan_tci)
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+
+ if (p) {
+ arp_xmit(skb);
+ } else {
+ skb_reset_mac_header(skb);
+ __skb_pull(skb, skb_network_offset(skb));
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->pkt_type = PACKET_HOST;
+
+ netif_rx_ni(skb);
+ }
+}
+
+static int br_chk_addr_ip(struct net_device *dev, void *data)
+{
+ __be32 ip = *(__be32 *)data;
+ struct in_device *in_dev;
+ __be32 addr = 0;
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev)
+ addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip,
+ RT_SCOPE_HOST);
+
+ if (addr == ip)
+ return 1;
+
+ return 0;
+}
+
+static bool br_is_local_ip(struct net_device *dev, __be32 ip)
+{
+ if (br_chk_addr_ip(dev, &ip))
+ return true;
+
+ /* check if ip is configured on upper dev */
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip))
+ return true;
+
+ return false;
+}
+
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p)
+{
+ struct net_device *dev = br->dev;
+ struct net_device *vlandev = dev;
+ struct neighbour *n;
+ struct arphdr *parp;
+ u8 *arpptr, *sha;
+ __be32 sip, tip;
+
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+ if ((dev->flags & IFF_NOARP) ||
+ !pskb_may_pull(skb, arp_hdr_len(dev)))
+ return;
+
+ parp = arp_hdr(skb);
+
+ if (parp->ar_pro != htons(ETH_P_IP) ||
+ parp->ar_hln != dev->addr_len ||
+ parp->ar_pln != 4)
+ return;
+
+ arpptr = (u8 *)parp + sizeof(struct arphdr);
+ sha = arpptr;
+ arpptr += dev->addr_len; /* sha */
+ memcpy(&sip, arpptr, sizeof(sip));
+ arpptr += sizeof(sip);
+ arpptr += dev->addr_len; /* tha */
+ memcpy(&tip, arpptr, sizeof(tip));
+
+ if (ipv4_is_loopback(tip) ||
+ ipv4_is_multicast(tip))
+ return;
+
+ if (br->neigh_suppress_enabled) {
+ if (p && (p->flags & BR_NEIGH_SUPPRESS))
+ return;
+ if (ipv4_is_zeronet(sip) || sip == tip) {
+ /* prevent flooding to neigh suppress ports */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+ }
+
+ if (parp->ar_op != htons(ARPOP_REQUEST))
+ return;
+
+ if (vid != 0) {
+ vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto,
+ vid);
+ if (!vlandev)
+ return;
+ }
+
+ if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) {
+ /* its our local ip, so don't proxy reply
+ * and don't forward to neigh suppress ports
+ */
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ return;
+ }
+
+ n = neigh_lookup(&arp_tbl, &tip, vlandev);
+ if (n) {
+ struct net_bridge_fdb_entry *f;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ neigh_release(n);
+ return;
+ }
+
+ f = br_fdb_find_rcu(br, n->ha, vid);
+ if (f) {
+ bool replied = false;
+
+ if ((p && (p->flags & BR_PROXYARP)) ||
+ (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI |
+ BR_NEIGH_SUPPRESS)))) {
+ if (!vid)
+ br_arp_send(br, p, skb->dev, sip, tip,
+ sha, n->ha, sha, 0, 0);
+ else
+ br_arp_send(br, p, skb->dev, sip, tip,
+ sha, n->ha, sha,
+ skb->vlan_proto,
+ skb_vlan_tag_get(skb));
+ replied = true;
+ }
+
+ /* If we have replied or as long as we know the
+ * mac, indicate to arp replied
+ */
+ if (replied || br->neigh_suppress_enabled)
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ }
+
+ neigh_release(n);
+ }
+}
+#endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 7acb77c..eb30c6a 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
const struct nf_br_ops *nf_ops;
const unsigned char *dest;
+ struct ethhdr *eth;
u16 vid = 0;
rcu_read_lock();
@@ -57,11 +58,19 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
+ eth = eth_hdr(skb);
skb_pull(skb, ETH_HLEN);
if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
+ if (IS_ENABLED(CONFIG_INET) &&
+ (eth->h_proto == htons(ETH_P_ARP) ||
+ eth->h_proto == htons(ETH_P_RARP)) &&
+ br->neigh_suppress_enabled) {
+ br_do_proxy_suppress_arp(skb, br, vid, NULL);
+ }
+
dest = eth_hdr(skb)->h_dest;
if (is_broadcast_ether_addr(dest)) {
br_flood(br, skb, BR_PKT_BROADCAST, false, true);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7cb6137..4b8d2ec 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb)
br_netif_receive_skb);
}
-static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
- u16 vid, struct net_bridge_port *p)
-{
- struct net_device *dev = br->dev;
- struct neighbour *n;
- struct arphdr *parp;
- u8 *arpptr, *sha;
- __be32 sip, tip;
-
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
-
- if ((dev->flags & IFF_NOARP) ||
- !pskb_may_pull(skb, arp_hdr_len(dev)))
- return;
-
- parp = arp_hdr(skb);
-
- if (parp->ar_pro != htons(ETH_P_IP) ||
- parp->ar_op != htons(ARPOP_REQUEST) ||
- parp->ar_hln != dev->addr_len ||
- parp->ar_pln != 4)
- return;
-
- arpptr = (u8 *)parp + sizeof(struct arphdr);
- sha = arpptr;
- arpptr += dev->addr_len; /* sha */
- memcpy(&sip, arpptr, sizeof(sip));
- arpptr += sizeof(sip);
- arpptr += dev->addr_len; /* tha */
- memcpy(&tip, arpptr, sizeof(tip));
-
- if (ipv4_is_loopback(tip) ||
- ipv4_is_multicast(tip))
- return;
-
- n = neigh_lookup(&arp_tbl, &tip, dev);
- if (n) {
- struct net_bridge_fdb_entry *f;
-
- if (!(n->nud_state & NUD_VALID)) {
- neigh_release(n);
- return;
- }
-
- f = br_fdb_find_rcu(br, n->ha, vid);
- if (f && ((p->flags & BR_PROXYARP) ||
- (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
- arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
- sha, n->ha, sha);
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
- }
-
- neigh_release(n);
- }
-}
-
/* note: already called with rcu_read_lock */
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -171,8 +115,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
BR_INPUT_SKB_CB(skb)->brdev = br->dev;
- if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
- br_do_proxy_arp(skb, br, vid, p);
+ if (IS_ENABLED(CONFIG_INET) &&
+ (skb->protocol == htons(ETH_P_ARP) ||
+ skb->protocol == htons(ETH_P_RARP))) {
+ br_do_proxy_suppress_arp(skb, br, vid, p);
+ }
switch (pkt_type) {
case BR_PKT_MULTICAST:
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 00fa371..4e6b25b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1140,5 +1140,8 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
}
#endif /* CONFIG_NET_SWITCHDEV */
+/* br_arp_nd_proxy.c */
void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
+void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
+ u16 vid, struct net_bridge_port *p);
#endif
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v5 1/3] bridge: add new BR_NEIGH_SUPPRESS port flag to suppress arp and nd flood
From: Roopa Prabhu @ 2017-10-06 18:34 UTC (permalink / raw)
To: davem; +Cc: netdev, nikolay, stephen, makita.toshiaki, bridge
In-Reply-To: <1507314880-16310-1-git-send-email-roopa@cumulusnetworks.com>
From: Roopa Prabhu <roopa@cumulusnetworks.com>
This patch adds a new bridge port flag BR_NEIGH_SUPPRESS to
suppress arp and nd flood on bridge ports. It implements
rfc7432, section 10.
https://tools.ietf.org/html/rfc7432#section-10
for ethernet VPN deployments. It is similar to the existing
BR_PROXYARP* flags but has a few semantic differences to conform
to EVPN standard. Unlike the existing flags, this new flag suppresses
flood of all neigh discovery packets (arp and nd) to tunnel ports.
Supports both vlan filtering and non-vlan filtering bridges.
In case of EVPN, it is mainly used to avoid flooding
of arp and nd packets to tunnel ports like vxlan.
This patch adds netlink and sysfs support to set this bridge port
flag.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
include/linux/if_bridge.h | 1 +
include/uapi/linux/if_link.h | 1 +
net/bridge/Makefile | 2 +-
net/bridge/br_arp_nd_proxy.c | 32 ++++++++++++++++++++++++++++++++
net/bridge/br_forward.c | 2 +-
net/bridge/br_if.c | 5 +++++
net/bridge/br_netlink.c | 10 +++++++++-
net/bridge/br_private.h | 2 ++
net/bridge/br_sysfs_if.c | 2 ++
9 files changed, 54 insertions(+), 3 deletions(-)
create mode 100644 net/bridge/br_arp_nd_proxy.c
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3cd18ac..316ee11 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -49,6 +49,7 @@ struct br_ip_list {
#define BR_MULTICAST_TO_UNICAST BIT(12)
#define BR_VLAN_TUNNEL BIT(13)
#define BR_BCAST_FLOOD BIT(14)
+#define BR_NEIGH_SUPPRESS BIT(15)
#define BR_DEFAULT_AGEING_TIME (300 * HZ)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cd580fc..b037e0a 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -327,6 +327,7 @@ enum {
IFLA_BRPORT_VLAN_TUNNEL,
IFLA_BRPORT_BCAST_FLOOD,
IFLA_BRPORT_GROUP_FWD_MASK,
+ IFLA_BRPORT_NEIGH_SUPPRESS,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index 40b1ede..4aee55f 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o
bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
br_ioctl.o br_stp.o br_stp_bpdu.o \
br_stp_if.o br_stp_timer.o br_netlink.o \
- br_netlink_tunnel.o
+ br_netlink_tunnel.o br_arp_nd_proxy.o
bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
new file mode 100644
index 0000000..f889ad5
--- /dev/null
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -0,0 +1,32 @@
+/*
+ * Handle bridge arp/nd proxy/suppress
+ *
+ * Copyright (C) 2017 Cumulus Networks
+ * Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * Authors:
+ * Roopa Prabhu <roopa@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 the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include "br_private.h"
+
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br)
+{
+ struct net_bridge_port *p;
+ bool neigh_suppress = false;
+
+ list_for_each_entry(p, &br->port_list, list) {
+ if (p->flags & BR_NEIGH_SUPPRESS) {
+ neigh_suppress = true;
+ break;
+ }
+ }
+
+ br->neigh_suppress_enabled = neigh_suppress;
+}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 48fb174..b4eed11 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
/* Do not flood to ports that enable proxy ARP */
if (p->flags & BR_PROXYARP)
continue;
- if ((p->flags & BR_PROXYARP_WIFI) &&
+ if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
continue;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 59a74a4..ae38547 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
del_nbp(p);
}
+ br_recalculate_neigh_suppress_enabled(br);
+
br_fdb_delete_by_port(br, NULL, 0, 1);
cancel_delayed_work_sync(&br->gc_work);
@@ -660,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
if (mask & BR_AUTO_MASK)
nbp_update_port_count(br);
+
+ if (mask & BR_NEIGH_SUPPRESS)
+ br_recalculate_neigh_suppress_enabled(br);
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index dea88a2..f0e8268 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
+ nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */
+ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */
@@ -210,7 +211,9 @@ static int br_port_fill_attrs(struct sk_buff *skb,
nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) ||
nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags &
BR_VLAN_TUNNEL)) ||
- nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask))
+ nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) ||
+ nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS,
+ !!(p->flags & BR_NEIGH_SUPPRESS)))
return -EMSGSIZE;
timerval = br_timer_value(&p->message_age_timer);
@@ -785,6 +788,11 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
p->group_fwd_mask = fwd_mask;
}
+ err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS,
+ BR_NEIGH_SUPPRESS);
+ if (err)
+ return err;
+
br_port_flags_change(p, old_flags ^ p->flags);
return 0;
}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index ab4df24..00fa371 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -404,6 +404,7 @@ struct net_bridge {
#ifdef CONFIG_NET_SWITCHDEV
int offload_fwd_mark;
#endif
+ bool neigh_suppress_enabled;
};
struct br_input_skb_cb {
@@ -1139,4 +1140,5 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
}
#endif /* CONFIG_NET_SWITCHDEV */
+void br_recalculate_neigh_suppress_enabled(struct net_bridge *br);
#endif
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 9110d5e..0a1fa9c 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -191,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI);
BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD);
BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD);
+BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -241,6 +242,7 @@ static const struct brport_attribute *brport_attrs[] = {
&brport_attr_multicast_flood,
&brport_attr_broadcast_flood,
&brport_attr_group_fwd_mask,
+ &brport_attr_neigh_suppress,
NULL
};
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v5 0/3] bridge: neigh msg proxy and flood suppression support
From: Roopa Prabhu @ 2017-10-06 18:34 UTC (permalink / raw)
To: davem; +Cc: netdev, nikolay, stephen, makita.toshiaki, bridge
From: Roopa Prabhu <roopa@cumulusnetworks.com>
This series implements arp and nd suppression in the bridge
driver for ethernet vpns. It implements rfc7432, section 10
https://tools.ietf.org/html/rfc7432#section-10
for ethernet VPN deployments. It is similar to the existing
BR_PROXYARP* flags but has a few semantic differences to conform
to EVPN standard. Unlike the existing flags, this new flag suppresses
flood of all neigh discovery packets (arp and nd) to tunnel ports.
Supports both vlan filtering and non-vlan filtering bridges.
In case of EVPN, it is mainly used to avoid flooding
of arp and nd packets to tunnel ports like vxlan.
v2 : rebase to latest + address some optimization feedback from Nikolay.
v3 : fix kbuild reported build errors with CONFIG_INET off
v4 : simplify port flag mask as suggested by stephen
v5 : address some feedback from Toshiaki
Roopa Prabhu (3):
bridge: add new BR_NEIGH_SUPPRESS port flag to suppress arp and nd
flood
neigh arp suppress first
bridge: suppress nd messages from going to BR_NEIGH_SUPPRESS ports
include/linux/if_bridge.h | 1 +
include/uapi/linux/if_link.h | 1 +
net/bridge/Makefile | 2 +-
net/bridge/br_arp_nd_proxy.c | 492 +++++++++++++++++++++++++++++++++++++++++++
net/bridge/br_device.c | 18 ++
net/bridge/br_forward.c | 3 +-
net/bridge/br_if.c | 5 +
net/bridge/br_input.c | 73 ++-----
net/bridge/br_netlink.c | 16 +-
net/bridge/br_private.h | 9 +
net/bridge/br_sysfs_if.c | 2 +
11 files changed, 561 insertions(+), 61 deletions(-)
create mode 100644 net/bridge/br_arp_nd_proxy.c
--
2.1.4
^ permalink raw reply
* Re: [patch net-next 2/2] mlxsw: spectrum: Propagate extack further for bridge enslavements
From: David Ahern @ 2017-10-06 18:24 UTC (permalink / raw)
To: Jiri Pirko, netdev; +Cc: davem, idosch, mlxsw
In-Reply-To: <20171005214000.14022-3-jiri@resnulli.us>
On 10/5/17 3:40 PM, Jiri Pirko wrote:
> From: Ido Schimmel <idosch@mellanox.com>
>
> The code that actually takes care of bridge offload introduces a few
> more non-trivial constraints with regards to bridge enslavements.
> Propagate extack there to indicate the reason.
>
> $ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10
> $ ip link add link enp1s0np1 name enp1s0np1.20 type vlan id 20
> $ ip link add name br0 type bridge
> $ ip link set dev enp1s0np1.10 master br0
> $ ip link set dev enp1s0np1.20 master br0
> Error: spectrum: Can not bridge VLAN uppers of the same port.
>
> Signed-off-by: Ido Schimmel <idosch@mellanox.com>
> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
> ---
> drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++++--
> drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 3 ++-
> .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 25 +++++++++++++++-------
> 3 files changed, 23 insertions(+), 11 deletions(-)
Acked-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [patch net-next 1/2] mlxsw: spectrum: Add extack for VLAN enslavements
From: David Ahern @ 2017-10-06 18:24 UTC (permalink / raw)
To: Jiri Pirko, netdev; +Cc: davem, idosch, mlxsw
In-Reply-To: <20171005214000.14022-2-jiri@resnulli.us>
On 10/5/17 3:39 PM, Jiri Pirko wrote:
> From: Ido Schimmel <idosch@mellanox.com>
>
> Similar to physical ports, enslavement of VLAN devices can also fail.
> Use extack to indicate why the enslavement failed.
>
> $ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10
> $ ip link add name bond0 type bond mode 802.3ad
> $ ip link set dev enp1s0np1.10 master bond0
> Error: spectrum: VLAN devices only support bridge and VRF uppers.
>
> Signed-off-by: Ido Schimmel <idosch@mellanox.com>
> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
> ---
> drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 12 ++++++++++--
> 1 file changed, 10 insertions(+), 2 deletions(-)
Acked-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH net] bpf: fix liveness marking
From: Daniel Borkmann @ 2017-10-06 18:20 UTC (permalink / raw)
To: Alexei Starovoitov, David S . Miller; +Cc: Edward Cree, netdev, kernel-team
In-Reply-To: <20171005232056.2234669-1-ast@fb.com>
On 10/06/2017 01:20 AM, Alexei Starovoitov wrote:
> while processing Rx = Ry instruction the verifier does
> regs[insn->dst_reg] = regs[insn->src_reg]
> which often clears write mark (when Ry doesn't have it)
> that was just set by check_reg_arg(Rx) prior to the assignment.
> That causes mark_reg_read() to keep marking Rx in this block as
> REG_LIVE_READ (since the logic incorrectly misses that it's
> screened by the write) and in many of its parents (until lucky
> write into the same Rx or beginning of the program).
> That causes is_state_visited() logic to miss many pruning opportunities.
>
> Furthermore mark_reg_read() logic propagates the read mark
> for BPF_REG_FP as well (though it's readonly) which causes
> harmless but unnecssary work during is_state_visited().
> Note that do_propagate_liveness() skips FP correctly,
> so do the same in mark_reg_read() as well.
> It saves 0.2 seconds for the test below
>
> program before after
> bpf_lb-DLB_L3.o 2604 2304
> bpf_lb-DLB_L4.o 11159 3723
> bpf_lb-DUNKNOWN.o 1116 1110
> bpf_lxc-DDROP_ALL.o 34566 28004
> bpf_lxc-DUNKNOWN.o 53267 39026
> bpf_netdev.o 17843 16943
> bpf_overlay.o 8672 7929
> time ~11 sec ~4 sec
>
> Fixes: dc503a8ad984 ("bpf/verifier: track liveness for pruning")
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
LGTM, thanks!
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [Intel-wired-lan] [PATCH] PCI: Check/Set ARI capability before setting numVFs
From: Bjorn Helgaas @ 2017-10-06 18:19 UTC (permalink / raw)
To: Alexander Duyck
Cc: Tony Nguyen, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org, intel-wired-lan, Netdev,
Bjorn Helgaas
In-Reply-To: <20171005195959.GW25517@bhelgaas-glaptop.roam.corp.google.com>
On Thu, Oct 05, 2017 at 04:07:41PM -0500, Bjorn Helgaas wrote:
> On Wed, Oct 04, 2017 at 04:29:14PM -0700, Alexander Duyck wrote:
> > On Wed, Oct 4, 2017 at 4:01 PM, Bjorn Helgaas <helgaas@kernel.org> wrote:
> > > On Wed, Oct 04, 2017 at 08:52:58AM -0700, Tony Nguyen wrote:
> > >> This fixes a bug that can occur if an AER error is encountered while SRIOV
> > >> devices are present.
I applied the patch below with Alex's ack to pci/virtualization for v4.15.
> commit 95594dedd443e42ab0c16b9fba0109e955e7be13
> Author: Tony Nguyen <anthony.l.nguyen@intel.com>
> Date: Wed Oct 4 08:52:58 2017 -0700
>
> PCI: Restore "ARI Capable Hierarchy" before setting numVFs
>
> In the restore path, we previously read PCI_SRIOV_VF_OFFSET and
> PCI_SRIOV_VF_STRIDE before restoring PCI_SRIOV_CTRL_ARI, which
> affects the offset and stride:
>
> pci_restore_state
> pci_restore_iov_state
> sriov_restore_state
> pci_iov_set_numvfs
> pci_read_config_word(... PCI_SRIOV_VF_OFFSET, &iov->offset)
> pci_write_config_word(... PCI_SRIOV_CTRL, iov->ctrl)
>
> The effect is that suspend/resume and AER recovery, which use
> pci_restore_state(), may corrupt iov->offset and iov->stride. The iov
> state is associated with the device, not the driver, so if we reload the
> driver, it will use the the corrupted data, which may cause crashes like
> this:
>
> kernel BUG at drivers/pci/iov.c:157!
> RIP: 0010:pci_iov_add_virtfn+0x2eb/0x350
> Call Trace:
> pci_enable_sriov+0x353/0x440
> ixgbe_pci_sriov_configure+0xd5/0x1f0 [ixgbe]
> sriov_numvfs_store+0xf7/0x170
> dev_attr_store+0x18/0x30
> sysfs_kf_write+0x37/0x40
> kernfs_fop_write+0x120/0x1b0
> vfs_write+0xb5/0x1a0
> SyS_write+0x55/0xc0
>
> The occurs since during AER recovery the ARI Capable Hierarchy bit, which
> can affect the values for First VF Offset and VF Stride, is not set until
> after pci_iov_set_numvfs() is called. This can cause the iov structure to
> be populated with values that are incorrect if the bit is later set.
> Check and set this bit, if needed, before calling pci_iov_set_numvfs() so
> that the values being populated properly take the ARI bit into account.
>
> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
> [bhelgaas: changelog, add comment, also clear ARI if necessary]
> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
> CC: Alexander Duyck <alexander.h.duyck@intel.com>
> CC: Emil Tantilov <emil.s.tantilov@intel.com>
>
> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> index ce24cf235f01..6bacb8995e96 100644
> --- a/drivers/pci/iov.c
> +++ b/drivers/pci/iov.c
> @@ -498,6 +498,14 @@ static void sriov_restore_state(struct pci_dev *dev)
> if (ctrl & PCI_SRIOV_CTRL_VFE)
> return;
>
> + /*
> + * Restore PCI_SRIOV_CTRL_ARI before pci_iov_set_numvfs() because
> + * it reads offset & stride, which depend on PCI_SRIOV_CTRL_ARI.
> + */
> + ctrl &= ~PCI_SRIOV_CTRL_ARI;
> + ctrl |= iov->ctrl & PCI_SRIOV_CTRL_ARI;
> + pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, ctrl);
> +
> for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++)
> pci_update_resource(dev, i);
>
^ permalink raw reply
* Re: [PATCH net] net: enable interface alias removal via rtnl
From: David Ahern @ 2017-10-06 18:18 UTC (permalink / raw)
To: Nicolas Dichtel, davem; +Cc: netdev, Oliver Hartkopp, Stephen Hemminger
In-Reply-To: <20171005101940.28550-1-nicolas.dichtel@6wind.com>
On 10/5/17 4:19 AM, Nicolas Dichtel wrote:
> IFLA_IFALIAS is defined as NLA_STRING. It means that the minimal length of
> the attribute is 1 ("\0"). However, to remove an alias, the attribute
> length must be 0 (see dev_set_alias()).
why not add a check in dev_set_alias that if len is 1 and the 1
character is '\0' it means remove the alias?
>
> Let's define the type to NLA_BINARY, so that the alias can be removed.
that changes the uapi
^ permalink raw reply
* Re: [PATCH net-next 1/1] [net] bonding: Add NUMA notice
From: Eric Dumazet @ 2017-10-06 18:08 UTC (permalink / raw)
To: Patrick Talbert; +Cc: Andrew Lunn, netdev
In-Reply-To: <CAPRrrxUGMpOqEA8MxzY91RyMTQp+OisO8xB5jVR+QA+dqLeSww@mail.gmail.com>
On Fri, 2017-10-06 at 13:54 -0400, Patrick Talbert wrote:
>
> My goal with the patch is not to prevent some one from bonding
> whichever interfaces they want, only to notify them that what they are
> doing is *likely* to be less than ideal from a performance
> perspective. Even if some theoretical load balancing bonding mode was
> intelligent enough to consider NUMA when choosing a transmit
> interface, it never has control over the interface traffic is received
> on (excluding the strange balance-alb mode).
Note that following the NUMA node of current process would lead to
reordering for TCP flows.
XPS makes sure we stick to one TXQ to avoid reorders.
I am not sure your patch will really help, since you do not warn if a
process from another NUMA node tries to send packet to a bonding driver
using slaves on another NUMA node.
^ permalink raw reply
* [net-next 12/15] i40e: do not enter PHY debug mode while setting LEDs behaviour
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Mariusz Stachura, netdev, nhorman, sassmann, jogreene,
Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Mariusz Stachura <mariusz.stachura@intel.com>
Previous implementation of LED set/get functions required to enter
PHY debug mode, in order to prevent access to it from FW and SW at
the same time. Reset of all ports was a unwanted side effect.
Signed-off-by: Mariusz Stachura <mariusz.stachura@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 6203d362438c..de0dfe340494 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2010,7 +2010,9 @@ static int i40e_set_phys_id(struct net_device *netdev,
if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) {
pf->led_status = i40e_led_get(hw);
} else {
- i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL);
+ if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+ i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL,
+ NULL);
ret = i40e_led_get_phy(hw, &temp_status,
&pf->phy_led_val);
pf->led_status = temp_status;
@@ -2035,7 +2037,8 @@ static int i40e_set_phys_id(struct net_device *netdev,
ret = i40e_led_set_phy(hw, false, pf->led_status,
(pf->phy_led_val |
I40E_PHY_LED_MODE_ORIG));
- i40e_aq_set_phy_debug(hw, 0, NULL);
+ if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE))
+ i40e_aq_set_phy_debug(hw, 0, NULL);
}
break;
default:
--
2.14.2
^ permalink raw reply related
* [net-next 14/15] i40e: ignore skb->xmit_more when deciding to set RS bit
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
Since commit 6a7fded776a7 ("i40e: Fix RS bit update in Tx path and
disable force WB workaround") we've tried to "optimize" setting the
RS bit based around skb->xmit_more. This same logic was refactored
in commit 1dc8b538795f ("i40e: Reorder logic for coalescing RS bits"),
but ultimately was not functionally changed.
Using skb->xmit_more in this way is incorrect, because in certain
circumstances we may see a large number of skbs in sequence with
xmit_more set. This leads to a performance loss as the hardware does not
writeback anything for those packets, which delays the time it takes for
us to respond to the stack transmit requests. This significantly impacts
UDP performance, especially when layered with multiple devices, such as
bonding, VLANs, and vnet setups.
This was not noticed until now because it is difficult to create a setup
which reproduces the issue. It was discovered in a UDP_STREAM test in
a VM, connected using a vnet device to a bridge, which is connected to
a bonded pair of X710 ports in active-backup mode with a VLAN. These
layered devices seem to compound the number of skbs transmitted at once
by the qdisc. Additionally, the problem can be masked by reducing the
ITR value.
Since the original commit does not provide strong justification for this
RS bit "optimization", revert to the previous behavior of setting the RS
bit every 4th packet.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 34 ++++-------------------------
1 file changed, 4 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d9fdf69bbc6e..3bd176606c09 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3167,38 +3167,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
/* write last descriptor with EOP bit */
td_cmd |= I40E_TX_DESC_CMD_EOP;
- /* We can OR these values together as they both are checked against
- * 4 below and at this point desc_count will be used as a boolean value
- * after this if/else block.
+ /* We OR these values together to check both against 4 (WB_STRIDE)
+ * below. This is safe since we don't re-use desc_count afterwards.
*/
desc_count |= ++tx_ring->packet_stride;
- /* Algorithm to optimize tail and RS bit setting:
- * if queue is stopped
- * mark RS bit
- * reset packet counter
- * else if xmit_more is supported and is true
- * advance packet counter to 4
- * reset desc_count to 0
- *
- * if desc_count >= 4
- * mark RS bit
- * reset packet counter
- * if desc_count > 0
- * update tail
- *
- * Note: If there are less than 4 descriptors
- * pending and interrupts were disabled the service task will
- * trigger a force WB.
- */
- if (netif_xmit_stopped(txring_txq(tx_ring))) {
- goto do_rs;
- } else if (skb->xmit_more) {
- /* set stride to arm on next packet and reset desc_count */
- tx_ring->packet_stride = WB_STRIDE;
- desc_count = 0;
- } else if (desc_count >= WB_STRIDE) {
-do_rs:
+ if (desc_count >= WB_STRIDE) {
/* write last descriptor with RS bit set */
td_cmd |= I40E_TX_DESC_CMD_RS;
tx_ring->packet_stride = 0;
@@ -3219,7 +3193,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (desc_count) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
--
2.14.2
^ permalink raw reply related
* [net-next 13/15] i40evf: enable support for VF VLAN tag stripping control
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
A recent commit 809481484e5d ("i40e/i40evf: support for VF VLAN tag
stripping control") added support for VFs to negotiate the control of
VLAN tag stripping. This should have allowed VFs to disable the feature.
Unfortunately, the flag was set only in netdev->feature flags and not in
netdev->hw_features.
This ultimately causes the stack to assume that it cannot change the
flag, so it was unchangeable and marked as [fixed] in the ethtool -k
output.
Fix this by setting the feature in hw_features first, just as we do for
the PF code. This enables ethtool -K to disable the feature correctly,
and fully enables user control of the VLAN tag stripping feature.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40evf/i40evf_main.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index bc76378a71e2..1d2fc898b664 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2423,10 +2423,6 @@ static netdev_features_t i40evf_features_check(struct sk_buff *skb,
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
-#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\
- NETIF_F_HW_VLAN_CTAG_RX |\
- NETIF_F_HW_VLAN_CTAG_FILTER)
-
/**
* i40evf_fix_features - fix up the netdev feature bits
* @netdev: our net device
@@ -2439,9 +2435,11 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev,
{
struct i40evf_adapter *adapter = netdev_priv(netdev);
- features &= ~I40EVF_VLAN_FEATURES;
- if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
- features |= I40EVF_VLAN_FEATURES;
+ if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+ features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER);
+
return features;
}
@@ -2572,9 +2570,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
*/
hw_features = hw_enc_features;
+ /* Enable VLAN features if supported */
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+ hw_features |= (NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX);
+
netdev->hw_features |= hw_features;
- netdev->features |= hw_features | I40EVF_VLAN_FEATURES;
+ netdev->features |= hw_features;
+
+ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+ netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
adapter->vsi.id = adapter->vsi_res->vsi_id;
--
2.14.2
^ permalink raw reply related
* [net-next 15/15] i40e/i40evf: organize and re-number feature flags
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
Now that we've reduced the number of flags, organize similar flags
together and re-number them accordingly.
Since we don't yet have more than 32 flags, we'll use a u32 for both the
hw_features and flag field. Should we gain more flags in the future, we
may need to convert to a u64 or separate flags out into two fields.
One alternative approach considered, but not implemented here, was to
use an enumeration for the flag variables, and create a macro
I40E_FLAG() which used string concatenation to generate BIT_ULL values.
This has the advantage of making the actual bit values compile-time
dynamic so that we do not need to worry about matching the order to the
bit value. However, this does produce a high level of code churn, and
makes it more difficult to read a dumped flags value when debugging.
Change-ID: I8653fff69453cd547d6fe98d29dfa9d8710387d1
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 98 +++++++++++++-------------
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 6 +-
drivers/net/ethernet/intel/i40evf/i40evf.h | 32 ++++-----
3 files changed, 68 insertions(+), 68 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 4dc6d43f8812..18c453a3e728 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -403,57 +403,57 @@ struct i40e_pf {
struct timer_list service_timer;
struct work_struct service_task;
- u64 hw_features;
-#define I40E_HW_RSS_AQ_CAPABLE BIT_ULL(0)
-#define I40E_HW_128_QP_RSS_CAPABLE BIT_ULL(1)
-#define I40E_HW_ATR_EVICT_CAPABLE BIT_ULL(2)
-#define I40E_HW_WB_ON_ITR_CAPABLE BIT_ULL(3)
-#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(4)
-#define I40E_HW_NO_PCI_LINK_CHECK BIT_ULL(5)
-#define I40E_HW_100M_SGMII_CAPABLE BIT_ULL(6)
-#define I40E_HW_NO_DCB_SUPPORT BIT_ULL(7)
-#define I40E_HW_USE_SET_LLDP_MIB BIT_ULL(8)
-#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT_ULL(9)
-#define I40E_HW_PTP_L4_CAPABLE BIT_ULL(10)
-#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(11)
-#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT_ULL(12)
-#define I40E_HW_HAVE_CRT_RETIMER BIT_ULL(13)
-#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT_ULL(14)
-#define I40E_HW_PHY_CONTROLS_LEDS BIT_ULL(15)
-#define I40E_HW_STOP_FW_LLDP BIT_ULL(16)
-#define I40E_HW_PORT_ID_VALID BIT_ULL(17)
-#define I40E_HW_RESTART_AUTONEG BIT_ULL(18)
+ u32 hw_features;
+#define I40E_HW_RSS_AQ_CAPABLE BIT(0)
+#define I40E_HW_128_QP_RSS_CAPABLE BIT(1)
+#define I40E_HW_ATR_EVICT_CAPABLE BIT(2)
+#define I40E_HW_WB_ON_ITR_CAPABLE BIT(3)
+#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT(4)
+#define I40E_HW_NO_PCI_LINK_CHECK BIT(5)
+#define I40E_HW_100M_SGMII_CAPABLE BIT(6)
+#define I40E_HW_NO_DCB_SUPPORT BIT(7)
+#define I40E_HW_USE_SET_LLDP_MIB BIT(8)
+#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT(9)
+#define I40E_HW_PTP_L4_CAPABLE BIT(10)
+#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT(11)
+#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT(12)
+#define I40E_HW_HAVE_CRT_RETIMER BIT(13)
+#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT(14)
+#define I40E_HW_PHY_CONTROLS_LEDS BIT(15)
+#define I40E_HW_STOP_FW_LLDP BIT(16)
+#define I40E_HW_PORT_ID_VALID BIT(17)
+#define I40E_HW_RESTART_AUTONEG BIT(18)
u64 flags;
-#define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1)
-#define I40E_FLAG_MSI_ENABLED BIT_ULL(2)
-#define I40E_FLAG_MSIX_ENABLED BIT_ULL(3)
-#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(4)
-#define I40E_FLAG_RSS_ENABLED BIT_ULL(6)
-#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7)
-#define I40E_FLAG_IWARP_ENABLED BIT_ULL(10)
-#define I40E_FLAG_FILTER_SYNC BIT_ULL(15)
-#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16)
-#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19)
-#define I40E_FLAG_DCB_ENABLED BIT_ULL(20)
-#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21)
-#define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22)
-#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(23)
-#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(24)
-#define I40E_FLAG_PTP BIT_ULL(25)
-#define I40E_FLAG_MFP_ENABLED BIT_ULL(26)
-#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27)
-#define I40E_FLAG_DCB_CAPABLE BIT_ULL(29)
-#define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(37)
-#define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39)
-#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40)
-#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51)
-#define I40E_FLAG_CLIENT_RESET BIT_ULL(54)
-#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55)
-#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56)
-#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(57)
-#define I40E_FLAG_LEGACY_RX BIT_ULL(58)
-#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(59)
+#define I40E_FLAG_RX_CSUM_ENABLED BIT(0)
+#define I40E_FLAG_MSI_ENABLED BIT(1)
+#define I40E_FLAG_MSIX_ENABLED BIT(2)
+#define I40E_FLAG_RSS_ENABLED BIT(3)
+#define I40E_FLAG_VMDQ_ENABLED BIT(4)
+#define I40E_FLAG_FILTER_SYNC BIT(5)
+#define I40E_FLAG_SRIOV_ENABLED BIT(6)
+#define I40E_FLAG_DCB_CAPABLE BIT(7)
+#define I40E_FLAG_DCB_ENABLED BIT(8)
+#define I40E_FLAG_FD_SB_ENABLED BIT(9)
+#define I40E_FLAG_FD_ATR_ENABLED BIT(10)
+#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT(11)
+#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT(12)
+#define I40E_FLAG_MFP_ENABLED BIT(13)
+#define I40E_FLAG_UDP_FILTER_SYNC BIT(14)
+#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT(15)
+#define I40E_FLAG_VEB_MODE_ENABLED BIT(16)
+#define I40E_FLAG_VEB_STATS_ENABLED BIT(17)
+#define I40E_FLAG_LINK_POLLING_ENABLED BIT(18)
+#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT(19)
+#define I40E_FLAG_TEMP_LINK_POLLING BIT(20)
+#define I40E_FLAG_LEGACY_RX BIT(21)
+#define I40E_FLAG_PTP BIT(22)
+#define I40E_FLAG_IWARP_ENABLED BIT(23)
+#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT(24)
+#define I40E_FLAG_CLIENT_L2_CHANGE BIT(25)
+#define I40E_FLAG_CLIENT_RESET BIT(26)
+#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27)
+#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28)
struct i40e_client_instance *cinst;
bool stat_offsets_loaded;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index de0dfe340494..afd3ca8d9851 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4095,7 +4095,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- u64 orig_flags, new_flags, changed_flags;
+ u32 orig_flags, new_flags, changed_flags;
u32 i, j;
orig_flags = READ_ONCE(pf->flags);
@@ -4147,12 +4147,12 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
return -EOPNOTSUPP;
/* Compare and exchange the new flags into place. If we failed, that
- * is if cmpxchg64 returns anything but the old value, this means that
+ * is if cmpxchg returns anything but the old value, this means that
* something else has modified the flags variable since we copied it
* originally. We'll just punt with an error and log something in the
* message buffer.
*/
- if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) {
+ if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) {
dev_warn(&pf->pdev->dev,
"Unable to update pf->flags as it was modified by another thread...\n");
return -EAGAIN;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 5982362c5643..de0af521d602 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -222,22 +222,22 @@ struct i40evf_adapter {
u32 flags;
#define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0)
-#define I40EVF_FLAG_IMIR_ENABLED BIT(5)
-#define I40EVF_FLAG_MQ_CAPABLE BIT(6)
-#define I40EVF_FLAG_PF_COMMS_FAILED BIT(8)
-#define I40EVF_FLAG_RESET_PENDING BIT(9)
-#define I40EVF_FLAG_RESET_NEEDED BIT(10)
-#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(11)
-#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12)
-#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13)
-#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14)
-#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15)
-#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16)
-#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17)
-#define I40EVF_FLAG_PROMISC_ON BIT(18)
-#define I40EVF_FLAG_ALLMULTI_ON BIT(19)
-#define I40EVF_FLAG_LEGACY_RX BIT(20)
-#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21)
+#define I40EVF_FLAG_IMIR_ENABLED BIT(1)
+#define I40EVF_FLAG_MQ_CAPABLE BIT(2)
+#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3)
+#define I40EVF_FLAG_RESET_PENDING BIT(4)
+#define I40EVF_FLAG_RESET_NEEDED BIT(5)
+#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6)
+#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(7)
+#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8)
+#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12)
+#define I40EVF_FLAG_PROMISC_ON BIT(13)
+#define I40EVF_FLAG_ALLMULTI_ON BIT(14)
+#define I40EVF_FLAG_LEGACY_RX BIT(15)
+#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16)
/* duplicates for common code */
#define I40E_FLAG_DCB_ENABLED 0
#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED
--
2.14.2
^ permalink raw reply related
* [net-next 11/15] i40e: implement split PCI error reset handler
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This patch implements the PCI error handler reset_prepare and reset_done.
This allows us to handle function level reset. Without this patch we
are unable to perform and recover from an FLR correctly and this will cause
VFs to be unable to recover from an FLR on the PF.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 9704cfef2f05..60b11fdeca2d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12045,6 +12045,28 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
return result;
}
+/**
+ * i40e_pci_error_reset_prepare - prepare device driver for pci reset
+ * @pdev: PCI device information struct
+ */
+static void i40e_pci_error_reset_prepare(struct pci_dev *pdev)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+ i40e_prep_for_reset(pf, false);
+}
+
+/**
+ * i40e_pci_error_reset_done - pci reset done, device driver reset can begin
+ * @pdev: PCI device information struct
+ */
+static void i40e_pci_error_reset_done(struct pci_dev *pdev)
+{
+ struct i40e_pf *pf = pci_get_drvdata(pdev);
+
+ i40e_reset_and_rebuild(pf, false, false);
+}
+
/**
* i40e_pci_error_resume - restart operations after PCI error recovery
* @pdev: PCI device information struct
@@ -12235,6 +12257,8 @@ static int i40e_resume(struct device *dev)
static const struct pci_error_handlers i40e_err_handler = {
.error_detected = i40e_pci_error_detected,
.slot_reset = i40e_pci_error_slot_reset,
+ .reset_prepare = i40e_pci_error_reset_prepare,
+ .reset_done = i40e_pci_error_reset_done,
.resume = i40e_pci_error_resume,
};
--
2.14.2
^ permalink raw reply related
* [net-next 09/15] i40e: Display error message if module does not meet thermal requirements
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Filip Sadowski, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Filip Sadowski <filip.sadowski@intel.com>
This patch causes error message to be displayed when NIC detects
insertion of module that does not meet thermal requirements.
Signed-off-by: Filip Sadowski <filip.sadowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 1 +
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 1 +
drivers/net/ethernet/intel/i40e/i40e_main.c | 24 +++++++++++++++++-----
.../net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 1 +
4 files changed, 22 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index c78448daa7a1..4dc6d43f8812 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -451,6 +451,7 @@ struct i40e_pf {
#define I40E_FLAG_CLIENT_RESET BIT_ULL(54)
#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55)
#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56)
+#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(57)
#define I40E_FLAG_LEGACY_RX BIT_ULL(58)
#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(59)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 50c5a4c630b8..a8f65aed5421 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1772,6 +1772,7 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
I40E_PHY_TYPE_MAX,
+ I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
I40E_PHY_TYPE_EMPTY = 0xFE,
I40E_PHY_TYPE_DEFAULT = 0xFF,
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 628101bb08d4..3d6d6a283327 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6558,12 +6558,26 @@ static void i40e_handle_link_event(struct i40e_pf *pf,
*/
i40e_link_event(pf);
- /* check for unqualified module, if link is down */
- if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) &&
- (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) &&
- (!(status->link_info & I40E_AQ_LINK_UP)))
+ /* Check if module meets thermal requirements */
+ if (status->phy_type == I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP) {
dev_err(&pf->pdev->dev,
- "The driver failed to link because an unqualified module was detected.\n");
+ "Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n");
+ dev_err(&pf->pdev->dev,
+ "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
+ } else {
+ /* check for unqualified module, if link is down, suppress
+ * the message if link was forced to be down.
+ */
+ if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) &&
+ (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) &&
+ (!(status->link_info & I40E_AQ_LINK_UP)) &&
+ (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) {
+ dev_err(&pf->pdev->dev,
+ "Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n");
+ dev_err(&pf->pdev->dev,
+ "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n");
+ }
+ }
}
/**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index dc6fc8b1bc79..60c892f559b9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1768,6 +1768,7 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
I40E_PHY_TYPE_MAX,
+ I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
I40E_PHY_TYPE_EMPTY = 0xFE,
I40E_PHY_TYPE_DEFAULT = 0xFF,
};
--
2.14.2
^ permalink raw reply related
* [net-next 06/15] i40e: fix incorrect register definition
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Mitch Williams, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Mitch Williams <mitch.a.williams@intel.com>
This register was defined incorrectly. Fix the increment value to 8, and
replace the iterator with _i to make the definition consistent with
other statistics registers.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_register.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 86ca27f72f02..c234758dad15 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -2794,7 +2794,7 @@
#define I40E_GLV_RUPP_MAX_INDEX 383
#define I40E_GLV_RUPP_RUPP_SHIFT 0
#define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT)
-#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */
+#define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */
#define I40E_GLV_TEPC_MAX_INDEX 383
#define I40E_GLV_TEPC_TEPC_SHIFT 0
#define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT)
--
2.14.2
^ permalink raw reply related
* [net-next 05/15] i40e: redfine I40E_PHY_TYPE_MAX
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Mitch Williams, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Mitch Williams <mitch.a.williams@intel.com>
Since I40E_PHY_TYPE_MAX is used as an iterator, usually combined with
some sort of bit-shifting, it should only include actual PHY types and
not error cases. Move it up in the enum declaration so that loops only
iterate across valid PHY types.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 2 +-
drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 4c85ea9cd89a..50c5a4c630b8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1771,9 +1771,9 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_MAX,
I40E_PHY_TYPE_EMPTY = 0xFE,
I40E_PHY_TYPE_DEFAULT = 0xFF,
- I40E_PHY_TYPE_MAX
};
#define I40E_LINK_SPEED_100MB_SHIFT 0x1
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index ed5602f4bbcd..dc6fc8b1bc79 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1767,9 +1767,9 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_MAX,
I40E_PHY_TYPE_EMPTY = 0xFE,
I40E_PHY_TYPE_DEFAULT = 0xFF,
- I40E_PHY_TYPE_MAX
};
#define I40E_LINK_SPEED_100MB_SHIFT 0x1
--
2.14.2
^ permalink raw reply related
* [net-next 10/15] i40e: Properly maintain flow director filters list
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Filip Sadowski, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Filip Sadowski <filip.sadowski@intel.com>
When there is no space for more flow director filters and user requested to
add a new one it is rejected by firmware and automatically removed from the
filter list maintained by driver. This behaviour is correct. Afterwards
existing filter can be removed making free slot for the new one. This
however causes the newly added filter to be accepted by firmware but
removed from driver filter list resulting in not showing after issuing
'ethtool -n <dev_name>'.
This happened due to not clearing the variable pf->fd_inv which stores
filter number to be removed from the list when firmware refused to add the
requested filter. It caused the filter with this specific ID to be
constantly removed once it was added to the list although it has been
accepted by firmware and effectively applied to the NIC.
It was fixed by clearing pf->fd_inv variable after removal of the filter
from the list when it was rejected by firmware.
Signed-off-by: Filip Sadowski <filip.sadowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3d6d6a283327..9704cfef2f05 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6232,6 +6232,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
hlist_del(&filter->fdir_node);
kfree(filter);
pf->fdir_pf_active_filters--;
+ pf->fd_inv = 0;
}
}
}
--
2.14.2
^ permalink raw reply related
* [net-next 07/15] i40e/i40evf: use DECLARE_BITMAP for state
From: Jeff Kirsher @ 2017-10-06 17:57 UTC (permalink / raw)
To: davem; +Cc: Jesse Brandeburg, netdev, nhorman, sassmann, jogreene,
Jeff Kirsher
In-Reply-To: <20171006175727.868-1-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
When using set_bit and friends, we should be using actual
bitmaps, and fix all the locations where we might access
it.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 8 ++++----
drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++--
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 3 ++-
drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 3 ++-
4 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 8f326f87a815..6f2725fc50a1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -278,8 +278,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
rx_ring->netdev,
rx_ring->rx_bi);
dev_info(&pf->pdev->dev,
- " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
- i, rx_ring->state,
+ " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n",
+ i, *rx_ring->state,
rx_ring->queue_index,
rx_ring->reg_idx);
dev_info(&pf->pdev->dev,
@@ -334,8 +334,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
tx_ring->netdev,
tx_ring->tx_bi);
dev_info(&pf->pdev->dev,
- " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
- i, tx_ring->state,
+ " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n",
+ i, *tx_ring->state,
tx_ring->queue_index,
tx_ring->reg_idx);
dev_info(&pf->pdev->dev,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 85132eee9f64..49401be7a2f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2891,7 +2891,7 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
return;
if ((vsi->tc_config.numtc <= 1) &&
- !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) {
+ !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) {
cpu = cpumask_local_spread(ring->q_vector->v_idx, -1);
netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu),
ring->queue_index);
@@ -3010,7 +3010,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
struct i40e_hmc_obj_rxq rx_ctx;
i40e_status err = 0;
- ring->state = 0;
+ bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
/* clear the context structure first */
memset(&rx_ctx, 0, sizeof(rx_ctx));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 2f848bc5e391..a4e3e665a1a1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -342,6 +342,7 @@ struct i40e_rx_queue_stats {
enum i40e_ring_state_t {
__I40E_TX_FDIR_INIT_DONE,
__I40E_TX_XPS_INIT_DONE,
+ __I40E_RING_STATE_NBITS /* must be last */
};
/* some useful defines for virtchannel interface, which
@@ -366,7 +367,7 @@ struct i40e_ring {
struct i40e_tx_buffer *tx_bi;
struct i40e_rx_buffer *rx_bi;
};
- unsigned long state;
+ DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
u16 queue_index; /* Queue number of ring */
u8 dcb_tc; /* Traffic class of ring */
u8 __iomem *tail;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 0d9f98bc07bd..d8ca802a71a9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -325,6 +325,7 @@ struct i40e_rx_queue_stats {
enum i40e_ring_state_t {
__I40E_TX_FDIR_INIT_DONE,
__I40E_TX_XPS_INIT_DONE,
+ __I40E_RING_STATE_NBITS /* must be last */
};
/* some useful defines for virtchannel interface, which
@@ -348,7 +349,7 @@ struct i40e_ring {
struct i40e_tx_buffer *tx_bi;
struct i40e_rx_buffer *rx_bi;
};
- unsigned long state;
+ DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
u16 queue_index; /* Queue number of ring */
u8 dcb_tc; /* Traffic class of ring */
u8 __iomem *tail;
--
2.14.2
^ 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