* [PATCH v3 11/17] net,l2tp: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928@gmail.com>
Switch l2tp to use the new hashtable implementation. This reduces the amount of
generic unrelated code in l2tp.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
net/l2tp/l2tp_core.c | 134 +++++++++++++++++-----------------------------
net/l2tp/l2tp_core.h | 8 ++--
net/l2tp/l2tp_debugfs.c | 19 +++----
3 files changed, 61 insertions(+), 100 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 393355d..1d395ce 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -44,6 +44,7 @@
#include <linux/udp.h>
#include <linux/l2tp.h>
#include <linux/hash.h>
+#include <linux/hashtable.h>
#include <linux/sort.h>
#include <linux/file.h>
#include <linux/nsproxy.h>
@@ -107,8 +108,8 @@ static unsigned int l2tp_net_id;
struct l2tp_net {
struct list_head l2tp_tunnel_list;
spinlock_t l2tp_tunnel_list_lock;
- struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
- spinlock_t l2tp_session_hlist_lock;
+ DEFINE_HASHTABLE(l2tp_session_hash, L2TP_HASH_BITS_2)
+ spinlock_t l2tp_session_hash_lock;
};
static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
@@ -156,30 +157,17 @@ do { \
#define l2tp_tunnel_dec_refcount(t) l2tp_tunnel_dec_refcount_1(t)
#endif
-/* Session hash global list for L2TPv3.
- * The session_id SHOULD be random according to RFC3931, but several
- * L2TP implementations use incrementing session_ids. So we do a real
- * hash on the session_id, rather than a simple bitmask.
- */
-static inline struct hlist_head *
-l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
-{
- return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)];
-
-}
-
/* Lookup a session by id in the global session list
*/
static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
{
struct l2tp_net *pn = l2tp_pernet(net);
- struct hlist_head *session_list =
- l2tp_session_id_hash_2(pn, session_id);
struct l2tp_session *session;
struct hlist_node *walk;
rcu_read_lock_bh();
- hlist_for_each_entry_rcu(session, walk, session_list, global_hlist) {
+ hash_for_each_possible_rcu(pn->l2tp_session_hash, session, walk,
+ global_hlist, session_id) {
if (session->session_id == session_id) {
rcu_read_unlock_bh();
return session;
@@ -190,23 +178,10 @@ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
return NULL;
}
-/* Session hash list.
- * The session_id SHOULD be random according to RFC2661, but several
- * L2TP implementations (Cisco and Microsoft) use incrementing
- * session_ids. So we do a real hash on the session_id, rather than a
- * simple bitmask.
- */
-static inline struct hlist_head *
-l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
-{
- return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
-}
-
/* Lookup a session by id
*/
struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id)
{
- struct hlist_head *session_list;
struct l2tp_session *session;
struct hlist_node *walk;
@@ -217,15 +192,14 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
if (tunnel == NULL)
return l2tp_session_find_2(net, session_id);
- session_list = l2tp_session_id_hash(tunnel, session_id);
- read_lock_bh(&tunnel->hlist_lock);
- hlist_for_each_entry(session, walk, session_list, hlist) {
+ read_lock_bh(&tunnel->hash_lock);
+ hash_for_each_possible(tunnel->session_hash, session, walk, hlist, session_id) {
if (session->session_id == session_id) {
- read_unlock_bh(&tunnel->hlist_lock);
+ read_unlock_bh(&tunnel->hash_lock);
return session;
}
}
- read_unlock_bh(&tunnel->hlist_lock);
+ read_unlock_bh(&tunnel->hash_lock);
return NULL;
}
@@ -238,17 +212,15 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
struct l2tp_session *session;
int count = 0;
- read_lock_bh(&tunnel->hlist_lock);
- for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
- hlist_for_each_entry(session, walk, &tunnel->session_hlist[hash], hlist) {
- if (++count > nth) {
- read_unlock_bh(&tunnel->hlist_lock);
- return session;
- }
+ read_lock_bh(&tunnel->hash_lock);
+ hash_for_each(tunnel->session_hash, hash, walk, session, hlist) {
+ if (++count > nth) {
+ read_unlock_bh(&tunnel->hash_lock);
+ return session;
}
}
- read_unlock_bh(&tunnel->hlist_lock);
+ read_unlock_bh(&tunnel->hash_lock);
return NULL;
}
@@ -265,12 +237,10 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
struct l2tp_session *session;
rcu_read_lock_bh();
- for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
- hlist_for_each_entry_rcu(session, walk, &pn->l2tp_session_hlist[hash], global_hlist) {
- if (!strcmp(session->ifname, ifname)) {
- rcu_read_unlock_bh();
- return session;
- }
+ hash_for_each_rcu(pn->l2tp_session_hash, hash, walk, session, global_hlist) {
+ if (!strcmp(session->ifname, ifname)) {
+ rcu_read_unlock_bh();
+ return session;
}
}
@@ -1272,7 +1242,7 @@ end:
*/
static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
{
- int hash;
+ int hash, found = 0;
struct hlist_node *walk;
struct hlist_node *tmp;
struct l2tp_session *session;
@@ -1282,16 +1252,14 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n",
tunnel->name);
- write_lock_bh(&tunnel->hlist_lock);
- for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
-again:
- hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
- session = hlist_entry(walk, struct l2tp_session, hlist);
-
+ write_lock_bh(&tunnel->hash_lock);
+ do {
+ found = 0;
+ hash_for_each_safe(tunnel->session_hash, hash, walk, tmp, session, hlist) {
l2tp_info(session, L2TP_MSG_CONTROL,
"%s: closing session\n", session->name);
- hlist_del_init(&session->hlist);
+ hash_del(&session->hlist);
/* Since we should hold the sock lock while
* doing any unbinding, we need to release the
@@ -1302,14 +1270,14 @@ again:
if (session->ref != NULL)
(*session->ref)(session);
- write_unlock_bh(&tunnel->hlist_lock);
+ write_unlock_bh(&tunnel->hash_lock);
if (tunnel->version != L2TP_HDR_VER_2) {
struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_del_init_rcu(&session->global_hlist);
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ spin_lock_bh(&pn->l2tp_session_hash_lock);
+ hash_del_rcu(&session->global_hlist);
+ spin_unlock_bh(&pn->l2tp_session_hash_lock);
synchronize_rcu();
}
@@ -1319,17 +1287,17 @@ again:
if (session->deref != NULL)
(*session->deref)(session);
- write_lock_bh(&tunnel->hlist_lock);
+ write_lock_bh(&tunnel->hash_lock);
/* Now restart from the beginning of this hash
* chain. We always remove a session from the
* list so we are guaranteed to make forward
* progress.
*/
- goto again;
+ found = 1;
}
- }
- write_unlock_bh(&tunnel->hlist_lock);
+ } while (found);
+ write_unlock_bh(&tunnel->hash_lock);
}
/* Really kill the tunnel.
@@ -1575,7 +1543,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
tunnel->magic = L2TP_TUNNEL_MAGIC;
sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
- rwlock_init(&tunnel->hlist_lock);
+ rwlock_init(&tunnel->hash_lock);
/* The net we belong to */
tunnel->l2tp_net = net;
@@ -1610,6 +1578,8 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
/* Add tunnel to our list */
INIT_LIST_HEAD(&tunnel->list);
+
+ hash_init(tunnel->session_hash);
atomic_inc(&l2tp_tunnel_count);
/* Bump the reference count. The tunnel context is deleted
@@ -1674,17 +1644,17 @@ void l2tp_session_free(struct l2tp_session *session)
BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
/* Delete the session from the hash */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_del_init(&session->hlist);
- write_unlock_bh(&tunnel->hlist_lock);
+ write_lock_bh(&tunnel->hash_lock);
+ hash_del(&session->hlist);
+ write_unlock_bh(&tunnel->hash_lock);
/* Unlink from the global hash if not L2TPv2 */
if (tunnel->version != L2TP_HDR_VER_2) {
struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_del_init_rcu(&session->global_hlist);
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ spin_lock_bh(&pn->l2tp_session_hash_lock);
+ hash_del_rcu(&session->global_hlist);
+ spin_unlock_bh(&pn->l2tp_session_hash_lock);
synchronize_rcu();
}
@@ -1797,19 +1767,17 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
sock_hold(tunnel->sock);
/* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- l2tp_session_id_hash(tunnel, session_id));
- write_unlock_bh(&tunnel->hlist_lock);
+ write_lock_bh(&tunnel->hash_lock);
+ hash_add(tunnel->session_hash, &session->hlist, session_id);
+ write_unlock_bh(&tunnel->hash_lock);
/* And to the global session list if L2TPv3 */
if (tunnel->version != L2TP_HDR_VER_2) {
struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_add_head_rcu(&session->global_hlist,
- l2tp_session_id_hash_2(pn, session_id));
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ spin_lock_bh(&pn->l2tp_session_hash_lock);
+ hash_add(pn->l2tp_session_hash, &session->global_hlist, session_id);
+ spin_unlock_bh(&pn->l2tp_session_hash_lock);
}
/* Ignore management session in session count value */
@@ -1828,15 +1796,13 @@ EXPORT_SYMBOL_GPL(l2tp_session_create);
static __net_init int l2tp_init_net(struct net *net)
{
struct l2tp_net *pn = net_generic(net, l2tp_net_id);
- int hash;
INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
spin_lock_init(&pn->l2tp_tunnel_list_lock);
- for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
- INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]);
+ hash_init(pn->l2tp_session_hash);
- spin_lock_init(&pn->l2tp_session_hlist_lock);
+ spin_lock_init(&pn->l2tp_session_hash_lock);
return 0;
}
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a38ec6c..23bf320 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -11,17 +11,17 @@
#ifndef _L2TP_CORE_H_
#define _L2TP_CORE_H_
+#include <linux/hashtable.h>
+
/* Just some random numbers */
#define L2TP_TUNNEL_MAGIC 0x42114DDA
#define L2TP_SESSION_MAGIC 0x0C04EB7D
/* Per tunnel, session hash table size */
#define L2TP_HASH_BITS 4
-#define L2TP_HASH_SIZE (1 << L2TP_HASH_BITS)
/* System-wide, session hash table size */
#define L2TP_HASH_BITS_2 8
-#define L2TP_HASH_SIZE_2 (1 << L2TP_HASH_BITS_2)
/* Debug message categories for the DEBUG socket option */
enum {
@@ -163,8 +163,8 @@ struct l2tp_tunnel_cfg {
struct l2tp_tunnel {
int magic; /* Should be L2TP_TUNNEL_MAGIC */
- rwlock_t hlist_lock; /* protect session_hlist */
- struct hlist_head session_hlist[L2TP_HASH_SIZE];
+ rwlock_t hash_lock; /* protect session_hash */
+ DEFINE_HASHTABLE(session_hash, L2TP_HASH_BITS);
/* hashed list of sessions,
* hashed by id */
u32 tunnel_id;
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index c3813bc..655f1fa 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -105,21 +105,16 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
int session_count = 0;
int hash;
struct hlist_node *walk;
- struct hlist_node *tmp;
+ struct l2tp_session *session;
- read_lock_bh(&tunnel->hlist_lock);
- for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
- hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
- struct l2tp_session *session;
+ read_lock_bh(&tunnel->hash_lock);
+ hash_for_each(tunnel->session_hash, hash, walk, session, hlist) {
+ if (session->session_id == 0)
+ continue;
- session = hlist_entry(walk, struct l2tp_session, hlist);
- if (session->session_id == 0)
- continue;
-
- session_count++;
- }
+ session_count++;
}
- read_unlock_bh(&tunnel->hlist_lock);
+ read_unlock_bh(&tunnel->hash_lock);
seq_printf(m, "\nTUNNEL %u peer %u", tunnel->tunnel_id, tunnel->peer_tunnel_id);
if (tunnel->sock) {
--
1.7.8.6
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v3 12/17] dm: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928@gmail.com>
Switch dm to use the new hashtable implementation. This reduces the amount of
generic unrelated code in the dm.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
drivers/md/dm-snap.c | 24 ++++-----------
drivers/md/persistent-data/dm-block-manager.c | 1 -
.../persistent-data/dm-persistent-data-internal.h | 19 ------------
.../md/persistent-data/dm-transaction-manager.c | 30 ++++++--------------
4 files changed, 16 insertions(+), 58 deletions(-)
delete mode 100644 drivers/md/persistent-data/dm-persistent-data-internal.h
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index a143921..7ac121f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -34,9 +34,7 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge";
*/
#define MIN_IOS 256
-#define DM_TRACKED_CHUNK_HASH_SIZE 16
-#define DM_TRACKED_CHUNK_HASH(x) ((unsigned long)(x) & \
- (DM_TRACKED_CHUNK_HASH_SIZE - 1))
+#define DM_TRACKED_CHUNK_HASH_BITS 4
struct dm_exception_table {
uint32_t hash_mask;
@@ -80,7 +78,7 @@ struct dm_snapshot {
/* Chunks with outstanding reads */
spinlock_t tracked_chunk_lock;
mempool_t *tracked_chunk_pool;
- struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE];
+ DEFINE_HASHTABLE(tracked_chunk_hash, DM_TRACKED_CHUNK_HASH_BITS);
/* The on disk metadata handler */
struct dm_exception_store *store;
@@ -203,8 +201,7 @@ static struct dm_snap_tracked_chunk *track_chunk(struct dm_snapshot *s,
c->chunk = chunk;
spin_lock_irqsave(&s->tracked_chunk_lock, flags);
- hlist_add_head(&c->node,
- &s->tracked_chunk_hash[DM_TRACKED_CHUNK_HASH(chunk)]);
+ hash_add(s->tracked_chunk_hash, &c->node, chunk);
spin_unlock_irqrestore(&s->tracked_chunk_lock, flags);
return c;
@@ -216,7 +213,7 @@ static void stop_tracking_chunk(struct dm_snapshot *s,
unsigned long flags;
spin_lock_irqsave(&s->tracked_chunk_lock, flags);
- hlist_del(&c->node);
+ hash_del(&c->node);
spin_unlock_irqrestore(&s->tracked_chunk_lock, flags);
mempool_free(c, s->tracked_chunk_pool);
@@ -230,8 +227,7 @@ static int __chunk_is_tracked(struct dm_snapshot *s, chunk_t chunk)
spin_lock_irq(&s->tracked_chunk_lock);
- hlist_for_each_entry(c, hn,
- &s->tracked_chunk_hash[DM_TRACKED_CHUNK_HASH(chunk)], node) {
+ hash_for_each_possible(s->tracked_chunk_hash, c, hn, node, chunk) {
if (c->chunk == chunk) {
found = 1;
break;
@@ -1033,7 +1029,6 @@ static void stop_merge(struct dm_snapshot *s)
static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct dm_snapshot *s;
- int i;
int r = -EINVAL;
char *origin_path, *cow_path;
unsigned args_used, num_flush_requests = 1;
@@ -1128,8 +1123,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad_tracked_chunk_pool;
}
- for (i = 0; i < DM_TRACKED_CHUNK_HASH_SIZE; i++)
- INIT_HLIST_HEAD(&s->tracked_chunk_hash[i]);
+ hash_init(s->tracked_chunk_hash);
spin_lock_init(&s->tracked_chunk_lock);
@@ -1253,9 +1247,6 @@ static void __handover_exceptions(struct dm_snapshot *snap_src,
static void snapshot_dtr(struct dm_target *ti)
{
-#ifdef CONFIG_DM_DEBUG
- int i;
-#endif
struct dm_snapshot *s = ti->private;
struct dm_snapshot *snap_src = NULL, *snap_dest = NULL;
@@ -1286,8 +1277,7 @@ static void snapshot_dtr(struct dm_target *ti)
smp_mb();
#ifdef CONFIG_DM_DEBUG
- for (i = 0; i < DM_TRACKED_CHUNK_HASH_SIZE; i++)
- BUG_ON(!hlist_empty(&s->tracked_chunk_hash[i]));
+ BUG_ON(!hash_empty(s->tracked_chunk_hash));
#endif
mempool_destroy(s->tracked_chunk_pool);
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 5ba2777..31edaf13 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -4,7 +4,6 @@
* This file is released under the GPL.
*/
#include "dm-block-manager.h"
-#include "dm-persistent-data-internal.h"
#include "../dm-bufio.h"
#include <linux/crc32c.h>
diff --git a/drivers/md/persistent-data/dm-persistent-data-internal.h b/drivers/md/persistent-data/dm-persistent-data-internal.h
deleted file mode 100644
index c49e26f..0000000
--- a/drivers/md/persistent-data/dm-persistent-data-internal.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright (C) 2011 Red Hat, Inc.
- *
- * This file is released under the GPL.
- */
-
-#ifndef _DM_PERSISTENT_DATA_INTERNAL_H
-#define _DM_PERSISTENT_DATA_INTERNAL_H
-
-#include "dm-block-manager.h"
-
-static inline unsigned dm_hash_block(dm_block_t b, unsigned hash_mask)
-{
- const unsigned BIG_PRIME = 4294967291UL;
-
- return (((unsigned) b) * BIG_PRIME) & hash_mask;
-}
-
-#endif /* _PERSISTENT_DATA_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index d247a35..a57c4ed 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -7,11 +7,11 @@
#include "dm-space-map.h"
#include "dm-space-map-disk.h"
#include "dm-space-map-metadata.h"
-#include "dm-persistent-data-internal.h"
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/device-mapper.h>
+#include <linux/hashtable.h>
#define DM_MSG_PREFIX "transaction manager"
@@ -25,8 +25,7 @@ struct shadow_info {
/*
* It would be nice if we scaled with the size of transaction.
*/
-#define HASH_SIZE 256
-#define HASH_MASK (HASH_SIZE - 1)
+#define DM_HASH_BITS 8
struct dm_transaction_manager {
int is_clone;
@@ -36,7 +35,7 @@ struct dm_transaction_manager {
struct dm_space_map *sm;
spinlock_t lock;
- struct hlist_head buckets[HASH_SIZE];
+ DEFINE_HASHTABLE(hash, DM_HASH_BITS);
};
/*----------------------------------------------------------------*/
@@ -44,12 +43,11 @@ struct dm_transaction_manager {
static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
{
int r = 0;
- unsigned bucket = dm_hash_block(b, HASH_MASK);
struct shadow_info *si;
struct hlist_node *n;
spin_lock(&tm->lock);
- hlist_for_each_entry(si, n, tm->buckets + bucket, hlist)
+ hash_for_each_possible(tm->hash, si, n, hlist, b)
if (si->where == b) {
r = 1;
break;
@@ -65,15 +63,13 @@ static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
*/
static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
{
- unsigned bucket;
struct shadow_info *si;
si = kmalloc(sizeof(*si), GFP_NOIO);
if (si) {
si->where = b;
- bucket = dm_hash_block(b, HASH_MASK);
spin_lock(&tm->lock);
- hlist_add_head(&si->hlist, tm->buckets + bucket);
+ hash_add(tm->hash, &si->hlist, b);
spin_unlock(&tm->lock);
}
}
@@ -82,18 +78,12 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
{
struct shadow_info *si;
struct hlist_node *n, *tmp;
- struct hlist_head *bucket;
int i;
spin_lock(&tm->lock);
- for (i = 0; i < HASH_SIZE; i++) {
- bucket = tm->buckets + i;
- hlist_for_each_entry_safe(si, n, tmp, bucket, hlist)
- kfree(si);
-
- INIT_HLIST_HEAD(bucket);
- }
-
+ hash_for_each_safe(tm->hash, i, n, tmp, si, hlist)
+ kfree(si);
+ hash_init(tm->hash);
spin_unlock(&tm->lock);
}
@@ -102,7 +92,6 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
struct dm_space_map *sm)
{
- int i;
struct dm_transaction_manager *tm;
tm = kmalloc(sizeof(*tm), GFP_KERNEL);
@@ -115,8 +104,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
tm->sm = sm;
spin_lock_init(&tm->lock);
- for (i = 0; i < HASH_SIZE; i++)
- INIT_HLIST_HEAD(tm->buckets + i);
+ hash_init(tm->hash);
return tm;
}
--
1.7.8.6
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v3 13/17] lockd: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch lockd to use the new hashtable implementation. This reduces the amount of
generic unrelated code in lockd.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
fs/lockd/svcsubs.c | 66 ++++++++++++++++++++++++++++-----------------------
1 files changed, 36 insertions(+), 30 deletions(-)
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 0deb5f6..d223a1f 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -20,6 +20,7 @@
#include <linux/lockd/share.h>
#include <linux/module.h>
#include <linux/mount.h>
+#include <linux/hashtable.h>
#define NLMDBG_FACILITY NLMDBG_SVCSUBS
@@ -28,8 +29,7 @@
* Global file hash table
*/
#define FILE_HASH_BITS 7
-#define FILE_NRHASH (1<<FILE_HASH_BITS)
-static struct hlist_head nlm_files[FILE_NRHASH];
+static DEFINE_HASHTABLE(nlm_files, FILE_HASH_BITS);
static DEFINE_MUTEX(nlm_file_mutex);
#ifdef NFSD_DEBUG
@@ -68,7 +68,7 @@ static inline unsigned int file_hash(struct nfs_fh *f)
int i;
for (i=0; i<NFS2_FHSIZE;i++)
tmp += f->data[i];
- return tmp & (FILE_NRHASH - 1);
+ return tmp;
}
/*
@@ -86,17 +86,17 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
{
struct hlist_node *pos;
struct nlm_file *file;
- unsigned int hash;
+ unsigned int key;
__be32 nfserr;
nlm_debug_print_fh("nlm_lookup_file", f);
- hash = file_hash(f);
+ key = file_hash(f);
/* Lock file table */
mutex_lock(&nlm_file_mutex);
- hlist_for_each_entry(file, pos, &nlm_files[hash], f_list)
+ hash_for_each_possible(nlm_files, file, pos, f_list, file_hash(f))
if (!nfs_compare_fh(&file->f_handle, f))
goto found;
@@ -123,7 +123,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
goto out_free;
}
- hlist_add_head(&file->f_list, &nlm_files[hash]);
+ hash_add(nlm_files, &file->f_list, key);
found:
dprintk("lockd: found file %p (count %d)\n", file, file->f_count);
@@ -147,8 +147,8 @@ static inline void
nlm_delete_file(struct nlm_file *file)
{
nlm_debug_print_file("closing file", file);
- if (!hlist_unhashed(&file->f_list)) {
- hlist_del(&file->f_list);
+ if (hash_hashed(&file->f_list)) {
+ hash_del(&file->f_list);
nlmsvc_ops->fclose(file->f_file);
kfree(file);
} else {
@@ -253,27 +253,25 @@ nlm_traverse_files(void *data, nlm_host_match_fn_t match,
int i, ret = 0;
mutex_lock(&nlm_file_mutex);
- for (i = 0; i < FILE_NRHASH; i++) {
- hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) {
- if (is_failover_file && !is_failover_file(data, file))
- continue;
- file->f_count++;
- mutex_unlock(&nlm_file_mutex);
-
- /* Traverse locks, blocks and shares of this file
- * and update file->f_locks count */
- if (nlm_inspect_file(data, file, match))
- ret = 1;
-
- mutex_lock(&nlm_file_mutex);
- file->f_count--;
- /* No more references to this file. Let go of it. */
- if (list_empty(&file->f_blocks) && !file->f_locks
- && !file->f_shares && !file->f_count) {
- hlist_del(&file->f_list);
- nlmsvc_ops->fclose(file->f_file);
- kfree(file);
- }
+ hash_for_each_safe(nlm_files, i, pos, next, file, f_list) {
+ if (is_failover_file && !is_failover_file(data, file))
+ continue;
+ file->f_count++;
+ mutex_unlock(&nlm_file_mutex);
+
+ /* Traverse locks, blocks and shares of this file
+ * and update file->f_locks count */
+ if (nlm_inspect_file(data, file, match))
+ ret = 1;
+
+ mutex_lock(&nlm_file_mutex);
+ file->f_count--;
+ /* No more references to this file. Let go of it. */
+ if (list_empty(&file->f_blocks) && !file->f_locks
+ && !file->f_shares && !file->f_count) {
+ hash_del(&file->f_list);
+ nlmsvc_ops->fclose(file->f_file);
+ kfree(file);
}
}
mutex_unlock(&nlm_file_mutex);
@@ -451,3 +449,11 @@ nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr)
return ret ? -EIO : 0;
}
EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_ip);
+
+static int __init nlm_init(void)
+{
+ hash_init(nlm_files);
+ return 0;
+}
+
+module_init(nlm_init);
--
1.7.8.6
^ permalink raw reply related
* [PATCH v3 14/17] net,rds: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928@gmail.com>
Switch rds to use the new hashtable implementation. This reduces the amount of
generic unrelated code in rds.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
net/rds/bind.c | 28 +++++++++-----
net/rds/connection.c | 102 ++++++++++++++++++++++----------------------------
2 files changed, 63 insertions(+), 67 deletions(-)
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 637bde5..79d65ce 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -36,16 +36,16 @@
#include <linux/if_arp.h>
#include <linux/jhash.h>
#include <linux/ratelimit.h>
+#include <linux/hashtable.h>
#include "rds.h"
-#define BIND_HASH_SIZE 1024
-static struct hlist_head bind_hash_table[BIND_HASH_SIZE];
+#define BIND_HASH_BITS 10
+static DEFINE_HASHTABLE(bind_hash_table, BIND_HASH_BITS);
static DEFINE_SPINLOCK(rds_bind_lock);
-static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
+static u32 rds_hash(__be32 addr, __be16 port)
{
- return bind_hash_table + (jhash_2words((u32)addr, (u32)port, 0) &
- (BIND_HASH_SIZE - 1));
+ return jhash_2words((u32)addr, (u32)port, 0);
}
static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
@@ -53,12 +53,12 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
{
struct rds_sock *rs;
struct hlist_node *node;
- struct hlist_head *head = hash_to_bucket(addr, port);
+ u32 key = rds_hash(addr, port);
u64 cmp;
u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port);
rcu_read_lock();
- hlist_for_each_entry_rcu(rs, node, head, rs_bound_node) {
+ hash_for_each_possible_rcu(bind_hash_table, rs, node, rs_bound_node, key) {
cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) |
be16_to_cpu(rs->rs_bound_port);
@@ -74,13 +74,13 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
* make sure our addr and port are set before
* we are added to the list, other people
* in rcu will find us as soon as the
- * hlist_add_head_rcu is done
+ * hash_add_rcu is done
*/
insert->rs_bound_addr = addr;
insert->rs_bound_port = port;
rds_sock_addref(insert);
- hlist_add_head_rcu(&insert->rs_bound_node, head);
+ hash_add_rcu(bind_hash_table, &insert->rs_bound_node, key);
}
return NULL;
}
@@ -152,7 +152,7 @@ void rds_remove_bound(struct rds_sock *rs)
rs, &rs->rs_bound_addr,
ntohs(rs->rs_bound_port));
- hlist_del_init_rcu(&rs->rs_bound_node);
+ hash_del_rcu(&rs->rs_bound_node);
rds_sock_put(rs);
rs->rs_bound_addr = 0;
}
@@ -202,3 +202,11 @@ out:
synchronize_rcu();
return ret;
}
+
+static int __init rds_init(void)
+{
+ hash_init(bind_hash_table);
+ return 0;
+}
+
+module_init(rds_init);
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 9e07c75..5b09ee1 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -34,28 +34,24 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/hashtable.h>
#include <net/inet_hashtables.h>
#include "rds.h"
#include "loop.h"
#define RDS_CONNECTION_HASH_BITS 12
-#define RDS_CONNECTION_HASH_ENTRIES (1 << RDS_CONNECTION_HASH_BITS)
-#define RDS_CONNECTION_HASH_MASK (RDS_CONNECTION_HASH_ENTRIES - 1)
/* converting this to RCU is a chore for another day.. */
static DEFINE_SPINLOCK(rds_conn_lock);
static unsigned long rds_conn_count;
-static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
+static DEFINE_HASHTABLE(rds_conn_hash, RDS_CONNECTION_HASH_BITS);
static struct kmem_cache *rds_conn_slab;
-static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
+static unsigned long rds_conn_hashfn(__be32 laddr, __be32 faddr)
{
/* Pass NULL, don't need struct net for hash */
- unsigned long hash = inet_ehashfn(NULL,
- be32_to_cpu(laddr), 0,
- be32_to_cpu(faddr), 0);
- return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
+ return inet_ehashfn(NULL, be32_to_cpu(laddr), 0, be32_to_cpu(faddr), 0);
}
#define rds_conn_info_set(var, test, suffix) do { \
@@ -64,14 +60,14 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
} while (0)
/* rcu read lock must be held or the connection spinlock */
-static struct rds_connection *rds_conn_lookup(struct hlist_head *head,
- __be32 laddr, __be32 faddr,
+static struct rds_connection *rds_conn_lookup(__be32 laddr, __be32 faddr,
struct rds_transport *trans)
{
struct rds_connection *conn, *ret = NULL;
struct hlist_node *pos;
+ unsigned long key = rds_conn_hashfn(laddr, faddr);
- hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) {
+ hash_for_each_possible_rcu(rds_conn_hash, conn, pos, c_hash_node, key) {
if (conn->c_faddr == faddr && conn->c_laddr == laddr &&
conn->c_trans == trans) {
ret = conn;
@@ -117,13 +113,12 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
int is_outgoing)
{
struct rds_connection *conn, *parent = NULL;
- struct hlist_head *head = rds_conn_bucket(laddr, faddr);
struct rds_transport *loop_trans;
unsigned long flags;
int ret;
rcu_read_lock();
- conn = rds_conn_lookup(head, laddr, faddr, trans);
+ conn = rds_conn_lookup(laddr, faddr, trans);
if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
!is_outgoing) {
/* This is a looped back IB connection, and we're
@@ -224,13 +219,15 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
/* Creating normal conn */
struct rds_connection *found;
- found = rds_conn_lookup(head, laddr, faddr, trans);
+ found = rds_conn_lookup(laddr, faddr, trans);
if (found) {
trans->conn_free(conn->c_transport_data);
kmem_cache_free(rds_conn_slab, conn);
conn = found;
} else {
- hlist_add_head_rcu(&conn->c_hash_node, head);
+ unsigned long key = rds_conn_hashfn(laddr, faddr);
+
+ hash_add_rcu(rds_conn_hash, &conn->c_hash_node, key);
rds_cong_add_conn(conn);
rds_conn_count++;
}
@@ -303,7 +300,7 @@ void rds_conn_shutdown(struct rds_connection *conn)
* conn - the reconnect is always triggered by the active peer. */
cancel_delayed_work_sync(&conn->c_conn_w);
rcu_read_lock();
- if (!hlist_unhashed(&conn->c_hash_node)) {
+ if (hash_hashed(&conn->c_hash_node)) {
rcu_read_unlock();
rds_queue_reconnect(conn);
} else {
@@ -329,7 +326,7 @@ void rds_conn_destroy(struct rds_connection *conn)
/* Ensure conn will not be scheduled for reconnect */
spin_lock_irq(&rds_conn_lock);
- hlist_del_init_rcu(&conn->c_hash_node);
+ hash_del(&conn->c_hash_node);
spin_unlock_irq(&rds_conn_lock);
synchronize_rcu();
@@ -375,7 +372,6 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
struct rds_info_lengths *lens,
int want_send)
{
- struct hlist_head *head;
struct hlist_node *pos;
struct list_head *list;
struct rds_connection *conn;
@@ -388,27 +384,24 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
rcu_read_lock();
- for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
- i++, head++) {
- hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) {
- if (want_send)
- list = &conn->c_send_queue;
- else
- list = &conn->c_retrans;
-
- spin_lock_irqsave(&conn->c_lock, flags);
-
- /* XXX too lazy to maintain counts.. */
- list_for_each_entry(rm, list, m_conn_item) {
- total++;
- if (total <= len)
- rds_inc_info_copy(&rm->m_inc, iter,
- conn->c_laddr,
- conn->c_faddr, 0);
- }
-
- spin_unlock_irqrestore(&conn->c_lock, flags);
+ hash_for_each_rcu(rds_conn_hash, i, pos, conn, c_hash_node) {
+ if (want_send)
+ list = &conn->c_send_queue;
+ else
+ list = &conn->c_retrans;
+
+ spin_lock_irqsave(&conn->c_lock, flags);
+
+ /* XXX too lazy to maintain counts.. */
+ list_for_each_entry(rm, list, m_conn_item) {
+ total++;
+ if (total <= len)
+ rds_inc_info_copy(&rm->m_inc, iter,
+ conn->c_laddr,
+ conn->c_faddr, 0);
}
+
+ spin_unlock_irqrestore(&conn->c_lock, flags);
}
rcu_read_unlock();
@@ -438,7 +431,6 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
size_t item_len)
{
uint64_t buffer[(item_len + 7) / 8];
- struct hlist_head *head;
struct hlist_node *pos;
struct rds_connection *conn;
size_t i;
@@ -448,23 +440,19 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
lens->nr = 0;
lens->each = item_len;
- for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
- i++, head++) {
- hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) {
-
- /* XXX no c_lock usage.. */
- if (!visitor(conn, buffer))
- continue;
-
- /* We copy as much as we can fit in the buffer,
- * but we count all items so that the caller
- * can resize the buffer. */
- if (len >= item_len) {
- rds_info_copy(iter, buffer, item_len);
- len -= item_len;
- }
- lens->nr++;
+ hash_for_each_rcu(rds_conn_hash, i, pos, conn, c_hash_node) {
+ /* XXX no c_lock usage.. */
+ if (!visitor(conn, buffer))
+ continue;
+
+ /* We copy as much as we can fit in the buffer,
+ * but we count all items so that the caller
+ * can resize the buffer. */
+ if (len >= item_len) {
+ rds_info_copy(iter, buffer, item_len);
+ len -= item_len;
}
+ lens->nr++;
}
rcu_read_unlock();
}
@@ -518,6 +506,8 @@ int rds_conn_init(void)
rds_info_register_func(RDS_INFO_RETRANS_MESSAGES,
rds_conn_message_info_retrans);
+ hash_init(rds_conn_hash);
+
return 0;
}
@@ -525,8 +515,6 @@ void rds_conn_exit(void)
{
rds_loop_exit();
- WARN_ON(!hlist_empty(rds_conn_hash));
-
kmem_cache_destroy(rds_conn_slab);
rds_info_deregister_func(RDS_INFO_CONNECTIONS, rds_conn_info);
--
1.7.8.6
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v3 15/17] openvswitch: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928@gmail.com>
Switch openvswitch to use the new hashtable implementation. This reduces the amount of
generic unrelated code in openvswitch.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
net/openvswitch/vport.c | 30 +++++++++++++-----------------
1 files changed, 13 insertions(+), 17 deletions(-)
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 6140336..3484120 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -27,6 +27,7 @@
#include <linux/rcupdate.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
+#include <linux/hashtable.h>
#include "vport.h"
#include "vport-internal_dev.h"
@@ -39,8 +40,8 @@ static const struct vport_ops *vport_ops_list[] = {
};
/* Protected by RCU read lock for reading, RTNL lock for writing. */
-static struct hlist_head *dev_table;
-#define VPORT_HASH_BUCKETS 1024
+#define VPORT_HASH_BITS 10
+static DEFINE_HASHTABLE(dev_table, VPORT_HASH_BITS);
/**
* ovs_vport_init - initialize vport subsystem
@@ -49,10 +50,7 @@ static struct hlist_head *dev_table;
*/
int ovs_vport_init(void)
{
- dev_table = kzalloc(VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
- GFP_KERNEL);
- if (!dev_table)
- return -ENOMEM;
+ hash_init(dev_table);
return 0;
}
@@ -67,12 +65,6 @@ void ovs_vport_exit(void)
kfree(dev_table);
}
-static struct hlist_head *hash_bucket(const char *name)
-{
- unsigned int hash = full_name_hash(name, strlen(name));
- return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
-}
-
/**
* ovs_vport_locate - find a port that has already been created
*
@@ -82,11 +74,11 @@ static struct hlist_head *hash_bucket(const char *name)
*/
struct vport *ovs_vport_locate(const char *name)
{
- struct hlist_head *bucket = hash_bucket(name);
struct vport *vport;
struct hlist_node *node;
+ int key = full_name_hash(name, strlen(name));
- hlist_for_each_entry_rcu(vport, node, bucket, hash_node)
+ hash_for_each_possible_rcu(dev_table, vport, node, hash_node, key)
if (!strcmp(name, vport->ops->get_name(vport)))
return vport;
@@ -170,14 +162,18 @@ struct vport *ovs_vport_add(const struct vport_parms *parms)
for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
if (vport_ops_list[i]->type == parms->type) {
+ int key;
+ const char *name;
+
vport = vport_ops_list[i]->create(parms);
if (IS_ERR(vport)) {
err = PTR_ERR(vport);
goto out;
}
- hlist_add_head_rcu(&vport->hash_node,
- hash_bucket(vport->ops->get_name(vport)));
+ name = vport->ops->get_name(vport);
+ key = full_name_hash(name, strlen(name));
+ hash_add_rcu(dev_table, &vport->hash_node, key);
return vport;
}
}
@@ -218,7 +214,7 @@ void ovs_vport_del(struct vport *vport)
{
ASSERT_RTNL();
- hlist_del_rcu(&vport->hash_node);
+ hash_del_rcu(&vport->hash_node);
vport->ops->destroy(vport);
}
--
1.7.8.6
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v3 16/17] tracing output: use new hashtable implementation
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch tracing to use the new hashtable implementation. This reduces the amount of
generic unrelated code in the tracing module.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
kernel/trace/trace_output.c | 20 ++++++++------------
1 files changed, 8 insertions(+), 12 deletions(-)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 123b189..1324c1a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -8,15 +8,15 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/ftrace.h>
+#include <linux/hashtable.h>
#include "trace_output.h"
-/* must be a power of 2 */
-#define EVENT_HASHSIZE 128
+#define EVENT_HASH_BITS 7
DECLARE_RWSEM(trace_event_mutex);
-static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
+static DEFINE_HASHTABLE(event_hash, EVENT_HASH_BITS);
static int next_event_type = __TRACE_LAST_TYPE + 1;
@@ -712,11 +712,8 @@ struct trace_event *ftrace_find_event(int type)
{
struct trace_event *event;
struct hlist_node *n;
- unsigned key;
- key = type & (EVENT_HASHSIZE - 1);
-
- hlist_for_each_entry(event, n, &event_hash[key], node) {
+ hash_for_each_possible(event_hash, event, n, node, type) {
if (event->type == type)
return event;
}
@@ -781,7 +778,6 @@ void trace_event_read_unlock(void)
*/
int register_ftrace_event(struct trace_event *event)
{
- unsigned key;
int ret = 0;
down_write(&trace_event_mutex);
@@ -833,9 +829,7 @@ int register_ftrace_event(struct trace_event *event)
if (event->funcs->binary == NULL)
event->funcs->binary = trace_nop_print;
- key = event->type & (EVENT_HASHSIZE - 1);
-
- hlist_add_head(&event->node, &event_hash[key]);
+ hash_add(event_hash, &event->node, event->type);
ret = event->type;
out:
@@ -850,7 +844,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_event);
*/
int __unregister_ftrace_event(struct trace_event *event)
{
- hlist_del(&event->node);
+ hash_del(&event->node);
list_del(&event->list);
return 0;
}
@@ -1323,6 +1317,8 @@ __init static int init_events(void)
}
}
+ hash_init(event_hash);
+
return 0;
}
early_initcall(init_events);
--
1.7.8.6
^ permalink raw reply related
* [PATCH v3 17/17] SUNRPC: use new hashtable implementation in auth
From: Sasha Levin @ 2012-08-22 2:27 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1345602432-27673-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch sunrpc/auth.c to use the new hashtable implementation. This reduces the amount of
generic unrelated code in auth.c.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
net/sunrpc/auth.c | 45 +++++++++++++++++++--------------------------
1 files changed, 19 insertions(+), 26 deletions(-)
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index b5c067b..5d50e2d 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -15,6 +15,7 @@
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/spinlock.h>
+#include <linux/hashtable.h>
#ifdef RPC_DEBUG
# define RPCDBG_FACILITY RPCDBG_AUTH
@@ -222,7 +223,7 @@ static DEFINE_SPINLOCK(rpc_credcache_lock);
static void
rpcauth_unhash_cred_locked(struct rpc_cred *cred)
{
- hlist_del_rcu(&cred->cr_hash);
+ hash_del_rcu(&cred->cr_hash);
smp_mb__before_clear_bit();
clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags);
}
@@ -249,16 +250,15 @@ int
rpcauth_init_credcache(struct rpc_auth *auth)
{
struct rpc_cred_cache *new;
- unsigned int hashsize;
new = kmalloc(sizeof(*new), GFP_KERNEL);
if (!new)
goto out_nocache;
new->hashbits = auth_hashbits;
- hashsize = 1U << new->hashbits;
- new->hashtable = kcalloc(hashsize, sizeof(new->hashtable[0]), GFP_KERNEL);
+ new->hashtable = kmalloc(HASH_REQUIRED_SIZE(new->hashbits), GFP_KERNEL);
if (!new->hashtable)
goto out_nohashtbl;
+ hash_init_size(new->hashtable, new->hashbits);
spin_lock_init(&new->lock);
auth->au_credcache = new;
return 0;
@@ -292,25 +292,20 @@ void
rpcauth_clear_credcache(struct rpc_cred_cache *cache)
{
LIST_HEAD(free);
- struct hlist_head *head;
+ struct hlist_node *n, *t;
struct rpc_cred *cred;
- unsigned int hashsize = 1U << cache->hashbits;
- int i;
+ int i;
spin_lock(&rpc_credcache_lock);
spin_lock(&cache->lock);
- for (i = 0; i < hashsize; i++) {
- head = &cache->hashtable[i];
- while (!hlist_empty(head)) {
- cred = hlist_entry(head->first, struct rpc_cred, cr_hash);
- get_rpccred(cred);
- if (!list_empty(&cred->cr_lru)) {
- list_del(&cred->cr_lru);
- number_cred_unused--;
- }
- list_add_tail(&cred->cr_lru, &free);
- rpcauth_unhash_cred_locked(cred);
+ hash_for_each_safe_size(cache->hashtable, cache->hashbits, i, n, t, cred, cr_hash) {
+ get_rpccred(cred);
+ if (!list_empty(&cred->cr_lru)) {
+ list_del(&cred->cr_lru);
+ number_cred_unused--;
}
+ list_add_tail(&cred->cr_lru, &free);
+ rpcauth_unhash_cred_locked(cred);
}
spin_unlock(&cache->lock);
spin_unlock(&rpc_credcache_lock);
@@ -408,14 +403,11 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
LIST_HEAD(free);
struct rpc_cred_cache *cache = auth->au_credcache;
struct hlist_node *pos;
- struct rpc_cred *cred = NULL,
- *entry, *new;
- unsigned int nr;
-
- nr = hash_long(acred->uid, cache->hashbits);
+ struct rpc_cred *cred = NULL, *entry = NULL, *new;
rcu_read_lock();
- hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) {
+ hash_for_each_possible_rcu_size(cache->hashtable, cred, cache->hashbits,
+ pos, cr_hash, acred->uid) {
if (!entry->cr_ops->crmatch(acred, entry, flags))
continue;
spin_lock(&cache->lock);
@@ -439,7 +431,8 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
}
spin_lock(&cache->lock);
- hlist_for_each_entry(entry, pos, &cache->hashtable[nr], cr_hash) {
+ hash_for_each_possible_size(cache->hashtable, entry, cache->hashbits, pos,
+ cr_hash, acred->uid) {
if (!entry->cr_ops->crmatch(acred, entry, flags))
continue;
cred = get_rpccred(entry);
@@ -448,7 +441,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
if (cred == NULL) {
cred = new;
set_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags);
- hlist_add_head_rcu(&cred->cr_hash, &cache->hashtable[nr]);
+ hash_add_size(cache->hashtable, cache->hashbits, &cred->cr_hash, acred->uid);
} else
list_add_tail(&new->cr_lru, &free);
spin_unlock(&cache->lock);
--
1.7.8.6
^ permalink raw reply related
* Re: [PATCH 0/3] x86_64, sfc: 128-bit memory-mapped I/O
From: H. Peter Anvin @ 2012-08-22 2:31 UTC (permalink / raw)
To: Ben Hutchings
Cc: Thomas Gleixner, Ingo Molnar, netdev, linux-net-drivers, x86
In-Reply-To: <1345601423.2659.100.camel@bwh-desktop.uk.solarflarecom.com>
On 08/21/2012 07:10 PM, Ben Hutchings wrote:
>>
>> Yes, you have to make sure you properly enforce the necessary ordering
>> requirements manually (I think you can do that with sfence).
>
> We did put an sfence after the writes to each register. But some
> systems only want to combine writes that cover an entire cache line, and
> the writes covering a 128-bit register get broken back up into multiple
> writes at the PCIe level. And on some systems these are sent in
> decreasing address order, which breaks the rules for writing to
> TX_DESC_UPD.
>
> To avoid this we'd have to put an sfence in between the writes to a
> register, leaving us back where we started.
>
You realize the same applies to 128-bit writes, right? Some cores
and/or systems will break them up.
-hpa
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: David Miller @ 2012-08-22 2:34 UTC (permalink / raw)
To: bhutchings; +Cc: hpa, tglx, mingo, netdev, linux-net-drivers, x86
In-Reply-To: <1345601051.2659.93.camel@bwh-desktop.uk.solarflarecom.com>
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 22 Aug 2012 03:04:11 +0100
> On Tue, 2012-08-21 at 18:37 -0700, H. Peter Anvin wrote:
>> On 08/21/2012 06:23 PM, Ben Hutchings wrote:
>> > Define reado(), writeo() and their raw counterparts using SSE.
>> >
>> > Based on work by Stuart Hodgson <smhodgson@solarflare.com>.
>>
>> It would be vastly better if we explicitly controlled this with
>> kernel_fpu_begin()/kernel_fpu_end() rather than hiding it in primitives
>> than might tempt the user to do very much the wrong thing.
>>
>> Also, it needs to be extremely clear to the user that these operations
>> use the FPU, and all the requirements there need to be met, including
>> not using them at interrupt time.
>
> Well we can sometimes use the FPU state at IRQ time, can't we
> (irq_fpu_usable())? So we might need, say, try_reado() and
> try_writeo() with callers expected to fall back to alternatives. (Which
> they must have anyway for any architecture that doesn't support this.)
I really hope we eventually get rid of this rediculous restriction the
x86 code has.
It really needs a proper stack of FPU state saves like sparc64 has.
Half of the code and complexity in arch/x86/crypto/ would just
disappear, because most of it has to do with handling this obtuse
FPU usage restriction which shouldn't even be an issue in the first
place.
I continually see more and more code that has to check this
irq_fpu_usable() thing, and have ugly fallback code, and therefore is
a sign that this really needs to be fixed properly.
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: H. Peter Anvin @ 2012-08-22 3:24 UTC (permalink / raw)
To: David Miller
Cc: bhutchings, tglx, mingo, netdev, linux-net-drivers, x86,
Linus Torvalds
In-Reply-To: <20120821.193446.1534561579811962053.davem@davemloft.net>
On 08/21/2012 07:34 PM, David Miller wrote:
>
> I really hope we eventually get rid of this rediculous restriction the
> x86 code has.
>
> It really needs a proper stack of FPU state saves like sparc64 has.
>
> Half of the code and complexity in arch/x86/crypto/ would just
> disappear, because most of it has to do with handling this obtuse
> FPU usage restriction which shouldn't even be an issue in the first
> place.
>
> I continually see more and more code that has to check this
> irq_fpu_usable() thing, and have ugly fallback code, and therefore is
> a sign that this really needs to be fixed properly.
>
[Cc: Linus, since he has had very strong opinions on this in the past.]
I'm all ears... tell me how sparc64 deals with this, maybe we can
implement something similar. At the same time, do keep in mind that on
x86 this is not just a matter of the FPU state, but the entire "extended
state" which can be very large.
Given the cost of state save/enable, however, nothing is going to change
the need for kernel_fpu_begin/end, nor the fact that those things will
want to bracket large regions.
-hpa
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: David Miller @ 2012-08-22 3:29 UTC (permalink / raw)
To: hpa; +Cc: bhutchings, tglx, mingo, netdev, linux-net-drivers, x86, torvalds
In-Reply-To: <503450E2.2040504@zytor.com>
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Tue, 21 Aug 2012 20:24:18 -0700
> I'm all ears... tell me how sparc64 deals with this, maybe we can
> implement something similar. At the same time, do keep in mind that on
> x86 this is not just a matter of the FPU state, but the entire "extended
> state" which can be very large.
Sparc's state is pretty huge too. 256 bytes worth of FPU registers,
plus a set of 64-bit control registers.
What we do is we have a FPU stack that grows up from the end of the
thread_info struct, towards the bottom of the kernel stack.
Slot 0 is always the user FPU state.
Slot 1 and further are kernel FPU state save areas.
We hold a counter which keep track of how far deeply saved we are
in the stack.
Not for the purpose of space saving, but for overhead reduction we
sometimes can get away with only saving away half of the FPU
registers. The chip provides a pair of dirty bits, one for the lower
half of the FPU register file and one for the upper half. We only
save the bits that are actually dirty.
Furthermore, when we have FPU using code in the kernel that only uses
the lower half of the registers, we only save away that part of the
state around the routine.
^ permalink raw reply
* [PATCH RFC] ipv6: Add net.ipv6.conf.*.accept_ra_defrtr_table sysctl.
From: Ben Jencks @ 2012-08-22 3:48 UTC (permalink / raw)
To: netdev
Allows configuration of the routing table to which default routes from
RAs are added on a per-interface basis.
One use case where this is required is a multi-homed router advertising
multiple prefixes, one for each upstream. The proper routing policy is
something like:
0: from all lookup local
10: from all lookup main
20: from <prefix1> lookup provider1
30: from <prefix2> lookup provider2
with directly connected and internal routes in main, and default routes
from providers 1 and 2 in their respective tables. With static routes
this is straightforward; if the route for either or both providers is
received via RA this configuration option becomes necessary to put the
routes in the appropriate tables.
Signed-off-by: Ben Jencks <ben@bjencks.net>
---
Patch is against v3.5.2, but applies cleanly to master as of today.
Looking for feedback on:
* Is this a worthwhile feature? Did I miss a good way to do this in
userspace?
* Is a sysctl the right place to configure it? I know it's discouraged
to add new ones, but it seems to fit best with the other similar
configuration options.
* Is the rt6_purge_dflt_routers behavior correct? Should
addrconf_fixup_forwarding be modified so that in the single device
case it only purges from that device's table?
Documentation/networking/ip-sysctl.txt | 6 +++++
include/linux/ipv6.h | 2 ++
include/linux/sysctl.h | 1 +
kernel/sysctl_binary.c | 1 +
net/ipv6/addrconf.c | 10 +++++++
net/ipv6/route.c | 45 ++++++++++++++++++++++----------
6 files changed, 51 insertions(+), 14 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6f896b9..0d0947a 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1085,6 +1085,12 @@ accept_ra_defrtr - BOOLEAN
Functional default: enabled if accept_ra is enabled.
disabled if accept_ra is disabled.
+accept_ra_defrtr_table - INTEGER
+ Routing table into which to put default route learned via Router
+ Advertisement.
+
+ Functional default: "main" routing table (254)
+
accept_ra_pinfo - BOOLEAN
Learn Prefix Information in Router Advertisement.
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 8260ef7..fa9b4fe 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -153,6 +153,7 @@ struct ipv6_devconf {
#endif
__s32 max_addresses;
__s32 accept_ra_defrtr;
+ __s32 accept_ra_defrtr_table;
__s32 accept_ra_pinfo;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
@@ -202,6 +203,7 @@ enum {
DEVCONF_MAX_ADDRESSES,
DEVCONF_FORCE_MLD_VERSION,
DEVCONF_ACCEPT_RA_DEFRTR,
+ DEVCONF_ACCEPT_RA_DEFRTR_TABLE,
DEVCONF_ACCEPT_RA_PINFO,
DEVCONF_ACCEPT_RA_RTR_PREF,
DEVCONF_RTR_PROBE_INTERVAL,
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index c34b4c8..80115c8 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -568,6 +568,7 @@ enum {
NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN=22,
NET_IPV6_PROXY_NDP=23,
NET_IPV6_ACCEPT_SOURCE_ROUTE=25,
+ NET_IPV6_ACCEPT_RA_DEFRTR_TABLE=26,
__NET_IPV6_MAX
};
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index a650694..da964f3 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -517,6 +517,7 @@ static const struct bin_table bin_net_ipv6_conf_var_table[] = {
{ CTL_INT, NET_IPV6_MAX_ADDRESSES, "max_addresses" },
{ CTL_INT, NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" },
{ CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR_TABLE, "accept_ra_defrtr_table" },
{ CTL_INT, NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" },
{ CTL_INT, NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" },
{ CTL_INT, NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" },
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8f6411c..2bdb96c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -188,6 +188,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
#endif
.max_addresses = IPV6_MAX_ADDRESSES,
.accept_ra_defrtr = 1,
+ .accept_ra_defrtr_table = RT6_TABLE_DFLT,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -222,6 +223,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
#endif
.max_addresses = IPV6_MAX_ADDRESSES,
.accept_ra_defrtr = 1,
+ .accept_ra_defrtr_table = RT6_TABLE_DFLT,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -3894,6 +3896,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
#endif
array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+ array[DEVCONF_ACCEPT_RA_DEFRTR_TABLE] = cnf->accept_ra_defrtr_table;
array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
#ifdef CONFIG_IPV6_ROUTER_PREF
array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -4496,6 +4499,13 @@ static struct addrconf_sysctl_table
.proc_handler = proc_dointvec,
},
{
+ .procname = "accept_ra_defrtr_table",
+ .data = &ipv6_devconf.accept_ra_defrtr_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_pinfo",
.data = &ipv6_devconf.accept_ra_pinfo,
.maxlen = sizeof(int),
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index becb048..dafcb61 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1916,8 +1916,12 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
{
struct rt6_info *rt;
struct fib6_table *table;
+ struct inet6_dev *idev;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+ idev = __in6_dev_get(dev);
+ if (!idev)
+ return NULL;
+ table = fib6_get_table(dev_net(dev), idev->cnf.accept_ra_defrtr_table);
if (!table)
return NULL;
@@ -1939,7 +1943,6 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_DFLT,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -1948,7 +1951,12 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = dev_net(dev),
};
+ struct inet6_dev *idev;
+ /* idev should not be null, since we were called from
+ * ndisc_router_discovery which already checked it */
+ idev = __in6_dev_get(dev);
+ cfg.fc_table = idev->cnf.accept_ra_defrtr_table;
cfg.fc_gateway = *gwaddr;
ip6_route_add(&cfg);
@@ -1960,23 +1968,32 @@ void rt6_purge_dflt_routers(struct net *net)
{
struct rt6_info *rt;
struct fib6_table *table;
+ struct net_device *dev;
+ struct inet6_dev *idev;
- /* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (!table)
- return;
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (idev == NULL) {
+ continue;
+ }
+ table = fib6_get_table(net, idev->cnf.accept_ra_defrtr_table);
+ if (!table)
+ continue;
restart:
- read_lock_bh(&table->tb6_lock);
- for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- ip6_del_rt(rt);
- goto restart;
+ read_lock_bh(&table->tb6_lock);
+ for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
+ dst_hold(&rt->dst);
+ read_unlock_bh(&table->tb6_lock);
+ ip6_del_rt(rt);
+ goto restart;
+ }
}
+ read_unlock_bh(&table->tb6_lock);
}
- read_unlock_bh(&table->tb6_lock);
+ rcu_read_unlock();
}
static void rtmsg_to_fib6_config(struct net *net,
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: H. Peter Anvin @ 2012-08-22 3:49 UTC (permalink / raw)
To: David Miller
Cc: bhutchings, tglx, mingo, netdev, linux-net-drivers, x86, torvalds
In-Reply-To: <20120821.202945.2278895156403194101.davem@davemloft.net>
On 08/21/2012 08:29 PM, David Miller wrote:
>
> What we do is we have a FPU stack that grows up from the end of the
> thread_info struct, towards the bottom of the kernel stack.
>
We have 8K of kernel stack, and an xstate which is pushing a kilobyte
already. This seems like a nightmare. Even if we allocate a larger
stack for this sole purpose, we'd have to put a pretty hard cap on how
far it could grow.
> Slot 0 is always the user FPU state.
>
> Slot 1 and further are kernel FPU state save areas.
>
> We hold a counter which keep track of how far deeply saved we are
> in the stack.
>
> Not for the purpose of space saving, but for overhead reduction we
> sometimes can get away with only saving away half of the FPU
> registers. The chip provides a pair of dirty bits, one for the lower
> half of the FPU register file and one for the upper half. We only
> save the bits that are actually dirty.
>
> Furthermore, when we have FPU using code in the kernel that only uses
> the lower half of the registers, we only save away that part of the
> state around the routine.
This is messy on x86; it is somewhat doable but it gets really hairy
because of the monolithic [f]xsave/[f]xrstor instruction.
-hpa
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: Linus Torvalds @ 2012-08-22 3:52 UTC (permalink / raw)
To: H. Peter Anvin
Cc: David Miller, bhutchings, tglx, mingo, netdev, linux-net-drivers,
x86
In-Reply-To: <503450E2.2040504@zytor.com>
On Tue, Aug 21, 2012 at 8:24 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>
>> I continually see more and more code that has to check this
>> irq_fpu_usable() thing, and have ugly fallback code, and therefore is
>> a sign that this really needs to be fixed properly.
>>
>
> [Cc: Linus, since he has had very strong opinions on this in the past.]
I have strong opinions, because I don't think you *can* do it any
other way on x86.
Saving FPU state on kernel entry IS NOT GOING TO HAPPEN. End of story.
It's too f*cking slow.
And if we don't save it, we cannot use the FP state in kernel mode
without explicitly checking, because the FPU state may not be there,
and touching FP registers can cause exceptions etc. In fact, under
many loads the exception is going to be the common case.
Keeping the FP state live all the time (and then perhaps just saving a
single MMX register for kernel use) and switching it synchronously on
every task switch sounds like a really really bad idea too. It
apparently works better on modern CPU's, but it sucked horribly on
older ones. The FPU state save is horribly expensive, to the point
that we saw it very clearly on benchmarks for signal handling and task
switching.
So the normal operation is going to be "touching the FPU causes a fault".
That said, we might *try* to make the kernel FPU use be cheaper. We
could do something like:
- if we need to restore FPU state for user mode, don't do it
synchronously in kernel_fpu_end(), just set a work-flag, and do it
just once before returning to user mode
- that makes kernel_fpu_end() a no-op, and while we can't get rid of
kernel_fpu_begin(), we could at least make it cheap to do many times
consecutively (ie we'd have to check "who owns FPU state" and perhaps
save it, but the save would have to be done only the first time).
I haven't seen the patch being discussed, or the rationale for it. But
I doubt it makes sense to do 128-bit MMIO and expect any kind of
atomicity things anyway, and I very much doubt that using SSE would
make all that much sense. What's the background, and why would you
want to do this crap?
Linus
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: H. Peter Anvin @ 2012-08-22 3:59 UTC (permalink / raw)
To: Linus Torvalds
Cc: David Miller, bhutchings, tglx, mingo, netdev, linux-net-drivers,
x86
In-Reply-To: <CA+55aFy=ohFoZ1yZGdj1DCcNXU9gsndgH9Qod4q8+s=sbGKUzQ@mail.gmail.com>
On 08/21/2012 08:52 PM, Linus Torvalds wrote:
>
> That said, we might *try* to make the kernel FPU use be cheaper. We
> could do something like:
>
> - if we need to restore FPU state for user mode, don't do it
> synchronously in kernel_fpu_end(), just set a work-flag, and do it
> just once before returning to user mode
>
> - that makes kernel_fpu_end() a no-op, and while we can't get rid of
> kernel_fpu_begin(), we could at least make it cheap to do many times
> consecutively (ie we'd have to check "who owns FPU state" and perhaps
> save it, but the save would have to be done only the first time).
>
The zeroeth order thing we should do is to make it nest; there are cases
where we do multiple kernel_fpu_begin/_end in sequence for no good reason.
kernel_fpu_end() would still have to re-enable preemption (and
preemption would have to check the work flag), but that should be cheap.
We could allow the FPU in the kernel to have preemption, if we allocated
space for two xstates per thread instead of one. That is, however, a
fair hunk of memory.
-hpa
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: David Miller @ 2012-08-22 4:14 UTC (permalink / raw)
To: hpa; +Cc: torvalds, bhutchings, tglx, mingo, netdev, linux-net-drivers, x86
In-Reply-To: <5034591E.3040908@zytor.com>
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Tue, 21 Aug 2012 20:59:26 -0700
> kernel_fpu_end() would still have to re-enable preemption (and
> preemption would have to check the work flag), but that should be cheap.
>
> We could allow the FPU in the kernel to have preemption, if we allocated
> space for two xstates per thread instead of one. That is, however, a
> fair hunk of memory.
Once you have done the first FPU save for the sake of the kernel, you
can minimize what you save for any deeper nesting because the kernel
only cares about a very limited part of that FPU state not the whole
1K thing.
Those bits you can save by hand with a bunch of explicit stores of the
XMM registers, or something like that.
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: Linus Torvalds @ 2012-08-22 4:35 UTC (permalink / raw)
To: H. Peter Anvin
Cc: David Miller, bhutchings, tglx, mingo, netdev, linux-net-drivers,
x86
In-Reply-To: <5034591E.3040908@zytor.com>
On Tue, Aug 21, 2012 at 8:59 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>
> kernel_fpu_end() would still have to re-enable preemption (and
> preemption would have to check the work flag), but that should be cheap.
No, done right, you don't even have to disable preemption. Sure, you
might disable preemption inside of kernel_fpu_begin() itself (around
the test for "do we need to save FPU state and set the flag to restore
it at return-to-user-mode time"), but I think that you should be able
to run the code afterwards with preemption enabled.
Why? Because you've saved the FPU state, and you've set the per-thread
flag saying "I will restore at return to user mode". And that, coupled
with teaching the scheduler about this case ("don't set TS, only save
xmm0 in a special kernel-xmm0-save-area") means that the thing can
preempt fine.
The nesting case would be about just saving (again) that xmm0 register
in any nested kernel_fpu_begin/end pair. But that doesn't need
preemption, that just needs local storage for the kernel_fpu_begin/end
(and it can do the xmm0 save/restore with regular "mov" instructions,
because the kernel owns the FPU at that point, since it's nested).
So it's doable. One question is how many registers to save for kernel
use. It might be that we'd need to make that a "actual FPU user needs
to save/restore the registers it uses", and not do the saving in
kernel_fpu_begin()/end() at all.
My biggest reason to question this all is that I don't think it's
worth it. Why would we ever care to do all this in the first place?
There's no really sane use for it.
Judging from the subject line, some crazy person wants to do 128-bit
MMIO. That's just crap. Nobody sane cares. Do it non-atomically with
regular accesses. If it's high-performance IO, it uses DMA. If it
doesn't use DMA and depends on CPU MMIO accesses, WHO THE F*CK CARES?
Nobody.
And if some crazy device depends on 128-bit atomic writes, the device
is shit. Forget about it. Tell people to stop digging themselves
deeper down a hole it's simply not worth going.
Linus
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: Linus Torvalds @ 2012-08-22 4:42 UTC (permalink / raw)
To: H. Peter Anvin
Cc: David Miller, bhutchings, tglx, mingo, netdev, linux-net-drivers,
x86
In-Reply-To: <CA+55aFy=ohFoZ1yZGdj1DCcNXU9gsndgH9Qod4q8+s=sbGKUzQ@mail.gmail.com>
On Tue, Aug 21, 2012 at 8:52 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> I haven't seen the patch being discussed, or the rationale for it. But
> I doubt it makes sense to do 128-bit MMIO and expect any kind of
> atomicity things anyway, and I very much doubt that using SSE would
> make all that much sense. What's the background, and why would you
> want to do this crap?
Btw, for the 64-bit case, we did have ordering issues, and maybe some
128-bit model has similar ordering issues. Fine. You can't rely on
128-bit atomic accesses anyway on 99% of all hardware - either the CPU
itself cannot do it, or it's too damn inconvenient with XMM only
registers, or the bus itself is limited to 64 bits at a time anyway,
so the CPU or the IO interface would split such an access *anyway*.
So the whole concept of "we rely on atomic 128-bit MMIO accesses"
seems terminally broken. Any driver that thinks it needs that is just
crazy.
And those issues have nothing to do with x86 kernel_fpu_begin/end()
what-so-ever.
So judging by that, I would say that some driver writer needs to take
a few pills, clear up their head, and take another look at their life.
Tell them to look at
include/asm-generic/io-64-nonatomic-hi-lo.h
(and *-lo-hi.h) instead, and ponder the wisdom of just doing it that
way. Tell them to go f*ck themselves if they think they need XMM
registers. They are wrong, for one reason or another.
Linus
^ permalink raw reply
* copy_skb_header() and sk_buff flags (question)
From: Kevin Wilson @ 2012-08-22 4:55 UTC (permalink / raw)
To: netdev
Hello,
I have a question if I may, as I cannot understand this point:
I try to understand why in __copy_skb_header() we copy various flags
(like ip_summed,
local_df, pkt_type, priority, ipvs_property, and more. But there are
flags which we do
not copy, like nohdr, or fclone, or peeked.
Aren't these flags part of the sk_buff header?
regards,
Kevin
^ permalink raw reply
* Re: [PATCH 2/3] x86_64: Define 128-bit memory-mapped I/O operations
From: David Miller @ 2012-08-22 5:00 UTC (permalink / raw)
To: torvalds; +Cc: hpa, bhutchings, tglx, mingo, netdev, linux-net-drivers, x86
In-Reply-To: <CA+55aFz39tCSO7sf7+czNEBcEx7q4=KbnAcKEoS-KBwr6D3Psg@mail.gmail.com>
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 21 Aug 2012 21:35:22 -0700
> My biggest reason to question this all is that I don't think it's
> worth it. Why would we ever care to do all this in the first place?
> There's no really sane use for it.
All the x86 crypto code hits this case all the time, easiest example
is doing a dm-crypt on a block device when an IPSEC packet arrives.
The crypto code has all of this special code and layering that is
there purely so it can fall back to the slow non-optimized version
of the crypto operation when it hits this can't-nest-fpu-saving
situation.
^ permalink raw reply
* Re[2]: [PATCH 05/19] netfilter: nf_conntrack_ipv6: improve fragmentation handling
From: Hans Schillstrom @ 2012-08-22 5:01 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Patrick McHardy, netfilter-devel, netdev, Julian Anastasov,
Hans Schillstrom
Hi
>
>On Sun, 2012-08-19 at 21:44 +0200, Patrick McHardy wrote:
>> On Sun, 19 Aug 2012, Jesper Dangaard Brouer wrote:
>> > On Sat, 2012-08-18 at 14:26 +0200, Patrick McHardy wrote:
>[...]
>
>> > Don't I need to load some of the helper modules, or just the
>> > nf_conntrack_ipv6 module, or perhaps only nf_defrag_ipv6 ?
>>
>> Not with the entire patchset, just IPv6 conntrack is enough. Aith IPv6 NAT
>> the first packet of a connection must always be defragemented, independant
>> of an assigned helper.
>
>When loading "nf_conntrack_ipv6" I run into issues.
>
>When sending a fragmented UDP packet. With these patches, the IPVS
>stack will no longer see the fragmented packets, but instead see one
>large SKB. This will trigger a MTU path check in e.g.
>ip_vs_dr_xmit_v6() and an ICMPv6 too big packet is send back.
>
> IPVS: ip_vs_dr_xmit_v6(): frag needed
>
>Perhaps we could change/fix the MTU check in IPVS?
>(This would also solve issues I've seen with TSO/GSO frames, hitting
>this code path).
>
I ran into this as well,
try this for the mtu check.
if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
(IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
/Hans
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v7] bonding: support for IPv6 transmit hashing
From: John Eaglesham @ 2012-08-22 5:12 UTC (permalink / raw)
To: netdev; +Cc: John Eaglesham
In-Reply-To: <eb20e8f67e6aad94c233219e058c3e793ed755cb.1341167171.git.linux@8192.net>
From: John Eaglesham <linux@8192.net>
Currently the "bonding" driver does not support load balancing outgoing
traffic in LACP mode for IPv6 traffic. IPv4 (and TCP or UDP over IPv4)
are currently supported; this patch adds transmit hashing for IPv6 (and
TCP or UDP over IPv6), bringing IPv6 up to par with IPv4 support in the
bonding driver. In addition, bounds checking has been added to all
transmit hashing functions.
The algorithm chosen (xor'ing the bottom three quads of the source and
destination addresses together, then xor'ing each byte of that result into
the bottom byte, finally xor'ing with the last bytes of the MAC addresses)
was selected after testing almost 400,000 unique IPv6 addresses harvested
from server logs. This algorithm had the most even distribution for both
big- and little-endian architectures while still using few instructions. Its
behavior also attempts to closely match that of the IPv4 algorithm.
The IPv6 flow label was intentionally not included in the hash as it appears
to be unset in the vast majority of IPv6 traffic sampled, and the current
algorithm not using the flow label already offers a very even distribution.
Fragmented IPv6 packets are handled the same way as fragmented IPv4 packets,
ie, they are not balanced based on layer 4 information. Additionally,
IPv6 packets with intermediate headers are not balanced based on layer
4 information. In practice these intermediate headers are not common and
this should not cause any problems, and the alternative (a packet-parsing
loop and look-up table) seemed slow and complicated for little gain.
Changes:
v2)
* Clarify description
* Add bounds checking to more functions
* All functions call bond_xmit_hash_policy_l2 rather than re-
implement the same logic.
v3)
* Patch against net-next.
* Style corrections.
v4)
* Correct indenting.
v5)
* Squash documentation and code patches into one.
v6)
* Modify IPv6 hash to behave more like the IPv4 hash, update
documentation with modified algorithm.
* Clean up formatting.
* Move all variable declaration to the top of the function.
* Minor change to IPv6 layer 4 hash to match IPv4 hash behavior
(mix all hashed address bits together rather than just the
bottom 24 bits).
v7)
* Improve bounds checking code (handle truncated IPv6 header,
removed goto, fewer if statements).
* Re-write pseudocode in documentation to match actual code more
closely.
* Correct indenting, align parentheses, wrap code at <= 80 columns
(based on Jay's changes).
Patch has been tested and performs as expected.
Signed-off-by: John Eaglesham
---
Documentation/networking/bonding.txt | 30 ++++++++++--
drivers/net/bonding/bond_main.c | 89 +++++++++++++++++++++++++-----------
2 files changed, 88 insertions(+), 31 deletions(-)
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 6b1c711..10a015c 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -752,12 +752,22 @@ xmit_hash_policy
protocol information to generate the hash.
Uses XOR of hardware MAC addresses and IP addresses to
- generate the hash. The formula is
+ generate the hash. The IPv4 formula is
(((source IP XOR dest IP) AND 0xffff) XOR
( source MAC XOR destination MAC ))
modulo slave count
+ The IPv6 formula is
+
+ hash = (source ip quad 2 XOR dest IP quad 2) XOR
+ (source ip quad 3 XOR dest IP quad 3) XOR
+ (source ip quad 4 XOR dest IP quad 4)
+
+ (((hash >> 24) XOR (hash >> 16) XOR (hash >> 8) XOR hash)
+ XOR (source MAC XOR destination MAC))
+ modulo slave count
+
This algorithm will place all traffic to a particular
network peer on the same slave. For non-IP traffic,
the formula is the same as for the layer2 transmit
@@ -778,19 +788,29 @@ xmit_hash_policy
slaves, although a single connection will not span
multiple slaves.
- The formula for unfragmented TCP and UDP packets is
+ The formula for unfragmented IPv4 TCP and UDP packets is
((source port XOR dest port) XOR
((source IP XOR dest IP) AND 0xffff)
modulo slave count
- For fragmented TCP or UDP packets and all other IP
- protocol traffic, the source and destination port
+ The formula for unfragmented IPv6 TCP and UDP packets is
+
+ hash = (source port XOR dest port) XOR
+ ((source ip quad 2 XOR dest IP quad 2) XOR
+ (source ip quad 3 XOR dest IP quad 3) XOR
+ (source ip quad 4 XOR dest IP quad 4))
+
+ ((hash >> 24) XOR (hash >> 16) XOR (hash >> 8) XOR hash)
+ modulo slave count
+
+ For fragmented TCP or UDP packets and all other IPv4 and
+ IPv6 protocol traffic, the source and destination port
information is omitted. For non-IP traffic, the
formula is the same as for the layer2 transmit hash
policy.
- This policy is intended to mimic the behavior of
+ The IPv4 policy is intended to mimic the behavior of
certain switches, notably Cisco switches with PFC2 as
well as some Foundry and IBM products.
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d95fbc3..4221e57 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3354,56 +3354,93 @@ static struct notifier_block bond_netdev_notifier = {
/*---------------------------- Hashing Policies -----------------------------*/
/*
+ * Hash for the output device based upon layer 2 data
+ */
+static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
+{
+ struct ethhdr *data = (struct ethhdr *)skb->data;
+
+ if (skb_headlen(skb) >= offsetof(struct ethhdr, h_proto))
+ return (data->h_dest[5] ^ data->h_source[5]) % count;
+
+ return 0;
+}
+
+/*
* Hash for the output device based upon layer 2 and layer 3 data. If
- * the packet is not IP mimic bond_xmit_hash_policy_l2()
+ * the packet is not IP, fall back on bond_xmit_hash_policy_l2()
*/
static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
- struct iphdr *iph = ip_hdr(skb);
-
- if (skb->protocol == htons(ETH_P_IP)) {
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ u32 v6hash;
+ __be32 *s, *d;
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ skb_network_header_len(skb) >= sizeof(*iph)) {
+ iph = ip_hdr(skb);
return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^
(data->h_dest[5] ^ data->h_source[5])) % count;
+ } else if (skb->protocol == htons(ETH_P_IPV6) &&
+ skb_network_header_len(skb) >= sizeof(*ipv6h)) {
+ ipv6h = ipv6_hdr(skb);
+ s = &ipv6h->saddr.s6_addr32[0];
+ d = &ipv6h->daddr.s6_addr32[0];
+ v6hash = (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
+ v6hash ^= (v6hash >> 24) ^ (v6hash >> 16) ^ (v6hash >> 8);
+ return (v6hash ^ data->h_dest[5] ^ data->h_source[5]) % count;
}
- return (data->h_dest[5] ^ data->h_source[5]) % count;
+ return bond_xmit_hash_policy_l2(skb, count);
}
/*
* Hash for the output device based upon layer 3 and layer 4 data. If
* the packet is a frag or not TCP or UDP, just use layer 3 data. If it is
- * altogether not IP, mimic bond_xmit_hash_policy_l2()
+ * altogether not IP, fall back on bond_xmit_hash_policy_l2()
*/
static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count)
{
- struct ethhdr *data = (struct ethhdr *)skb->data;
- struct iphdr *iph = ip_hdr(skb);
- __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
- int layer4_xor = 0;
-
- if (skb->protocol == htons(ETH_P_IP)) {
+ u32 layer4_xor = 0;
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ __be32 *s, *d;
+ __be16 *layer4hdr;
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ skb_network_header_len(skb) >= sizeof(*iph)) {
+ iph = ip_hdr(skb);
if (!ip_is_fragment(iph) &&
(iph->protocol == IPPROTO_TCP ||
- iph->protocol == IPPROTO_UDP)) {
- layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1)));
+ iph->protocol == IPPROTO_UDP) &&
+ (skb_headlen(skb) - skb_network_offset(skb) >=
+ iph->ihl * sizeof(u32) + sizeof(*layer4hdr) * 2)) {
+ layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
+ layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1));
}
return (layer4_xor ^
((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
-
+ } else if (skb->protocol == htons(ETH_P_IPV6) &&
+ skb_network_header_len(skb) >= sizeof(*ipv6h)) {
+ ipv6h = ipv6_hdr(skb);
+ if ((ipv6h->nexthdr == IPPROTO_TCP ||
+ ipv6h->nexthdr == IPPROTO_UDP) &&
+ (skb_headlen(skb) - skb_network_offset(skb) >=
+ sizeof(*ipv6h) + sizeof(*layer4hdr) * 2)) {
+ layer4hdr = (__be16 *)(ipv6h + 1);
+ layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1));
+ }
+ s = &ipv6h->saddr.s6_addr32[0];
+ d = &ipv6h->daddr.s6_addr32[0];
+ layer4_xor ^= (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
+ layer4_xor ^= (layer4_xor >> 24) ^ (layer4_xor >> 16) ^
+ (layer4_xor >> 8);
+ return layer4_xor % count;
}
- return (data->h_dest[5] ^ data->h_source[5]) % count;
-}
-
-/*
- * Hash for the output device based upon layer 2 data
- */
-static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
-{
- struct ethhdr *data = (struct ethhdr *)skb->data;
-
- return (data->h_dest[5] ^ data->h_source[5]) % count;
+ return bond_xmit_hash_policy_l2(skb, count);
}
/*-------------------------- Device entry points ----------------------------*/
--
1.7.11
^ permalink raw reply related
* Re: copy_skb_header() and sk_buff flags (question)
From: Eric Dumazet @ 2012-08-22 5:21 UTC (permalink / raw)
To: Kevin Wilson; +Cc: netdev
In-Reply-To: <CAGXs5wVp2bLnwFiuYEg6ZOv0t3DX4PCCgY-EURbs5bySgEqtdw@mail.gmail.com>
On Wed, 2012-08-22 at 07:55 +0300, Kevin Wilson wrote:
> Hello,
>
> I have a question if I may, as I cannot understand this point:
>
> I try to understand why in __copy_skb_header() we copy various flags
> (like ip_summed,
> local_df, pkt_type, priority, ipvs_property, and more. But there are
> flags which we do
> not copy, like nohdr, or fclone, or peeked.
>
> Aren't these flags part of the sk_buff header?
Caller should take care of said bits.
peeked is probably always 0 at this point...
I tried to use a single memcpy() to speedup things, but found out
it was not a trivial thing...
^ permalink raw reply
* Re: [PATCH v7] bonding: support for IPv6 transmit hashing
From: David Miller @ 2012-08-22 5:29 UTC (permalink / raw)
To: linux; +Cc: netdev
In-Reply-To: <2e01d8f94c42c61af9886683a4c35caf6816bc3d.1345610688.git.linux@8192.net>
From: John Eaglesham <linux@8192.net>
Date: Tue, 21 Aug 2012 22:12:33 -0700
> Signed-off-by: John Eaglesham
This is not a proper signoff, you must put an email address on this line.
Also, the changelog between the versions doesn't belong in the commit
log message itself. It gets placed in commentary after the "---" line.
^ permalink raw reply
* Re: smsc75xx & smsc95xx, setting skb->truesize correctly?
From: Jussi Kivilinna @ 2012-08-22 5:35 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev, Steve Glendinning
In-Reply-To: <1345542398.5158.446.camel@edumazet-glaptop>
Quoting Eric Dumazet <eric.dumazet@gmail.com>:
> On Mon, 2012-08-20 at 17:57 +0300, Jussi Kivilinna wrote:
>> Hello,
>>
>> Is setting skb->truesize in smsc75xx and smsc95xx correct?
>> In smsc75xx/smsc95xx_rx_fixup(), input skb containing multiple packets
>> is cloned and truesize for each clone is set to packet-size +
>> sizeof(struct sk_buff), but input skb has minimum allocation size of
>> 9000 bytes (MAX_SINGLE_PACKET_SIZE) and maximum of 18944 bytes
>> (DEFAULT_HS_BURST_CAP_SIZE) (+ NET_IP_ALIGN). Doesn't this cause
>> truesize to be underestimated?
>
> This has been discussed in a "TCP transmit performance regression"
> thread some weeks ago.
>
> More generally, skb_clone() is not a good idea in rx path.
So all skb_clone use in drivers/net/usb/ should be removed/replaced
with following?
>
> I dont have the hardware so cannot send a formal patch.
Neither do I, was looking for gigabit-usb dongle to buy and ended up
checking various drivers.
I guess I could do and test this for rndis_host/rndis_wlan and add
rx-skb recycling to usbnet core for drivers that do copy-break in
rx_fixup.
-Jussi
>
> diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
> index b1112e7..3d9566f 100644
> --- a/drivers/net/usb/smsc95xx.c
> +++ b/drivers/net/usb/smsc95xx.c
> @@ -1080,30 +1080,17 @@ static int smsc95xx_rx_fixup(struct usbnet
> *dev, struct sk_buff *skb)
> return 0;
> }
>
> - /* last frame in this batch */
> - if (skb->len == size) {
> - if (dev->net->features & NETIF_F_RXCSUM)
> - smsc95xx_rx_csum_offload(skb);
> - skb_trim(skb, skb->len - 4); /* remove fcs */
> - skb->truesize = size + sizeof(struct sk_buff);
> -
> - return 1;
> - }
> -
> - ax_skb = skb_clone(skb, GFP_ATOMIC);
> + ax_skb = netdev_alloc_skb_ip_align(dev->net, size);
> if (unlikely(!ax_skb)) {
> netdev_warn(dev->net, "Error allocating skb\n");
> return 0;
> }
>
> - ax_skb->len = size;
> - ax_skb->data = packet;
> - skb_set_tail_pointer(ax_skb, size);
> + memcpy(skb_put(ax_skb, size), packet, size);
>
> if (dev->net->features & NETIF_F_RXCSUM)
> smsc95xx_rx_csum_offload(ax_skb);
> - skb_trim(ax_skb, ax_skb->len - 4); /* remove fcs */
> - ax_skb->truesize = size + sizeof(struct sk_buff);
> + __skb_trim(ax_skb, ax_skb->len - 4); /* remove fcs */
>
> usbnet_skb_return(dev, ax_skb);
> }
>
>
>
>
^ permalink raw reply
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