* [PATCH 2/3] ipvs: remove extra lookups for ICMP packets
From: Simon Horman @ 2011-02-16 6:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter-devel, netfilter
Cc: Julian Anastasov, Patrick Schaaf, Patrick McHardy, Simon Horman
In-Reply-To: <1297836293-5942-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Remove code that should not be called anymore.
Now when ip_vs_out handles replies for local clients at
LOCAL_IN hook we do not need to call conn_out_get and
handle_response_icmp from ip_vs_in_icmp* because such
lookups were already performed for the ICMP packet and no
connection was found.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 28 +++-------------------------
1 files changed, 3 insertions(+), 25 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4d06617..2d1f932 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -729,7 +729,7 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
#endif
/* Handle relevant response ICMP messages - forward to the right
- * destination host. Used for NAT and local client.
+ * destination host.
*/
static int handle_response_icmp(int af, struct sk_buff *skb,
union nf_inet_addr *snet,
@@ -979,7 +979,6 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
}
/* Handle response packets: rewrite addresses and send away...
- * Used for NAT and local client.
*/
static unsigned int
handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
@@ -1280,7 +1279,6 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
unsigned int offset, ihl, verdict;
- union nf_inet_addr snet;
*related = 1;
@@ -1339,17 +1337,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
ip_vs_fill_iphdr(AF_INET, cih, &ciph);
/* The embedded headers contain source and dest in reverse order */
cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
- if (!cp) {
- /* The packet could also belong to a local client */
- cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
- if (cp) {
- snet.ip = iph->saddr;
- return handle_response_icmp(AF_INET, skb, &snet,
- cih->protocol, cp, pp,
- offset, ihl);
- }
+ if (!cp)
return NF_ACCEPT;
- }
verdict = NF_DROP;
@@ -1395,7 +1384,6 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
unsigned int offset, verdict;
- union nf_inet_addr snet;
struct rt6_info *rt;
*related = 1;
@@ -1455,18 +1443,8 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
/* The embedded headers contain source and dest in reverse order */
cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
- if (!cp) {
- /* The packet could also belong to a local client */
- cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
- if (cp) {
- ipv6_addr_copy(&snet.in6, &iph->saddr);
- return handle_response_icmp(AF_INET6, skb, &snet,
- cih->nexthdr,
- cp, pp, offset,
- sizeof(struct ipv6hdr));
- }
+ if (!cp)
return NF_ACCEPT;
- }
verdict = NF_DROP;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 1/3] ipvs: fix timer in get_curr_sync_buff
From: Simon Horman @ 2011-02-16 6:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter-devel, netfilter
Cc: Julian Anastasov, Patrick Schaaf, Patrick McHardy, Tinggong Wang,
Simon Horman
In-Reply-To: <1297836293-5942-1-git-send-email-horms@verge.net.au>
From: Tinggong Wang <wangtinggong@gmail.com>
Fix get_curr_sync_buff to keep buffer for 2 seconds
as intended, not just for the current jiffie. By this way
we will sync more connection structures with single packet.
Signed-off-by: Tinggong Wang <wangtinggong@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index d1b7298..fecf24d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -374,8 +374,8 @@ get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
struct ip_vs_sync_buff *sb;
spin_lock_bh(&ipvs->sync_buff_lock);
- if (ipvs->sync_buff && (time == 0 ||
- time_before(jiffies - ipvs->sync_buff->firstuse, time))) {
+ if (ipvs->sync_buff &&
+ time_after_eq(jiffies - ipvs->sync_buff->firstuse, time)) {
sb = ipvs->sync_buff;
ipvs->sync_buff = NULL;
} else
--
1.7.2.3
^ permalink raw reply related
* [GIT PULL nf-next-2.6] IPVS
From: Simon Horman @ 2011-02-16 6:04 UTC (permalink / raw)
To: lvs-devel, netdev, netfilter-devel, netfilter
Cc: Julian Anastasov, Patrick Schaaf, Patrick McHardy
Hi Patrick,
please consider pulling
git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6.git master
go get:
* Removal of unused ICMP code by Julian
* More informative "no destination available" messages
by Patrick Schaaf
* Fix to buffering of synchronisation messages
by Tinggong Wang and Julian
include/net/ip_vs.h | 2 ++
net/netfilter/ipvs/ip_vs_core.c | 28 +++-------------------------
net/netfilter/ipvs/ip_vs_lblc.c | 2 +-
net/netfilter/ipvs/ip_vs_lblcr.c | 2 +-
net/netfilter/ipvs/ip_vs_lc.c | 2 +-
net/netfilter/ipvs/ip_vs_nq.c | 2 +-
net/netfilter/ipvs/ip_vs_rr.c | 2 +-
net/netfilter/ipvs/ip_vs_sched.c | 25 +++++++++++++++++++++++++
net/netfilter/ipvs/ip_vs_sed.c | 2 +-
net/netfilter/ipvs/ip_vs_sh.c | 2 +-
net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
net/netfilter/ipvs/ip_vs_wlc.c | 2 +-
net/netfilter/ipvs/ip_vs_wrr.c | 14 ++++++++------
13 files changed, 48 insertions(+), 41 deletions(-)
^ permalink raw reply
* Re: [PATCH] bnx2x: Support for managing RX indirection table
From: Vlad Zolotarov @ 2011-02-16 5:53 UTC (permalink / raw)
To: Tom Herbert
Cc: Ben Hutchings, davem@davemloft.net, Eilon Greenstein,
netdev@vger.kernel.org
In-Reply-To: <AANLkTi=VT7BMpJZeE_gKOceNw+=Db40p3znmyt=Jc2Un@mail.gmail.com>
On Wednesday 16 February 2011 00:50:18 Tom Herbert wrote:
> >> + u32 rx_indir_table[128];
> >
> > Shouldn't the dimension be TSTORM_INDIRECTION_TABLE_SIZE?
> >
>
> It's not a defined constant, so the alternative would be to malloc it
> which seems like overkill to me.
>
> Broadcom guys: are there any adapters or configuration of bnx2x where
> the indirection table would be greater than 128?
Although for all currently supported adapters the actual value of the indirection
table size is 128 I agree with Ben and would like to ask u to use the above macro (which
is a rename for an entry in a per-adapter array of constants) to keep the code
scalable and clean. I don't think that a malloc would be too much of a price for it... ;)
thanks,
vlad
>
> Tom
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
^ permalink raw reply
* [PATCH v6 9/9] loopback: convert to hw_features
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
This also enables TSOv6, TSO-ECN, and UFO as loopback clearly can handle them.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
drivers/net/loopback.c | 9 ++++-----
1 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 2d9663a..ea0dc45 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -129,10 +129,6 @@ static u32 always_on(struct net_device *dev)
static const struct ethtool_ops loopback_ethtool_ops = {
.get_link = always_on,
- .set_tso = ethtool_op_set_tso,
- .get_tx_csum = always_on,
- .get_sg = always_on,
- .get_rx_csum = always_on,
};
static int loopback_dev_init(struct net_device *dev)
@@ -169,9 +165,12 @@ static void loopback_setup(struct net_device *dev)
dev->type = ARPHRD_LOOPBACK; /* 0x0001*/
dev->flags = IFF_LOOPBACK;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ dev->hw_features = NETIF_F_ALL_TSO | NETIF_F_UFO;
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
- | NETIF_F_TSO
+ | NETIF_F_ALL_TSO
+ | NETIF_F_UFO
| NETIF_F_NO_CSUM
+ | NETIF_F_RXCSUM
| NETIF_F_HIGHDMA
| NETIF_F_LLTX
| NETIF_F_NETNS_LOCAL;
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 8/9] net: introduce NETIF_F_RXCSUM
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
Introduce NETIF_F_RXCSUM to replace device-private flags for RX checksum
offload. Integrate it with ndo_fix_features.
ethtool_op_get_rx_csum() is removed altogether as nothing in-tree uses it.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/ethtool.h | 1 -
include/linux/netdevice.h | 5 +++-
net/core/ethtool.c | 47 ++++++++++++++++++++++-----------------------
3 files changed, 27 insertions(+), 26 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 806e716..54d776c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -625,7 +625,6 @@ struct net_device;
/* Some generic methods drivers may use in their ethtool_ops */
u32 ethtool_op_get_link(struct net_device *dev);
-u32 ethtool_op_get_rx_csum(struct net_device *dev);
u32 ethtool_op_get_tx_csum(struct net_device *dev);
int ethtool_op_set_tx_csum(struct net_device *dev, u32 data);
int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 85f67e2..ffe56c1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -977,6 +977,7 @@ struct net_device {
#define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
#define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */
#define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */
+#define NETIF_F_RXCSUM (1 << 29) /* Receive checksumming offload */
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
@@ -992,7 +993,7 @@ struct net_device {
/* = all defined minus driver/device-class-related */
#define NETIF_F_NEVER_CHANGE (NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \
NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
-#define NETIF_F_ETHTOOL_BITS (0x1f3fffff & ~NETIF_F_NEVER_CHANGE)
+#define NETIF_F_ETHTOOL_BITS (0x3f3fffff & ~NETIF_F_NEVER_CHANGE)
/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \
@@ -2510,6 +2511,8 @@ static inline int dev_ethtool_get_settings(struct net_device *dev,
static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev)
{
+ if (dev->hw_features & NETIF_F_RXCSUM)
+ return !!(dev->features & NETIF_F_RXCSUM);
if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum)
return 0;
return dev->ethtool_ops->get_rx_csum(dev);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 65b3d50..66cdc76 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -34,12 +34,6 @@ u32 ethtool_op_get_link(struct net_device *dev)
}
EXPORT_SYMBOL(ethtool_op_get_link);
-u32 ethtool_op_get_rx_csum(struct net_device *dev)
-{
- return (dev->features & NETIF_F_ALL_CSUM) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_rx_csum);
-
u32 ethtool_op_get_tx_csum(struct net_device *dev)
{
return (dev->features & NETIF_F_ALL_CSUM) != 0;
@@ -274,7 +268,7 @@ static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GS
/* NETIF_F_FCOE_MTU */ "fcoe-mtu",
/* NETIF_F_NTUPLE */ "rx-ntuple-filter",
/* NETIF_F_RXHASH */ "rx-hashing",
- "",
+ /* NETIF_F_RXCSUM */ "rx-checksum",
"",
"",
};
@@ -313,6 +307,9 @@ static u32 ethtool_get_feature_mask(u32 eth_cmd)
case ETHTOOL_GTXCSUM:
case ETHTOOL_STXCSUM:
return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM;
+ case ETHTOOL_GRXCSUM:
+ case ETHTOOL_SRXCSUM:
+ return NETIF_F_RXCSUM;
case ETHTOOL_GSG:
case ETHTOOL_SSG:
return NETIF_F_SG;
@@ -343,6 +340,8 @@ static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
switch (ethcmd) {
case ETHTOOL_GTXCSUM:
return ops->get_tx_csum;
+ case ETHTOOL_GRXCSUM:
+ return ops->get_rx_csum;
case ETHTOOL_SSG:
return ops->get_sg;
case ETHTOOL_STSO:
@@ -354,6 +353,11 @@ static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
}
}
+static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev)
+{
+ return !!(dev->features & NETIF_F_ALL_CSUM);
+}
+
static int ethtool_get_one_feature(struct net_device *dev,
char __user *useraddr, u32 ethcmd)
{
@@ -369,6 +373,10 @@ static int ethtool_get_one_feature(struct net_device *dev,
actor = __ethtool_get_one_feature_actor(dev, ethcmd);
+ /* bug compatibility with old get_rx_csum */
+ if (ethcmd == ETHTOOL_GRXCSUM && !actor)
+ actor = __ethtool_get_rx_csum_oldbug;
+
if (actor)
edata.data = actor(dev);
}
@@ -379,6 +387,7 @@ static int ethtool_get_one_feature(struct net_device *dev,
}
static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
+static int __ethtool_set_rx_csum(struct net_device *dev, u32 data);
static int __ethtool_set_sg(struct net_device *dev, u32 data);
static int __ethtool_set_tso(struct net_device *dev, u32 data);
static int __ethtool_set_ufo(struct net_device *dev, u32 data);
@@ -416,6 +425,8 @@ static int ethtool_set_one_feature(struct net_device *dev,
switch (ethcmd) {
case ETHTOOL_STXCSUM:
return __ethtool_set_tx_csum(dev, edata.data);
+ case ETHTOOL_SRXCSUM:
+ return __ethtool_set_rx_csum(dev, edata.data);
case ETHTOOL_SSG:
return __ethtool_set_sg(dev, edata.data);
case ETHTOOL_STSO:
@@ -1404,20 +1415,15 @@ static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
return dev->ethtool_ops->set_tx_csum(dev, data);
}
-static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_rx_csum(struct net_device *dev, u32 data)
{
- struct ethtool_value edata;
-
if (!dev->ethtool_ops->set_rx_csum)
return -EOPNOTSUPP;
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
-
- if (!edata.data && dev->ethtool_ops->set_sg)
+ if (!data)
dev->features &= ~NETIF_F_GRO;
- return dev->ethtool_ops->set_rx_csum(dev, edata.data);
+ return dev->ethtool_ops->set_rx_csum(dev, data);
}
static int __ethtool_set_tso(struct net_device *dev, u32 data)
@@ -1765,15 +1771,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SPAUSEPARAM:
rc = ethtool_set_pauseparam(dev, useraddr);
break;
- case ETHTOOL_GRXCSUM:
- rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_rx_csum ?
- dev->ethtool_ops->get_rx_csum :
- ethtool_op_get_rx_csum));
- break;
- case ETHTOOL_SRXCSUM:
- rc = ethtool_set_rx_csum(dev, useraddr);
- break;
case ETHTOOL_TEST:
rc = ethtool_self_test(dev, useraddr);
break;
@@ -1846,6 +1843,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
rc = ethtool_set_features(dev, useraddr);
break;
case ETHTOOL_GTXCSUM:
+ case ETHTOOL_GRXCSUM:
case ETHTOOL_GSG:
case ETHTOOL_GTSO:
case ETHTOOL_GUFO:
@@ -1854,6 +1852,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
rc = ethtool_get_one_feature(dev, useraddr, ethcmd);
break;
case ETHTOOL_STXCSUM:
+ case ETHTOOL_SRXCSUM:
case ETHTOOL_SSG:
case ETHTOOL_STSO:
case ETHTOOL_SUFO:
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 3/9] ethtool: factorize ethtool_get_strings() and ethtool_get_sset_count()
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
This is needed for unified offloads patch.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
net/core/ethtool.c | 35 +++++++++++++++++++++++------------
1 files changed, 23 insertions(+), 12 deletions(-)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9eb8277..85aaeab 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -172,6 +172,25 @@ EXPORT_SYMBOL(ethtool_ntuple_flush);
/* Handlers for each ethtool command */
+static int __ethtool_get_sset_count(struct net_device *dev, int sset)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (ops && ops->get_sset_count && ops->get_strings)
+ return ops->get_sset_count(dev, sset);
+ else
+ return -EOPNOTSUPP;
+}
+
+static void __ethtool_get_strings(struct net_device *dev,
+ u32 stringset, u8 *data)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ /* ops->get_strings is valid because checked earlier */
+ ops->get_strings(dev, stringset, data);
+}
+
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
@@ -252,14 +271,10 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_sset_info info;
- const struct ethtool_ops *ops = dev->ethtool_ops;
u64 sset_mask;
int i, idx = 0, n_bits = 0, ret, rc;
u32 *info_buf = NULL;
- if (!ops->get_sset_count)
- return -EOPNOTSUPP;
-
if (copy_from_user(&info, useraddr, sizeof(info)))
return -EFAULT;
@@ -286,7 +301,7 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev,
if (!(sset_mask & (1ULL << i)))
continue;
- rc = ops->get_sset_count(dev, i);
+ rc = __ethtool_get_sset_count(dev, i);
if (rc >= 0) {
info.sset_mask |= (1ULL << i);
info_buf[idx++] = rc;
@@ -1287,17 +1302,13 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gstrings gstrings;
- const struct ethtool_ops *ops = dev->ethtool_ops;
u8 *data;
int ret;
- if (!ops->get_strings || !ops->get_sset_count)
- return -EOPNOTSUPP;
-
if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
return -EFAULT;
- ret = ops->get_sset_count(dev, gstrings.string_set);
+ ret = __ethtool_get_sset_count(dev, gstrings.string_set);
if (ret < 0)
return ret;
@@ -1307,7 +1318,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
if (!data)
return -ENOMEM;
- ops->get_strings(dev, gstrings.string_set, data);
+ __ethtool_get_strings(dev, gstrings.string_set, data);
ret = -EFAULT;
if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1317,7 +1328,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
goto out;
ret = 0;
- out:
+out:
kfree(data);
return ret;
}
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 7/9] net: use ndo_fix_features for ethtool_ops->set_flags
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
net/core/ethtool.c | 31 +++++++++++++++++++++++++++++--
1 files changed, 29 insertions(+), 2 deletions(-)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6599997..65b3d50 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -427,6 +427,34 @@ static int ethtool_set_one_feature(struct net_device *dev,
}
}
+static int __ethtool_set_flags(struct net_device *dev, u32 data)
+{
+ u32 changed;
+
+ if (data & ~flags_dup_features)
+ return -EINVAL;
+
+ /* legacy set_flags() op */
+ if (dev->ethtool_ops->set_flags) {
+ if (unlikely(dev->hw_features & flags_dup_features))
+ netdev_warn(dev,
+ "driver BUG: mixed hw_features and set_flags()\n");
+ return dev->ethtool_ops->set_flags(dev, data);
+ }
+
+ /* allow changing only bits set in hw_features */
+ changed = (data ^ dev->wanted_features) & flags_dup_features;
+ if (changed & ~dev->hw_features)
+ return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP;
+
+ dev->wanted_features =
+ (dev->wanted_features & ~changed) | data;
+
+ netdev_update_features(dev);
+
+ return 0;
+}
+
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
@@ -1768,8 +1796,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
ethtool_op_get_flags));
break;
case ETHTOOL_SFLAGS:
- rc = ethtool_set_value(dev, useraddr,
- dev->ethtool_ops->set_flags);
+ rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags);
break;
case ETHTOOL_GPFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 5/9] net: Introduce new feature setting ops
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
This introduces a new framework to handle device features setting.
It consists of:
- new fields in struct net_device:
+ hw_features - features that hw/driver supports toggling
+ wanted_features - features that user wants enabled, when possible
- new netdev_ops:
+ feat = ndo_fix_features(dev, feat) - API checking constraints for
enabling features or their combinations
+ ndo_set_features(dev) - API updating hardware state to match
changed dev->features
- new ethtool commands:
+ ETHTOOL_GFEATURES/ETHTOOL_SFEATURES: get/set dev->wanted_features
and trigger device reconfiguration if resulting dev->features
changed
+ ETHTOOL_GSTRINGS(ETH_SS_FEATURES): get feature bits names (meaning)
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/ethtool.h | 85 ++++++++++++++++++++++++++++++
include/linux/netdevice.h | 37 +++++++++++++-
net/core/dev.c | 46 ++++++++++++++--
net/core/ethtool.c | 125 ++++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 283 insertions(+), 10 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 1908929..806e716 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -251,6 +251,7 @@ enum ethtool_stringset {
ETH_SS_STATS,
ETH_SS_PRIV_FLAGS,
ETH_SS_NTUPLE_FILTERS,
+ ETH_SS_FEATURES,
};
/* for passing string sets for data tagging */
@@ -523,6 +524,87 @@ struct ethtool_flash {
char data[ETHTOOL_FLASH_MAX_FILENAME];
};
+/* for returning and changing feature sets */
+
+/**
+ * struct ethtool_get_features_block - block with state of 32 features
+ * @available: mask of changeable features
+ * @requested: mask of features requested to be enabled if possible
+ * @active: mask of currently enabled features
+ * @never_changed: mask of features not changeable for any device
+ */
+struct ethtool_get_features_block {
+ __u32 available;
+ __u32 requested;
+ __u32 active;
+ __u32 never_changed;
+};
+
+/**
+ * struct ethtool_gfeatures - command to get state of device's features
+ * @cmd: command number = %ETHTOOL_GFEATURES
+ * @size: in: number of elements in the features[] array;
+ * out: number of elements in features[] needed to hold all features
+ * @features: state of features
+ */
+struct ethtool_gfeatures {
+ __u32 cmd;
+ __u32 size;
+ struct ethtool_get_features_block features[0];
+};
+
+/**
+ * struct ethtool_set_features_block - block with request for 32 features
+ * @valid: mask of features to be changed
+ * @requested: values of features to be changed
+ */
+struct ethtool_set_features_block {
+ __u32 valid;
+ __u32 requested;
+};
+
+/**
+ * struct ethtool_sfeatures - command to request change in device's features
+ * @cmd: command number = %ETHTOOL_SFEATURES
+ * @size: array size of the features[] array
+ * @features: feature change masks
+ */
+struct ethtool_sfeatures {
+ __u32 cmd;
+ __u32 size;
+ struct ethtool_set_features_block features[0];
+};
+
+/*
+ * %ETHTOOL_SFEATURES changes features present in features[].valid to the
+ * values of corresponding bits in features[].requested. Bits in .requested
+ * not set in .valid or not changeable are ignored.
+ *
+ * Returns %EINVAL when .valid contains undefined or never-changable bits
+ * or size is not equal to required number of features words (32-bit blocks).
+ * Returns >= 0 if request was completed; bits set in the value mean:
+ * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not
+ * changeable (not present in %ETHTOOL_GFEATURES' features[].available)
+ * those bits were ignored.
+ * %ETHTOOL_F_WISH - some or all changes requested were recorded but the
+ * resulting state of bits masked by .valid is not equal to .requested.
+ * Probably there are other device-specific constraints on some features
+ * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
+ * here as though ignored bits were cleared.
+ *
+ * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
+ * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
+ * for ETH_SS_FEATURES string set. First entry in the table corresponds to least
+ * significant bit in features[0] fields. Empty strings mark undefined features.
+ */
+enum ethtool_sfeatures_retval_bits {
+ ETHTOOL_F_UNSUPPORTED__BIT,
+ ETHTOOL_F_WISH__BIT,
+};
+
+#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT)
+#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT)
+
#ifdef __KERNEL__
#include <linux/rculist.h>
@@ -744,6 +826,9 @@ struct ethtool_ops {
#define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */
#define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */
+#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */
+#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */
+
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dede3fd..85f67e2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -791,6 +791,18 @@ struct netdev_tc_txq {
*
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to release previously enslaved netdev.
+ *
+ * Feature/offload setting functions.
+ * u32 (*ndo_fix_features)(struct net_device *dev, u32 features);
+ * Adjusts the requested feature flags according to device-specific
+ * constraints, and returns the resulting flags. Must not modify
+ * the device state.
+ *
+ * int (*ndo_set_features)(struct net_device *dev, u32 features);
+ * Called to update device configuration to new features. Passed
+ * feature set might be less than what was returned by ndo_fix_features()).
+ * Must return >0 or -errno if it changed dev->features itself.
+ *
*/
#define HAVE_NET_DEVICE_OPS
struct net_device_ops {
@@ -874,6 +886,10 @@ struct net_device_ops {
struct net_device *slave_dev);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
+ u32 (*ndo_fix_features)(struct net_device *dev,
+ u32 features);
+ int (*ndo_set_features)(struct net_device *dev,
+ u32 features);
};
/*
@@ -925,12 +941,18 @@ struct net_device {
struct list_head napi_list;
struct list_head unreg_list;
- /* Net device features */
+ /* currently active device features */
u32 features;
-
+ /* user-changeable features */
+ u32 hw_features;
+ /* user-requested features */
+ u32 wanted_features;
/* VLAN feature mask */
u32 vlan_features;
+ /* Net device feature bits; if you change something,
+ * also update netdev_features_strings[] in ethtool.c */
+
#define NETIF_F_SG 1 /* Scatter/gather IO. */
#define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */
#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */
@@ -966,6 +988,12 @@ struct net_device {
#define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
#define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
+ /* Features valid for ethtool to change */
+ /* = all defined minus driver/device-class-related */
+#define NETIF_F_NEVER_CHANGE (NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \
+ NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+#define NETIF_F_ETHTOOL_BITS (0x1f3fffff & ~NETIF_F_NEVER_CHANGE)
+
/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \
NETIF_F_TSO6 | NETIF_F_UFO)
@@ -2428,8 +2456,13 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
extern void linkwatch_run_queue(void);
+static inline u32 netdev_get_wanted_features(struct net_device *dev)
+{
+ return (dev->features & ~dev->hw_features) | dev->wanted_features;
+}
u32 netdev_increment_features(u32 all, u32 one, u32 mask);
u32 netdev_fix_features(struct net_device *dev, u32 features);
+void netdev_update_features(struct net_device *dev);
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 8686f6f..4f69439 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5302,6 +5302,37 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
}
EXPORT_SYMBOL(netdev_fix_features);
+void netdev_update_features(struct net_device *dev)
+{
+ u32 features;
+ int err = 0;
+
+ features = netdev_get_wanted_features(dev);
+
+ if (dev->netdev_ops->ndo_fix_features)
+ features = dev->netdev_ops->ndo_fix_features(dev, features);
+
+ /* driver might be less strict about feature dependencies */
+ features = netdev_fix_features(dev, features);
+
+ if (dev->features == features)
+ return;
+
+ netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n",
+ dev->features, features);
+
+ if (dev->netdev_ops->ndo_set_features)
+ err = dev->netdev_ops->ndo_set_features(dev, features);
+
+ if (!err)
+ dev->features = features;
+ else if (err < 0)
+ netdev_err(dev,
+ "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
+ err, features, dev->features);
+}
+EXPORT_SYMBOL(netdev_update_features);
+
/**
* netif_stacked_transfer_operstate - transfer operstate
* @rootdev: the root or lower level device to transfer state from
@@ -5436,15 +5467,18 @@ int register_netdevice(struct net_device *dev)
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
- /* Enable software offloads by default - will be stripped in
- * netdev_fix_features() if not supported. */
- dev->features |= NETIF_F_SOFT_FEATURES;
+ /* Transfer changeable features to wanted_features and enable
+ * software offloads (GSO and GRO).
+ */
+ dev->hw_features |= NETIF_F_SOFT_FEATURES;
+ dev->wanted_features = (dev->features & dev->hw_features)
+ | NETIF_F_SOFT_FEATURES;
/* Avoid warning from netdev_fix_features() for GSO without SG */
- if (!(dev->features & NETIF_F_SG))
- dev->features &= ~NETIF_F_GSO;
+ if (!(dev->wanted_features & NETIF_F_SG))
+ dev->wanted_features &= ~NETIF_F_GSO;
- dev->features = netdev_fix_features(dev, dev->features);
+ netdev_update_features(dev);
/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
* vlan_dev_init() will do the dev->features check, so these features
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c3fb8f9..9577396 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -172,10 +172,120 @@ EXPORT_SYMBOL(ethtool_ntuple_flush);
/* Handlers for each ethtool command */
+#define ETHTOOL_DEV_FEATURE_WORDS 1
+
+static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
+{
+ struct ethtool_gfeatures cmd = {
+ .cmd = ETHTOOL_GFEATURES,
+ .size = ETHTOOL_DEV_FEATURE_WORDS,
+ };
+ struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = {
+ {
+ .available = dev->hw_features,
+ .requested = dev->wanted_features,
+ .active = dev->features,
+ .never_changed = NETIF_F_NEVER_CHANGE,
+ },
+ };
+ u32 __user *sizeaddr;
+ u32 copy_size;
+
+ sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
+ if (get_user(copy_size, sizeaddr))
+ return -EFAULT;
+
+ if (copy_size > ETHTOOL_DEV_FEATURE_WORDS)
+ copy_size = ETHTOOL_DEV_FEATURE_WORDS;
+
+ if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
+ return -EFAULT;
+ useraddr += sizeof(cmd);
+ if (copy_to_user(useraddr, features, copy_size * sizeof(*features)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
+{
+ struct ethtool_sfeatures cmd;
+ struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
+ int ret = 0;
+
+ if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
+ return -EFAULT;
+ useraddr += sizeof(cmd);
+
+ if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS)
+ return -EINVAL;
+
+ if (copy_from_user(features, useraddr, sizeof(features)))
+ return -EFAULT;
+
+ if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
+ return -EINVAL;
+
+ if (features[0].valid & ~dev->hw_features) {
+ features[0].valid &= dev->hw_features;
+ ret |= ETHTOOL_F_UNSUPPORTED;
+ }
+
+ dev->wanted_features &= ~features[0].valid;
+ dev->wanted_features |= features[0].valid & features[0].requested;
+ netdev_update_features(dev);
+
+ if ((dev->wanted_features ^ dev->features) & features[0].valid)
+ ret |= ETHTOOL_F_WISH;
+
+ return ret;
+}
+
+static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = {
+ /* NETIF_F_SG */ "tx-scatter-gather",
+ /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4",
+ /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded",
+ /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic",
+ /* NETIF_F_IPV6_CSUM */ "tx_checksum-ipv6",
+ /* NETIF_F_HIGHDMA */ "highdma",
+ /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist",
+ /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert",
+
+ /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse",
+ /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter",
+ /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged",
+ /* NETIF_F_GSO */ "tx-generic-segmentation",
+ /* NETIF_F_LLTX */ "tx-lockless",
+ /* NETIF_F_NETNS_LOCAL */ "netns-local",
+ /* NETIF_F_GRO */ "rx-gro",
+ /* NETIF_F_LRO */ "rx-lro",
+
+ /* NETIF_F_TSO */ "tx-tcp-segmentation",
+ /* NETIF_F_UFO */ "tx-udp-fragmentation",
+ /* NETIF_F_GSO_ROBUST */ "tx-gso-robust",
+ /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation",
+ /* NETIF_F_TSO6 */ "tx-tcp6-segmentation",
+ /* NETIF_F_FSO */ "tx-fcoe-segmentation",
+ "",
+ "",
+
+ /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc",
+ /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp",
+ /* NETIF_F_FCOE_MTU */ "fcoe-mtu",
+ /* NETIF_F_NTUPLE */ "rx-ntuple-filter",
+ /* NETIF_F_RXHASH */ "rx-hashing",
+ "",
+ "",
+ "",
+};
+
static int __ethtool_get_sset_count(struct net_device *dev, int sset)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
+ if (sset == ETH_SS_FEATURES)
+ return ARRAY_SIZE(netdev_features_strings);
+
if (ops && ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
@@ -187,8 +297,12 @@ static void __ethtool_get_strings(struct net_device *dev,
{
const struct ethtool_ops *ops = dev->ethtool_ops;
- /* ops->get_strings is valid because checked earlier */
- ops->get_strings(dev, stringset, data);
+ if (stringset == ETH_SS_FEATURES)
+ memcpy(data, netdev_features_strings,
+ sizeof(netdev_features_strings));
+ else
+ /* ops->get_strings is valid because checked earlier */
+ ops->get_strings(dev, stringset, data);
}
static u32 ethtool_get_feature_mask(u32 eth_cmd)
@@ -1533,6 +1647,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
+ case ETHTOOL_GFEATURES:
break;
default:
if (!capable(CAP_NET_ADMIN))
@@ -1678,6 +1793,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXFHINDIR:
rc = ethtool_set_rxfh_indir(dev, useraddr);
break;
+ case ETHTOOL_GFEATURES:
+ rc = ethtool_get_features(dev, useraddr);
+ break;
+ case ETHTOOL_SFEATURES:
+ rc = ethtool_set_features(dev, useraddr);
+ break;
case ETHTOOL_GTXCSUM:
case ETHTOOL_GSG:
case ETHTOOL_GTSO:
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 6/9] net: ethtool: use ndo_fix_features for offload setting
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
net/core/ethtool.c | 45 ++++++++++++++++++++++++++++++++-------------
1 files changed, 32 insertions(+), 13 deletions(-)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9577396..6599997 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -357,15 +357,21 @@ static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
static int ethtool_get_one_feature(struct net_device *dev,
char __user *useraddr, u32 ethcmd)
{
+ u32 mask = ethtool_get_feature_mask(ethcmd);
struct ethtool_value edata = {
.cmd = ethcmd,
- .data = !!(dev->features & ethtool_get_feature_mask(ethcmd)),
+ .data = !!(dev->features & mask),
};
- u32 (*actor)(struct net_device *);
- actor = __ethtool_get_one_feature_actor(dev, ethcmd);
- if (actor)
- edata.data = actor(dev);
+ /* compatibility with discrete get_ ops */
+ if (!(dev->hw_features & mask)) {
+ u32 (*actor)(struct net_device *);
+
+ actor = __ethtool_get_one_feature_actor(dev, ethcmd);
+
+ if (actor)
+ edata.data = actor(dev);
+ }
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
@@ -386,6 +392,27 @@ static int ethtool_set_one_feature(struct net_device *dev,
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
+ mask = ethtool_get_feature_mask(ethcmd);
+ mask &= dev->hw_features;
+ if (mask) {
+ if (edata.data)
+ dev->wanted_features |= mask;
+ else
+ dev->wanted_features &= ~mask;
+
+ netdev_update_features(dev);
+ return 0;
+ }
+
+ /* Driver is not converted to ndo_fix_features or does not
+ * support changing this offload. In the latter case it won't
+ * have corresponding ethtool_ops field set.
+ *
+ * Following part is to be removed after all drivers advertise
+ * their changeable features in netdev->hw_features and stop
+ * using discrete offload setting ops.
+ */
+
switch (ethcmd) {
case ETHTOOL_STXCSUM:
return __ethtool_set_tx_csum(dev, edata.data);
@@ -395,14 +422,6 @@ static int ethtool_set_one_feature(struct net_device *dev,
return __ethtool_set_tso(dev, edata.data);
case ETHTOOL_SUFO:
return __ethtool_set_ufo(dev, edata.data);
- case ETHTOOL_SGSO:
- case ETHTOOL_SGRO:
- mask = ethtool_get_feature_mask(ethcmd);
- if (edata.data)
- dev->features |= mask;
- else
- dev->features &= ~mask;
- return 0;
default:
return -EOPNOTSUPP;
}
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 2/9] ethtool: enable GSO and GRO by default
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/netdevice.h | 3 +++
net/core/dev.c | 18 ++++++++++++++----
2 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d08ef65..168e3ad 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -984,6 +984,9 @@ struct net_device {
NETIF_F_SG | NETIF_F_HIGHDMA | \
NETIF_F_FRAGLIST)
+ /* changeable features with no special hardware requirements */
+#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+
/* Interface index. Unique device identifier */
int ifindex;
int iflink;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4580460..8686f6f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5274,6 +5274,12 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
features &= ~NETIF_F_TSO;
}
+ /* Software GSO depends on SG. */
+ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) {
+ netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
+ features &= ~NETIF_F_GSO;
+ }
+
/* UFO needs SG and checksumming */
if (features & NETIF_F_UFO) {
/* maybe split UFO into V4 and V6? */
@@ -5430,12 +5436,16 @@ int register_netdevice(struct net_device *dev)
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
+ /* Enable software offloads by default - will be stripped in
+ * netdev_fix_features() if not supported. */
+ dev->features |= NETIF_F_SOFT_FEATURES;
+
+ /* Avoid warning from netdev_fix_features() for GSO without SG */
+ if (!(dev->features & NETIF_F_SG))
+ dev->features &= ~NETIF_F_GSO;
+
dev->features = netdev_fix_features(dev, dev->features);
- /* Enable software GSO if SG is supported. */
- if (dev->features & NETIF_F_SG)
- dev->features |= NETIF_F_GSO;
-
/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
* vlan_dev_init() will do the dev->features check, so these features
* are enabled only if supported by underlying device.
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 1/9] ethtool: move EXPORT_SYMBOL(ethtool_op_set_tx_csum) to correct place
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
net/core/ethtool.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 5984ee0..9eb8277 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -55,6 +55,7 @@ int ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
return 0;
}
+EXPORT_SYMBOL(ethtool_op_set_tx_csum);
int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data)
{
@@ -1124,7 +1125,6 @@ static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr)
return dev->ethtool_ops->set_tx_csum(dev, edata.data);
}
-EXPORT_SYMBOL(ethtool_op_set_tx_csum);
static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
{
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 4/9] ethtool: factorize get/set_one_feature
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <cover.1297824704.git.mirq-linux@rere.qmqm.pl>
This allows to enable GRO even if RX csum is disabled. GRO will not
be used for packets without hardware checksum anyway.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/netdevice.h | 6 +
net/core/ethtool.c | 274 ++++++++++++++++++++++-----------------------
2 files changed, 138 insertions(+), 142 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 168e3ad..dede3fd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -976,6 +976,12 @@ struct net_device {
#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
+#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+#define NETIF_F_ALL_TX_OFFLOADS (NETIF_F_ALL_CSUM | NETIF_F_SG | \
+ NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_SCTP_CSUM | NETIF_F_FCOE_CRC)
+
/*
* If one device supports one of these features, then enable them
* for all in netdev_increment_features.
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 85aaeab..c3fb8f9 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -191,6 +191,109 @@ static void __ethtool_get_strings(struct net_device *dev,
ops->get_strings(dev, stringset, data);
}
+static u32 ethtool_get_feature_mask(u32 eth_cmd)
+{
+ /* feature masks of legacy discrete ethtool ops */
+
+ switch (eth_cmd) {
+ case ETHTOOL_GTXCSUM:
+ case ETHTOOL_STXCSUM:
+ return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM;
+ case ETHTOOL_GSG:
+ case ETHTOOL_SSG:
+ return NETIF_F_SG;
+ case ETHTOOL_GTSO:
+ case ETHTOOL_STSO:
+ return NETIF_F_ALL_TSO;
+ case ETHTOOL_GUFO:
+ case ETHTOOL_SUFO:
+ return NETIF_F_UFO;
+ case ETHTOOL_GGSO:
+ case ETHTOOL_SGSO:
+ return NETIF_F_GSO;
+ case ETHTOOL_GGRO:
+ case ETHTOOL_SGRO:
+ return NETIF_F_GRO;
+ default:
+ BUG();
+ }
+}
+
+static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (!ops)
+ return NULL;
+
+ switch (ethcmd) {
+ case ETHTOOL_GTXCSUM:
+ return ops->get_tx_csum;
+ case ETHTOOL_SSG:
+ return ops->get_sg;
+ case ETHTOOL_STSO:
+ return ops->get_tso;
+ case ETHTOOL_SUFO:
+ return ops->get_ufo;
+ default:
+ return NULL;
+ }
+}
+
+static int ethtool_get_one_feature(struct net_device *dev,
+ char __user *useraddr, u32 ethcmd)
+{
+ struct ethtool_value edata = {
+ .cmd = ethcmd,
+ .data = !!(dev->features & ethtool_get_feature_mask(ethcmd)),
+ };
+ u32 (*actor)(struct net_device *);
+
+ actor = __ethtool_get_one_feature_actor(dev, ethcmd);
+ if (actor)
+ edata.data = actor(dev);
+
+ if (copy_to_user(useraddr, &edata, sizeof(edata)))
+ return -EFAULT;
+ return 0;
+}
+
+static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
+static int __ethtool_set_sg(struct net_device *dev, u32 data);
+static int __ethtool_set_tso(struct net_device *dev, u32 data);
+static int __ethtool_set_ufo(struct net_device *dev, u32 data);
+
+static int ethtool_set_one_feature(struct net_device *dev,
+ void __user *useraddr, u32 ethcmd)
+{
+ struct ethtool_value edata;
+ u32 mask;
+
+ if (copy_from_user(&edata, useraddr, sizeof(edata)))
+ return -EFAULT;
+
+ switch (ethcmd) {
+ case ETHTOOL_STXCSUM:
+ return __ethtool_set_tx_csum(dev, edata.data);
+ case ETHTOOL_SSG:
+ return __ethtool_set_sg(dev, edata.data);
+ case ETHTOOL_STSO:
+ return __ethtool_set_tso(dev, edata.data);
+ case ETHTOOL_SUFO:
+ return __ethtool_set_ufo(dev, edata.data);
+ case ETHTOOL_SGSO:
+ case ETHTOOL_SGRO:
+ mask = ethtool_get_feature_mask(ethcmd);
+ if (edata.data)
+ dev->features |= mask;
+ else
+ dev->features &= ~mask;
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
@@ -1107,6 +1210,9 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data)
{
int err;
+ if (data && !(dev->features & NETIF_F_ALL_CSUM))
+ return -EINVAL;
+
if (!data && dev->ethtool_ops->set_tso) {
err = dev->ethtool_ops->set_tso(dev, 0);
if (err)
@@ -1121,24 +1227,20 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data)
return dev->ethtool_ops->set_sg(dev, data);
}
-static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
{
- struct ethtool_value edata;
int err;
if (!dev->ethtool_ops->set_tx_csum)
return -EOPNOTSUPP;
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
-
- if (!edata.data && dev->ethtool_ops->set_sg) {
+ if (!data && dev->ethtool_ops->set_sg) {
err = __ethtool_set_sg(dev, 0);
if (err)
return err;
}
- return dev->ethtool_ops->set_tx_csum(dev, edata.data);
+ return dev->ethtool_ops->set_tx_csum(dev, data);
}
static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
@@ -1157,108 +1259,28 @@ static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
return dev->ethtool_ops->set_rx_csum(dev, edata.data);
}
-static int ethtool_set_sg(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_tso(struct net_device *dev, u32 data)
{
- struct ethtool_value edata;
-
- if (!dev->ethtool_ops->set_sg)
- return -EOPNOTSUPP;
-
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
-
- if (edata.data &&
- !(dev->features & NETIF_F_ALL_CSUM))
- return -EINVAL;
-
- return __ethtool_set_sg(dev, edata.data);
-}
-
-static int ethtool_set_tso(struct net_device *dev, char __user *useraddr)
-{
- struct ethtool_value edata;
-
if (!dev->ethtool_ops->set_tso)
return -EOPNOTSUPP;
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
-
- if (edata.data && !(dev->features & NETIF_F_SG))
+ if (data && !(dev->features & NETIF_F_SG))
return -EINVAL;
- return dev->ethtool_ops->set_tso(dev, edata.data);
+ return dev->ethtool_ops->set_tso(dev, data);
}
-static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_ufo(struct net_device *dev, u32 data)
{
- struct ethtool_value edata;
-
if (!dev->ethtool_ops->set_ufo)
return -EOPNOTSUPP;
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
- if (edata.data && !(dev->features & NETIF_F_SG))
+ if (data && !(dev->features & NETIF_F_SG))
return -EINVAL;
- if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) ||
+ if (data && !((dev->features & NETIF_F_GEN_CSUM) ||
(dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
== (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)))
return -EINVAL;
- return dev->ethtool_ops->set_ufo(dev, edata.data);
-}
-
-static int ethtool_get_gso(struct net_device *dev, char __user *useraddr)
-{
- struct ethtool_value edata = { ETHTOOL_GGSO };
-
- edata.data = dev->features & NETIF_F_GSO;
- if (copy_to_user(useraddr, &edata, sizeof(edata)))
- return -EFAULT;
- return 0;
-}
-
-static int ethtool_set_gso(struct net_device *dev, char __user *useraddr)
-{
- struct ethtool_value edata;
-
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
- if (edata.data)
- dev->features |= NETIF_F_GSO;
- else
- dev->features &= ~NETIF_F_GSO;
- return 0;
-}
-
-static int ethtool_get_gro(struct net_device *dev, char __user *useraddr)
-{
- struct ethtool_value edata = { ETHTOOL_GGRO };
-
- edata.data = dev->features & NETIF_F_GRO;
- if (copy_to_user(useraddr, &edata, sizeof(edata)))
- return -EFAULT;
- return 0;
-}
-
-static int ethtool_set_gro(struct net_device *dev, char __user *useraddr)
-{
- struct ethtool_value edata;
-
- if (copy_from_user(&edata, useraddr, sizeof(edata)))
- return -EFAULT;
-
- if (edata.data) {
- u32 rxcsum = dev->ethtool_ops->get_rx_csum ?
- dev->ethtool_ops->get_rx_csum(dev) :
- ethtool_op_get_rx_csum(dev);
-
- if (!rxcsum)
- return -EINVAL;
- dev->features |= NETIF_F_GRO;
- } else
- dev->features &= ~NETIF_F_GRO;
-
- return 0;
+ return dev->ethtool_ops->set_ufo(dev, data);
}
static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
@@ -1590,33 +1612,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXCSUM:
rc = ethtool_set_rx_csum(dev, useraddr);
break;
- case ETHTOOL_GTXCSUM:
- rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_tx_csum ?
- dev->ethtool_ops->get_tx_csum :
- ethtool_op_get_tx_csum));
- break;
- case ETHTOOL_STXCSUM:
- rc = ethtool_set_tx_csum(dev, useraddr);
- break;
- case ETHTOOL_GSG:
- rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_sg ?
- dev->ethtool_ops->get_sg :
- ethtool_op_get_sg));
- break;
- case ETHTOOL_SSG:
- rc = ethtool_set_sg(dev, useraddr);
- break;
- case ETHTOOL_GTSO:
- rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_tso ?
- dev->ethtool_ops->get_tso :
- ethtool_op_get_tso));
- break;
- case ETHTOOL_STSO:
- rc = ethtool_set_tso(dev, useraddr);
- break;
case ETHTOOL_TEST:
rc = ethtool_self_test(dev, useraddr);
break;
@@ -1632,21 +1627,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GPERMADDR:
rc = ethtool_get_perm_addr(dev, useraddr);
break;
- case ETHTOOL_GUFO:
- rc = ethtool_get_value(dev, useraddr, ethcmd,
- (dev->ethtool_ops->get_ufo ?
- dev->ethtool_ops->get_ufo :
- ethtool_op_get_ufo));
- break;
- case ETHTOOL_SUFO:
- rc = ethtool_set_ufo(dev, useraddr);
- break;
- case ETHTOOL_GGSO:
- rc = ethtool_get_gso(dev, useraddr);
- break;
- case ETHTOOL_SGSO:
- rc = ethtool_set_gso(dev, useraddr);
- break;
case ETHTOOL_GFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
(dev->ethtool_ops->get_flags ?
@@ -1677,12 +1657,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXCLSRLINS:
rc = ethtool_set_rxnfc(dev, ethcmd, useraddr);
break;
- case ETHTOOL_GGRO:
- rc = ethtool_get_gro(dev, useraddr);
- break;
- case ETHTOOL_SGRO:
- rc = ethtool_set_gro(dev, useraddr);
- break;
case ETHTOOL_FLASHDEV:
rc = ethtool_flash_device(dev, useraddr);
break;
@@ -1704,6 +1678,22 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXFHINDIR:
rc = ethtool_set_rxfh_indir(dev, useraddr);
break;
+ case ETHTOOL_GTXCSUM:
+ case ETHTOOL_GSG:
+ case ETHTOOL_GTSO:
+ case ETHTOOL_GUFO:
+ case ETHTOOL_GGSO:
+ case ETHTOOL_GGRO:
+ rc = ethtool_get_one_feature(dev, useraddr, ethcmd);
+ break;
+ case ETHTOOL_STXCSUM:
+ case ETHTOOL_SSG:
+ case ETHTOOL_STSO:
+ case ETHTOOL_SUFO:
+ case ETHTOOL_SGSO:
+ case ETHTOOL_SGRO:
+ rc = ethtool_set_one_feature(dev, useraddr, ethcmd);
+ break;
default:
rc = -EOPNOTSUPP;
}
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 0/9] net: Unified offload configuration
From: Michał Mirosław @ 2011-02-16 2:59 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
Here's a v6 of the ethtool unification patch series.
What's in it?
1..4:
cleanups for the core patches
5:
the patch - implement unified ethtool setting ops
6..7:
implement interoperation between old and new ethtool ops
8:
include RX checksum in features and plug it into new framework
9:
convert loopback device to new framework
What is it good for?
- unifies driver behaviour wrt hardware offloads
- removes a lot of boilerplate code from drivers
- allows better fine-grained control over used offloads
This version is not tested, yet.
Best Regards,
Michał Mirosław
v1: http://marc.info/?l=linux-netdev&m=129245188832643&w=3
Changes from v5:
- register_netdevice(): avoid warning on GSO for non-SG capable devices
- rebased on current net-next (introduction of ndo_add/del_slave)
Changes from v4:
- more split cleanups
- fix error return for ETHTOOL_SFLAGS
- fix ETHTOOL_G* compatibility for not converted drivers
Changes from v3:
- fixed kernel-doc and other comments
- added HIGHDMA to never-changeable features
- changed GFEATURES .size interpretation
- changed feature strings
- change __ethtool_set_flags() to reject invalid changes
Changes from v2:
- rebase to net-next after merging v2 leading patches
- fix missing comma in feature name table
- force NETIF_F_SOFT_FEATURES in hw_features for simpler code
(fixes a bug that disallowed changing GSO and GRO state)
Changes from v1:
- split structures for GFEATURES/SFEATURES
- naming of feature bits using GSTRINGS ETH_SS_FEATURES
- strict checking of bits used in SFEATURES call
- more comments and kernel-doc
- rebased to net-next after 2.6.37
---
Michał Mirosław (9):
ethtool: move EXPORT_SYMBOL(ethtool_op_set_tx_csum) to correct place
ethtool: enable GSO and GRO by default
ethtool: factorize ethtool_get_strings() and ethtool_get_sset_count()
ethtool: factorize get/set_one_feature
net: Introduce new feature setting ops
net: ethtool: use ndo_fix_features for offload setting
net: use ndo_fix_features for ethtool_ops->set_flags
net: introduce NETIF_F_RXCSUM
loopback: convert to hw_features
drivers/net/loopback.c | 9 +-
include/linux/ethtool.h | 86 ++++++++-
include/linux/netdevice.h | 49 ++++-
net/core/dev.c | 52 ++++-
net/core/ethtool.c | 527 +++++++++++++++++++++++++++++---------------
5 files changed, 531 insertions(+), 192 deletions(-)
--
1.7.2.3
^ permalink raw reply
* Re: [RFC !!BONUS!! PATCH 6/5] ipv4: Delete routing cache.
From: David Miller @ 2011-02-16 2:55 UTC (permalink / raw)
To: netdev
In-Reply-To: <20110209.223939.246547003.davem@davemloft.net>
From: David Miller <davem@davemloft.net>
Date: Wed, 09 Feb 2011 22:39:39 -0800 (PST)
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
Ok, this patch had one nasty bug:
> + if (!err == 0)
Yeah... right.
I'm actively testing this version at the moment, against net-next-2.6,
works fine thus far.
--------------------
ipv4: Delete routing cache.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/fib_frontend.c | 5 -
net/ipv4/route.c | 891 ++---------------------------------------------
3 files changed, 23 insertions(+), 874 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index bf790c1..fcf1b11 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -117,7 +117,6 @@ extern int ip_rt_init(void);
extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
__be32 src, struct net_device *dev);
extern void rt_cache_flush(struct net *net, int how);
-extern void rt_cache_flush_batch(struct net *net);
extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2a49c06..694145c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -978,11 +978,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
rt_cache_flush(dev_net(dev), 0);
break;
case NETDEV_UNREGISTER_BATCH:
- /* The batch unregister is only called on the first
- * device in the list of devices being unregistered.
- * Therefore we should not pass dev_net(dev) in here.
- */
- rt_cache_flush_batch(NULL);
break;
}
return NOTIFY_DONE;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 756f544..58419fe 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int rt_chain_length_max __read_mostly = 20;
/*
* Interface to generic destination cache.
@@ -222,184 +221,30 @@ const __u8 ip_tos2prio[16] = {
};
-/*
- * Route cache.
- */
-
-/* The locking scheme is rather straight forward:
- *
- * 1) Read-Copy Update protects the buckets of the central route hash.
- * 2) Only writers remove entries, and they hold the lock
- * as they look at rtable reference counts.
- * 3) Only readers acquire references to rtable entries,
- * they do so with atomic increments and with the
- * lock held.
- */
-
-struct rt_hash_bucket {
- struct rtable __rcu *chain;
-};
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
- defined(CONFIG_PROVE_LOCKING)
-/*
- * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
- * The size of this table is a power of two and depends on the number of CPUS.
- * (on lockdep we have a quite big spinlock_t, so keep the size down there)
- */
-#ifdef CONFIG_LOCKDEP
-# define RT_HASH_LOCK_SZ 256
-#else
-# if NR_CPUS >= 32
-# define RT_HASH_LOCK_SZ 4096
-# elif NR_CPUS >= 16
-# define RT_HASH_LOCK_SZ 2048
-# elif NR_CPUS >= 8
-# define RT_HASH_LOCK_SZ 1024
-# elif NR_CPUS >= 4
-# define RT_HASH_LOCK_SZ 512
-# else
-# define RT_HASH_LOCK_SZ 256
-# endif
-#endif
-
-static spinlock_t *rt_hash_locks;
-# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
-
-static __init void rt_hash_lock_init(void)
-{
- int i;
-
- rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
- GFP_KERNEL);
- if (!rt_hash_locks)
- panic("IP: failed to allocate rt_hash_locks\n");
-
- for (i = 0; i < RT_HASH_LOCK_SZ; i++)
- spin_lock_init(&rt_hash_locks[i]);
-}
-#else
-# define rt_hash_lock_addr(slot) NULL
-
-static inline void rt_hash_lock_init(void)
-{
-}
-#endif
-
-static struct rt_hash_bucket *rt_hash_table __read_mostly;
-static unsigned rt_hash_mask __read_mostly;
-static unsigned int rt_hash_log __read_mostly;
-
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
-static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
-{
- return jhash_3words((__force u32)daddr, (__force u32)saddr,
- idx, genid)
- & rt_hash_mask;
-}
-
static inline int rt_genid(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#ifdef CONFIG_PROC_FS
-struct rt_cache_iter_state {
- struct seq_net_private p;
- int bucket;
- int genid;
-};
-
-static struct rtable *rt_cache_get_first(struct seq_file *seq)
-{
- struct rt_cache_iter_state *st = seq->private;
- struct rtable *r = NULL;
-
- for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
- if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain))
- continue;
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- while (r) {
- if (dev_net(r->dst.dev) == seq_file_net(seq) &&
- r->rt_genid == st->genid)
- return r;
- r = rcu_dereference_bh(r->dst.rt_next);
- }
- rcu_read_unlock_bh();
- }
- return r;
-}
-
-static struct rtable *__rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
-
- r = rcu_dereference_bh(r->dst.rt_next);
- while (!r) {
- rcu_read_unlock_bh();
- do {
- if (--st->bucket < 0)
- return NULL;
- } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain));
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
- while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->dst.dev) != seq_file_net(seq))
- continue;
- if (r->rt_genid == st->genid)
- break;
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
-{
- struct rtable *r = rt_cache_get_first(seq);
-
- if (r)
- while (pos && (r = rt_cache_get_next(seq, r)))
- --pos;
- return pos ? NULL : r;
-}
-
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct rt_cache_iter_state *st = seq->private;
if (*pos)
- return rt_cache_get_idx(seq, *pos - 1);
- st->genid = rt_genid(seq_file_net(seq));
+ return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct rtable *r;
-
- if (v == SEQ_START_TOKEN)
- r = rt_cache_get_first(seq);
- else
- r = rt_cache_get_next(seq, v);
++*pos;
- return r;
+ return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
- if (v && v != SEQ_START_TOKEN)
- rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
@@ -409,29 +254,6 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
- else {
- struct rtable *r = v;
- int len;
-
- seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
- "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->dst.dev ? r->dst.dev->name : "*",
- (__force u32)r->rt_dst,
- (__force u32)r->rt_gateway,
- r->rt_flags, atomic_read(&r->dst.__refcnt),
- r->dst.__use, 0, (__force u32)r->rt_src,
- dst_metric_advmss(&r->dst) + 40,
- dst_metric(&r->dst, RTAX_WINDOW),
- (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
- dst_metric(&r->dst, RTAX_RTTVAR)),
- r->fl.fl4_tos,
- r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
- r->dst.hh ? (r->dst.hh->hh_output ==
- dev_queue_xmit) : 0,
- r->rt_spec_dst, &len);
-
- seq_printf(seq, "%*s\n", 127 - len, "");
- }
return 0;
}
@@ -444,8 +266,7 @@ static const struct seq_operations rt_cache_seq_ops = {
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &rt_cache_seq_ops,
- sizeof(struct rt_cache_iter_state));
+ return seq_open_net(inode, file, &rt_cache_seq_ops, 0);
}
static const struct file_operations rt_cache_seq_fops = {
@@ -643,184 +464,12 @@ static inline int ip_rt_proc_init(void)
}
#endif /* CONFIG_PROC_FS */
-static inline void rt_free(struct rtable *rt)
-{
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline void rt_drop(struct rtable *rt)
-{
- ip_rt_put(rt);
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline int rt_fast_clean(struct rtable *rth)
-{
- /* Kill broadcast/multicast entries very aggresively, if they
- collide in hash table with more useful entries */
- return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
- rt_is_input_route(rth) && rth->dst.rt_next;
-}
-
-static inline int rt_valuable(struct rtable *rth)
-{
- return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- (rth->peer && rth->peer->pmtu_expires);
-}
-
-static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
-{
- unsigned long age;
- int ret = 0;
-
- if (atomic_read(&rth->dst.__refcnt))
- goto out;
-
- age = jiffies - rth->dst.lastuse;
- if ((age <= tmo1 && !rt_fast_clean(rth)) ||
- (age <= tmo2 && rt_valuable(rth)))
- goto out;
- ret = 1;
-out: return ret;
-}
-
-/* Bits of score are:
- * 31: very valuable
- * 30: not quite useless
- * 29..0: usage counter
- */
-static inline u32 rt_score(struct rtable *rt)
-{
- u32 score = jiffies - rt->dst.lastuse;
-
- score = ~score & ~(3<<30);
-
- if (rt_valuable(rt))
- score |= (1<<31);
-
- if (rt_is_output_route(rt) ||
- !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
- score |= (1<<30);
-
- return score;
-}
-
-static inline bool rt_caching(const struct net *net)
-{
- return net->ipv4.current_rt_cache_rebuild_count <=
- net->ipv4.sysctl_rt_cache_rebuild_count;
-}
-
-static inline bool compare_hash_inputs(const struct flowi *fl1,
- const struct flowi *fl2)
-{
- return ((((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
- ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
- (fl1->iif ^ fl2->iif)) == 0);
-}
-
-static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
-{
- return (((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
- ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
- (fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->fl4_tos ^ *(u16 *)&fl2->fl4_tos) |
- (fl1->oif ^ fl2->oif) |
- (fl1->iif ^ fl2->iif)) == 0;
-}
-
-static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
-{
- return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
-}
-
static inline int rt_is_expired(struct rtable *rth)
{
return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
- * Perform a full scan of hash table and free all entries.
- * Can be called by a softirq or a process.
- * In the later case, we want to be reschedule if necessary
- */
-static void rt_do_flush(struct net *net, int process_context)
-{
- unsigned int i;
- struct rtable *rth, *next;
-
- for (i = 0; i <= rt_hash_mask; i++) {
- struct rtable __rcu **pprev;
- struct rtable *list;
-
- if (process_context && need_resched())
- cond_resched();
- rth = rcu_dereference_raw(rt_hash_table[i].chain);
- if (!rth)
- continue;
-
- spin_lock_bh(rt_hash_lock_addr(i));
-
- list = NULL;
- pprev = &rt_hash_table[i].chain;
- rth = rcu_dereference_protected(*pprev,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- while (rth) {
- next = rcu_dereference_protected(rth->dst.rt_next,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- if (!net ||
- net_eq(dev_net(rth->dst.dev), net)) {
- rcu_assign_pointer(*pprev, next);
- rcu_assign_pointer(rth->dst.rt_next, list);
- list = rth;
- } else {
- pprev = &rth->dst.rt_next;
- }
- rth = next;
- }
-
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; list; list = next) {
- next = rcu_dereference_protected(list->dst.rt_next, 1);
- rt_free(list);
- }
- }
-}
-
-/*
- * While freeing expired entries, we compute average chain length
- * and standard deviation, using fixed-point arithmetic.
- * This to have an estimation of rt_chain_length_max
- * rt_chain_length_max = max(elasticity, AVG + 4*SD)
- * We use 3 bits for frational part, and 29 (or 61) for magnitude.
- */
-
-#define FRACT_BITS 3
-#define ONE (1UL << FRACT_BITS)
-
-/*
- * Given a hash chain and an item in this hash chain,
- * find if a previous entry has the same hash_inputs
- * (but differs on tos, mark or oif)
- * Returns 0 if an alias is found.
- * Returns ONE if rth has no alias before itself.
- */
-static int has_noalias(const struct rtable *head, const struct rtable *rth)
-{
- const struct rtable *aux = head;
-
- while (aux != rth) {
- if (compare_hash_inputs(&aux->fl, &rth->fl))
- return 0;
- aux = rcu_dereference_protected(aux->dst.rt_next, 1);
- }
- return ONE;
-}
-
-/*
* Pertubation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
* many times (2^24) without giving recent rt_genid.
@@ -841,366 +490,32 @@ static void rt_cache_invalidate(struct net *net)
void rt_cache_flush(struct net *net, int delay)
{
rt_cache_invalidate(net);
- if (delay >= 0)
- rt_do_flush(net, !in_softirq());
-}
-
-/* Flush previous cache invalidated entries from the cache */
-void rt_cache_flush_batch(struct net *net)
-{
- rt_do_flush(net, !in_softirq());
}
-static void rt_emergency_hash_rebuild(struct net *net)
-{
- if (net_ratelimit())
- printk(KERN_WARNING "Route hash chain too long!\n");
- rt_cache_invalidate(net);
-}
-
-/*
- Short description of GC goals.
-
- We want to build algorithm, which will keep routing cache
- at some equilibrium point, when number of aged off entries
- is kept approximately equal to newly generated ones.
-
- Current expiration strength is variable "expire".
- We try to adjust it dynamically, so that if networking
- is idle expires is large enough to keep enough of warm entries,
- and when load increases it reduces to limit cache size.
- */
-
static int rt_garbage_collect(struct dst_ops *ops)
{
- static unsigned long expire = RT_GC_TIMEOUT;
- static unsigned long last_gc;
- static int rover;
- static int equilibrium;
- struct rtable *rth;
- struct rtable __rcu **rthp;
- unsigned long now = jiffies;
- int goal;
- int entries = dst_entries_get_fast(&ipv4_dst_ops);
-
- /*
- * Garbage collection is pretty expensive,
- * do not make it too frequently.
- */
-
RT_CACHE_STAT_INC(gc_total);
-
- if (now - last_gc < ip_rt_gc_min_interval &&
- entries < ip_rt_max_size) {
- RT_CACHE_STAT_INC(gc_ignored);
- goto out;
- }
-
- entries = dst_entries_get_slow(&ipv4_dst_ops);
- /* Calculate number of entries, which we want to expire now. */
- goal = entries - (ip_rt_gc_elasticity << rt_hash_log);
- if (goal <= 0) {
- if (equilibrium < ipv4_dst_ops.gc_thresh)
- equilibrium = ipv4_dst_ops.gc_thresh;
- goal = entries - equilibrium;
- if (goal > 0) {
- equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- goal = entries - equilibrium;
- }
- } else {
- /* We are in dangerous area. Try to reduce cache really
- * aggressively.
- */
- goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- equilibrium = entries - goal;
- }
-
- if (now - last_gc >= ip_rt_gc_min_interval)
- last_gc = now;
-
- if (goal <= 0) {
- equilibrium += goal;
- goto work_done;
- }
-
- do {
- int i, k;
-
- for (i = rt_hash_mask, k = rover; i >= 0; i--) {
- unsigned long tmo = expire;
-
- k = (k + 1) & rt_hash_mask;
- rthp = &rt_hash_table[k].chain;
- spin_lock_bh(rt_hash_lock_addr(k));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) {
- if (!rt_is_expired(rth) &&
- !rt_may_expire(rth, tmo, expire)) {
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- continue;
- }
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- goal--;
- }
- spin_unlock_bh(rt_hash_lock_addr(k));
- if (goal <= 0)
- break;
- }
- rover = k;
-
- if (goal <= 0)
- goto work_done;
-
- /* Goal is not achieved. We stop process if:
-
- - if expire reduced to zero. Otherwise, expire is halfed.
- - if table is not full.
- - if we are called from interrupt.
- - jiffies check is just fallback/debug loop breaker.
- We will not spin here for long time in any case.
- */
-
- RT_CACHE_STAT_INC(gc_goal_miss);
-
- if (expire == 0)
- break;
-
- expire >>= 1;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, i);
-#endif
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- } while (!in_softirq() && time_before_eq(jiffies, now));
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- if (net_ratelimit())
- printk(KERN_WARNING "dst cache overflow\n");
- RT_CACHE_STAT_INC(gc_dst_overflow);
- return 1;
-
-work_done:
- expire += ip_rt_gc_min_interval;
- if (expire > ip_rt_gc_timeout ||
- dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
- dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
- expire = ip_rt_gc_timeout;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, rover);
-#endif
-out: return 0;
-}
-
-/*
- * Returns number of entries in a hash chain that have different hash_inputs
- */
-static int slow_chain_length(const struct rtable *head)
-{
- int length = 0;
- const struct rtable *rth = head;
-
- while (rth) {
- length += has_noalias(head, rth);
- rth = rcu_dereference_protected(rth->dst.rt_next, 1);
- }
- return length >> FRACT_BITS;
+ return 0;
}
-static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb, int ifindex)
+static int rt_finalize(struct rtable *rt, struct rtable **rp, struct sk_buff *skb)
{
- struct rtable *rth, *cand;
- struct rtable __rcu **rthp, **candp;
- unsigned long now;
- u32 min_score;
- int chain_length;
- int attempts = !in_softirq();
-
-restart:
- chain_length = 0;
- min_score = ~(u32)0;
- cand = NULL;
- candp = NULL;
- now = jiffies;
-
- if (!rt_caching(dev_net(rt->dst.dev))) {
- /*
- * If we're not caching, just tell the caller we
- * were successful and don't touch the route. The
- * caller hold the sole reference to the cache entry, and
- * it will be released when the caller is done with it.
- * If we drop it here, the callers have no way to resolve routes
- * when we're not caching. Instead, just point *rp at rt, so
- * the caller gets a single use out of the route
- * Note that we do rt_free on this new route entry, so that
- * once its refcount hits zero, we are still able to reap it
- * (Thanks Alexey)
- * Note: To avoid expensive rcu stuff for this uncached dst,
- * we set DST_NOCACHE so that dst_release() can free dst without
- * waiting a grace period.
- */
-
- rt->dst.flags |= DST_NOCACHE;
- if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = arp_bind_neighbour(&rt->dst);
- if (err) {
- if (net_ratelimit())
- printk(KERN_WARNING
- "Neighbour table failure & not caching routes.\n");
- ip_rt_put(rt);
- return err;
- }
- }
-
- goto skip_hashing;
- }
-
- rthp = &rt_hash_table[hash].chain;
-
- spin_lock_bh(rt_hash_lock_addr(hash));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (rt_is_expired(rth)) {
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- continue;
- }
- if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
- /* Put it first */
- *rthp = rth->dst.rt_next;
- /*
- * Since lookup is lockfree, the deletion
- * must be visible to another weakly ordered CPU before
- * the insertion at the start of the hash chain.
- */
- rcu_assign_pointer(rth->dst.rt_next,
- rt_hash_table[hash].chain);
- /*
- * Since lookup is lockfree, the update writes
- * must be ordered for consistency on SMP.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rth);
-
- dst_use(&rth->dst, now);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- rt_drop(rt);
- if (rp)
- *rp = rth;
- else
- skb_dst_set(skb, &rth->dst);
- return 0;
- }
-
- if (!atomic_read(&rth->dst.__refcnt)) {
- u32 score = rt_score(rth);
-
- if (score <= min_score) {
- cand = rth;
- candp = rthp;
- min_score = score;
- }
- }
-
- chain_length++;
-
- rthp = &rth->dst.rt_next;
- }
-
- if (cand) {
- /* ip_rt_gc_elasticity used to be average length of chain
- * length, when exceeded gc becomes really aggressive.
- *
- * The second limit is less certain. At the moment it allows
- * only 2 entries per bucket. We will see.
- */
- if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->dst.rt_next;
- rt_free(cand);
- }
- } else {
- if (chain_length > rt_chain_length_max &&
- slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
- struct net *net = dev_net(rt->dst.dev);
- int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(net)) {
- printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
- rt->dst.dev->name, num);
- }
- rt_emergency_hash_rebuild(net);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
- ifindex, rt_genid(net));
- goto restart;
- }
- }
-
- /* Try to bind route to arp only if it is output
- route or unicast forwarding path.
+ /* To avoid expensive rcu stuff for this uncached dst, we set
+ * DST_NOCACHE so that dst_release() can free dst without
+ * waiting a grace period.
*/
+ rt->dst.flags |= DST_NOCACHE;
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = arp_bind_neighbour(&rt->dst);
if (err) {
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- if (err != -ENOBUFS) {
- rt_drop(rt);
- return err;
- }
-
- /* Neighbour tables are full and nothing
- can be released. Try to shrink route cache,
- it is most likely it holds some neighbour records.
- */
- if (attempts-- > 0) {
- int saved_elasticity = ip_rt_gc_elasticity;
- int saved_int = ip_rt_gc_min_interval;
- ip_rt_gc_elasticity = 1;
- ip_rt_gc_min_interval = 0;
- rt_garbage_collect(&ipv4_dst_ops);
- ip_rt_gc_min_interval = saved_int;
- ip_rt_gc_elasticity = saved_elasticity;
- goto restart;
- }
-
if (net_ratelimit())
- printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
- rt_drop(rt);
- return -ENOBUFS;
+ printk(KERN_WARNING
+ "Neighbour table failure & not caching routes.\n");
+ ip_rt_put(rt);
+ return err;
}
}
- rt->dst.rt_next = rt_hash_table[hash].chain;
-
-#if RT_CACHE_DEBUG >= 2
- if (rt->dst.rt_next) {
- struct rtable *trt;
- printk(KERN_DEBUG "rt_cache @%02x: %pI4",
- hash, &rt->rt_dst);
- for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
- printk(" . %pI4", &trt->rt_dst);
- printk("\n");
- }
-#endif
- /*
- * Since lookup is lockfree, we must make sure
- * previous writes to rt are comitted to memory
- * before making rt visible to other CPUS.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
-
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
-skip_hashing:
if (rp)
*rp = rt;
else
@@ -1270,26 +585,6 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void rt_del(unsigned hash, struct rtable *rt)
-{
- struct rtable __rcu **rthp;
- struct rtable *aux;
-
- rthp = &rt_hash_table[hash].chain;
- spin_lock_bh(rt_hash_lock_addr(hash));
- ip_rt_put(rt);
- while ((aux = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->dst.rt_next;
- rt_free(aux);
- continue;
- }
- rthp = &aux->dst.rt_next;
- }
- spin_unlock_bh(rt_hash_lock_addr(hash));
-}
-
/* called in rcu_read_lock() section */
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 saddr, struct net_device *dev)
@@ -1348,14 +643,11 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
ip_rt_put(rt);
ret = NULL;
} else if (rt->rt_flags & RTCF_REDIRECTED) {
- unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
- rt->fl.oif,
- rt_genid(dev_net(dst->dev)));
#if RT_CACHE_DEBUG >= 1
printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
- &rt->rt_dst, rt->fl.fl4_tos);
+ &rt->rt_dst, rt->fl.fl4_tos);
#endif
- rt_del(hash, rt);
+ ip_rt_put(rt);
ret = NULL;
} else if (rt->peer &&
rt->peer->pmtu_expires &&
@@ -1820,7 +1112,6 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -1887,8 +1178,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
+ return rt_finalize(rth, NULL, skb);
e_nobufs:
return -ENOBUFS;
@@ -2035,7 +1325,6 @@ static int ip_mkroute_input(struct sk_buff *skb,
{
struct rtable* rth = NULL;
int err;
- unsigned hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1 && fl->oif == 0)
@@ -2048,9 +1337,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
return err;
/* put it into the cache */
- hash = rt_hash(daddr, saddr, fl->iif,
- rt_genid(dev_net(rth->dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
+ return rt_finalize(rth, NULL, skb);
}
/*
@@ -2078,7 +1365,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
- unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
struct net * net = dev_net(dev);
@@ -2197,8 +1483,7 @@ local_input:
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
- hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
+ err = rt_finalize(rth, NULL, skb);
goto out;
no_route:
@@ -2242,47 +1527,10 @@ martian_source_keep_err:
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool noref)
{
- struct rtable * rth;
- unsigned hash;
- int iif = dev->ifindex;
- struct net *net;
int res;
- net = dev_net(dev);
-
rcu_read_lock();
- if (!rt_caching(net))
- goto skip_cache;
-
- tos &= IPTOS_RT_MASK;
- hash = rt_hash(daddr, saddr, iif, rt_genid(net));
-
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->dst.rt_next)) {
- if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
- ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
- (rth->fl.iif ^ iif) |
- rth->fl.oif |
- (rth->fl.fl4_tos ^ tos)) == 0 &&
- rth->fl.mark == skb->mark &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- if (noref) {
- dst_use_noref(&rth->dst, jiffies);
- skb_dst_set_noref(skb, &rth->dst);
- } else {
- dst_use(&rth->dst, jiffies);
- skb_dst_set(skb, &rth->dst);
- }
- RT_CACHE_STAT_INC(in_hit);
- rcu_read_unlock();
- return 0;
- }
- RT_CACHE_STAT_INC(in_hlist_search);
- }
-
-skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
@@ -2439,12 +1687,9 @@ static int ip_mkroute_output(struct rtable **rp,
{
struct rtable *rth = NULL;
int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
- unsigned hash;
- if (err == 0) {
- hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
- rt_genid(dev_net(dev_out)));
- err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
- }
+
+ if (err == 0)
+ err = rt_finalize(rth, rp, NULL);
return err;
}
@@ -2635,38 +1880,8 @@ out: return err;
int __ip_route_output_key(struct net *net, struct rtable **rp,
const struct flowi *flp)
{
- unsigned int hash;
int res;
- struct rtable *rth;
- if (!rt_caching(net))
- goto slow_output;
-
- hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
-
- rcu_read_lock_bh();
- for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference_bh(rth->dst.rt_next)) {
- if (rth->fl.fl4_dst == flp->fl4_dst &&
- rth->fl.fl4_src == flp->fl4_src &&
- rt_is_output_route(rth) &&
- rth->fl.oif == flp->oif &&
- rth->fl.mark == flp->mark &&
- !((rth->fl.fl4_tos ^ flp->fl4_tos) &
- (IPTOS_RT_MASK | RTO_ONLINK)) &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- dst_use(&rth->dst, jiffies);
- RT_CACHE_STAT_INC(out_hit);
- rcu_read_unlock_bh();
- *rp = rth;
- return 0;
- }
- RT_CACHE_STAT_INC(out_hlist_search);
- }
- rcu_read_unlock_bh();
-
-slow_output:
rcu_read_lock();
res = ip_route_output_slow(net, rp, flp);
rcu_read_unlock();
@@ -2966,43 +2181,6 @@ errout_free:
int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct rtable *rt;
- int h, s_h;
- int idx, s_idx;
- struct net *net;
-
- net = sock_net(skb->sk);
-
- s_h = cb->args[0];
- if (s_h < 0)
- s_h = 0;
- s_idx = idx = cb->args[1];
- for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
- if (!rt_hash_table[h].chain)
- continue;
- rcu_read_lock_bh();
- for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
- if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
- continue;
- if (rt_is_expired(rt))
- continue;
- skb_dst_set_noref(skb, &rt->dst);
- if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, RTM_NEWROUTE,
- 1, NLM_F_MULTI) <= 0) {
- skb_dst_drop(skb);
- rcu_read_unlock_bh();
- goto done;
- }
- skb_dst_drop(skb);
- }
- rcu_read_unlock_bh();
- }
-
-done:
- cb->args[0] = h;
- cb->args[1] = idx;
return skb->len;
}
@@ -3235,16 +2413,6 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_IP_ROUTE_CLASSID */
-static __initdata unsigned long rhash_entries;
-static int __init set_rhash_entries(char *str)
-{
- if (!str)
- return 0;
- rhash_entries = simple_strtoul(str, &str, 0);
- return 1;
-}
-__setup("rhash_entries=", set_rhash_entries);
-
int __init ip_rt_init(void)
{
int rc = 0;
@@ -3267,21 +2435,8 @@ int __init ip_rt_init(void)
if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0)
panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n");
- rt_hash_table = (struct rt_hash_bucket *)
- alloc_large_system_hash("IP route cache",
- sizeof(struct rt_hash_bucket),
- rhash_entries,
- (totalram_pages >= 128 * 1024) ?
- 15 : 17,
- 0,
- &rt_hash_log,
- &rt_hash_mask,
- rhash_entries ? 0 : 512 * 1024);
- memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
- rt_hash_lock_init();
-
- ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
- ip_rt_max_size = (rt_hash_mask + 1) * 16;
+ ipv4_dst_ops.gc_thresh = ~0;
+ ip_rt_max_size = INT_MAX;
devinet_init();
ip_fib_init();
--
1.7.4.1
^ permalink raw reply related
* Re: [PATCH v6 2/9] ethtool: enable GSO and GRO by default
From: Michał Mirosław @ 2011-02-16 2:50 UTC (permalink / raw)
To: David Miller; +Cc: netdev, bhutchings
In-Reply-To: <20110215.184808.226754921.davem@davemloft.net>
On Tue, Feb 15, 2011 at 06:48:08PM -0800, David Miller wrote:
> You can't just update specific patches, you have to freshly resend
> the entire series again if you want me to apply your work.
Ah, ok. I tried to minimize duplicate mails in your mailbox. :)
-- Michał Mirosław
^ permalink raw reply
* Re: [PATCH v6 2/9] ethtool: enable GSO and GRO by default
From: David Miller @ 2011-02-16 2:48 UTC (permalink / raw)
To: mirq-linux; +Cc: netdev, bhutchings
In-Reply-To: <d256f661690245d75bec50f5a6acafcefcae1d8a.1297823573.git.mirq-linux@rere.qmqm.pl>
You can't just update specific patches, you have to freshly resend
the entire series again if you want me to apply your work.
^ permalink raw reply
* [PATCH v6 5/9] net: Introduce new feature setting ops
From: Michał Mirosław @ 2011-02-16 2:43 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <33a801222e3b4254ff15de0fc5799de82f05aea8.1297594674.git.mirq-linux@rere.qmqm.pl>
This introduces a new framework to handle device features setting.
It consists of:
- new fields in struct net_device:
+ hw_features - features that hw/driver supports toggling
+ wanted_features - features that user wants enabled, when possible
- new netdev_ops:
+ feat = ndo_fix_features(dev, feat) - API checking constraints for
enabling features or their combinations
+ ndo_set_features(dev) - API updating hardware state to match
changed dev->features
- new ethtool commands:
+ ETHTOOL_GFEATURES/ETHTOOL_SFEATURES: get/set dev->wanted_features
and trigger device reconfiguration if resulting dev->features
changed
+ ETHTOOL_GSTRINGS(ETH_SS_FEATURES): get feature bits names (meaning)
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
[updated to not generate a warning when registering non-SG capable device]
[rebased against current net-next]
include/linux/ethtool.h | 85 ++++++++++++++++++++++++++++++
include/linux/netdevice.h | 37 +++++++++++++-
net/core/dev.c | 46 ++++++++++++++--
net/core/ethtool.c | 125 ++++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 283 insertions(+), 10 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 1908929..806e716 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -251,6 +251,7 @@ enum ethtool_stringset {
ETH_SS_STATS,
ETH_SS_PRIV_FLAGS,
ETH_SS_NTUPLE_FILTERS,
+ ETH_SS_FEATURES,
};
/* for passing string sets for data tagging */
@@ -523,6 +524,87 @@ struct ethtool_flash {
char data[ETHTOOL_FLASH_MAX_FILENAME];
};
+/* for returning and changing feature sets */
+
+/**
+ * struct ethtool_get_features_block - block with state of 32 features
+ * @available: mask of changeable features
+ * @requested: mask of features requested to be enabled if possible
+ * @active: mask of currently enabled features
+ * @never_changed: mask of features not changeable for any device
+ */
+struct ethtool_get_features_block {
+ __u32 available;
+ __u32 requested;
+ __u32 active;
+ __u32 never_changed;
+};
+
+/**
+ * struct ethtool_gfeatures - command to get state of device's features
+ * @cmd: command number = %ETHTOOL_GFEATURES
+ * @size: in: number of elements in the features[] array;
+ * out: number of elements in features[] needed to hold all features
+ * @features: state of features
+ */
+struct ethtool_gfeatures {
+ __u32 cmd;
+ __u32 size;
+ struct ethtool_get_features_block features[0];
+};
+
+/**
+ * struct ethtool_set_features_block - block with request for 32 features
+ * @valid: mask of features to be changed
+ * @requested: values of features to be changed
+ */
+struct ethtool_set_features_block {
+ __u32 valid;
+ __u32 requested;
+};
+
+/**
+ * struct ethtool_sfeatures - command to request change in device's features
+ * @cmd: command number = %ETHTOOL_SFEATURES
+ * @size: array size of the features[] array
+ * @features: feature change masks
+ */
+struct ethtool_sfeatures {
+ __u32 cmd;
+ __u32 size;
+ struct ethtool_set_features_block features[0];
+};
+
+/*
+ * %ETHTOOL_SFEATURES changes features present in features[].valid to the
+ * values of corresponding bits in features[].requested. Bits in .requested
+ * not set in .valid or not changeable are ignored.
+ *
+ * Returns %EINVAL when .valid contains undefined or never-changable bits
+ * or size is not equal to required number of features words (32-bit blocks).
+ * Returns >= 0 if request was completed; bits set in the value mean:
+ * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not
+ * changeable (not present in %ETHTOOL_GFEATURES' features[].available)
+ * those bits were ignored.
+ * %ETHTOOL_F_WISH - some or all changes requested were recorded but the
+ * resulting state of bits masked by .valid is not equal to .requested.
+ * Probably there are other device-specific constraints on some features
+ * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
+ * here as though ignored bits were cleared.
+ *
+ * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
+ * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
+ * for ETH_SS_FEATURES string set. First entry in the table corresponds to least
+ * significant bit in features[0] fields. Empty strings mark undefined features.
+ */
+enum ethtool_sfeatures_retval_bits {
+ ETHTOOL_F_UNSUPPORTED__BIT,
+ ETHTOOL_F_WISH__BIT,
+};
+
+#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT)
+#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT)
+
#ifdef __KERNEL__
#include <linux/rculist.h>
@@ -744,6 +826,9 @@ struct ethtool_ops {
#define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */
#define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */
+#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */
+#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */
+
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dede3fd..85f67e2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -791,6 +791,18 @@ struct netdev_tc_txq {
*
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to release previously enslaved netdev.
+ *
+ * Feature/offload setting functions.
+ * u32 (*ndo_fix_features)(struct net_device *dev, u32 features);
+ * Adjusts the requested feature flags according to device-specific
+ * constraints, and returns the resulting flags. Must not modify
+ * the device state.
+ *
+ * int (*ndo_set_features)(struct net_device *dev, u32 features);
+ * Called to update device configuration to new features. Passed
+ * feature set might be less than what was returned by ndo_fix_features()).
+ * Must return >0 or -errno if it changed dev->features itself.
+ *
*/
#define HAVE_NET_DEVICE_OPS
struct net_device_ops {
@@ -874,6 +886,10 @@ struct net_device_ops {
struct net_device *slave_dev);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
+ u32 (*ndo_fix_features)(struct net_device *dev,
+ u32 features);
+ int (*ndo_set_features)(struct net_device *dev,
+ u32 features);
};
/*
@@ -925,12 +941,18 @@ struct net_device {
struct list_head napi_list;
struct list_head unreg_list;
- /* Net device features */
+ /* currently active device features */
u32 features;
-
+ /* user-changeable features */
+ u32 hw_features;
+ /* user-requested features */
+ u32 wanted_features;
/* VLAN feature mask */
u32 vlan_features;
+ /* Net device feature bits; if you change something,
+ * also update netdev_features_strings[] in ethtool.c */
+
#define NETIF_F_SG 1 /* Scatter/gather IO. */
#define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */
#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */
@@ -966,6 +988,12 @@ struct net_device {
#define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
#define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
+ /* Features valid for ethtool to change */
+ /* = all defined minus driver/device-class-related */
+#define NETIF_F_NEVER_CHANGE (NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \
+ NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+#define NETIF_F_ETHTOOL_BITS (0x1f3fffff & ~NETIF_F_NEVER_CHANGE)
+
/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \
NETIF_F_TSO6 | NETIF_F_UFO)
@@ -2428,8 +2456,13 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
extern void linkwatch_run_queue(void);
+static inline u32 netdev_get_wanted_features(struct net_device *dev)
+{
+ return (dev->features & ~dev->hw_features) | dev->wanted_features;
+}
u32 netdev_increment_features(u32 all, u32 one, u32 mask);
u32 netdev_fix_features(struct net_device *dev, u32 features);
+void netdev_update_features(struct net_device *dev);
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 8686f6f..4f69439 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5302,6 +5302,37 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
}
EXPORT_SYMBOL(netdev_fix_features);
+void netdev_update_features(struct net_device *dev)
+{
+ u32 features;
+ int err = 0;
+
+ features = netdev_get_wanted_features(dev);
+
+ if (dev->netdev_ops->ndo_fix_features)
+ features = dev->netdev_ops->ndo_fix_features(dev, features);
+
+ /* driver might be less strict about feature dependencies */
+ features = netdev_fix_features(dev, features);
+
+ if (dev->features == features)
+ return;
+
+ netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n",
+ dev->features, features);
+
+ if (dev->netdev_ops->ndo_set_features)
+ err = dev->netdev_ops->ndo_set_features(dev, features);
+
+ if (!err)
+ dev->features = features;
+ else if (err < 0)
+ netdev_err(dev,
+ "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
+ err, features, dev->features);
+}
+EXPORT_SYMBOL(netdev_update_features);
+
/**
* netif_stacked_transfer_operstate - transfer operstate
* @rootdev: the root or lower level device to transfer state from
@@ -5436,15 +5467,18 @@ int register_netdevice(struct net_device *dev)
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
- /* Enable software offloads by default - will be stripped in
- * netdev_fix_features() if not supported. */
- dev->features |= NETIF_F_SOFT_FEATURES;
+ /* Transfer changeable features to wanted_features and enable
+ * software offloads (GSO and GRO).
+ */
+ dev->hw_features |= NETIF_F_SOFT_FEATURES;
+ dev->wanted_features = (dev->features & dev->hw_features)
+ | NETIF_F_SOFT_FEATURES;
/* Avoid warning from netdev_fix_features() for GSO without SG */
- if (!(dev->features & NETIF_F_SG))
- dev->features &= ~NETIF_F_GSO;
+ if (!(dev->wanted_features & NETIF_F_SG))
+ dev->wanted_features &= ~NETIF_F_GSO;
- dev->features = netdev_fix_features(dev, dev->features);
+ netdev_update_features(dev);
/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
* vlan_dev_init() will do the dev->features check, so these features
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c3fb8f9..9577396 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -172,10 +172,120 @@ EXPORT_SYMBOL(ethtool_ntuple_flush);
/* Handlers for each ethtool command */
+#define ETHTOOL_DEV_FEATURE_WORDS 1
+
+static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
+{
+ struct ethtool_gfeatures cmd = {
+ .cmd = ETHTOOL_GFEATURES,
+ .size = ETHTOOL_DEV_FEATURE_WORDS,
+ };
+ struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = {
+ {
+ .available = dev->hw_features,
+ .requested = dev->wanted_features,
+ .active = dev->features,
+ .never_changed = NETIF_F_NEVER_CHANGE,
+ },
+ };
+ u32 __user *sizeaddr;
+ u32 copy_size;
+
+ sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
+ if (get_user(copy_size, sizeaddr))
+ return -EFAULT;
+
+ if (copy_size > ETHTOOL_DEV_FEATURE_WORDS)
+ copy_size = ETHTOOL_DEV_FEATURE_WORDS;
+
+ if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
+ return -EFAULT;
+ useraddr += sizeof(cmd);
+ if (copy_to_user(useraddr, features, copy_size * sizeof(*features)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
+{
+ struct ethtool_sfeatures cmd;
+ struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
+ int ret = 0;
+
+ if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
+ return -EFAULT;
+ useraddr += sizeof(cmd);
+
+ if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS)
+ return -EINVAL;
+
+ if (copy_from_user(features, useraddr, sizeof(features)))
+ return -EFAULT;
+
+ if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
+ return -EINVAL;
+
+ if (features[0].valid & ~dev->hw_features) {
+ features[0].valid &= dev->hw_features;
+ ret |= ETHTOOL_F_UNSUPPORTED;
+ }
+
+ dev->wanted_features &= ~features[0].valid;
+ dev->wanted_features |= features[0].valid & features[0].requested;
+ netdev_update_features(dev);
+
+ if ((dev->wanted_features ^ dev->features) & features[0].valid)
+ ret |= ETHTOOL_F_WISH;
+
+ return ret;
+}
+
+static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = {
+ /* NETIF_F_SG */ "tx-scatter-gather",
+ /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4",
+ /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded",
+ /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic",
+ /* NETIF_F_IPV6_CSUM */ "tx_checksum-ipv6",
+ /* NETIF_F_HIGHDMA */ "highdma",
+ /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist",
+ /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert",
+
+ /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse",
+ /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter",
+ /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged",
+ /* NETIF_F_GSO */ "tx-generic-segmentation",
+ /* NETIF_F_LLTX */ "tx-lockless",
+ /* NETIF_F_NETNS_LOCAL */ "netns-local",
+ /* NETIF_F_GRO */ "rx-gro",
+ /* NETIF_F_LRO */ "rx-lro",
+
+ /* NETIF_F_TSO */ "tx-tcp-segmentation",
+ /* NETIF_F_UFO */ "tx-udp-fragmentation",
+ /* NETIF_F_GSO_ROBUST */ "tx-gso-robust",
+ /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation",
+ /* NETIF_F_TSO6 */ "tx-tcp6-segmentation",
+ /* NETIF_F_FSO */ "tx-fcoe-segmentation",
+ "",
+ "",
+
+ /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc",
+ /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp",
+ /* NETIF_F_FCOE_MTU */ "fcoe-mtu",
+ /* NETIF_F_NTUPLE */ "rx-ntuple-filter",
+ /* NETIF_F_RXHASH */ "rx-hashing",
+ "",
+ "",
+ "",
+};
+
static int __ethtool_get_sset_count(struct net_device *dev, int sset)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
+ if (sset == ETH_SS_FEATURES)
+ return ARRAY_SIZE(netdev_features_strings);
+
if (ops && ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
@@ -187,8 +297,12 @@ static void __ethtool_get_strings(struct net_device *dev,
{
const struct ethtool_ops *ops = dev->ethtool_ops;
- /* ops->get_strings is valid because checked earlier */
- ops->get_strings(dev, stringset, data);
+ if (stringset == ETH_SS_FEATURES)
+ memcpy(data, netdev_features_strings,
+ sizeof(netdev_features_strings));
+ else
+ /* ops->get_strings is valid because checked earlier */
+ ops->get_strings(dev, stringset, data);
}
static u32 ethtool_get_feature_mask(u32 eth_cmd)
@@ -1533,6 +1647,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
+ case ETHTOOL_GFEATURES:
break;
default:
if (!capable(CAP_NET_ADMIN))
@@ -1678,6 +1793,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXFHINDIR:
rc = ethtool_set_rxfh_indir(dev, useraddr);
break;
+ case ETHTOOL_GFEATURES:
+ rc = ethtool_get_features(dev, useraddr);
+ break;
+ case ETHTOOL_SFEATURES:
+ rc = ethtool_set_features(dev, useraddr);
+ break;
case ETHTOOL_GTXCSUM:
case ETHTOOL_GSG:
case ETHTOOL_GTSO:
--
1.7.2.3
^ permalink raw reply related
* [PATCH v6 2/9] ethtool: enable GSO and GRO by default
From: Michał Mirosław @ 2011-02-16 2:43 UTC (permalink / raw)
To: netdev; +Cc: Ben Hutchings, David Miller
In-Reply-To: <20110216024237.GA6434@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
[updated to not generate a warning when registering non-SG capable device]
include/linux/netdevice.h | 3 +++
net/core/dev.c | 18 ++++++++++++++----
2 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d08ef65..168e3ad 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -984,6 +984,9 @@ struct net_device {
NETIF_F_SG | NETIF_F_HIGHDMA | \
NETIF_F_FRAGLIST)
+ /* changeable features with no special hardware requirements */
+#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+
/* Interface index. Unique device identifier */
int ifindex;
int iflink;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4580460..8686f6f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5274,6 +5274,12 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
features &= ~NETIF_F_TSO;
}
+ /* Software GSO depends on SG. */
+ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) {
+ netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
+ features &= ~NETIF_F_GSO;
+ }
+
/* UFO needs SG and checksumming */
if (features & NETIF_F_UFO) {
/* maybe split UFO into V4 and V6? */
@@ -5430,12 +5436,16 @@ int register_netdevice(struct net_device *dev)
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
+ /* Enable software offloads by default - will be stripped in
+ * netdev_fix_features() if not supported. */
+ dev->features |= NETIF_F_SOFT_FEATURES;
+
+ /* Avoid warning from netdev_fix_features() for GSO without SG */
+ if (!(dev->features & NETIF_F_SG))
+ dev->features &= ~NETIF_F_GSO;
+
dev->features = netdev_fix_features(dev, dev->features);
- /* Enable software GSO if SG is supported. */
- if (dev->features & NETIF_F_SG)
- dev->features |= NETIF_F_GSO;
-
/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
* vlan_dev_init() will do the dev->features check, so these features
* are enabled only if supported by underlying device.
--
1.7.2.3
^ permalink raw reply related
* Re: [PATCH v5 RESEND 2/9] ethtool: enable GSO and GRO by default
From: Michał Mirosław @ 2011-02-16 2:42 UTC (permalink / raw)
To: David Miller; +Cc: netdev, bhutchings
In-Reply-To: <20110215.140043.59699086.davem@davemloft.net>
On Tue, Feb 15, 2011 at 02:00:43PM -0800, David Miller wrote:
> From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
> Date: Tue, 15 Feb 2011 22:46:49 +0100
> > On Sun, Feb 13, 2011 at 10:50:23AM -0800, David Miller wrote:
> >> From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
> >> Date: Sun, 13 Feb 2011 12:11:45 +0100 (CET)
> >> > Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
> >> This is not appropriate.
> >>
> >> Now, every driver that lacks SG support will spit out that warning
> >> message in netdev_fix_features().
> >>
> >> That's why the check is there conditionalizing NETIF_F_GSO on
> >> NETIF_F_SG in register_netdevice().
> > I think all those messages should be converted to DEBUG level. Those
> > conditions are constant and can be better described in
> > Documentation/networking/ or ethtool manpage. Preferably along the
> > device-specific conditions when implemented.
> >
> > Or I could just drop the message for the GSO case as it's something new here
> > anyway (I added it to make it consistent with handling of other features).
> The messages exist to let driver authors know they've constructed an
> illegal set of feature bits.
Only multiple checksum flags are actual driver bugs - those are handled
in register_netdevice(). netdev_fix_features() represents limitations of core
networking code . Hardware might as well handle TSO without SG or SG without
checksumming. What's the point in duplicating those restrictions in drivers?
> Since you're now adding the GSO bit yourself, you should perform
> due diligence and prevent the illegal combination yourself.
>
> This has no other impact on the other messages and cases, which
> definitely should stay intact.
>
> Your change is just wrong and knowingly introduces useless log
> messages, please just fix it up.
The messages from netdev_fix_features() will also be triggered by user
disabling required feature (ie. HW checksum for most of TX offloads)
for a device or its slave or sometimes on MTU changes (ie. for jme and
possibly others). Even after I fix triggering of "GSO needs SG"
message in register_netdevice(), this and other messages will show up
more often because of the way the new scheme works.
Best Regards,
Michał Mirosław
^ permalink raw reply
* Re: [kernel] net.ipv6.route.max_size
From: Mr. James W. Laferriere @ 2011-02-16 1:29 UTC (permalink / raw)
To: Lukasz Trabinski; +Cc: Linux Kernel Maillist, NetDev
In-Reply-To: <alpine.LFD.2.00.1102142024460.6561@oceanic.wsisiz.edu.pl>
Hello Lukasz ,
Since I have not seen anyone else suggest this or to do so I'll forward
this onto the NetDev <netdev@vger.kernel.org> list for their perusal as well .
Hth , JimL
On Mon, 14 Feb 2011, Lukasz Trabinski wrote:
> Hello
>
> IPv6 route table size is still growing. In stanard linux box configuration
> with IPv6 BGP session (with ipv6 world table) and BGP application like
> Quagga,
> we have problem like this:
>
> 2011/02/12 18:43:52 ZEBRA: netlink-cmd error: Cannot allocate memory,
> type=RTM_NEWROUTE(24), seq=11124600, pid=0
>
> This problem shows us that's all prefixes comes from BGP can't be install
> into FIB
>
> IN BGP application we can see, that's we recive 4484 prefixes from ipv6
> neighbor:
>
> cosmos> show bgp summary
> Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down
> State/PfxRcd
> 2001:1a68:0:c::1
> 4 24724 431945 70172 0 0 0 2d01h18m 4484
>
>
> I suggest that net->ipv6.sysctl.ip6_rt_max_size should be increase.
> Below _simple_ patch for this problem. I don't understand why in ipv4/route
> we have different method to count ip4_rt_max_size? My value 65536 in near
> future will be also wrong. I know also, that we can change it by sysctl, but
> I thing that it's not good way to fix it.
>
>
> --- route.c~ 2011-02-14 20:26:12.000000000 +0100
> +++ route.c 2011-02-14 20:30:04.000000000 +0100
> @@ -2708,7 +2708,7 @@
> #endif
>
> net->ipv6.sysctl.flush_delay = 0;
> - net->ipv6.sysctl.ip6_rt_max_size = 4096;
> + net->ipv6.sysctl.ip6_rt_max_size = 65536;
> net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
> net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
> net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
+------------------------------------------------------------------+
| James W. Laferriere | System Techniques | Give me VMS |
| Network&System Engineer | 3237 Holden Road | Give me Linux |
| babydr@baby-dragons.com | Fairbanks, AK. 99709 | only on AXP |
+------------------------------------------------------------------+
^ permalink raw reply
* Re: Multicast snooping fixes and suggestions
From: Stephen Hemminger @ 2011-02-15 23:41 UTC (permalink / raw)
To: Linus Lüssing, Herbert Xu
Cc: David S. Miller, bridge, netdev, linux-kernel
In-Reply-To: <1297811961-19249-1-git-send-email-linus.luessing@web.de>
On Wed, 16 Feb 2011 00:19:16 +0100
Linus Lüssing <linus.luessing@web.de> wrote:
> Hello everyone,
>
> While testing the (very awesome!) bridge igmp/mld snooping support I came across
> two issues which are breaking IPv6 multicast snooping and IPv6
> non-link-local multicast on bridges with multicast snooping support enabled
> in general. The first two patches shall fix these issues.
>
> The third one addresses a potential bug on little endian machines which I noticed
> during this little code reviewing. This patch is untested though, feedback welcome.
>
> The fourth and fifth patch are a suggestion to also permit using the bridge multicast
> snooping feature for link local multimedia multicast traffic. Therefore
> using the transient multicast flag instead of the non-link-local scope criteria
> seems to be a suitable solution at least for IPv6, in my opinion. Let me know what
> you think about it.
>
> Thanks for reviewing these patches.
>
> Cheers,
> Linus
These look correct. Did you test them with real traffic?
^ permalink raw reply
* [PATCH 4/5] ipv6: Add IPv6 multicast address flag defines
From: Linus Lüssing @ 2011-02-15 23:19 UTC (permalink / raw)
To: Stephen Hemminger, David S. Miller, bridge
Cc: netdev, linux-kernel, Herbert Xu, Linus Lüssing
In-Reply-To: <1297811961-19249-1-git-send-email-linus.luessing@web.de>
This commit adds the missing IPv6 multicast address flag defines to
complement the already existing multicast address scope defines and to
be able to check these flags nicely in the future.
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
---
include/net/ipv6.h | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4a3cd2c..96e50e0 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -89,6 +89,18 @@
#define IPV6_ADDR_SCOPE_GLOBAL 0x0e
/*
+ * Addr flags
+ */
+#ifdef __KERNEL__
+#define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \
+ ((a)->s6_addr[1] & 0x10)
+#define IPV6_ADDR_MC_FLAG_PREFIX(a) \
+ ((a)->s6_addr[1] & 0x20)
+#define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \
+ ((a)->s6_addr[1] & 0x40)
+#endif
+
+/*
* fragmentation header
*/
--
1.7.2.3
^ permalink raw reply related
* [PATCH 5/5] bridge: Allow mcast snooping for transient link local addresses too
From: Linus Lüssing @ 2011-02-15 23:19 UTC (permalink / raw)
To: Stephen Hemminger, David S. Miller, bridge
Cc: netdev, linux-kernel, Herbert Xu, Linus Lüssing
In-Reply-To: <1297811961-19249-1-git-send-email-linus.luessing@web.de>
Currently the multicast bridge snooping support is not active for
link local multicast. I assume this has been done to leave
important multicast data untouched, like IPv6 Neighborhood Discovery.
In larger, bridged, local networks it could however be desirable to
optimize for instance local multicast audio/video streaming too.
With the transient flag in IPv6 multicast addresses we have an easy
way to optimize such multimedia traffic without tempering with the
high priority multicast data from well-known addresses.
This patch alters the multicast bridge snooping for IPv6, to take
effect for transient multicast addresses instead of non-link-local
addresses.
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
---
net/bridge/br_multicast.c | 9 ++++-----
1 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index e8fdaab..b5eb28a 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -37,10 +37,9 @@
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static inline int ipv6_is_local_multicast(const struct in6_addr *addr)
+static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
{
- if (ipv6_addr_is_multicast(addr) &&
- IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL)
+ if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
return 1;
return 0;
}
@@ -781,7 +780,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
{
struct br_ip br_group;
- if (ipv6_is_local_multicast(group))
+ if (!ipv6_is_transient_multicast(group))
return 0;
ipv6_addr_copy(&br_group.u.ip6, group);
@@ -1342,7 +1341,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
{
struct br_ip br_group;
- if (ipv6_is_local_multicast(group))
+ if (!ipv6_is_transient_multicast(group))
return;
ipv6_addr_copy(&br_group.u.ip6, group);
--
1.7.2.3
^ permalink raw reply related
* [PATCH 3/5] bridge: Add missing ntohs()s for MLDv2 report parsing
From: Linus Lüssing @ 2011-02-15 23:19 UTC (permalink / raw)
To: Stephen Hemminger, David S. Miller, bridge
Cc: netdev, linux-kernel, Herbert Xu, Linus Lüssing
In-Reply-To: <1297811961-19249-1-git-send-email-linus.luessing@web.de>
The nsrcs number is 2 Byte wide, therefore we need to call ntohs()
before using it.
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
---
net/bridge/br_multicast.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 45dcf10..e8fdaab 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1021,11 +1021,12 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
if (!pskb_may_pull(skb,
len + sizeof(*grec) +
- sizeof(struct in6_addr) * (*nsrcs)))
+ sizeof(struct in6_addr) * ntohs(*nsrcs)))
return -EINVAL;
grec = (struct mld2_grec *)(skb->data + len);
- len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs);
+ len += sizeof(*grec) +
+ sizeof(struct in6_addr) * ntohs(*nsrcs);
/* We treat these as MLDv1 reports for now. */
switch (grec->grec_type) {
--
1.7.2.3
^ 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