* [PATCH 5/6] IPVS: remove unused init and cleanup functions.
From: Hans Schillstrom @ 2011-04-20 18:33 UTC (permalink / raw)
To: horms, ja, ebiederm, lvs-devel, netdev, netfilter-devel
Cc: hans.schillstrom, Hans Schillstrom
In-Reply-To: <1303324434-14024-1-git-send-email-hans@schillstrom.com>
After restructuring, there is some unused or empty functions
left to be removed.
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
---
include/net/ip_vs.h | 6 ------
net/netfilter/ipvs/ip_vs_app.c | 10 ----------
net/netfilter/ipvs/ip_vs_core.c | 29 ++++-------------------------
net/netfilter/ipvs/ip_vs_est.c | 9 ---------
net/netfilter/ipvs/ip_vs_sync.c | 9 ---------
5 files changed, 4 insertions(+), 59 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index f7a0fdb..4d56af7 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1123,8 +1123,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_app_init(void);
-extern void ip_vs_app_cleanup(void);
void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
void ip_vs_unbind_pe(struct ip_vs_service *svc);
@@ -1227,15 +1225,11 @@ extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
__u8 syncid);
extern int stop_sync_thread(struct net *net, int state);
extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
-extern int ip_vs_sync_init(void);
-extern void ip_vs_sync_cleanup(void);
/*
* IPVS rate estimator prototypes (from ip_vs_est.c)
*/
-extern int ip_vs_estimator_init(void);
-extern void ip_vs_estimator_cleanup(void);
extern void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
extern void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 81b299d..5f34cf4 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -589,13 +589,3 @@ void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
proc_net_remove(net, "ip_vs_app");
}
-
-int __init ip_vs_app_init(void)
-{
- return 0;
-}
-
-
-void ip_vs_app_cleanup(void)
-{
-}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 00da1e5..48eb587 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1973,36 +1973,23 @@ static int __init ip_vs_init(void)
{
int ret;
- ip_vs_estimator_init();
ret = ip_vs_control_init();
if (ret < 0) {
pr_err("can't setup control.\n");
- goto cleanup_estimator;
+ goto exit;
}
ip_vs_protocol_init();
- ret = ip_vs_app_init();
- if (ret < 0) {
- pr_err("can't setup application helper.\n");
- goto cleanup_protocol;
- }
-
ret = ip_vs_conn_init();
if (ret < 0) {
pr_err("can't setup connection table.\n");
- goto cleanup_app;
- }
-
- ret = ip_vs_sync_init();
- if (ret < 0) {
- pr_err("can't setup sync data.\n");
- goto cleanup_conn;
+ goto cleanup_protocol;
}
ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */
if (ret < 0)
- goto cleanup_sync;
+ goto cleanup_conn;
ret = register_pernet_device(&ipvs_core_dev_ops);
if (ret < 0)
@@ -2022,17 +2009,12 @@ cleanup_dev:
unregister_pernet_device(&ipvs_core_dev_ops);
cleanup_sub:
unregister_pernet_subsys(&ipvs_core_ops);
-cleanup_sync:
- ip_vs_sync_cleanup();
cleanup_conn:
ip_vs_conn_cleanup();
-cleanup_app:
- ip_vs_app_cleanup();
cleanup_protocol:
ip_vs_protocol_cleanup();
ip_vs_control_cleanup();
-cleanup_estimator:
- ip_vs_estimator_cleanup();
+exit:
return ret;
}
@@ -2041,12 +2023,9 @@ static void __exit ip_vs_cleanup(void)
nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
unregister_pernet_device(&ipvs_core_dev_ops);
unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */
- ip_vs_sync_cleanup();
ip_vs_conn_cleanup();
- ip_vs_app_cleanup();
ip_vs_protocol_cleanup();
ip_vs_control_cleanup();
- ip_vs_estimator_cleanup();
pr_info("ipvs unloaded.\n");
}
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index f5d2a01..0fac601 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -207,12 +207,3 @@ void __net_exit ip_vs_estimator_net_cleanup(struct net *net)
{
del_timer_sync(&net_ipvs(net)->est_timer);
}
-
-int __init ip_vs_estimator_init(void)
-{
- return 0;
-}
-
-void ip_vs_estimator_cleanup(void)
-{
-}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 1036b34..ef09afb 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1689,12 +1689,3 @@ void ip_vs_sync_net_cleanup(struct net *net)
if (retc && retc != -EINVAL)
pr_err("Failed to stop Backup Daemon\n");
}
-
-int __init ip_vs_sync_init(void)
-{
- return 0;
-}
-
-void ip_vs_sync_cleanup(void)
-{
-}
--
1.7.2.3
^ permalink raw reply related
* [PATCH 6/6] IPVS: add debug functions
From: Hans Schillstrom @ 2011-04-20 18:33 UTC (permalink / raw)
To: horms, ja, ebiederm, lvs-devel, netdev, netfilter-devel
Cc: hans.schillstrom, Hans Schillstrom
In-Reply-To: <1303324434-14024-1-git-send-email-hans@schillstrom.com>
Optional patch, but it is nice to have.
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
---
net/netfilter/ipvs/ip_vs_ctl.c | 13 ++++++++++++-
1 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 34f05db..3b6c411 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -351,8 +351,11 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
svc->flags &= ~IP_VS_SVC_F_HASHED;
atomic_dec(&svc->refcnt);
/* No more services then no need for input */
- if (atomic_read(&svc->refcnt) == 0)
+ if (!atomic_read(&svc->refcnt)) {
atomic_set(&net_ipvs(svc->net)->enable, 0);
+ IP_VS_DBG(2, "Last service removed in net(%d) input disabled\n",
+ net_ipvs(svc->net)->gen);
+ }
return 1;
}
@@ -1222,6 +1225,10 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
write_unlock_bh(&__ip_vs_svc_lock);
*svc_p = svc;
+ if (atomic_read(&ipvs->enable) == 0)
+ pr_info("netns(%d) enabled first service added\n",
+ ipvs->gen);
+
/* Now there is a service - full throttle */
atomic_set(&ipvs->enable, 1);
return 0;
@@ -3695,6 +3702,7 @@ int __net_init ip_vs_control_net_init(struct net *net)
int idx;
struct netns_ipvs *ipvs = net_ipvs(net);
+ EnterFunction(2);
ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
/* Initialize rs_table */
@@ -3721,6 +3729,7 @@ int __net_init ip_vs_control_net_init(struct net *net)
if (ip_vs_control_net_init_sysctl(net))
goto err;
+ LeaveFunction(2);
return 0;
err:
@@ -3732,6 +3741,7 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ EnterFunction(2);
ip_vs_trash_cleanup(net);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
ip_vs_control_net_cleanup_sysctl(net);
@@ -3739,6 +3749,7 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
proc_net_remove(net, "ip_vs_stats");
proc_net_remove(net, "ip_vs");
free_percpu(ipvs->tot_stats.cpustats);
+ LeaveFunction(2);
}
int __init ip_vs_control_init(void)
--
1.7.2.3
^ permalink raw reply related
* [v2 PATCH 0/6] IPVS: init and cleanup.
From: Hans Schillstrom @ 2011-04-20 18:33 UTC (permalink / raw)
To: horms, ja, ebiederm, lvs-devel, netdev, netfilter-devel
Cc: hans.schillstrom, Hans Schillstrom
This patch series handles exit from a network name space.
REVISION
This is version 2
OVERVIEW
Basically there was three faults in the netns implementation.
- Kernel threads hold devices and preventing an exit.
- dst cache holds references to devices.
- Services was not always released.
Patch 1 & 3 contains the functionality
4 renames funcctions
5 removes empty functions
6 Debuging.
IMPLEMENTATION
- Avoid to increment the usage counter for kernel threads.
this is done in the first patch.
- Patch 3 tries to restore the cleanup order.
Add NETDEV_UNREGISTER notification for dst_reset
>From Julian -
"For __ip_vs_service_cleanup: it still has to use mutex.
Or we can avoid it by introducing ip_vs_unlink_service_nolock:
ip_vs_flush will look like your __ip_vs_service_cleanup and
will call ip_vs_unlink_service_nolock. ip_vs_unlink_service_nolock
will be called by ip_vs_flush and by ip_vs_unlink_service."
I will give above another try later on see if I can get it to work.
Right now ip_vs_service_net_cleanup() seems to work.
An netns exit could look like this
IPVS: Enter: __ip_vs_dev_cleanup, net/netfilter/ipvs/ip_vs_core.c
IPVS: stopping master sync thread 1286 ...
IPVS: stopping backup sync thread 1294 ...
IPVS: Leave: __ip_vs_dev_cleanup, net/netfilter/ipvs/ip_vs_core.c
IPVS: Enter: ip_vs_dst_event, net/netfilter/ipvs/ip_vs_ctl.c line
IPVS: Leave: ip_vs_dst_event, net/netfilter/ipvs/ip_vs_ctl.c line
...
IPVS: Enter: ip_vs_dst_event, net/netfilter/ipvs/ip_vs_ctl.c line
IPVS: Leave: ip_vs_dst_event, net/netfilter/ipvs/ip_vs_ctl.c line
IPVS: Enter: ip_vs_service_net_cleanup, net/netfilter/ipvs/ip_vs_ctl.c
IPVS: __ip_vs_del_service: enter
IPVS: Moving dest 192.168.1.6:0 into trash, dest->refcnt=43450
...
IPVS: Moving dest 192.168.1.3:0 into trash, dest->refcnt=43449
IPVS: __ip_vs_del_service: enter
IPVS: Removing destination 0/[2003:0000:0000:0000:0000:0002:0000:0006]:80
...
IPVS: Removing destination 0/[2003:0000:0000:0000:0000:0002:0000:0003]:80
IPVS: Removing service 0/[2003:0000:0000:0000:0000:0002:0004:0100]:80 usecnt=0
IPVS: Leave: ip_vs_service_net_cleanup, net/netfilter/ipvs/ip_vs_ctl.c
IPVS: Enter: ip_vs_control_net_cleanup, net/netfilter/ipvs/ip_vs_ctl.c
IPVS: Removing service 80/0.0.0.0:0 usecnt=0
IPVS: Leave: ip_vs_control_net_cleanup, net/netfilter/ipvs/ip_vs_ctl.c
IPVS: ipvs netns 8 released
PATCH SET
This patch set is based upon net-next-2.6 (2.6.39-rc2)
SUMMARY
include/net/ip_vs.h | 23 ++++--
net/netfilter/ipvs/ip_vs_app.c | 23 +-----
net/netfilter/ipvs/ip_vs_conn.c | 14 +---
net/netfilter/ipvs/ip_vs_core.c | 118 +++++++++++++++++++--------
net/netfilter/ipvs/ip_vs_ctl.c | 168 +++++++++++++++++++++++++++++++-------
net/netfilter/ipvs/ip_vs_est.c | 21 +----
net/netfilter/ipvs/ip_vs_proto.c | 11 +--
net/netfilter/ipvs/ip_vs_sync.c | 70 ++++++++--------
8 files changed, 281 insertions(+), 167 deletions(-)
^ permalink raw reply
* [PATCH 1/6] IPVS: Change of socket usage to enable name space exit.
From: Hans Schillstrom @ 2011-04-20 18:33 UTC (permalink / raw)
To: horms, ja, ebiederm, lvs-devel, netdev, netfilter-devel
Cc: hans.schillstrom, Hans Schillstrom
In-Reply-To: <1303324434-14024-1-git-send-email-hans@schillstrom.com>
To work this patch also needs the other patches in this series.
VERSION: 2
DESCRIPTION
If the sync daemons run in a name space while it crashes
or get killed, there is no way to stop them except for a reboot.
When all patches are there, ip_vs_core will handle register_pernet_(),
i.e. ip_vs_sync_init() and ip_vs_sync_cleanup() will be removed.
Kernel threads should not increment the use count of a socket.
By calling sk_change_net() after creating a socket this is avoided.
sock_release cant be used intead sk_release_kernel() should be used.
Thanks Eric W Biederman for your advices.
This patch is based on net-next-2.6 ver 2.6.39-rc2
CHANGES
Rev 2
sock_create_kern() used instead of __sock_create()
return codes of kthread_stop() used.
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
---
net/netfilter/ipvs/ip_vs_core.c | 2 +-
net/netfilter/ipvs/ip_vs_sync.c | 58 +++++++++++++++++++++++++--------------
2 files changed, 38 insertions(+), 22 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 07accf6..a0791dc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1896,7 +1896,7 @@ static int __net_init __ip_vs_init(struct net *net)
static void __net_exit __ip_vs_cleanup(struct net *net)
{
- IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen);
+ IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
}
static struct pernet_operations ipvs_core_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3e7961e..c187823 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net)
struct socket *sock;
int result;
- /* First create a socket */
- result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+ /* First create a socket move it to right name space later */
+ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
return ERR_PTR(result);
}
-
+ /*
+ * Kernel sockets that are a part of a namespace, should not
+ * hold a reference to a namespace in order to allow to stop it.
+ * After sk_change_net should be released using sk_release_kernel.
+ */
+ sk_change_net(sock->sk, net);
result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
@@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net)
return sock;
- error:
- sock_release(sock);
+error:
+ sk_release_kernel(sock->sk);
return ERR_PTR(result);
}
@@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net)
int result;
/* First create a socket */
- result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1);
+ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
return ERR_PTR(result);
}
-
+ /*
+ * Kernel sockets that are a part of a namespace, should not
+ * hold a reference to a namespace in order to allow to stop it.
+ * After sk_change_net should be released using sk_release_kernel.
+ */
+ sk_change_net(sock->sk, net);
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = 1;
@@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net)
return sock;
- error:
- sock_release(sock);
+error:
+ sk_release_kernel(sock->sk);
return ERR_PTR(result);
}
@@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data)
ip_vs_sync_buff_release(sb);
/* release the sending multicast socket */
- sock_release(tinfo->sock);
+ sk_release_kernel(tinfo->sock->sk);
kfree(tinfo);
return 0;
@@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data)
}
/* release the sending multicast socket */
- sock_release(tinfo->sock);
+ sk_release_kernel(tinfo->sock->sk);
kfree(tinfo->buf);
kfree(tinfo);
@@ -1601,7 +1611,7 @@ outtinfo:
outbuf:
kfree(buf);
outsocket:
- sock_release(sock);
+ sk_release_kernel(sock->sk);
out:
return result;
}
@@ -1610,6 +1620,7 @@ out:
int stop_sync_thread(struct net *net, int state)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ int retc = -EINVAL;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
@@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state)
spin_lock_bh(&ipvs->sync_lock);
ipvs->sync_state &= ~IP_VS_STATE_MASTER;
spin_unlock_bh(&ipvs->sync_lock);
- kthread_stop(ipvs->master_thread);
+ retc = kthread_stop(ipvs->master_thread);
ipvs->master_thread = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
if (!ipvs->backup_thread)
@@ -1639,16 +1650,14 @@ int stop_sync_thread(struct net *net, int state)
task_pid_nr(ipvs->backup_thread));
ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
- kthread_stop(ipvs->backup_thread);
+ retc = kthread_stop(ipvs->backup_thread);
ipvs->backup_thread = NULL;
- } else {
- return -EINVAL;
}
/* decrease the module use count */
ip_vs_use_count_dec();
- return 0;
+ return retc;
}
/*
@@ -1670,8 +1679,15 @@ static int __net_init __ip_vs_sync_init(struct net *net)
static void __ip_vs_sync_cleanup(struct net *net)
{
- stop_sync_thread(net, IP_VS_STATE_MASTER);
- stop_sync_thread(net, IP_VS_STATE_BACKUP);
+ int retc;
+
+ retc = stop_sync_thread(net, IP_VS_STATE_MASTER);
+ if (retc && retc != -EINVAL)
+ pr_err("Failed to stop Master Daemon\n");
+
+ retc = stop_sync_thread(net, IP_VS_STATE_BACKUP);
+ if (retc && retc != -EINVAL)
+ pr_err("Failed to stop Backup Daemon\n");
}
static struct pernet_operations ipvs_sync_ops = {
@@ -1682,10 +1698,10 @@ static struct pernet_operations ipvs_sync_ops = {
int __init ip_vs_sync_init(void)
{
- return register_pernet_subsys(&ipvs_sync_ops);
+ return register_pernet_device(&ipvs_sync_ops);
}
void ip_vs_sync_cleanup(void)
{
- unregister_pernet_subsys(&ipvs_sync_ops);
+ unregister_pernet_device(&ipvs_sync_ops);
}
--
1.7.2.3
^ permalink raw reply related
* Re: Suspend/resume - slow resume
From: Ciprian Docan @ 2011-04-20 18:51 UTC (permalink / raw)
To: Francois Romieu
Cc: Linus Torvalds, netdev, Linux Kernel Mailing List, Len Brown,
Pavel Machek, Rafael, J. Wysocki, Greg KH, nic_swsd
In-Reply-To: <20110420181602.GA18740@electric-eye.fr.zoreil.com>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 518 bytes --]
Hello Francois,
I tried your patch and my machine resumes properly.
> The firmware is cached during the first successfull call to open() and
> released once the network device is unregistered. The driver uses the
> cached firmware between open() and unregister_netdev().
Here is what I did to test it: I compiled the patched module, unloaded the
previous module, loaded the new one, and then suspend & resume. Output of
dmesg attached. Please let me know if you need any other information.
Regards,
--
Ciprian
[-- Attachment #2: Type: TEXT/PLAIN, Size: 12206 bytes --]
[74001.664088] r8169 0000:02:00.0: PCI INT A disabled
[74033.821473] r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
[74033.821497] r8169 0000:02:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[74033.822310] r8169 0000:02:00.0: setting latency timer to 64
[74033.822364] r8169 0000:02:00.0: irq 45 for MSI/MSI-X
[74033.822572] r8169 0000:02:00.0: eth0: RTL8168d/8111d at 0xffffc90027e2e000, 64:31:50:69:2c:61, XID 083000c0 IRQ 45
[74058.429717] wl_ops_bss_info_changed: qos enabled: false (implement)
[74058.429729] brcmsmac: wl_ops_bss_info_changed: disassociated
[74058.429735] wl_ops_bss_info_changed: use_cts_prot: false (implement)
[74058.429741] wl_ops_bss_info_changed: short preamble: false (implement)
[74058.429754] wl_ops_bss_info_changed: arp filtering: enabled false, count 1 (implement)
[74058.429764] wlan0: deauthenticating from 00:1e:2a:01:3e:bb by local choice (reason=3)
[74058.455026] wl_ops_bss_info_changed: BSS idle: true (implement)
[74058.455046] cfg80211: All devices are disconnected, going to restore regulatory settings
[74058.455055] cfg80211: Restoring regulatory settings
[74058.455064] cfg80211: Calling CRDA to update world regulatory domain
[74058.455069] wl_ops_bss_info_changed: BSS idle: false (implement)
[74058.460281] cfg80211: Updating information on frequency 2412 MHz for a 20 MHz width channel with regulatory rule:
[74058.460291] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460297] cfg80211: Updating information on frequency 2417 MHz for a 20 MHz width channel with regulatory rule:
[74058.460305] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460311] cfg80211: Updating information on frequency 2422 MHz for a 20 MHz width channel with regulatory rule:
[74058.460319] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460325] cfg80211: Updating information on frequency 2427 MHz for a 20 MHz width channel with regulatory rule:
[74058.460330] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460334] cfg80211: Updating information on frequency 2432 MHz for a 20 MHz width channel with regulatory rule:
[74058.460339] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460344] cfg80211: Updating information on frequency 2437 MHz for a 20 MHz width channel with regulatory rule:
[74058.460349] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460353] cfg80211: Updating information on frequency 2442 MHz for a 20 MHz width channel with regulatory rule:
[74058.460358] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460363] cfg80211: Updating information on frequency 2447 MHz for a 20 MHz width channel with regulatory rule:
[74058.460368] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460372] cfg80211: Updating information on frequency 2452 MHz for a 20 MHz width channel with regulatory rule:
[74058.460377] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460382] cfg80211: Updating information on frequency 2457 MHz for a 20 MHz width channel with regulatory rule:
[74058.460387] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460391] cfg80211: Updating information on frequency 2462 MHz for a 20 MHz width channel with regulatory rule:
[74058.460396] cfg80211: 2402000 KHz - 2472000 KHz @ KHz), (300 mBi, 2700 mBm)
[74058.460400] cfg80211: Disabling freq 2467 MHz
[74058.460403] cfg80211: Disabling freq 2472 MHz
[74058.460405] cfg80211: Disabling freq 2484 MHz
[74058.460410] cfg80211: World regulatory domain updated:
[74058.460413] cfg80211: (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp)
[74058.460418] cfg80211: (2402000 KHz - 2472000 KHz @ 40000 KHz), (300 mBi, 2000 mBm)
[74058.460423] cfg80211: (2457000 KHz - 2482000 KHz @ 20000 KHz), (300 mBi, 2000 mBm)
[74058.460427] cfg80211: (2474000 KHz - 2494000 KHz @ 20000 KHz), (300 mBi, 2000 mBm)
[74058.460432] cfg80211: (5170000 KHz - 5250000 KHz @ 40000 KHz), (300 mBi, 2000 mBm)
[74058.460437] cfg80211: (5735000 KHz - 5835000 KHz @ 40000 KHz), (300 mBi, 2000 mBm)
[74058.464926] wl_ops_bss_info_changed: BSS idle: true (implement)
[74059.892010] PM: Syncing filesystems ... done.
[74059.909543] PM: Preparing system for mem sleep
[74060.072757] Freezing user space processes ... (elapsed 0.01 seconds) done.
[74060.084607] Freezing remaining freezable tasks ... (elapsed 0.01 seconds) done.
[74060.095548] PM: Entering mem sleep
[74060.095712] Suspending console(s) (use no_console_suspend to debug)
[74060.107943] sd 0:0:0:0: [sda] Synchronizing SCSI cache
[74060.108024] sd 0:0:0:0: [sda] Stopping disk
[74060.147028] HDA Intel 0000:01:00.1: PCI INT B disabled
[74060.147031] brcmsmac 0000:03:00.0: PCI INT A disabled
[74060.147064] ACPI handle has no context!
[74060.157421] ehci_hcd 0000:00:1d.0: PCI INT A disabled
[74060.157444] ehci_hcd 0000:00:1a.0: PCI INT A disabled
[74060.248878] HDA Intel 0000:00:1b.0: PCI INT A disabled
[74062.612741] PM: suspend of devices complete after 2512.037 msecs
[74062.612949] r8169 0000:02:00.0: PME# enabled
[74062.621666] r8169 0000:02:00.0: wake-up capability enabled by ACPI
[74062.654658] PM: late suspend of devices complete after 42.007 msecs
[74062.654817] ACPI: Preparing to enter system sleep state S3
[74062.700627] PM: Saving platform NVS memory
[74062.704367] Disabling non-boot CPUs ...
[74062.706846] CPU 1 is now offline
[74062.724771] CPU 2 is now offline
[74062.734603] CPU 3 is now offline
[74062.734969] Extended CMOS year: 2000
[74062.735165] ACPI: Low-level resume complete
[74062.735220] PM: Restoring platform NVS memory
[74062.735780] Extended CMOS year: 2000
[74062.735802] Enabling non-boot CPUs ...
[74062.735923] Booting Node 0 Processor 1 APIC 0x1
[74062.735924] smpboot cpu 1: start_ip = 98000
[74062.826473] CPU1 is up
[74062.826637] Booting Node 0 Processor 2 APIC 0x4
[74062.826641] smpboot cpu 2: start_ip = 98000
[74062.826826] Switched to NOHz mode on CPU #1
[74062.917217] CPU2 is up
[74062.917382] Booting Node 0 Processor 3 APIC 0x5
[74062.917386] smpboot cpu 3: start_ip = 98000
[74062.917580] Switched to NOHz mode on CPU #2
[74063.008091] CPU3 is up
[74063.009302] Switched to NOHz mode on CPU #3
[74063.009672] ACPI: Waking up from system sleep state S3
[74063.090894] pcieport 0000:00:01.0: restoring config space at offset 0x1 (was 0x100007, writing 0x100407)
[74063.090915] i915 0000:00:02.0: restoring config space at offset 0x1 (was 0x900007, writing 0x900407)
[74063.090974] ehci_hcd 0000:00:1a.0: restoring config space at offset 0x1 (was 0x2900006, writing 0x2900002)
[74063.091009] HDA Intel 0000:00:1b.0: restoring config space at offset 0x1 (was 0x100006, writing 0x100002)
[74063.091117] ehci_hcd 0000:00:1d.0: restoring config space at offset 0x1 (was 0x2900006, writing 0x2900002)
[74063.091140] pci 0000:00:1e.0: restoring config space at offset 0xa (was 0xffffffff, writing 0x0)
[74063.091213] ahci 0000:00:1f.2: restoring config space at offset 0x1 (was 0x2b00007, writing 0x2b00407)
[74063.091336] HDA Intel 0000:01:00.1: restoring config space at offset 0x1 (was 0x100007, writing 0x100003)
[74063.091389] r8169 0000:02:00.0: restoring config space at offset 0x1 (was 0x100007, writing 0x100407)
[74063.091477] brcmsmac 0000:03:00.0: restoring config space at offset 0xf (was 0x100, writing 0x10a)
[74063.091496] brcmsmac 0000:03:00.0: restoring config space at offset 0x4 (was 0x4, writing 0xc2400004)
[74063.091502] brcmsmac 0000:03:00.0: restoring config space at offset 0x3 (was 0x0, writing 0x10)
[74063.091508] brcmsmac 0000:03:00.0: restoring config space at offset 0x1 (was 0x100000, writing 0x100006)
[74063.091655] PM: early resume of devices complete after 0.826 msecs
[74063.091803] i915 0000:00:02.0: setting latency timer to 64
[74063.091883] HDA Intel 0000:01:00.1: PCI INT B -> GSI 17 (level, low) -> IRQ 17
[74063.091888] ehci_hcd 0000:00:1a.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[74063.091890] HDA Intel 0000:01:00.1: setting latency timer to 64
[74063.091895] ehci_hcd 0000:00:1a.0: setting latency timer to 64
[74063.091938] HDA Intel 0000:01:00.1: irq 46 for MSI/MSI-X
[74063.091945] HDA Intel 0000:00:1b.0: PCI INT A -> GSI 22 (level, low) -> IRQ 22
[74063.091953] HDA Intel 0000:00:1b.0: setting latency timer to 64
[74063.091987] HDA Intel 0000:00:1b.0: irq 47 for MSI/MSI-X
[74063.091990] ehci_hcd 0000:00:1d.0: PCI INT A -> GSI 20 (level, low) -> IRQ 20
[74063.091996] ehci_hcd 0000:00:1d.0: setting latency timer to 64
[74063.092023] pci 0000:00:1e.0: setting latency timer to 64
[74063.092088] ahci 0000:00:1f.2: setting latency timer to 64
[74063.092096] brcmsmac 0000:03:00.0: PCI INT A -> GSI 17 (level, low) -> IRQ 17
[74063.092107] brcmsmac 0000:03:00.0: setting latency timer to 64
[74063.102150] sd 0:0:0:0: [sda] Starting disk
[74063.105668] r8169 0000:02:00.0: wake-up capability disabled by ACPI
[74063.105674] r8169 0000:02:00.0: PME# disabled
[74063.322691] usb 1-1.4: reset full speed USB device number 3 using ehci_hcd
[74063.406321] ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
[74063.410296] ata5: SATA link down (SStatus 0 SControl 300)
[74063.440225] ata2.00: configured for UDMA/100
[74063.480281] usb 2-1.3: reset full speed USB device number 3 using ehci_hcd
[74063.566915] btusb 2-1.3:1.0: no reset_resume for driver btusb?
[74063.566921] btusb 2-1.3:1.1: no reset_resume for driver btusb?
[74063.637853] usb 2-1.6: reset high speed USB device number 5 using ehci_hcd
[74064.566218] hci_cmd_timer: hci0 command tx timeout
[74065.849747] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[74065.861688] ata1.00: configured for UDMA/133
[74066.466771] PM: resume of devices complete after 3384.208 msecs
[74066.467065] PM: Finishing wakeup.
[74066.467067] Restarting tasks ... done.
[74066.475211] video LNXVIDEO:00: Restoring backlight state
[74066.475339] video LNXVIDEO:01: Restoring backlight state
[74066.740330] wl_ops_bss_info_changed: use_cts_prot: false (implement)
[74066.740334] wl_ops_bss_info_changed: short preamble: false (implement)
[74066.740349] wl_ops_config: change monitor mode: false (implement)
[74066.740350] wl_ops_config: change power-save mode: false (implement)
[74066.742592] wl_ops_bss_info_changed: qos enabled: false (implement)
[74066.743416] wl_ops_bss_info_changed: BSS idle: false (implement)
[74066.743435] ADDRCONF(NETDEV_UP): wlan0: link is not ready
[74066.833025] wl_ops_bss_info_changed: BSS idle: true (implement)
[74066.833049] wl_ops_bss_info_changed: BSS idle: false (implement)
[74066.922738] wl_ops_bss_info_changed: BSS idle: true (implement)
[74067.470305] hci_cmd_timer: hci0 command tx timeout
[74071.913773] wl_ops_bss_info_changed: BSS idle: false (implement)
[74072.813906] wl_ops_bss_info_changed: BSS idle: true (implement)
[74072.813930] wl_ops_bss_info_changed: BSS idle: false (implement)
[74072.813990] wlan0: deauthenticating from 00:1e:2a:00:2d:fe by local choice (reason=3)
[74072.903591] wlan0: authenticate with 00:1e:2a:00:2d:fe (try 1)
[74072.913250] wlan0: authenticated
[74072.913271] wl_ops_bss_info_changed: BSS idle: true (implement)
[74072.913304] wl_ops_bss_info_changed: BSS idle: false (implement)
[74072.913312] wlan0: associate with 00:1e:2a:00:2d:fe (try 1)
[74072.916142] wlan0: RX AssocResp from 00:1e:2a:00:2d:fe (capab=0x411 status=0 aid=1)
[74072.916147] wlan0: associated
[74072.917091] wl_ops_bss_info_changed: qos enabled: true (implement)
[74072.917096] brcmsmac: wl_ops_bss_info_changed: associated
[74072.917100] wl_ops_bss_info_changed: use_cts_prot: true (implement)
[74072.917103] wl_ops_bss_info_changed: short preamble: true (implement)
[74072.917111] wl_ops_bss_info_changed: Need to change Basic Rates: 0xf (implement)
[74072.917118] wl_ops_bss_info_changed: arp filtering: enabled true, count 0 (implement)
[74072.918403] ADDRCONF(NETDEV_CHANGE): wlan0: link becomes ready
[74073.806196] wl_ops_bss_info_changed: arp filtering: enabled true, count 1 (implement)
^ permalink raw reply
* Re: can: add missing socket check in can/raw release.
From: David Miller @ 2011-04-20 19:02 UTC (permalink / raw)
To: socketcan; +Cc: netdev, davej
In-Reply-To: <4DAEC7A0.1090103@hartkopp.net>
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 20 Apr 2011 13:46:40 +0200
> We can get here with a NULL socket argument passed from userspace,
> so we need to handle it accordingly.
>
> Thanks to Dave Jones pointing at this issue in net/can/bcm.c
>
> Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
I already applied Dave's patch from last night.
^ permalink raw reply
* Re: can: add missing socket check in can/raw release.
From: Dave Jones @ 2011-04-20 19:04 UTC (permalink / raw)
To: David Miller; +Cc: socketcan, netdev
In-Reply-To: <20110420.120218.15220634.davem@davemloft.net>
On Wed, Apr 20, 2011 at 12:02:18PM -0700, David Miller wrote:
> From: Oliver Hartkopp <socketcan@hartkopp.net>
> Date: Wed, 20 Apr 2011 13:46:40 +0200
>
> > We can get here with a NULL socket argument passed from userspace,
> > so we need to handle it accordingly.
> >
> > Thanks to Dave Jones pointing at this issue in net/can/bcm.c
> >
> > Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
>
> I already applied Dave's patch from last night.
This is in a different path.
Dave
^ permalink raw reply
* Re: Suspend/resume - slow resume
From: Ciprian Docan @ 2011-04-20 19:10 UTC (permalink / raw)
To: Francois Romieu
Cc: Linus Torvalds, netdev, Linux Kernel Mailing List, Len Brown,
Pavel Machek, Rafael, J. Wysocki, Greg KH, nic_swsd
In-Reply-To: <20110420181602.GA18740@electric-eye.fr.zoreil.com>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 201 bytes --]
Hello Francois,
I tried to unload the module, but it crashed. I re-booted the machine and
tried to unload the module again. I got the output from dmesg; please see
attached.
Regards,
--
Ciprian
[-- Attachment #2: Type: TEXT/PLAIN, Size: 7026 bytes --]
[ 7.007361] r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
[ 7.007383] r8169 0000:02:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[ 7.007454] r8169 0000:02:00.0: setting latency timer to 64
[ 7.007506] r8169 0000:02:00.0: irq 45 for MSI/MSI-X
[ 7.007628] r8169 0000:02:00.0: eth0: RTL8168d/8111d at 0xffffc90011810000, 64:31:50:69:2c:61, XID 083000c0 IRQ 45
...
[ 109.216074] r8169 0000:02:00.0: PCI INT A disabled
[ 116.748813] EXT4-fs (dm-1): mounted filesystem with ordered data mode. Opts: (null)
[ 166.963998] r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
[ 166.964100] r8169 0000:02:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[ 166.964319] r8169 0000:02:00.0: setting latency timer to 64
[ 166.964379] r8169 0000:02:00.0: irq 45 for MSI/MSI-X
[ 166.964593] r8169 0000:02:00.0: eth0: RTL8168d/8111d at 0xffffc90022fc4000, 64:31:50:69:2c:61, XID 083000c0 IRQ 45
[ 174.917306] BUG: unable to handle kernel paging request at fffffffffffffffd
[ 174.919573] IP: [<ffffffff8127b267>] firmware_free_data+0xf/0x55
[ 174.921828] PGD 1605067 PUD 1606067 PMD 0
[ 174.924088] Oops: 0000 [#1] SMP
[ 174.926323] last sysfs file: /sys/devices/pci0000:00/0000:00:1c.1/0000:03:00.0/ieee80211/phy0/rfkill0/uevent
[ 174.928649] CPU 2
[ 174.928670] Modules linked in: r8169(-) aes_x86_64 aes_generic fuse hidp fbcon tileblit font bitblit softcursor rfcomm bnep acpi_cpufreq mperf ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables ipv6 snd_hda_codec_hdmi snd_hda_codec_idt snd_hda_intel snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm arc4 snd_timer snd soundcore ecb btusb processor thermal uvcvideo hp_wmi psmouse fan videodev i2c_i801 sparse_keymap snd_page_alloc pcspkr brcmsmac(C) hp_accel iTCO_wdt mac80211 iTCO_vendor_support bluetooth lis3lv02d mii input_polldev serio_raw wmi v4l2_compat_ioctl32 cfg80211 rfkill microcode i915 drm_kms_helper drm fb fbdev intel_agp i2c_algo_bit cfbcopyarea intel_gtt agpgart i2c_core video cfbimgblt cfbfillrect [last unloaded: r8169]
[ 174.944284]
[ 174.946871] Pid: 2003, comm: rmmod Tainted: G C 2.6.39-rc3+ #13 Hewlett-Packard HP Pavilion dm4 Notebook PC /1603
[ 174.949618] RIP: 0010:[<ffffffff8127b267>] [<ffffffff8127b267>] firmware_free_data+0xf/0x55
[ 174.952348] RSP: 0018:ffff88023ad45d48 EFLAGS: 00010246
[ 174.954988] RAX: ffffffff815be000 RBX: fffffffffffffff5 RCX: ffff88024b1c0398
[ 174.957707] RDX: 0000000000000000 RSI: 0000000000000037 RDI: fffffffffffffff5
[ 174.960417] RBP: ffff88023ad45d58 R08: 0000000000000100 R09: ffffffff8172f690
[ 174.963039] R10: 000000000000000f R11: ffff88024b1c0000 R12: ffff88024f790000
[ 174.965662] R13: ffff88024b1c0000 R14: ffff88024f790090 R15: 0000000000000001
[ 174.968194] FS: 00007faaa8774720(0000) GS:ffff88025bc80000(0000) knlGS:0000000000000000
[ 174.970806] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 174.973388] CR2: fffffffffffffffd CR3: 000000024b828000 CR4: 00000000000006e0
[ 174.973392] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 174.973396] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 174.973400] Process rmmod (pid: 2003, threadinfo ffff88023ad44000, task ffff88023adb8000)
[ 174.973403] Stack:
[ 174.973405] fffffffffffffff5 ffff88024f790000 ffff88023ad45d78 ffffffff8127b2f6
[ 174.973410] ffff88023ad45d78 ffff88024b1c0740 ffff88023ad45db8 ffffffffa046e21e
[ 174.973415] ffff88024f7900f0 ffff88024f790090 ffffffffa0470030 ffff88024f790000
[ 174.973420] Call Trace:
[ 174.973427] [<ffffffff8127b2f6>] release_firmware+0x49/0x4f
[ 174.973437] [<ffffffffa046e21e>] rtl8169_remove_one+0x8f/0x118 [r8169]
[ 174.973446] [<ffffffff8120435c>] pci_device_remove+0x3f/0x91
[ 174.973453] [<ffffffff8127209c>] __device_release_driver+0x83/0xd9
[ 174.973458] [<ffffffff8127278c>] driver_detach+0x86/0xae
[ 174.973464] [<ffffffff81271f4e>] bus_remove_driver+0xb9/0xdf
[ 174.973469] [<ffffffff81272af7>] driver_unregister+0x6c/0x74
[ 174.973474] [<ffffffff8120463a>] pci_unregister_driver+0x44/0x89
[ 174.973482] [<ffffffffa046e2bc>] rtl8169_cleanup_module+0x15/0x17 [r8169]
[ 174.973491] [<ffffffff8106e474>] sys_delete_module+0x1ca/0x23b
[ 174.973498] [<ffffffff81109445>] ? path_put+0x22/0x27
[ 174.973505] [<ffffffff813d43eb>] system_call_fastpath+0x16/0x1b
[ 174.973508] Code: c4 18 5b 41 5c 41 5d 41 5e 41 5f c9 c3 4c 89 e7 e8 4d 8d e7 ff b8 f2 ff ff ff eb e2 55 48 89 e5 41 54 53 0f 1f 44 00 00 48 89 fb
[ 174.973529] 8b 7f 08 e8 e5 79 e6 ff 48 83 7b 10 00 74 31 45 31 e4 eb 0e
[ 174.973539] RIP [<ffffffff8127b267>] firmware_free_data+0xf/0x55
[ 174.973545] RSP <ffff88023ad45d48>
[ 174.973547] CR2: fffffffffffffffd
[ 174.973551] ---[ end trace 4aa4e169865c5c0c ]---
[ 174.973557] BUG: sleeping function called from invalid context at kernel/rwsem.c:21
[ 174.973561] in_atomic(): 0, irqs_disabled(): 1, pid: 2003, name: rmmod
[ 174.973565] Pid: 2003, comm: rmmod Tainted: G D C 2.6.39-rc3+ #13
[ 174.973569] Call Trace:
[ 174.973576] [<ffffffff8102dd7b>] __might_sleep+0xeb/0xf0
[ 174.973583] [<ffffffff813cd632>] down_read+0x24/0x3b
[ 174.973589] [<ffffffff810768f9>] acct_collect+0x4d/0x181
[ 174.973595] [<ffffffff81041ccd>] do_exit+0x22d/0x70a
[ 174.973600] [<ffffffff813cde9a>] ? _raw_spin_lock_irqsave+0x12/0x2f
[ 174.973605] [<ffffffff8103fc36>] ? kmsg_dump+0x49/0xdb
[ 174.973610] [<ffffffff813ceeea>] oops_end+0xb7/0xbf
[ 174.973616] [<ffffffff81022b3b>] no_context+0x1f9/0x208
[ 174.973620] [<ffffffff813cc815>] ? schedule+0x664/0x67e
[ 174.973626] [<ffffffff81022cd2>] __bad_area_nosemaphore+0x188/0x1ab
[ 174.973631] [<ffffffff81022d08>] bad_area_nosemaphore+0x13/0x15
[ 174.973636] [<ffffffff813d0d9d>] do_page_fault+0x16f/0x342
[ 174.973643] [<ffffffff8101c67b>] ? flat_send_IPI_allbutself+0x73/0x7e
[ 174.973649] [<ffffffff81018300>] ? native_send_call_func_ipi+0x76/0x96
[ 174.973655] [<ffffffff8106b119>] ? smp_call_function_many+0x1de/0x1ed
[ 174.973661] [<ffffffff813ce49f>] page_fault+0x1f/0x30
[ 174.973667] [<ffffffff8127b267>] ? firmware_free_data+0xf/0x55
[ 174.973672] [<ffffffff8127b2f6>] release_firmware+0x49/0x4f
[ 174.973679] [<ffffffffa046e21e>] rtl8169_remove_one+0x8f/0x118 [r8169]
[ 174.973685] [<ffffffff8120435c>] pci_device_remove+0x3f/0x91
[ 174.973691] [<ffffffff8127209c>] __device_release_driver+0x83/0xd9
[ 174.973696] [<ffffffff8127278c>] driver_detach+0x86/0xae
[ 174.973701] [<ffffffff81271f4e>] bus_remove_driver+0xb9/0xdf
[ 174.973706] [<ffffffff81272af7>] driver_unregister+0x6c/0x74
[ 174.973711] [<ffffffff8120463a>] pci_unregister_driver+0x44/0x89
[ 174.973719] [<ffffffffa046e2bc>] rtl8169_cleanup_module+0x15/0x17 [r8169]
[ 174.973724] [<ffffffff8106e474>] sys_delete_module+0x1ca/0x23b
[ 174.973729] [<ffffffff81109445>] ? path_put+0x22/0x27
[ 174.973735] [<ffffffff813d43eb>] system_call_fastpath+0x16/0x1b
^ permalink raw reply
* Re: r8169 : always copying the rx buffer to new skb
From: Francois Romieu @ 2011-04-20 19:13 UTC (permalink / raw)
To: John Lumby; +Cc: netdev, Ben Hutchings, nic_swsd
In-Reply-To: <4DACAC7E.4070400@hotmail.com>
John Lumby <johnlumby@hotmail.com> :
[...]
> I've verified that on my 8168c by simulating an allocation failure
> on 15 out of every 16 rx-Interrupts (unhooking the current skb and
> then simply not allocating a new skb and not giving the
> corresponding descriptor to the asic) and everything works just
> fine, with just a slight drop in throughput (down to 987 Mbits/sec,
> still well ahead of the always-copy).
Did your testing account for some memory pressure ?
> So do we really need to be that concerned about occasional
> allocation failure?
See $search_engine +r8169 high order memory allocation failure.
> And if someone is that concerned, then, with my proposal, they
> can leave the rx_copybreak at its default of 16383, when every
> packet is copied anyway. (My patch takes a slightly different
> approach if the allocation of the new skb fails - current 2.6.39
> drops the packet, I would propose to unhook and retain the
> descriptor because I can replenish later - but that is also
> debatable). Also that's why I favour making the rx ring size
> configurable.
Why don't you send the patch through the mailing list ?
(hint, hint)
> On 04/18/11 14:21, Francois Romieu wrote:
> >Short answer: it's mostly related to CVE-2009-4537 (see git log).
>
> I understand the need to make the rx_buf_size 16383 to defeat the
> DOS attacker, no suggestion to alter that. I'm just not sure I
> see why that has to imply the always_copy.
Because of high-order memory allocation failure under memory pressure and
memory wastage. Btw several 816x have limited jumbo frames abilities.
--
Ueimor
^ permalink raw reply
* Re: Add missing socket check in can/bcm release.
From: David Miller @ 2011-04-20 19:21 UTC (permalink / raw)
To: davej; +Cc: netdev
In-Reply-To: <20110420160350.GA24930@redhat.com>
From: Dave Jones <davej@redhat.com>
Date: Wed, 20 Apr 2011 12:03:50 -0400
> On Tue, Apr 19, 2011 at 08:37:20PM -0700, David Miller wrote:
> > From: Dave Jones <davej@redhat.com>
> > Date: Tue, 19 Apr 2011 23:30:01 -0400
> >
> > > We can get here with a NULL socket argument passed from userspace,
> > > so we need to handle it accordingly.
> > >
> > > Signed-off-by: Dave Jones <davej@redhat.com>
> >
> > Applied and queued up for -stable, thanks Dave.
>
> Out of curiousity, while I was asleep it occured to me.. is it ever valid
> for a ->release to get passed a NULL socket->sk ?
Yes, it happens all the time.
If accept() fails mid-stream, we'll have an 'sk' that hasn't been
hooked up to ->socket yet, but we still have to release the 'sk'
in the error handling.
See also commit c100c8f4c3c6f2a407bdbaaad2c4f1062e6a473a, which
fixes a bug triggered via the same code path.
^ permalink raw reply
* Re: r8169 doesn't report link state correctly.
From: Francois Romieu @ 2011-04-20 19:14 UTC (permalink / raw)
To: Ben Greear; +Cc: netdev
In-Reply-To: <20110413174815.GB17579@electric-eye.fr.zoreil.com>
François Romieu <romieu@fr.zoreil.com> :
> On Mon, Apr 11, 2011 at 01:09:19PM -0700, Ben Greear wrote:
> > I notice that in kernel 2.6.38-wl, the realtek 8169 NIC doesn't
> > report link down when in fact there is no cable connected. Instead,
[...]
> Thanks for the report. I'll try it tomorrow or friday.
I have not been able to notice it with a current kernel.
I'd welcome the XID of the 8169 NIC (see dmesg) and a short explanation
(no cable from boot ? cable removed after ifconfig up ? brand / ability
of the switch / hub ?).
Thanks.
--
Ueimor
^ permalink raw reply
* Re: [PATCH v2] can: add missing socket check in can/raw release
From: David Miller @ 2011-04-20 19:22 UTC (permalink / raw)
To: davej; +Cc: socketcan, netdev
In-Reply-To: <20110420170333.GD24930@redhat.com>
From: Dave Jones <davej@redhat.com>
Date: Wed, 20 Apr 2011 13:03:34 -0400
> On Wed, Apr 20, 2011 at 01:57:15PM +0200, Oliver Hartkopp wrote:
> > v2: added space after 'if' according code style.
> >
> > We can get here with a NULL socket argument passed from userspace,
> > so we need to handle it accordingly.
> >
> > Thanks to Dave Jones pointing at this issue in net/can/bcm.c
> >
> > Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
>
> ACK. That was the first thing I hit this morning ;-)
Aha, so this patch fixes the same bug in a different part of CAN,
I missed that :-)
Ok I'll apply this, thanks!
^ permalink raw reply
* Re: [PATCH v2] net: r8169: convert to hw_features
From: Francois Romieu @ 2011-04-20 19:13 UTC (permalink / raw)
To: David Miller; +Cc: dave, netdev, nic_swsd
In-Reply-To: <20110418.225400.189709717.davem@davemloft.net>
David Miller <davem@davemloft.net> :
[...]
> Francois, since TSO is disabled by default I'm applying this to
> net-next-2.6, thanks!
Fine.
> Maybe we can progressively start to try and turn these things on
> by default now that we know more about the TX descriptor layout
> differences.
Sure. I'd welcome a little timeslot to push a few configuration and
cosmetic things though.
--
Ueimor
^ permalink raw reply
* [PATCH net-next-2.6 v4 1/5] sctp: Add Auto-ASCONF support
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
SCTP reconfigure the IP addresses in the association by using ASCONF chunks as mentioned in RFC5061.
For example, we can start to use the newly configured IP address in the existing association.
ASCONF operation is invoked in two ways:
First is done by the application to call sctp_bindx() system call.
Second is automatic operation in the SCTP stack with address events in the host computer (called auto_asconf) .
The former is already implemented, and this patch implement the latter.
Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 505845d..8678cbd 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -121,6 +121,7 @@ extern int sctp_copy_local_addr_list(struct sctp_bind_addr *,
int flags);
extern struct sctp_pf *sctp_get_pf_specific(sa_family_t family);
extern int sctp_register_pf(struct sctp_pf *, sa_family_t);
+void sctp_addr_wq_mgmt(struct sctp_sockaddr_entry *, int);
/*
* sctp/socket.c
@@ -135,6 +136,7 @@ void sctp_sock_rfree(struct sk_buff *skb);
void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
extern struct percpu_counter sctp_sockets_allocated;
+int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
/*
* sctp/primitive.c
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index cc9185c..80974c3 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -205,6 +205,11 @@ extern struct sctp_globals {
* It is a list of sctp_sockaddr_entry.
*/
struct list_head local_addr_list;
+ int auto_asconf_enable;
+ struct list_head addr_waitq;
+ struct timer_list addr_wq_timer;
+ struct list_head auto_asconf_splist;
+ spinlock_t addr_wq_lock;
/* Lock that protects the local_addr_list writers */
spinlock_t addr_list_lock;
@@ -264,6 +269,11 @@ extern struct sctp_globals {
#define sctp_port_hashtable (sctp_globals.port_hashtable)
#define sctp_local_addr_list (sctp_globals.local_addr_list)
#define sctp_local_addr_lock (sctp_globals.addr_list_lock)
+#define sctp_auto_asconf_splist (sctp_globals.auto_asconf_splist)
+#define sctp_addr_waitq (sctp_globals.addr_waitq)
+#define sctp_addr_wq_timer (sctp_globals.addr_wq_timer)
+#define sctp_addr_wq_lock (sctp_globals.addr_wq_lock)
+#define sctp_auto_asconf_enable (sctp_globals.auto_asconf_enable)
#define sctp_scope_policy (sctp_globals.ipv4_scope_policy)
#define sctp_addip_enable (sctp_globals.addip_enable)
#define sctp_addip_noauth (sctp_globals.addip_noauth_enable)
@@ -341,6 +351,8 @@ struct sctp_sock {
atomic_t pd_mode;
/* Receive to here while partial delivery is in effect. */
struct sk_buff_head pd_lobby;
+ struct list_head auto_asconf_list;
+ int do_auto_asconf;
};
static inline struct sctp_sock *sctp_sk(const struct sock *sk)
@@ -796,6 +808,10 @@ struct sctp_sockaddr_entry {
__u8 valid;
};
+#define SCTP_NEWADDR 1
+#define SCTP_DELADDR 2
+#define SCTP_ADDRESS_TICK_DELAY 500
+
typedef struct sctp_chunk *(sctp_packet_phandler_t)(struct sctp_association *);
/* This structure holds lists of chunks as we are assembling for
@@ -1239,6 +1255,7 @@ sctp_scope_t sctp_scope(const union sctp_addr *);
int sctp_in_scope(const union sctp_addr *addr, const sctp_scope_t scope);
int sctp_is_any(struct sock *sk, const union sctp_addr *addr);
int sctp_addr_is_valid(const union sctp_addr *addr);
+int sctp_is_ep_boundall(struct sock *sk);
/* What type of endpoint? */
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index faf71d1..869267b 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -536,6 +536,21 @@ int sctp_in_scope(const union sctp_addr *addr, sctp_scope_t scope)
return 0;
}
+int sctp_is_ep_boundall(struct sock *sk)
+{
+ struct sctp_bind_addr *bp;
+ struct sctp_sockaddr_entry *addr;
+
+ bp = &sctp_sk(sk)->ep->base.bind_addr;
+ if (sctp_list_single_entry(&bp->address_list)) {
+ addr = list_entry(bp->address_list.next,
+ struct sctp_sockaddr_entry, list);
+ if (sctp_is_any(sk, &addr->a))
+ return 1;
+ }
+ return 0;
+}
+
/********************************************************************
* 3rd Level Abstractions
********************************************************************/
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 865ce7b..0ba27b9 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -105,6 +105,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
addr->valid = 1;
spin_lock_bh(&sctp_local_addr_lock);
list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+ sctp_addr_wq_mgmt(addr, SCTP_NEWADDR);
spin_unlock_bh(&sctp_local_addr_lock);
}
break;
@@ -115,6 +116,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
if (addr->a.sa.sa_family == AF_INET6 &&
ipv6_addr_equal(&addr->a.v6.sin6_addr,
&ifa->addr)) {
+ sctp_addr_wq_mgmt(addr, SCTP_DELADDR);
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 152976e..d8442a4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -636,6 +636,164 @@ static void sctp_v4_ecn_capable(struct sock *sk)
INET_ECN_xmit(sk);
}
+void sctp_addr_wq_timeout_handler(unsigned long arg)
+{
+ struct sctp_sockaddr_entry *addrw = NULL;
+ union sctp_addr *addr = NULL;
+ struct sctp_sock *sp = NULL;
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+retry_wq:
+ if (list_empty(&sctp_addr_waitq)) {
+ SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: nothing in addr waitq\n");
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+ addrw = list_first_entry(&sctp_addr_waitq, struct sctp_sockaddr_entry,
+ list);
+ addr = &addrw->a;
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addrwq_timo_handler: the first ent in wq %p is ",
+ " for cmd %d at entry %p\n", &sctp_addr_waitq, addr, addrw->state,
+ addrw);
+
+ /* Now we send an ASCONF for each association */
+ /* Note. we currently don't handle link local IPv6 addressees */
+ if (addr->sa.sa_family == AF_INET6) {
+ struct in6_addr *in6 = (struct in6_addr *)&addr->v6.sin6_addr;
+
+ if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
+ SCTP_DEBUG_PRINTK("sctp_timo_handler: link local, hence don't tell sockets\n");
+ list_del(&addrw->list);
+ kfree(addrw);
+ goto retry_wq;
+ }
+ if (ipv6_chk_addr(&init_net, in6, NULL, 0) == 0 &&
+ addrw->state == SCTP_NEWADDR) {
+ unsigned long timeo_val;
+
+ SCTP_DEBUG_PRINTK("sctp_timo_handler: this is on DAD, trying %d sec later\n",
+ SCTP_ADDRESS_TICK_DELAY);
+ timeo_val = jiffies;
+ timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
+ mod_timer(&sctp_addr_wq_timer, timeo_val);
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+ }
+ list_for_each_entry(sp, &sctp_auto_asconf_splist, auto_asconf_list) {
+ struct sock *sk;
+
+ if (sp == NULL) {
+ SCTP_DEBUG_PRINTK("addrwq_timo_handler: no socket\n");
+ continue;
+ }
+ sk = sctp_opt2sk(sp);
+ if (!sctp_is_ep_boundall(sk))
+ /* ignore bound-specific endpoints */
+ continue;
+ sctp_bh_lock_sock(sk);
+ if (sctp_asconf_mgmt(sp, addrw) < 0) {
+ SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n");
+ sctp_bh_unlock_sock(sk);
+ continue;
+ }
+ sctp_bh_unlock_sock(sk);
+ }
+
+ list_del(&addrw->list);
+ kfree(addrw);
+
+ if (!list_empty(&sctp_addr_waitq))
+ goto retry_wq;
+
+ spin_unlock_bh(&sctp_addr_wq_lock);
+}
+
+static void sctp_free_addr_wq()
+{
+ struct sctp_sockaddr_entry *addrw = NULL;
+ struct sctp_sockaddr_entry *temp = NULL;
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+ del_timer(&sctp_addr_wq_timer);
+ list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) {
+ list_del(&addrw->list);
+ kfree(addrw);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+}
+
+/* lookup the entry for the same address in the addr_waitq
+ * sctp_addr_wq MUST be locked
+ */
+static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct sctp_sockaddr_entry *addr)
+{
+ struct sctp_sockaddr_entry *addrw;
+
+ list_for_each_entry(addrw, &sctp_addr_waitq, list) {
+ if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
+ continue;
+ if (addrw->a.sa.sa_family == AF_INET) {
+ if (addrw->a.v4.sin_addr.s_addr ==
+ addr->a.v4.sin_addr.s_addr)
+ return addrw;
+ } else if (addrw->a.sa.sa_family == AF_INET6) {
+ if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
+ &addr->a.v6.sin6_addr))
+ return addrw;
+ }
+ }
+ return NULL;
+}
+
+void sctp_addr_wq_mgmt(struct sctp_sockaddr_entry *addr, int cmd)
+{
+ struct sctp_sockaddr_entry *addrw = NULL;
+ unsigned long timeo_val;
+ union sctp_addr *tmpaddr;
+
+ /* first, we check if an opposite message already exist in the queue.
+ * If we found such message, it is removed.
+ * This operation is a bit stupid, but the DHCP client attaches the
+ * new address after a couple of addition and deletion of that address
+ */
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+ /* Offsets existing events in addr_wq */
+ addrw = sctp_addr_wq_lookup(addr);
+ tmpaddr = &addrw->a;
+ if (addrw) {
+ if (addrw->state != cmd) {
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ",
+ " in wq %p\n", addrw->state, tmpaddr,
+ &sctp_addr_waitq);
+ list_del(&addrw->list);
+ kfree(addrw);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+
+ /* OK, we have to add the new address to the wait queue */
+ addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+ if (addrw == NULL) {
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+ addrw->state = cmd;
+ list_add_tail(&addrw->list, &sctp_addr_waitq);
+ tmpaddr = &addrw->a;
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ",
+ " in wq %p\n", addrw->state, tmpaddr, &sctp_addr_waitq);
+
+ if (!timer_pending(&sctp_addr_wq_timer)) {
+ timeo_val = jiffies;
+ timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
+ mod_timer(&sctp_addr_wq_timer, timeo_val);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+}
+
/* Event handler for inet address addition/deletion events.
* The sctp_local_addr_list needs to be protocted by a spin lock since
* multiple notifiers (say IPv4 and IPv6) may be running at the same
@@ -663,6 +821,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
addr->valid = 1;
spin_lock_bh(&sctp_local_addr_lock);
list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+ sctp_addr_wq_mgmt(addr, SCTP_NEWADDR);
spin_unlock_bh(&sctp_local_addr_lock);
}
break;
@@ -673,6 +832,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
if (addr->a.sa.sa_family == AF_INET &&
addr->a.v4.sin_addr.s_addr ==
ifa->ifa_local) {
+ sctp_addr_wq_mgmt(addr, SCTP_DELADDR);
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
@@ -1256,6 +1416,7 @@ SCTP_STATIC __init int sctp_init(void)
/* Disable ADDIP by default. */
sctp_addip_enable = 0;
sctp_addip_noauth = 0;
+ sctp_auto_asconf_enable = 0;
/* Enable PR-SCTP by default. */
sctp_prsctp_enable = 1;
@@ -1280,6 +1441,13 @@ SCTP_STATIC __init int sctp_init(void)
spin_lock_init(&sctp_local_addr_lock);
sctp_get_local_addr_list();
+ /* Initialize the address event list */
+ INIT_LIST_HEAD(&sctp_addr_waitq);
+ INIT_LIST_HEAD(&sctp_auto_asconf_splist);
+ spin_lock_init(&sctp_addr_wq_lock);
+ sctp_addr_wq_timer.expires = 0;
+ setup_timer(&sctp_addr_wq_timer, sctp_addr_wq_timeout_handler, 0);
+
status = sctp_v4_protosw_init();
if (status)
@@ -1344,6 +1512,7 @@ err_chunk_cachep:
/* Exit handler for the SCTP protocol. */
SCTP_STATIC __exit void sctp_exit(void)
{
+ sctp_free_addr_wq();
/* BUG. This should probably do something useful like clean
* up all the remaining associations and all that memory.
*/
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3951a10..29f2b1f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -807,6 +807,37 @@ out:
return retval;
}
+/* set addr events to assocs in the endpoint. ep and addr_wq must be locked */
+int
+sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw)
+{
+ struct sock *sk = sctp_opt2sk(sp);
+ union sctp_addr *addr = NULL;
+ int cmd;
+ int error = 0;
+
+ addr = &addrw->a;
+ addr->v4.sin_port = htons(sp->ep->base.bind_addr.port);
+ cmd = addrw->state;
+
+ SCTP_DEBUG_PRINTK("sctp_asconf_mgmt sp:%p\n", sp);
+ if (cmd == SCTP_NEWADDR) {
+ error = sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1);
+ if (error) {
+ SCTP_DEBUG_PRINTK("asconf_mgmt: send_asconf_add_ip returns %d\n", error);
+ return error;
+ }
+ } else if (cmd == SCTP_DELADDR) {
+ error = sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1);
+ if (error) {
+ SCTP_DEBUG_PRINTK("asconf_mgmt: send_asconf_del_ip returns %d\n", error);
+ return error;
+ }
+ }
+
+ return 0;
+}
+
/* Helper for tunneling sctp_bindx() requests through sctp_setsockopt()
*
* API 8.1
@@ -3770,6 +3801,13 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
local_bh_disable();
percpu_counter_inc(&sctp_sockets_allocated);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ if (sctp_auto_asconf_enable) {
+ list_add_tail(&sp->auto_asconf_list,
+ &sctp_auto_asconf_splist);
+ sp->do_auto_asconf = 1;
+ } else
+ sp->do_auto_asconf = 0;
+ SCTP_DEBUG_PRINTK("sctp_init_sk sk:%p ep:%p\n", sk, ep);
local_bh_enable();
return 0;
@@ -3779,11 +3817,17 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
SCTP_STATIC void sctp_destroy_sock(struct sock *sk)
{
struct sctp_endpoint *ep;
+ struct sctp_sock *sp;
SCTP_DEBUG_PRINTK("sctp_destroy_sock(sk: %p)\n", sk);
/* Release our hold on the endpoint. */
- ep = sctp_sk(sk)->ep;
+ sp = sctp_sk(sk);
+ ep = sp->ep;
+ if (sp->do_auto_asconf) {
+ sp->do_auto_asconf = 0;
+ list_del(&sp->auto_asconf_list);
+ }
sctp_endpoint_free(ep);
local_bh_disable();
percpu_counter_dec(&sctp_sockets_allocated);
^ permalink raw reply related
* [PATCH net-next-2.6 v4 2/5] sctp: Add sysctl support for Auto-ASCONF
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
This patch allows the system administrator to change default Auto-ASCONF on/off behavior via an sysctl value.
Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 50cb57f..df39789 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -183,6 +183,13 @@ static ctl_table sctp_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "auto_asconf_enable",
+ .data = &sctp_auto_asconf_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "prsctp_enable",
.data = &sctp_prsctp_enable,
.maxlen = sizeof(int),
^ permalink raw reply related
* [PATCH net-next-2.6 v4 3/5] sctp: Add socket option operation for Auto-ASCONF
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
This patch allows the application to operate Auto-ASCONF on/off behavior via setsockopt() and getsockopt().
Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---
diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h
index e73ebda..36bf64b 100644
--- a/include/net/sctp/user.h
+++ b/include/net/sctp/user.h
@@ -91,6 +91,7 @@ typedef __s32 sctp_assoc_t;
#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */
#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */
#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */
+#define SCTP_AUTO_ASCONF 29
/* Internal Socket Options. Some of the sctp library functions are
* implemented using these socket options.
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3951a10..c9be08a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3341,6 +3341,46 @@ static int sctp_setsockopt_del_key(struct sock *sk,
}
+/*
+ * 8.1.23 SCTP_AUTO_ASCONF
+ *
+ * This option will enable or disable the use of the automatic generation of
+ * ASCONF chunks to add and delete addresses to an existing association. Note
+ * that this option has two caveats namely: a) it only affects sockets that
+ * are bound to all addresses available to the SCTP stack, and b) the system
+ * administrator may have an overriding control that turns the ASCONF feature
+ * off no matter what setting the socket option may have.
+ * This option expects an integer boolean flag, where a non-zero value turns on
+ * the option, and a zero value turns off the option.
+ * Note. In this implementation, socket operation overrides default parameter
+ * being set by sysctl as well as FreeBSD implementation
+ */
+static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
+ unsigned int optlen)
+{
+ int val;
+ struct sctp_sock *sp = sctp_sk(sk);
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+ if (!sctp_is_ep_boundall(sk) && val)
+ return -EINVAL;
+ if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
+ return 0;
+
+ if (val == 0 && sp->do_auto_asconf) {
+ list_del(&sp->auto_asconf_list);
+ sp->do_auto_asconf = 0;
+ } else if (val && !sp->do_auto_asconf) {
+ list_add_tail(&sp->auto_asconf_list,
+ &sctp_auto_asconf_splist);
+ sp->do_auto_asconf = 1;
+ }
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
@@ -3488,6 +3528,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_AUTH_DELETE_KEY:
retval = sctp_setsockopt_del_key(sk, optval, optlen);
break;
+ case SCTP_AUTO_ASCONF:
+ retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -5283,6 +5326,28 @@ static int sctp_getsockopt_assoc_number(struct sock *sk, int len,
return 0;
}
+/*
+ * 8.1.23 SCTP_AUTO_ASCONF
+ * See the corresponding setsockopt entry as description
+ */
+static int sctp_getsockopt_auto_asconf(struct sock *sk, int len,
+ char __user *optval, int __user *optlen)
+{
+ int val = 0;
+
+ if (len < sizeof(int))
+ return -EINVAL;
+
+ len = sizeof(int);
+ if (sctp_sk(sk)->do_auto_asconf && sctp_is_ep_boundall(sk))
+ val = 1;
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+ return 0;
+}
+
SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -5415,6 +5480,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
case SCTP_GET_ASSOC_NUMBER:
retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen);
break;
+ case SCTP_AUTO_ASCONF:
+ retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
^ permalink raw reply related
* [PATCH net-next-2.6 v4 4/5] sctp: Add ASCONF operation on the single-homed host
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
SCTP can change the IP address on the single-homed host.
In this case, the SCTP association transmits an ASCONF packet including addition of the new IP address and deletion of the old address. This patch implements this functionality.
In this case, the ASCONF chunk is added to the beginning of the queue, because the other chunks cannot be transmitted in this state.
Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index c70d8cc..d7a4ee3 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -441,4 +441,8 @@ enum {
*/
#define SCTP_AUTH_RANDOM_LENGTH 32
+/* ASCONF PARAMETERS */
+#define SCTP_ASCONF_V4_PARAM_LEN 16
+#define SCTP_ASCONF_V6_PARAM_LEN 28
+
#endif /* __sctp_constants_h__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 9352d12..498a3cf 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -259,6 +259,7 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
struct sctp_chunk *asconf);
int sctp_process_asconf_ack(struct sctp_association *asoc,
struct sctp_chunk *asconf_ack);
+void sctp_path_check_and_react(struct sctp_association *, struct sockaddr *);
struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc,
__u32 new_cum_tsn, size_t nstreams,
struct sctp_fwdtsn_skip *skiplist);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index cc9185c..400ee8a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1901,6 +1901,9 @@ struct sctp_association {
* after reaching 4294967295.
*/
__u32 addip_serial;
+ union sctp_addr *asconf_addr_del_pending;
+ __u32 asconf_del_pending_cid;
+ int src_out_of_asoc_ok;
/* SCTP AUTH: list of the endpoint shared keys. These
* keys are provided out of band by the user applicaton
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 6b04287..6b19387 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -279,6 +279,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
asoc->peer.asconf_capable = 0;
if (sctp_addip_noauth)
asoc->peer.asconf_capable = 1;
+ asoc->asconf_addr_del_pending = NULL;
+ asoc->asconf_del_pending_cid = 0;
+ asoc->src_out_of_asoc_ok = 0;
/* Create an input queue. */
sctp_inq_init(&asoc->base.inqueue);
@@ -443,6 +446,10 @@ void sctp_association_free(struct sctp_association *asoc)
asoc->peer.transport_count = 0;
+ /* Free pending address space being deleted */
+ if (asoc->asconf_addr_del_pending != NULL)
+ kfree(asoc->asconf_addr_del_pending);
+
/* Free any cached ASCONF_ACK chunk. */
sctp_assoc_free_asconf_acks(asoc);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 865ce7b..56c97ce 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -332,6 +332,13 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk,
matchlen = bmatchlen;
}
}
+ if (laddr->state == SCTP_ADDR_NEW && asoc->src_out_of_asoc_ok) {
+ bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+ if (!baddr || (matchlen < bmatchlen)) {
+ baddr = &laddr->a;
+ matchlen = bmatchlen;
+ }
+ }
}
if (baddr) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 26dc005..033ea20 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -344,7 +344,14 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
break;
}
} else {
- list_add_tail(&chunk->list, &q->control_chunk_list);
+ /* We add the ASCONF for the only one newly added address at
+ * the front of the queue
+ */
+ if (q->asoc->src_out_of_asoc_ok && \
+ chunk->chunk_hdr->type == SCTP_CID_ASCONF)
+ list_add(&chunk->list, &q->control_chunk_list);
+ else
+ list_add_tail(&chunk->list, &q->control_chunk_list);
SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS);
}
@@ -850,6 +857,24 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
case SCTP_CID_SHUTDOWN:
case SCTP_CID_ECN_ECNE:
case SCTP_CID_ASCONF:
+ /* RFC 5061, 5.3
+ * F1) This means that until such time as the ASCONF
+ * containing the add is acknowledged, the sender MUST
+ * NOT use the new IP address as a source for ANY SCTP
+ * packet except on carrying an ASCONF Chunk.
+ */
+ if (asoc->src_out_of_asoc_ok) {
+ SCTP_DEBUG_PRINTK("outq_flush: out_of_asoc_ok, transmit chunk type %d\n",
+ chunk->chunk_hdr->type);
+ packet = &transport->packet;
+ sctp_packet_config(packet, vtag,
+ asoc->peer.ecn_capable);
+ sctp_packet_append_chunk(packet, chunk);
+ error = sctp_packet_transmit(packet);
+ if (error < 0)
+ return error;
+ goto sctp_flush_out;
+ }
case SCTP_CID_FWD_TSN:
status = sctp_packet_transmit_chunk(packet, chunk,
one_packet);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 152976e..b8ec3cc 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -510,7 +510,8 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
- if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
+ if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC &&
+ asoc->src_out_of_asoc_ok == 0))
continue;
if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
goto out_unlock;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index de98665..581a9f5 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2651,6 +2651,61 @@ __u32 sctp_generate_tsn(const struct sctp_endpoint *ep)
return retval;
}
+void
+sctp_path_check_and_react(struct sctp_association *asoc, struct sockaddr *sa)
+{
+ struct sctp_transport *trans;
+ int addrnum, family;
+ struct sctp_sockaddr_entry *saddr;
+ struct sctp_bind_addr *bp;
+ union sctp_addr *tmpaddr;
+
+ family = sa->sa_family;
+ bp = &asoc->base.bind_addr;
+ addrnum = 0;
+ /* count up the number of local addresses in the same family */
+ list_for_each_entry(saddr, &bp->address_list, list) {
+ if (saddr->a.sa.sa_family == family) {
+ tmpaddr = &saddr->a;
+ if (family == AF_INET6 &&
+ ipv6_addr_type(&tmpaddr->v6.sin6_addr) &
+ IPV6_ADDR_LINKLOCAL) {
+ continue;
+ }
+ addrnum++;
+ }
+ }
+ if (addrnum == 1) {
+ union sctp_addr *tmpaddr;
+ tmpaddr = (union sctp_addr *)sa;
+ SCTP_DEBUG_PRINTK_IPADDR("pcheck_react: only 1 local addr in asoc %p ",
+ " family %d\n", asoc, tmpaddr, family);
+ list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+ transports) {
+ /* reset path information and release refcount to the
+ * dst_entry based on the src change */
+ sctp_transport_hold(trans);
+ trans->cwnd = min(4*asoc->pathmtu,
+ max_t(__u32, 2*asoc->pathmtu, 4380));
+ trans->ssthresh = asoc->peer.i.a_rwnd;
+ trans->rtt = 0;
+ trans->srtt = 0;
+ trans->rttvar = 0;
+ trans->rto = asoc->rto_initial;
+ dst_release(trans->dst);
+ trans->dst = NULL;
+ memset(&trans->saddr, 0, sizeof(union sctp_addr));
+ sctp_transport_route(trans, NULL,
+ sctp_sk(asoc->base.sk));
+ SCTP_DEBUG_PRINTK_IPADDR("we freed dst_entry (asoc: %p dst: ",
+ " trans: %p)\n", asoc, (&trans->ipaddr), trans);
+ trans->rto_pending = 1;
+ sctp_transport_put(trans);
+ }
+ }
+ return;
+}
+
/*
* ADDIP 3.1.1 Address Configuration Change Chunk (ASCONF)
* 0 1 2 3
@@ -2744,11 +2799,24 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
int addr_param_len = 0;
int totallen = 0;
int i;
+ sctp_addip_param_t del_param; /* 8 Bytes (Type 0xC002, Len and CrrID) */
+ struct sctp_af *del_af;
+ int del_addr_param_len = 0;
+ int del_paramlen = sizeof(sctp_addip_param_t);
+ union sctp_addr_param del_addr_param; /* (v4) 8 Bytes, (v6) 20 Bytes */
+ int v4 = 0;
+ int v6 = 0;
/* Get total length of all the address parameters. */
addr_buf = addrs;
for (i = 0; i < addrcnt; i++) {
addr = (union sctp_addr *)addr_buf;
+ if (addr != NULL) {
+ if (addr->sa.sa_family == AF_INET)
+ v4 = 1;
+ else if (addr->sa.sa_family == AF_INET6)
+ v6 = 1;
+ }
af = sctp_get_af_specific(addr->v4.sin_family);
addr_param_len = af->to_addr_param(addr, &addr_param);
@@ -2757,6 +2825,24 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
addr_buf += af->sockaddr_len;
}
+ /* Add the length of a pending address being deleted */
+ if (flags == SCTP_PARAM_ADD_IP && asoc->asconf_addr_del_pending) {
+ if ((asoc->asconf_addr_del_pending->sa.sa_family == AF_INET
+ && v4) ||
+ (asoc->asconf_addr_del_pending->sa.sa_family == AF_INET6
+ && v6)) {
+ del_af = sctp_get_af_specific(
+ asoc->asconf_addr_del_pending->sa.sa_family);
+ del_addr_param_len = del_af->to_addr_param(
+ asoc->asconf_addr_del_pending, &del_addr_param);
+ totallen += del_paramlen;
+ totallen += del_addr_param_len;
+ SCTP_DEBUG_PRINTK("mkasconf_update_ip: now we picked del_pending addr, totallen for all addresses is %d\n",
+ totallen);
+ }
+ }
+ SCTP_DEBUG_PRINTK("mkasconf_update_ip: call mkasconf() for %d bytes\n",
+ totallen);
/* Create an asconf chunk with the required length. */
retval = sctp_make_asconf(asoc, laddr, totallen);
@@ -2778,6 +2864,20 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
addr_buf += af->sockaddr_len;
}
+ if (flags == SCTP_PARAM_ADD_IP && asoc->asconf_addr_del_pending) {
+ addr = asoc->asconf_addr_del_pending;
+ del_af = sctp_get_af_specific(addr->v4.sin_family);
+ del_addr_param_len = del_af->to_addr_param(addr,
+ &del_addr_param);
+ del_param.param_hdr.type = SCTP_PARAM_DEL_IP;
+ del_param.param_hdr.length = htons(del_paramlen +
+ del_addr_param_len);
+ del_param.crr_id = i;
+ asoc->asconf_del_pending_cid = i;
+
+ sctp_addto_chunk(retval, del_paramlen, &del_param);
+ sctp_addto_chunk(retval, del_addr_param_len, &del_addr_param);
+ }
return retval;
}
@@ -3193,16 +3293,37 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
local_bh_enable();
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
- if (transport->state == SCTP_ACTIVE)
+ if (transport->state == SCTP_ACTIVE &&
+ !asoc->src_out_of_asoc_ok)
continue;
dst_release(transport->dst);
sctp_transport_route(transport, NULL,
sctp_sk(asoc->base.sk));
}
+ asoc->src_out_of_asoc_ok = 0;
break;
case SCTP_PARAM_DEL_IP:
local_bh_disable();
sctp_del_bind_addr(bp, &addr);
+ if (asoc->asconf_addr_del_pending != NULL) {
+ if ((addr.sa.sa_family == AF_INET) &&
+ (asoc->asconf_addr_del_pending->sa.sa_family ==
+ AF_INET)) {
+ if (asoc->asconf_addr_del_pending->v4.sin_addr.s_addr == addr.v4.sin_addr.s_addr) {
+ kfree(asoc->asconf_addr_del_pending);
+ asoc->asconf_del_pending_cid = 0;
+ asoc->asconf_addr_del_pending = NULL;
+ }
+ } else if ((addr.sa.sa_family == AF_INET6) &&
+ (asoc->asconf_addr_del_pending->sa.sa_family ==
+ AF_INET6)) {
+ if (ipv6_addr_equal(&asoc->asconf_addr_del_pending->v6.sin6_addr, &addr.v6.sin6_addr)) {
+ kfree(asoc->asconf_addr_del_pending);
+ asoc->asconf_del_pending_cid = 0;
+ asoc->asconf_addr_del_pending = NULL;
+ }
+ }
+ }
local_bh_enable();
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
@@ -3293,6 +3414,8 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
int no_err = 1;
int retval = 0;
__be16 err_code = SCTP_ERROR_NO_ERROR;
+ sctp_addip_param_t *first_asconf_param = NULL;
+ int first_asconf_paramlen;
/* Skip the chunkhdr and addiphdr from the last asconf sent and store
* a pointer to address parameter.
@@ -3307,6 +3430,8 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
length = ntohs(addr_param->v4.param_hdr.length);
asconf_param = (sctp_addip_param_t *)((void *)addr_param + length);
asconf_len -= length;
+ first_asconf_param = asconf_param;
+ first_asconf_paramlen = ntohs(first_asconf_param->param_hdr.length);
/* ADDIP 4.1
* A8) If there is no response(s) to specific TLV parameter(s), and no
@@ -3361,6 +3486,35 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
asconf_len -= length;
}
+ /* When the source address obviously changes to newly added one, we
+ reset the cwnd to re-probe the path condition
+ */
+ if (no_err && first_asconf_param->param_hdr.type == SCTP_PARAM_ADD_IP) {
+ if (first_asconf_paramlen == SCTP_ASCONF_V4_PARAM_LEN) {
+ struct sockaddr_in sin;
+
+ memset(&sin, 0, sizeof(struct sockaddr_in));
+ sin.sin_family = AF_INET;
+ memcpy(&sin.sin_addr.s_addr, first_asconf_param + 1,
+ sizeof(struct in_addr));
+ sctp_path_check_and_react(asoc,
+ (struct sockaddr *)&sin);
+
+ } else if (first_asconf_paramlen == SCTP_ASCONF_V6_PARAM_LEN) {
+ struct sockaddr_in6 sin6;
+
+ memset(&sin6, 0, sizeof(struct sockaddr_in6));
+ sin6.sin6_family = AF_INET6;
+ memcpy(&sin6.sin6_addr, first_asconf_param + 1,
+ sizeof(struct in6_addr));
+ sctp_path_check_and_react(asoc,
+ (struct sockaddr *)&sin6);
+ } else {
+ SCTP_DEBUG_PRINTK("funny asconf_paramlen? (%d)\n",
+ first_asconf_paramlen);
+ }
+ }
+
/* Free the cached last sent asconf chunk. */
list_del_init(&asconf->transmitted_list);
sctp_chunk_free(asconf);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3951a10..2bfe2a9 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -527,6 +527,7 @@ static int sctp_send_asconf_add_ip(struct sock *sk,
struct list_head *p;
int i;
int retval = 0;
+ struct sctp_transport *trans = NULL;
if (!sctp_addip_enable)
return retval;
@@ -583,13 +584,10 @@ static int sctp_send_asconf_add_ip(struct sock *sk,
goto out;
}
- retval = sctp_send_asconf(asoc, chunk);
- if (retval)
- goto out;
-
/* Add the new addresses to the bind address list with
* use_as_src set to 0.
*/
+ SCTP_DEBUG_PRINTK("snd_asconf_addip: next, add_bind_addr with ADDR_NEW flag\n");
addr_buf = addrs;
for (i = 0; i < addrcnt; i++) {
addr = (union sctp_addr *)addr_buf;
@@ -599,6 +597,28 @@ static int sctp_send_asconf_add_ip(struct sock *sk,
SCTP_ADDR_NEW, GFP_ATOMIC);
addr_buf += af->sockaddr_len;
}
+ list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+ transports) {
+ if (asoc->asconf_addr_del_pending != NULL)
+ /* This ADDIP ASCONF piggybacks DELIP for the
+ * last address, so need to select src addr
+ * from the out_of_asoc addrs
+ */
+ asoc->src_out_of_asoc_ok = 1;
+ /* Clear the source and route cache in the path */
+ memset(&trans->saddr, 0, sizeof(union sctp_addr));
+ dst_release(trans->dst);
+ trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
+ 2*asoc->pathmtu, 4380));
+ trans->ssthresh = asoc->peer.i.a_rwnd;
+ trans->rto = asoc->rto_initial;
+ trans->rtt = 0;
+ trans->srtt = 0;
+ trans->rttvar = 0;
+ sctp_transport_route(trans, NULL,
+ sctp_sk(asoc->base.sk));
+ }
+ retval = sctp_send_asconf(asoc, chunk);
}
out:
@@ -711,7 +731,9 @@ static int sctp_send_asconf_del_ip(struct sock *sk,
struct sctp_sockaddr_entry *saddr;
int i;
int retval = 0;
+ int stored = 0;
+ chunk = NULL;
if (!sctp_addip_enable)
return retval;
@@ -762,8 +784,42 @@ static int sctp_send_asconf_del_ip(struct sock *sk,
bp = &asoc->base.bind_addr;
laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs,
addrcnt, sp);
- if (!laddr)
- continue;
+ if ((laddr == NULL) && (addrcnt == 1)) {
+ union sctp_addr *sa_addr = NULL;
+
+ if (asoc->asconf_addr_del_pending == NULL) {
+ asoc->asconf_addr_del_pending =
+ kmalloc(sizeof(union sctp_addr),
+ GFP_ATOMIC);
+ memset(asoc->asconf_addr_del_pending, 0,
+ sizeof(union sctp_addr));
+ if (addrs->sa_family == AF_INET) {
+ struct sockaddr_in *sin;
+
+ sin = (struct sockaddr_in *)addrs;
+ asoc->asconf_addr_del_pending->v4.sin_family = AF_INET;
+ memcpy(&asoc->asconf_addr_del_pending->v4.sin_addr, &sin->sin_addr, sizeof(struct in_addr));
+ } else if (addrs->sa_family == AF_INET6) {
+ struct sockaddr_in6 *sin6;
+
+ sin6 = (struct sockaddr_in6 *)addrs;
+ asoc->asconf_addr_del_pending->v6.sin6_family = AF_INET6;
+ memcpy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr, sizeof(struct in6_addr));
+ }
+ sa_addr = (union sctp_addr *)addrs;
+ SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ",
+ " at %p\n", asoc, sa_addr,
+ asoc->asconf_addr_del_pending);
+ stored = 1;
+ goto skip_mkasconf;
+ } else {
+ SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: asoc %p, deleting last address ",
+ " is already stored at %p\n", asoc,
+ asoc->asconf_addr_del_pending,
+ asoc->asconf_addr_del_pending);
+ continue;
+ }
+ }
/* We do not need RCU protection throughout this loop
* because this is done under a socket lock from the
@@ -776,6 +832,7 @@ static int sctp_send_asconf_del_ip(struct sock *sk,
goto out;
}
+skip_mkasconf:
/* Reset use_as_src flag for the addresses in the bind address
* list that are to be deleted.
*/
@@ -797,10 +854,16 @@ static int sctp_send_asconf_del_ip(struct sock *sk,
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
dst_release(transport->dst);
+ /* Clear source address cache */
+ memset(&transport->saddr, 0, sizeof(union sctp_addr));
sctp_transport_route(transport, NULL,
sctp_sk(asoc->base.sk));
}
+ if (stored) {
+ /* We don't need to transmit ASCONF */
+ continue;
+ }
retval = sctp_send_asconf(asoc, chunk);
}
out:
^ permalink raw reply related
* [PATCH net-next-2.6 v4 5/5] sctp: Add ADD/DEL ASCONF handling at the receiver
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
With this patch, ASCONF receiver supports deletion of the source address of the ASCONF chunk when the ADDIP co-located in the earlier parameter.
Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index de98665..a5d673b 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2914,6 +2914,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
struct sctp_af *af;
union sctp_addr addr;
union sctp_addr_param *addr_param;
+ int del_srcaddr_ok = 0;
addr_param = (union sctp_addr_param *)
((void *)asconf_param + sizeof(sctp_addip_param_t));
@@ -2973,6 +2974,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
/* Start the heartbeat timer. */
if (!mod_timer(&peer->hb_timer, sctp_transport_timeout(peer)))
sctp_transport_hold(peer);
+ del_srcaddr_ok = 1;
break;
case SCTP_PARAM_DEL_IP:
/* ADDIP 4.3 D7) If a request is received to delete the
@@ -2990,7 +2992,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
* an Error Cause TLV set to the new error code 'Request to
* Delete Source IP Address'
*/
- if (sctp_cmp_addr_exact(sctp_source(asconf), &addr))
+ if (sctp_cmp_addr_exact(sctp_source(asconf), &addr) &&
+ !del_srcaddr_ok)
return SCTP_ERROR_DEL_SRC_IP;
/* Section 4.2.2
^ permalink raw reply related
* Re: [PATCH v2] net: r8169: convert to hw_features
From: David Miller @ 2011-04-20 19:25 UTC (permalink / raw)
To: romieu; +Cc: dave, netdev, nic_swsd
In-Reply-To: <20110420191336.GB18805@electric-eye.fr.zoreil.com>
From: Francois Romieu <romieu@fr.zoreil.com>
Date: Wed, 20 Apr 2011 21:13:36 +0200
> David Miller <davem@davemloft.net> :
> [...]
>> Maybe we can progressively start to try and turn these things on
>> by default now that we know more about the TX descriptor layout
>> differences.
>
> Sure. I'd welcome a little timeslot to push a few configuration and
> cosmetic things though.
No problem.
^ permalink raw reply
* Re: [PATCH v2] net: filter: Just In Time compiler
From: Eric Dumazet @ 2011-04-20 19:27 UTC (permalink / raw)
To: David Miller; +Cc: avi, hagen, netdev, acme, bhutchings
In-Reply-To: <20110420.011454.226757908.davem@davemloft.net>
Le mercredi 20 avril 2011 à 01:14 -0700, David Miller a écrit :
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Wed, 20 Apr 2011 10:07:58 +0200
>
> > No problem, I'll wait your work on this then.
>
> Don't, please resubmit your BPF jit code so I can apply it.
>
> Waiting for some userspace pie-in-the-sky based solution, and blocking
> this perfectly functional thing we have now meanwhile, is not
> reasonable.
>
> We're pragmatic, not perfectionists.
>
> Thanks Eric.
Thanks David, let see how it flies...
V3 is same than V2 with the missing arch/x86/net/Makefile, and a change
to keep kmemcheck flags2 in struct skbuff
I dont know yet how to address net/core/timestamping.c PTP filter, since
we would need to compile it only if JIT enabled by the admin.
[PATCH v3] net: filter: Just In Time compiler
In order to speedup packet filtering, here is an implementation of a JIT
compiler for x86_64
It is disabled by default, and must be enabled by the admin.
echo 1 >/proc/sys/net/core/bpf_jit_enable
It uses module_alloc() and module_free() to get memory in the 2GB text
kernel range since we call helpers functions from the generated code.
EAX : BPF A accumulator
EBX : BPF X accumulator
RDI : pointer to skb (first argument given to JIT function)
RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
r9d : skb->len - skb->data_len (headlen)
r8 : skb->data
To get a trace of generated code, use :
echo 2 >/proc/sys/net/core/bpf_jit_enable
Example of generated code :
# tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24
flen=18 proglen=147 pass=3 image=ffffffffa00b5000
JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60
JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00
JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00
JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be
JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0
JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00
JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00
JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24
JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31
JIT code: ffffffffa00b5090: c0 c9 c3
BPF program is 144 bytes long, so native program is almost same size ;)
(000) ldh [12]
(001) jeq #0x800 jt 2 jf 8
(002) ld [26]
(003) and #0xffffff00
(004) jeq #0xc0a81400 jt 16 jf 5
(005) ld [30]
(006) and #0xffffff00
(007) jeq #0xc0a81400 jt 16 jf 17
(008) jeq #0x806 jt 10 jf 9
(009) jeq #0x8035 jt 10 jf 17
(010) ld [28]
(011) and #0xffffff00
(012) jeq #0xc0a81400 jt 16 jf 13
(013) ld [38]
(014) and #0xffffff00
(015) jeq #0xc0a81400 jt 16 jf 17
(016) ret #65535
(017) ret #0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
---
perf tool might need some changes to take into account JIT.
V3: missing arch/x86/net/makefile
V2: BPF_S_ALU_AND_K optimizations, BPF_S_ANC_QUEUE support
Move x86 files to arch/x86/net
Documentation/sysctl/net.txt | 11
MAINTAINERS | 1
arch/x86/Kbuild | 1
arch/x86/Kconfig | 1
arch/x86/net/Makefile | 4
arch/x86/net/bpf_jit.S | 142 +++++++
arch/x86/net/bpf_jit_comp.c | 655 +++++++++++++++++++++++++++++++++
include/linux/filter.h | 76 +++
include/linux/netdevice.h | 1
include/linux/skbuff.h | 4
net/Kconfig | 13
net/core/filter.c | 65 ---
net/core/sysctl_net_core.c | 9
net/packet/af_packet.c | 2
14 files changed, 921 insertions(+), 64 deletions(-)
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index cbd05ff..3201a70 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -32,6 +32,17 @@ Table : Subdirectories in /proc/sys/net
1. /proc/sys/net/core - Network core options
-------------------------------------------------------
+bpf_jit_enable
+--------------
+
+This enables Berkeley Packet Filter Just in Time compiler.
+Currently supported on x86_64 architecture, bpf_jit provides a framework
+to speed packet filtering, the one used by tcpdump/libpcap for example.
+Values :
+ 0 - disable the JIT (default value)
+ 1 - enable the JIT
+ 2 - enable the JIT and ask the compiler to emit traces on kernel log.
+
rmem_default
------------
diff --git a/MAINTAINERS b/MAINTAINERS
index b5266ad..17c0917 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4372,6 +4372,7 @@ S: Maintained
F: net/ipv4/
F: net/ipv6/
F: include/net/ip*
+F: arch/x86/net/*
NETWORKING [LABELED] (NetLabel, CIPSO, Labeled IPsec, SECMARK)
M: Paul Moore <paul.moore@hp.com>
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 0e10323..0e9dec6 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -15,3 +15,4 @@ obj-y += vdso/
obj-$(CONFIG_IA32_EMULATION) += ia32/
obj-y += platform/
+obj-y += net/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc6c53a..855a1bd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -72,6 +72,7 @@ config X86
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
select ARCH_NO_SYSDEV_OPS
+ select HAVE_BPF_JIT if X86_64
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile
new file mode 100644
index 0000000..90568c3
--- /dev/null
+++ b/arch/x86/net/Makefile
@@ -0,0 +1,4 @@
+#
+# Arch-specific network modules
+#
+obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
new file mode 100644
index 0000000..a0a9843
--- /dev/null
+++ b/arch/x86/net/bpf_jit.S
@@ -0,0 +1,142 @@
+/* bpf_jit.S : BPF JIT helper functions
+ *
+ * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+
+/*
+ * Calling convention :
+ * rdi : skb pointer
+ * esi : offset of byte(s) to fetch in skb (can be scratched)
+ * r8 : copy of skb->data
+ * r9d : hlen = skb->len - skb->data_len
+ */
+#define SKBDATA %r8
+
+sk_load_word_ind:
+ .globl sk_load_word_ind
+
+ add %ebx,%esi /* offset += X */
+# test %esi,%esi /* if (offset < 0) goto bpf_error; */
+ js bpf_error
+
+sk_load_word:
+ .globl sk_load_word
+
+ mov %r9d,%eax # hlen
+ sub %esi,%eax # hlen - offset
+ cmp $3,%eax
+ jle bpf_slow_path_word
+ mov (SKBDATA,%rsi),%eax
+ bswap %eax /* ntohl() */
+ ret
+
+
+sk_load_half_ind:
+ .globl sk_load_half_ind
+
+ add %ebx,%esi /* offset += X */
+ js bpf_error
+
+sk_load_half:
+ .globl sk_load_half
+
+ mov %r9d,%eax
+ sub %esi,%eax # hlen - offset
+ cmp $1,%eax
+ jle bpf_slow_path_half
+ movzwl (SKBDATA,%rsi),%eax
+ rol $8,%ax # ntohs()
+ ret
+
+sk_load_byte_ind:
+ .globl sk_load_byte_ind
+ add %ebx,%esi /* offset += X */
+ js bpf_error
+
+sk_load_byte:
+ .globl sk_load_byte
+
+ cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */
+ jle bpf_slow_path_byte
+ movzbl (SKBDATA,%rsi),%eax
+ ret
+
+/**
+ * sk_load_byte_msh - BPF_S_LDX_B_MSH helper
+ *
+ * Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf)
+ * Must preserve A accumulator (%eax)
+ * Inputs : %esi is the offset value, already known positive
+ */
+ENTRY(sk_load_byte_msh)
+ CFI_STARTPROC
+ cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
+ jle bpf_slow_path_byte_msh
+ movzbl (SKBDATA,%rsi),%ebx
+ and $15,%bl
+ shl $2,%bl
+ ret
+ CFI_ENDPROC
+ENDPROC(sk_load_byte_msh)
+
+bpf_error:
+# force a return 0 from jit handler
+ xor %eax,%eax
+ mov -8(%rbp),%rbx
+ leaveq
+ ret
+
+/* rsi contains offset and can be scratched */
+#define bpf_slow_path_common(LEN) \
+ push %rdi; /* save skb */ \
+ push %r9; \
+ push SKBDATA; \
+/* rsi already has offset */ \
+ mov $LEN,%ecx; /* len */ \
+ lea -12(%rbp),%rdx; \
+ call skb_copy_bits; \
+ test %eax,%eax; \
+ pop SKBDATA; \
+ pop %r9; \
+ pop %rdi
+
+
+bpf_slow_path_word:
+ bpf_slow_path_common(4)
+ js bpf_error
+ mov -12(%rbp),%eax
+ bswap %eax
+ ret
+
+bpf_slow_path_half:
+ bpf_slow_path_common(2)
+ js bpf_error
+ mov -12(%rbp),%ax
+ rol $8,%ax
+ movzwl %ax,%eax
+ ret
+
+bpf_slow_path_byte:
+ bpf_slow_path_common(1)
+ js bpf_error
+ movzbl -12(%rbp),%eax
+ ret
+
+bpf_slow_path_byte_msh:
+ xchg %eax,%ebx /* dont lose A , X is about to be scratched */
+ bpf_slow_path_common(1)
+ js bpf_error
+ movzbl -12(%rbp),%eax
+ and $15,%al
+ shl $2,%al
+ xchg %eax,%ebx
+ ret
+
+
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
new file mode 100644
index 0000000..1a21d82
--- /dev/null
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -0,0 +1,655 @@
+/* bpf_jit_comp.c : BPF JIT compiler
+ *
+ * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/moduleloader.h>
+#include <asm/cacheflush.h>
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+
+/*
+ * Conventions :
+ * EAX : BPF A accumulator
+ * EBX : BPF X accumulator
+ * RDI : pointer to skb (first argument given to JIT function)
+ * RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
+ * ECX,EDX,ESI : scratch registers
+ * r9d : skb->len - skb->data_len (headlen)
+ * r8 : skb->data
+ * -8(RBP) : saved RBX value
+ * -16(RBP)..-80(RBP) : BPF_MEMWORDS values
+ */
+int bpf_jit_enable __read_mostly;
+
+/*
+ * assembly code in arch/x86/net/bpf_jit.S
+ */
+extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+
+static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
+{
+ if (len == 1)
+ *ptr = bytes;
+ else if (len == 2)
+ *(u16 *)ptr = bytes;
+ else {
+ *(u32 *)ptr = bytes;
+ barrier();
+ }
+ return ptr + len;
+}
+
+#define EMIT(bytes, len) do { prog = emit_code(prog, bytes, len); } while (0)
+
+#define EMIT1(b1) EMIT(b1, 1)
+#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
+#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
+#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT1_off32(b1, off) do { EMIT1(b1); EMIT(off, 4);} while (0)
+
+#define CLEAR_A() EMIT2(0x31, 0xc0) /* xor %eax,%eax */
+#define CLEAR_X() EMIT2(0x31, 0xdb) /* xor %ebx,%ebx */
+
+static inline bool is_imm8(int value)
+{
+ return value <= 127 && value >= -128;
+}
+
+static inline bool is_near(int offset)
+{
+ return offset <= 127 && offset >= -128;
+}
+
+#define EMIT_JMP(offset) \
+do { \
+ if (offset) { \
+ if (is_near(offset)) \
+ EMIT2(0xeb, offset); /* jmp .+off8 */ \
+ else \
+ EMIT1_off32(0xe9, offset); /* jmp .+off32 */ \
+ } \
+} while (0)
+
+/* list of x86 cond jumps opcodes (. + s8)
+ * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
+ */
+#define X86_JB 0x72
+#define X86_JAE 0x73
+#define X86_JE 0x74
+#define X86_JNE 0x75
+#define X86_JBE 0x76
+#define X86_JA 0x77
+
+#define EMIT_COND_JMP(op, offset) \
+do { \
+ if (is_near(offset)) \
+ EMIT2(op, offset); /* jxx .+off8 */ \
+ else { \
+ EMIT2(0x0f, op + 0x10); \
+ EMIT(offset, 4); /* jxx .+off32 */ \
+ } \
+} while (0)
+
+#define COND_SEL(CODE, TOP, FOP) \
+ case CODE: \
+ t_op = TOP; \
+ f_op = FOP; \
+ goto cond_branch
+
+
+#define SEEN_DATAREF 1 /* might call external helpers */
+#define SEEN_XREG 2 /* ebx is used */
+#define SEEN_MEM 4 /* use mem[] for temporary storage */
+
+static inline void bpf_flush_icache(void *start, void *end)
+{
+ mm_segment_t old_fs = get_fs();
+
+ set_fs(KERNEL_DS);
+ smp_wmb();
+ flush_icache_range((unsigned long)start, (unsigned long)end);
+ set_fs(old_fs);
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+ u8 temp[64];
+ u8 *prog;
+ unsigned int proglen, oldproglen = 0;
+ int ilen, i;
+ int t_offset, f_offset;
+ u8 t_op, f_op, seen = 0, pass;
+ u8 *image = NULL;
+ u8 *func;
+ int pc_ret0 = -1; /* bpf index of first RET #0 instruction (if any) */
+ unsigned int cleanup_addr; /* epilogue code offset */
+ unsigned int *addrs;
+ const struct sock_filter *filter = fp->insns;
+ int flen = fp->len;
+
+ if (!bpf_jit_enable)
+ return;
+
+ addrs = kmalloc(flen * sizeof(*addrs), GFP_KERNEL);
+ if (addrs == NULL)
+ return;
+
+ /* Before first pass, make a rough estimation of addrs[]
+ * each bpf instruction is translated to less than 64 bytes
+ */
+ for (proglen = 0, i = 0; i < flen; i++) {
+ proglen += 64;
+ addrs[i] = proglen;
+ }
+ cleanup_addr = proglen; /* epilogue address */
+
+ for (pass = 0; pass < 10; pass++) {
+ /* no prologue/epilogue for trivial filters (RET something) */
+ proglen = 0;
+ prog = temp;
+
+ if (seen) {
+ EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
+ EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */
+ /* note : must save %rbx in case bpf_error is hit */
+ if (seen & (SEEN_XREG | SEEN_DATAREF))
+ EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
+ if (seen & SEEN_XREG)
+ CLEAR_X(); /* make sure we dont leek kernel memory */
+
+ /*
+ * If this filter needs to access skb data,
+ * loads r9 and r8 with :
+ * r9 = skb->len - skb->data_len
+ * r8 = skb->data
+ */
+ if (seen & SEEN_DATAREF) {
+ if (offsetof(struct sk_buff, len) <= 127)
+ /* mov off8(%rdi),%r9d */
+ EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
+ else {
+ /* mov off32(%rdi),%r9d */
+ EMIT3(0x44, 0x8b, 0x8f);
+ EMIT(offsetof(struct sk_buff, len), 4);
+ }
+ if (is_imm8(offsetof(struct sk_buff, data_len)))
+ /* sub off8(%rdi),%r9d */
+ EMIT4(0x44, 0x2b, 0x4f, offsetof(struct sk_buff, data_len));
+ else {
+ EMIT3(0x44, 0x2b, 0x8f);
+ EMIT(offsetof(struct sk_buff, data_len), 4);
+ }
+
+ if (is_imm8(offsetof(struct sk_buff, data)))
+ /* mov off8(%rdi),%r8 */
+ EMIT4(0x4c, 0x8b, 0x47, offsetof(struct sk_buff, data));
+ else {
+ /* mov off32(%rdi),%r8 */
+ EMIT3(0x4c, 0x8b, 0x87);
+ EMIT(offsetof(struct sk_buff, data), 4);
+ }
+ }
+ }
+
+ switch (filter[0].code) {
+ case BPF_S_RET_K:
+ case BPF_S_LD_W_LEN:
+ case BPF_S_ANC_PROTOCOL:
+ case BPF_S_ANC_IFINDEX:
+ case BPF_S_ANC_MARK:
+ case BPF_S_ANC_RXHASH:
+ case BPF_S_ANC_CPU:
+ case BPF_S_ANC_QUEUE:
+ case BPF_S_LD_W_ABS:
+ case BPF_S_LD_H_ABS:
+ case BPF_S_LD_B_ABS:
+ /* first instruction sets A register (or is RET 'constant') */
+ break;
+ default:
+ /* make sure we dont leak kernel information to user */
+ CLEAR_A(); /* A = 0 */
+ }
+
+ for (i = 0; i < flen; i++) {
+ unsigned int K = filter[i].k;
+
+ switch (filter[i].code) {
+ case BPF_S_ALU_ADD_X: /* A += X; */
+ seen |= SEEN_XREG;
+ EMIT2(0x01, 0xd8); /* add %ebx,%eax */
+ break;
+ case BPF_S_ALU_ADD_K: /* A += K; */
+ if (!K)
+ break;
+ if (is_imm8(K))
+ EMIT3(0x83, 0xc0, K); /* add imm8,%eax */
+ else
+ EMIT1_off32(0x05, K); /* add imm32,%eax */
+ break;
+ case BPF_S_ALU_SUB_X: /* A -= X; */
+ seen |= SEEN_XREG;
+ EMIT2(0x29, 0xd8); /* sub %ebx,%eax */
+ break;
+ case BPF_S_ALU_SUB_K: /* A -= K */
+ if (!K)
+ break;
+ if (is_imm8(K))
+ EMIT3(0x83, 0xe8, K); /* sub imm8,%eax */
+ else
+ EMIT1_off32(0x2d, K); /* sub imm32,%eax */
+ break;
+ case BPF_S_ALU_MUL_X: /* A *= X; */
+ seen |= SEEN_XREG;
+ EMIT3(0x0f, 0xaf, 0xc3); /* imul %ebx,%eax */
+ break;
+ case BPF_S_ALU_MUL_K: /* A *= K */
+ if (is_imm8(K))
+ EMIT3(0x6b, 0xc0, K); /* imul imm8,%eax,%eax */
+ else {
+ EMIT2(0x69, 0xc0); /* imul imm32,%eax */
+ EMIT(K, 4);
+ }
+ break;
+ case BPF_S_ALU_DIV_X: /* A /= X; */
+ seen |= SEEN_XREG;
+ EMIT2(0x85, 0xdb); /* test %ebx,%ebx */
+ if (pc_ret0 != -1)
+ EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4));
+ else {
+ EMIT_COND_JMP(X86_JNE, 2 + 5);
+ CLEAR_A();
+ EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
+ }
+ EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */
+ break;
+ case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+ EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
+ EMIT(K, 4);
+ EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+ break;
+ case BPF_S_ALU_AND_X:
+ seen |= SEEN_XREG;
+ EMIT2(0x21, 0xd8); /* and %ebx,%eax */
+ break;
+ case BPF_S_ALU_AND_K:
+ if (K >= 0xFFFFFF00) {
+ EMIT2(0x24, K & 0xFF); /* and imm8,%al */
+ } else if (K >= 0xFFFF0000) {
+ EMIT2(0x66, 0x25); /* and imm16,%ax */
+ EMIT2(K, 2);
+ } else {
+ EMIT1_off32(0x25, K); /* and imm32,%eax */
+ }
+ break;
+ case BPF_S_ALU_OR_X:
+ seen |= SEEN_XREG;
+ EMIT2(0x09, 0xd8); /* or %ebx,%eax */
+ break;
+ case BPF_S_ALU_OR_K:
+ if (is_imm8(K))
+ EMIT3(0x83, 0xc8, K); /* or imm8,%eax */
+ else
+ EMIT1_off32(0x0d, K); /* or imm32,%eax */
+ break;
+ case BPF_S_ALU_LSH_X: /* A <<= X; */
+ seen |= SEEN_XREG;
+ EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */
+ break;
+ case BPF_S_ALU_LSH_K:
+ if (K == 0)
+ break;
+ else if (K == 1)
+ EMIT2(0xd1, 0xe0); /* shl %eax */
+ else
+ EMIT3(0xc1, 0xe0, K);
+ break;
+ case BPF_S_ALU_RSH_X: /* A >>= X; */
+ seen |= SEEN_XREG;
+ EMIT4(0x89, 0xd9, 0xd3, 0xe8); /* mov %ebx,%ecx; shr %cl,%eax */
+ break;
+ case BPF_S_ALU_RSH_K: /* A >>= K; */
+ if (K == 0)
+ break;
+ else if (K == 1)
+ EMIT2(0xd1, 0xe8); /* shr %eax */
+ else
+ EMIT3(0xc1, 0xe8, K);
+ break;
+ case BPF_S_ALU_NEG:
+ EMIT2(0xf7, 0xd8); /* neg %eax */
+ break;
+ case BPF_S_RET_K:
+ if (!K) {
+ if (pc_ret0 == -1)
+ pc_ret0 = i;
+ CLEAR_A();
+ } else {
+ EMIT1_off32(0xb8, K); /* mov $imm32,%eax */
+ }
+ /* fallinto */
+ case BPF_S_RET_A:
+ if (seen) {
+ if (i != flen - 1) {
+ EMIT_JMP(cleanup_addr - addrs[i]);
+ break;
+ }
+ if (seen & SEEN_XREG)
+ EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */
+ EMIT1(0xc9); /* leaveq */
+ }
+ EMIT1(0xc3); /* ret */
+ break;
+ case BPF_S_MISC_TAX: /* X = A */
+ seen |= SEEN_XREG;
+ EMIT2(0x89, 0xc3); /* mov %eax,%ebx */
+ break;
+ case BPF_S_MISC_TXA: /* A = X */
+ seen |= SEEN_XREG;
+ EMIT2(0x89, 0xd8); /* mov %ebx,%eax */
+ break;
+ case BPF_S_LD_IMM: /* A = K */
+ if (!K)
+ CLEAR_A();
+ else
+ EMIT1_off32(0xb8, K); /* mov $imm32,%eax */
+ break;
+ case BPF_S_LDX_IMM: /* X = K */
+ seen |= SEEN_XREG;
+ if (!K)
+ CLEAR_X();
+ else
+ EMIT1_off32(0xbb, K); /* mov $imm32,%ebx */
+ break;
+ case BPF_S_LD_MEM: /* A = mem[K] : mov off8(%rbp),%eax */
+ seen |= SEEN_MEM;
+ EMIT3(0x8b, 0x45, 0xf0 - K*4);
+ break;
+ case BPF_S_LDX_MEM: /* X = mem[K] : mov off8(%rbp),%ebx */
+ seen |= SEEN_XREG | SEEN_MEM;
+ EMIT3(0x8b, 0x5d, 0xf0 - K*4);
+ break;
+ case BPF_S_ST: /* mem[K] = A : mov %eax,off8(%rbp) */
+ seen |= SEEN_MEM;
+ EMIT3(0x89, 0x45, 0xf0 - K*4);
+ break;
+ case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
+ seen |= SEEN_XREG | SEEN_MEM;
+ EMIT3(0x89, 0x5d, 0xf0 - K*4);
+ break;
+ case BPF_S_LD_W_LEN: /* A = skb->len; */
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+ if (is_imm8(offsetof(struct sk_buff, len)))
+ /* mov off8(%rdi),%eax */
+ EMIT3(0x8b, 0x47, offsetof(struct sk_buff, len));
+ else {
+ EMIT2(0x8b, 0x87);
+ EMIT(offsetof(struct sk_buff, len), 4);
+ }
+ break;
+ case BPF_S_LDX_W_LEN: /* X = skb->len; */
+ seen |= SEEN_XREG;
+ if (is_imm8(offsetof(struct sk_buff, len)))
+ /* mov off8(%rdi),%ebx */
+ EMIT3(0x8b, 0x5f, offsetof(struct sk_buff, len));
+ else {
+ EMIT2(0x8b, 0x9f);
+ EMIT(offsetof(struct sk_buff, len), 4);
+ }
+ break;
+ case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+ if (is_imm8(offsetof(struct sk_buff, protocol))) {
+ /* movzwl off8(%rdi),%eax */
+ EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, protocol));
+ } else {
+ EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
+ EMIT(offsetof(struct sk_buff, protocol), 4);
+ }
+ EMIT2(0x86, 0xc4); /* ntohs() : xchg %al,%ah */
+ break;
+ case BPF_S_ANC_IFINDEX:
+ if (is_imm8(offsetof(struct sk_buff, dev))) {
+ /* movq off8(%rdi),%rax */
+ EMIT4(0x48, 0x8b, 0x47, offsetof(struct sk_buff, dev));
+ } else {
+ EMIT3(0x48, 0x8b, 0x87); /* movq off32(%rdi),%rax */
+ EMIT(offsetof(struct sk_buff, dev), 4);
+ }
+ EMIT3(0x48, 0x85, 0xc0); /* test %rax,%rax */
+ EMIT_COND_JMP(X86_JE, cleanup_addr - (addrs[i] - 6));
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+ EMIT2(0x8b, 0x80); /* mov off32(%rax),%eax */
+ EMIT(offsetof(struct net_device, ifindex), 4);
+ break;
+ case BPF_S_ANC_MARK:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+ if (is_imm8(offsetof(struct sk_buff, mark))) {
+ /* mov off8(%rdi),%eax */
+ EMIT3(0x8b, 0x47, offsetof(struct sk_buff, mark));
+ } else {
+ EMIT2(0x8b, 0x87);
+ EMIT(offsetof(struct sk_buff, mark), 4);
+ }
+ break;
+ case BPF_S_ANC_RXHASH:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+ if (is_imm8(offsetof(struct sk_buff, rxhash))) {
+ /* mov off8(%rdi),%eax */
+ EMIT3(0x8b, 0x47, offsetof(struct sk_buff, rxhash));
+ } else {
+ EMIT2(0x8b, 0x87);
+ EMIT(offsetof(struct sk_buff, rxhash), 4);
+ }
+ break;
+ case BPF_S_ANC_QUEUE:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+ if (is_imm8(offsetof(struct sk_buff, queue_mapping))) {
+ /* movzwl off8(%rdi),%eax */
+ EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, queue_mapping));
+ } else {
+ EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
+ EMIT(offsetof(struct sk_buff, queue_mapping), 4);
+ }
+ break;
+ case BPF_S_ANC_CPU:
+#ifdef CONFIG_SMP
+ EMIT4(0x65, 0x8b, 0x04, 0x25); /* mov %gs:off32,%eax */
+ EMIT((u32)(unsigned long)&cpu_number, 4); /* A = smp_processor_id(); */
+#else
+ CLEAR_A();
+#endif
+ break;
+ case BPF_S_LD_W_ABS:
+ func = sk_load_word;
+common_load: seen |= SEEN_DATAREF;
+ if ((int)K < 0)
+ goto out;
+ t_offset = func - (image + addrs[i]);
+ EMIT1_off32(0xbe, K); /* mov imm32,%esi */
+ EMIT1_off32(0xe8, t_offset); /* call */
+ break;
+ case BPF_S_LD_H_ABS:
+ func = sk_load_half;
+ goto common_load;
+ case BPF_S_LD_B_ABS:
+ func = sk_load_byte;
+ goto common_load;
+ case BPF_S_LDX_B_MSH:
+ if ((int)K < 0) {
+ if (pc_ret0 != -1) {
+ EMIT_JMP(addrs[pc_ret0] - addrs[i]);
+ break;
+ }
+ CLEAR_A();
+ EMIT_JMP(cleanup_addr - addrs[i]);
+ break;
+ }
+ seen |= SEEN_DATAREF | SEEN_XREG;
+ t_offset = sk_load_byte_msh - (image + addrs[i]);
+ EMIT1_off32(0xbe, K); /* mov imm32,%esi */
+ EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
+ break;
+ case BPF_S_LD_W_IND:
+ func = sk_load_word_ind;
+common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG;
+ t_offset = func - (image + addrs[i]);
+ EMIT1_off32(0xbe, K); /* mov imm32,%esi */
+ EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */
+ break;
+ case BPF_S_LD_H_IND:
+ func = sk_load_half_ind;
+ goto common_load_ind;
+ case BPF_S_LD_B_IND:
+ func = sk_load_byte_ind;
+ goto common_load_ind;
+ case BPF_S_JMP_JA:
+ t_offset = addrs[i + K] - addrs[i];
+ EMIT_JMP(t_offset);
+ break;
+ COND_SEL(BPF_S_JMP_JGT_K, X86_JA, X86_JBE);
+ COND_SEL(BPF_S_JMP_JGE_K, X86_JAE, X86_JB);
+ COND_SEL(BPF_S_JMP_JEQ_K, X86_JE, X86_JNE);
+ COND_SEL(BPF_S_JMP_JSET_K,X86_JNE, X86_JE);
+ COND_SEL(BPF_S_JMP_JGT_X, X86_JA, X86_JBE);
+ COND_SEL(BPF_S_JMP_JGE_X, X86_JAE, X86_JB);
+ COND_SEL(BPF_S_JMP_JEQ_X, X86_JE, X86_JNE);
+ COND_SEL(BPF_S_JMP_JSET_X,X86_JNE, X86_JE);
+
+cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i];
+ t_offset = addrs[i + filter[i].jt] - addrs[i];
+
+ /* same targets, can avoid doing the test :) */
+ if (filter[i].jt == filter[i].jf) {
+ EMIT_JMP(t_offset);
+ break;
+ }
+
+ switch (filter[i].code) {
+ case BPF_S_JMP_JGT_X:
+ case BPF_S_JMP_JGE_X:
+ case BPF_S_JMP_JEQ_X:
+ seen |= SEEN_XREG;
+ EMIT2(0x39, 0xd8); /* cmp %ebx,%eax */
+ break;
+ case BPF_S_JMP_JSET_X:
+ seen |= SEEN_XREG;
+ EMIT2(0x85, 0xd8); /* test %ebx,%eax */
+ break;
+ case BPF_S_JMP_JEQ_K:
+ if (K == 0) {
+ EMIT2(0x85, 0xc0); /* test %eax,%eax */
+ break;
+ }
+ case BPF_S_JMP_JGT_K:
+ case BPF_S_JMP_JGE_K:
+ if (K <= 127)
+ EMIT3(0x83, 0xf8, K); /* cmp imm8,%eax */
+ else
+ EMIT1_off32(0x3d, K); /* cmp imm32,%eax */
+ break;
+ case BPF_S_JMP_JSET_K:
+ if (K <= 0xFF)
+ EMIT2(0xa8, K); /* test imm8,%al */
+ else if (!(K & 0xFFFF00FF))
+ EMIT3(0xf6, 0xc4, K >> 8); /* test imm8,%ah */
+ else if (K <= 0xFFFF) {
+ EMIT2(0x66, 0xa9); /* test imm16,%ax */
+ EMIT(K, 2);
+ } else {
+ EMIT1_off32(0xa9, K); /* test imm32,%eax */
+ }
+ break;
+ }
+ if (filter[i].jt != 0) {
+ if (filter[i].jf)
+ t_offset += is_near(f_offset) ? 2 : 6;
+ EMIT_COND_JMP(t_op, t_offset);
+ if (filter[i].jf)
+ EMIT_JMP(f_offset);
+ break;
+ }
+ EMIT_COND_JMP(f_op, f_offset);
+ break;
+ default:
+ /* hmm, too complex filter, give up with jit compiler */
+ goto out;
+ }
+ ilen = prog - temp;
+ if (image) {
+ if (unlikely(proglen + ilen > oldproglen)) {
+ pr_err("bpb_jit_compile fatal error\n");
+ kfree(addrs);
+ module_free(NULL, image);
+ return;
+ }
+ memcpy(image + proglen, temp, ilen);
+ }
+ proglen += ilen;
+ addrs[i] = proglen;
+ prog = temp;
+ }
+ /* last bpf instruction is always a RET :
+ * use it to give the cleanup instruction(s) addr
+ */
+ cleanup_addr = proglen - 1; /* ret */
+ if (seen)
+ cleanup_addr -= 1; /* leaveq */
+ if (seen & SEEN_XREG)
+ cleanup_addr -= 4; /* mov -8(%rbp),%rbx */
+
+ if (image) {
+ WARN_ON(proglen != oldproglen);
+ break;
+ }
+ if (proglen == oldproglen) {
+ image = module_alloc(max_t(unsigned int,
+ proglen,
+ sizeof(struct work_struct)));
+ if (!image)
+ goto out;
+ }
+ oldproglen = proglen;
+ }
+ if (bpf_jit_enable > 1)
+ pr_err("flen=%d proglen=%u pass=%d image=%p\n",
+ flen, proglen, pass, image);
+
+ if (image) {
+ if (bpf_jit_enable > 1)
+ print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_ADDRESS,
+ 16, 1, image, proglen, false);
+
+ bpf_flush_icache(image, image + proglen);
+
+ fp->bpf_func = (void *)image;
+ }
+out:
+ kfree(addrs);
+ return;
+}
+
+static void jit_free_defer(struct work_struct *arg)
+{
+ module_free(NULL, arg);
+}
+
+/* run from softirq, we must use a work_struct to call
+ * module_free() from process context
+ */
+void bpf_jit_free(struct sk_filter *fp)
+{
+ if (fp->bpf_func != sk_run_filter) {
+ struct work_struct *work = (struct work_struct *)fp->bpf_func;
+
+ INIT_WORK(work, jit_free_defer);
+ schedule_work(work);
+ }
+}
+
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 45266b7..4609b85 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -135,6 +135,8 @@ struct sk_filter
{
atomic_t refcnt;
unsigned int len; /* Number of filter blocks */
+ unsigned int (*bpf_func)(const struct sk_buff *skb,
+ const struct sock_filter *filter);
struct rcu_head rcu;
struct sock_filter insns[0];
};
@@ -153,6 +155,80 @@ extern unsigned int sk_run_filter(const struct sk_buff *skb,
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, int flen);
+
+#ifdef CONFIG_BPF_JIT
+extern void bpf_jit_compile(struct sk_filter *fp);
+extern void bpf_jit_free(struct sk_filter *fp);
+#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
+#else
+static inline void bpf_jit_compile(struct sk_filter *fp)
+{
+}
+static inline void bpf_jit_free(struct sk_filter *fp)
+{
+}
+#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
+#endif
+
+enum {
+ BPF_S_RET_K = 1,
+ BPF_S_RET_A,
+ BPF_S_ALU_ADD_K,
+ BPF_S_ALU_ADD_X,
+ BPF_S_ALU_SUB_K,
+ BPF_S_ALU_SUB_X,
+ BPF_S_ALU_MUL_K,
+ BPF_S_ALU_MUL_X,
+ BPF_S_ALU_DIV_X,
+ BPF_S_ALU_AND_K,
+ BPF_S_ALU_AND_X,
+ BPF_S_ALU_OR_K,
+ BPF_S_ALU_OR_X,
+ BPF_S_ALU_LSH_K,
+ BPF_S_ALU_LSH_X,
+ BPF_S_ALU_RSH_K,
+ BPF_S_ALU_RSH_X,
+ BPF_S_ALU_NEG,
+ BPF_S_LD_W_ABS,
+ BPF_S_LD_H_ABS,
+ BPF_S_LD_B_ABS,
+ BPF_S_LD_W_LEN,
+ BPF_S_LD_W_IND,
+ BPF_S_LD_H_IND,
+ BPF_S_LD_B_IND,
+ BPF_S_LD_IMM,
+ BPF_S_LDX_W_LEN,
+ BPF_S_LDX_B_MSH,
+ BPF_S_LDX_IMM,
+ BPF_S_MISC_TAX,
+ BPF_S_MISC_TXA,
+ BPF_S_ALU_DIV_K,
+ BPF_S_LD_MEM,
+ BPF_S_LDX_MEM,
+ BPF_S_ST,
+ BPF_S_STX,
+ BPF_S_JMP_JA,
+ BPF_S_JMP_JEQ_K,
+ BPF_S_JMP_JEQ_X,
+ BPF_S_JMP_JGE_K,
+ BPF_S_JMP_JGE_X,
+ BPF_S_JMP_JGT_K,
+ BPF_S_JMP_JGT_X,
+ BPF_S_JMP_JSET_K,
+ BPF_S_JMP_JSET_X,
+ /* Ancillary data */
+ BPF_S_ANC_PROTOCOL,
+ BPF_S_ANC_PKTTYPE,
+ BPF_S_ANC_IFINDEX,
+ BPF_S_ANC_NLATTR,
+ BPF_S_ANC_NLATTR_NEST,
+ BPF_S_ANC_MARK,
+ BPF_S_ANC_QUEUE,
+ BPF_S_ANC_HATYPE,
+ BPF_S_ANC_RXHASH,
+ BPF_S_ANC_CPU,
+};
+
#endif /* __KERNEL__ */
#endif /* __LINUX_FILTER_H__ */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb8178a..364bcf2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2514,6 +2514,7 @@ extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
extern int weight_p;
+extern int bpf_jit_enable;
extern int netdev_set_master(struct net_device *dev, struct net_device *master);
extern int netdev_set_bond_master(struct net_device *dev,
struct net_device *master);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d0ae90a..79aafbb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -391,8 +391,8 @@ struct sk_buff {
__u32 rxhash;
+ __u16 queue_mapping;
kmemcheck_bitfield_begin(flags2);
- __u16 queue_mapping:16;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
diff --git a/net/Kconfig b/net/Kconfig
index 79cabf1..745fb02 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -232,6 +232,19 @@ config XPS
depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
default y
+config HAVE_BPF_JIT
+ bool
+
+config BPF_JIT
+ bool "enable BPF Just In Time compiler"
+ depends on HAVE_BPF_JIT
+ ---help---
+ Berkeley Packet Filter filtering capabilities are normally handled
+ by an interpreter. This option allows kernel to generate a native
+ code when filter is loaded in memory. This should speedup
+ packet sniffing (libpcap/tcpdump). Note : Admin should enable
+ this feature changing /proc/sys/net/core/bpf_jit_enable
+
menu "Network testing"
config NET_PKTGEN
diff --git a/net/core/filter.c b/net/core/filter.c
index afb8afb..0eb8c44 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -39,65 +39,6 @@
#include <linux/filter.h>
#include <linux/reciprocal_div.h>
-enum {
- BPF_S_RET_K = 1,
- BPF_S_RET_A,
- BPF_S_ALU_ADD_K,
- BPF_S_ALU_ADD_X,
- BPF_S_ALU_SUB_K,
- BPF_S_ALU_SUB_X,
- BPF_S_ALU_MUL_K,
- BPF_S_ALU_MUL_X,
- BPF_S_ALU_DIV_X,
- BPF_S_ALU_AND_K,
- BPF_S_ALU_AND_X,
- BPF_S_ALU_OR_K,
- BPF_S_ALU_OR_X,
- BPF_S_ALU_LSH_K,
- BPF_S_ALU_LSH_X,
- BPF_S_ALU_RSH_K,
- BPF_S_ALU_RSH_X,
- BPF_S_ALU_NEG,
- BPF_S_LD_W_ABS,
- BPF_S_LD_H_ABS,
- BPF_S_LD_B_ABS,
- BPF_S_LD_W_LEN,
- BPF_S_LD_W_IND,
- BPF_S_LD_H_IND,
- BPF_S_LD_B_IND,
- BPF_S_LD_IMM,
- BPF_S_LDX_W_LEN,
- BPF_S_LDX_B_MSH,
- BPF_S_LDX_IMM,
- BPF_S_MISC_TAX,
- BPF_S_MISC_TXA,
- BPF_S_ALU_DIV_K,
- BPF_S_LD_MEM,
- BPF_S_LDX_MEM,
- BPF_S_ST,
- BPF_S_STX,
- BPF_S_JMP_JA,
- BPF_S_JMP_JEQ_K,
- BPF_S_JMP_JEQ_X,
- BPF_S_JMP_JGE_K,
- BPF_S_JMP_JGE_X,
- BPF_S_JMP_JGT_K,
- BPF_S_JMP_JGT_X,
- BPF_S_JMP_JSET_K,
- BPF_S_JMP_JSET_X,
- /* Ancillary data */
- BPF_S_ANC_PROTOCOL,
- BPF_S_ANC_PKTTYPE,
- BPF_S_ANC_IFINDEX,
- BPF_S_ANC_NLATTR,
- BPF_S_ANC_NLATTR_NEST,
- BPF_S_ANC_MARK,
- BPF_S_ANC_QUEUE,
- BPF_S_ANC_HATYPE,
- BPF_S_ANC_RXHASH,
- BPF_S_ANC_CPU,
-};
-
/* No hurry in this branch */
static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
{
@@ -145,7 +86,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = sk_run_filter(skb, filter->insns);
+ unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
@@ -638,6 +579,7 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
+ bpf_jit_free(fp);
kfree(fp);
}
EXPORT_SYMBOL(sk_filter_release_rcu);
@@ -672,6 +614,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
+ fp->bpf_func = sk_run_filter;
err = sk_chk_filter(fp->insns, fp->len);
if (err) {
@@ -679,6 +622,8 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
return err;
}
+ bpf_jit_compile(fp);
+
old_fp = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
rcu_assign_pointer(sk->sk_filter, fp);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 385b609..a829e3f 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -122,6 +122,15 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+#ifdef CONFIG_BPF_JIT
+ {
+ .procname = "bpf_jit_enable",
+ .data = &bpf_jit_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+#endif
{
.procname = "netdev_tstamp_prequeue",
.data = &netdev_tstamp_prequeue,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b5362e9..549527b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -538,7 +538,7 @@ static inline unsigned int run_filter(const struct sk_buff *skb,
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter != NULL)
- res = sk_run_filter(skb, filter->insns);
+ res = SK_RUN_FILTER(filter, skb);
rcu_read_unlock();
return res;
^ permalink raw reply related
* [PATCH] atl1c: Fix work event interrupt/task races
From: Tim Gardner @ 2011-04-20 19:00 UTC (permalink / raw)
To: netdev; +Cc: jie.yang
commit eab846b1823e05a045a28d2c87e219ef1b6e3c49
Author: Tim Gardner <tim.gardner@canonical.com>
Date: Wed Apr 20 11:31:09 2011 -0600
atl1c: Fix work event interrupt/task races
The mechanism used to initiate work events from the interrupt
handler has a classic read/modify/write race between the interrupt
handler that sets the condition, and the worker task that reads and
clears the condition. Close these races by using atomic
bit fields.
Cc: stable@kernel.org
Cc: Jie Yang <jie.yang@atheros.com>
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
diff --git a/drivers/net/atl1c/atl1c.h b/drivers/net/atl1c/atl1c.h
index 9ab5809..dec8110 100644
--- a/drivers/net/atl1c/atl1c.h
+++ b/drivers/net/atl1c/atl1c.h
@@ -566,9 +566,9 @@ struct atl1c_adapter {
#define __AT_TESTING 0x0001
#define __AT_RESETTING 0x0002
#define __AT_DOWN 0x0003
- u8 work_event;
-#define ATL1C_WORK_EVENT_RESET 0x01
-#define ATL1C_WORK_EVENT_LINK_CHANGE 0x02
+ unsigned long work_event;
+#define ATL1C_WORK_EVENT_RESET 0
+#define ATL1C_WORK_EVENT_LINK_CHANGE 1
u32 msg_enable;
bool have_msi;
diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c
index 3824382..dffc7f7 100644
--- a/drivers/net/atl1c/atl1c_main.c
+++ b/drivers/net/atl1c/atl1c_main.c
@@ -325,7 +325,7 @@ static void atl1c_link_chg_event(struct atl1c_adapter *adapter)
}
}
- adapter->work_event |= ATL1C_WORK_EVENT_LINK_CHANGE;
+ set_bit(ATL1C_WORK_EVENT_LINK_CHANGE, &adapter->work_event);
schedule_work(&adapter->common_task);
}
@@ -337,20 +337,16 @@ static void atl1c_common_task(struct work_struct *work)
adapter = container_of(work, struct atl1c_adapter, common_task);
netdev = adapter->netdev;
- if (adapter->work_event & ATL1C_WORK_EVENT_RESET) {
- adapter->work_event &= ~ATL1C_WORK_EVENT_RESET;
+ if (test_and_clear_bit(ATL1C_WORK_EVENT_RESET, &adapter->work_event)) {
netif_device_detach(netdev);
atl1c_down(adapter);
atl1c_up(adapter);
netif_device_attach(netdev);
- return;
}
- if (adapter->work_event & ATL1C_WORK_EVENT_LINK_CHANGE) {
- adapter->work_event &= ~ATL1C_WORK_EVENT_LINK_CHANGE;
+ if (test_and_clear_bit(ATL1C_WORK_EVENT_LINK_CHANGE,
+ &adapter->work_event))
atl1c_check_link_status(adapter);
- }
- return;
}
@@ -369,7 +365,7 @@ static void atl1c_tx_timeout(struct net_device *netdev)
struct atl1c_adapter *adapter = netdev_priv(netdev);
/* Do the reset outside of interrupt context */
- adapter->work_event |= ATL1C_WORK_EVENT_RESET;
+ set_bit(ATL1C_WORK_EVENT_RESET, &adapter->work_event);
schedule_work(&adapter->common_task);
}
^ permalink raw reply related
* [PATCH net-next-2.6 v4 0/5] sctp: Patch series
From: Michio Honda @ 2011-04-20 19:24 UTC (permalink / raw)
To: netdev; +Cc: lksctp-developers
Series of 5 patches to support auto_asconf and the other related functionalities that auto_asconf relies on.
Cheers,
- Michio
[1/5] Add Auto-ASCONF support
[2/5] Add sysctl support for Auto-ASCONF
[3/5] Add socket option operation for Auto-ASCONF
[4/5] Add ASCONF operation on the single-homed host
[5/5] Add ADD/DEL ASCONF handling at the receiver
^ permalink raw reply
* [PATCH V3 0/8] macvtap/vhost TX zero copy support
From: Shirley Ma @ 2011-04-20 19:36 UTC (permalink / raw)
To: David Miller, mst, Eric Dumazet, Avi Kivity, Arnd Bergmann
Cc: netdev, kvm, linux-kernel
This patchset add supports for TX zero-copy between guest and host
kernel through vhost. It significantly reduces CPU utilization on the
local host on which the guest is located (It reduced 30-50% CPU usage
for vhost thread for single stream test). The patchset is based on
previous submission and comments from the community regarding when/how
to handle guest kernel buffers to be released. This is the simplest
approach I can think of after comparing with several other solutions.
This patchset includes:
1/8: Add a new sock zero-copy flag, SOCK_ZEROCOPY;
2/8: Add a new device flag, NETIF_F_ZEROCOPY for lower level device
support zero-copy;
3/8: Add a new struct skb_ubuf_info in skb_share_info for userspace
buffers release callback when lower device DMA has done for that skb;
4/8: Add vhost zero-copy callback in vhost when skb last refcnt is gone;
add vhost_zerocopy_add_used_and_signal to notify guest to release TX skb
buffers.
5/8: Add macvtap zero-copy in lower device when sending packet is
greater than 128 bytes.
6/8: Add Chelsio 10Gb NIC to zero copy feature flag
7/8: Add Intel 10Gb NIC zero copy feature flag
8/8: Add Emulex 10Gb NIC zero copy feature flag
The patchset is built against most recent linux 2.6.git. It has passed
netperf/netserver multiple streams stress test on above NICs.
The single stream test results from 2.6.37 kernel on Chelsio:
64K message size: copy_from_user dropped from 40% to 5%; vhost thread
cpu utilization dropped from 76% to 28%
I am collecting more test results against 2.6.39-rc3 kernel and will
provide the test matrix later.
Thanks
Shirley
^ permalink raw reply
* [PATCH V3 1/8] Add a new sock zerocopy flag
From: Shirley Ma @ 2011-04-20 19:42 UTC (permalink / raw)
To: David Miller
Cc: mst, Eric Dumazet, Avi Kivity, Arnd Bergmann, netdev, kvm,
linux-kernel
In-Reply-To: <1303328216.19336.18.camel@localhost.localdomain>
This sock zerocopy flag is used to support lower level device DMA
userspace buffers.
Signed-off-by: Shirley Ma <xma@us.ibm.com>
---
include/net/sock.h | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 01810a3..daa0a80 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -562,6 +562,7 @@ enum sock_flags {
SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
SOCK_FASYNC, /* fasync() active */
SOCK_RXQ_OVFL,
+ SOCK_ZEROCOPY,
};
static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
^ permalink raw reply related
* [PATCH V3 2/8] Add a new zerocopy device flag
From: Shirley Ma @ 2011-04-20 19:44 UTC (permalink / raw)
To: David Miller
Cc: mst, Eric Dumazet, Avi Kivity, Arnd Bergmann, netdev, kvm,
linux-kernel
In-Reply-To: <1303328216.19336.18.camel@localhost.localdomain>
This zerocopy flag is used to support device DMA userspace buffers.
Signed-off-by: Shirley Ma <xma@us.ibm.com>
---
include/linux/netdevice.h | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0249fe7..0998d3d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1067,6 +1067,9 @@ struct net_device {
#define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */
#define NETIF_F_RXCSUM (1 << 29) /* Receive checksumming offload */
+/* bit 29 is for device to map userspace buffers -- zerocopy */
+#define NETIF_F_ZEROCOPY (1 << 29)
+
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
#define NETIF_F_GSO_MASK 0x00ff0000
^ 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