* IPsecv6 tunnel mode fragmentation
From: Joy Latten @ 2010-12-05 22:18 UTC (permalink / raw)
To: netdev; +Cc: samudrala, rashmin
[-- Attachment #1: Type: text/plain, Size: 1520 bytes --]
We have come across an ipsec problem that I think was
noted a while back in the following link.
http://www.mail-archive.com/netdev@vger.kernel.org/msg61659.html
When an icmpv6 pkt-too-big message for a destination
is received, it is processed and the route's mtu is adjusted.
Transport mode uses "adjusted" mtu and works ok, but tunnel-mode
which has inner and outer iphdrs has problems.
ah and esp leave it to the ipv6 layer to fragment.
So, it seems esp/ah tunnel mode can produce an outgoing ipsec tunnel
mode pkt whose inner pkthdr has the dst with the adjusted mtu,
but inner pkt size larger than the adjusted mtu.
The outer pkthdr has tunnel's dst mtu which has not been
adjusted, since the pkt-too-big message was not for it.
So, ipv6 layer will use outer mtu to decide whether to fragment or not.
It doesn't appear to use the inner, "adjusted" mtu.
In the tcpdump attached below, since outer mtu is larger than the
outgoing pkt's size, it is not fragmented.
Thus lies the problem. So when the link with the "adjusted" mtu
gets the decrypted packet, the decrypted pkt may be too large for the
link's mtu. The "adjusted" mtu was never regarded when creating the pkt.
Hopefully, I have explained this clearly, if not
let me know. Should esp/ah pre-fragment... or should mtu of
inner pkt's dst be used for outer pkt? What's the best way to approach
this? Thanks for any info.
regards,
Joy
ipsec config:
target <-------> Secuity gateway <-----> host
(tunnel)
attachment is tcpdump from target.
[-- Attachment #2: target.bin --]
[-- Type: application/octet-stream, Size: 10236 bytes --]
^ permalink raw reply
* [PATCH] atm: correct sysfs 'device' link creation and parent relationships
From: Dan Williams @ 2010-12-05 22:17 UTC (permalink / raw)
To: netdev-u79uwXL29TY76Z2rM5mHXA
Cc: Duncan Sands, linux-usb-u79uwXL29TY76Z2rM5mHXA, Chas Williams,
Kay Sievers
The ATM subsystem was incorrectly creating the 'device' link for ATM
nodes in sysfs. This led to incorrect device/parent relationships
exposed by sysfs and udev. Instead of rolling the 'device' link by hand
in the generic ATM code, pass each ATM driver's bus device down to the
sysfs code and let sysfs do this stuff correctly.
Signed-off-by: Dan Williams <dcbw-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
Note: I preserved original formatting for style consistency instead of
fixing up checkpatch.pl errors for "space required before XXXX".
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index b910181..2b464b6 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -366,7 +366,7 @@ static int atmtcp_create(int itf,int persist,struct atm_dev **result)
if (!dev_data)
return -ENOMEM;
- dev = atm_dev_register(DEV_LABEL,&atmtcp_v_dev_ops,itf,NULL);
+ dev = atm_dev_register(DEV_LABEL,NULL,&atmtcp_v_dev_ops,itf,NULL);
if (!dev) {
kfree(dev_data);
return itf == -1 ? -ENOMEM : -EBUSY;
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 97c5898..c495fae 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2244,7 +2244,7 @@ static int __devinit eni_init_one(struct pci_dev *pci_dev,
&zeroes);
if (!cpu_zeroes) goto out1;
}
- dev = atm_dev_register(DEV_LABEL,&ops,-1,NULL);
+ dev = atm_dev_register(DEV_LABEL, &pci_dev->dev, &ops, -1, NULL);
if (!dev) goto out2;
pci_set_drvdata(pci_dev, dev);
eni_dev->pci_dev = pci_dev;
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 5d86bb8..7d912ba 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1911,7 +1911,7 @@ static int __devinit firestream_init_one (struct pci_dev *pci_dev,
fs_dev, sizeof (struct fs_dev));
if (!fs_dev)
goto err_out;
- atm_dev = atm_dev_register("fs", &ops, -1, NULL);
+ atm_dev = atm_dev_register("fs", &pci_dev->dev, &ops, -1, NULL);
if (!atm_dev)
goto err_out_free_fs_dev;
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 801e8b6..6cf59bf 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -366,7 +366,7 @@ he_init_one(struct pci_dev *pci_dev, const struct pci_device_id *pci_ent)
goto init_one_failure;
}
- atm_dev = atm_dev_register(DEV_LABEL, &he_ops, -1, NULL);
+ atm_dev = atm_dev_register(DEV_LABEL, &pci_dev->dev, &he_ops, -1, NULL);
if (!atm_dev) {
err = -ENODEV;
goto init_one_failure;
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 2f3516b..af37a5f 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -771,7 +771,7 @@ static int __devinit ns_init_card(int i, struct pci_dev *pcidev)
}
/* Register device */
- card->atmdev = atm_dev_register("nicstar", &atm_ops, -1, NULL);
+ card->atmdev = atm_dev_register("nicstar", &card->pcidev->dev, &atm_ops, -1, NULL);
if (card->atmdev == NULL) {
printk("nicstar%d: can't register device.\n", i);
error = 17;
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 2e08c99..73fb1c4 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -166,7 +166,7 @@ static irqreturn_t solos_irq(int irq, void *dev_id);
static struct atm_vcc* find_vcc(struct atm_dev *dev, short vpi, int vci);
static int list_vccs(int vci);
static void release_vccs(struct atm_dev *dev);
-static int atm_init(struct solos_card *);
+static int atm_init(struct solos_card *, struct device *);
static void atm_remove(struct solos_card *);
static int send_command(struct solos_card *card, int dev, const char *buf, size_t size);
static void solos_bh(unsigned long);
@@ -1210,7 +1210,7 @@ static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id)
if (db_firmware_upgrade)
flash_upgrade(card, 3);
- err = atm_init(card);
+ err = atm_init(card, &dev->dev);
if (err)
goto out_free_irq;
@@ -1233,7 +1233,7 @@ static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id)
return err;
}
-static int atm_init(struct solos_card *card)
+static int atm_init(struct solos_card *card, struct device *parent)
{
int i;
@@ -1244,7 +1244,7 @@ static int atm_init(struct solos_card *card)
skb_queue_head_init(&card->tx_queue[i]);
skb_queue_head_init(&card->cli_queue[i]);
- card->atmdev[i] = atm_dev_register("solos-pci", &fpga_ops, -1, NULL);
+ card->atmdev[i] = atm_dev_register("solos-pci", parent, &fpga_ops, -1, NULL);
if (!card->atmdev[i]) {
dev_err(&card->dev->dev, "Could not register ATM device %d\n", i);
atm_remove(card);
diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c
index 05bf5a2..989e16e 100644
--- a/drivers/usb/atm/usbatm.c
+++ b/drivers/usb/atm/usbatm.c
@@ -951,7 +951,9 @@ static int usbatm_atm_init(struct usbatm_data *instance)
* condition: callbacks we register can be executed at once, before we have
* initialized the struct atm_dev. To protect against this, all callbacks
* abort if atm_dev->dev_data is NULL. */
- atm_dev = atm_dev_register(instance->driver_name, &usbatm_atm_devops, -1, NULL);
+ atm_dev = atm_dev_register(instance->driver_name,
+ &instance->usb_intf->dev, &usbatm_atm_devops,
+ -1, NULL);
if (!atm_dev) {
usb_err(instance, "%s: failed to register ATM device!\n", __func__);
return -1;
@@ -966,14 +968,6 @@ static int usbatm_atm_init(struct usbatm_data *instance)
/* temp init ATM device, set to 128kbit */
atm_dev->link_rate = 128 * 1000 / 424;
- ret = sysfs_create_link(&atm_dev->class_dev.kobj,
- &instance->usb_intf->dev.kobj, "device");
- if (ret) {
- atm_err(instance, "%s: sysfs_create_link failed: %d\n",
- __func__, ret);
- goto fail_sysfs;
- }
-
if (instance->driver->atm_start && ((ret = instance->driver->atm_start(instance, atm_dev)) < 0)) {
atm_err(instance, "%s: atm_start failed: %d!\n", __func__, ret);
goto fail;
@@ -992,8 +986,6 @@ static int usbatm_atm_init(struct usbatm_data *instance)
return 0;
fail:
- sysfs_remove_link(&atm_dev->class_dev.kobj, "device");
- fail_sysfs:
instance->atm_dev = NULL;
atm_dev_deregister(atm_dev); /* usbatm_atm_dev_close will eventually be called */
return ret;
@@ -1329,7 +1321,6 @@ void usbatm_usb_disconnect(struct usb_interface *intf)
/* ATM finalize */
if (instance->atm_dev) {
- sysfs_remove_link(&instance->atm_dev->class_dev.kobj, "device");
atm_dev_deregister(instance->atm_dev);
instance->atm_dev = NULL;
}
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index a8e4e83..475f8c4 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -427,8 +427,10 @@ extern rwlock_t vcc_sklist_lock;
#define ATM_SKB(skb) (((struct atm_skb_data *) (skb)->cb))
-struct atm_dev *atm_dev_register(const char *type,const struct atmdev_ops *ops,
- int number,unsigned long *flags); /* number == -1: pick first available */
+struct atm_dev *atm_dev_register(const char *type, struct device *parent,
+ const struct atmdev_ops *ops,
+ int number, /* -1 == pick first available */
+ unsigned long *flags);
struct atm_dev *atm_dev_lookup(int number);
void atm_dev_deregister(struct atm_dev *dev);
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
index 799c631..f7fa67c 100644
--- a/net/atm/atm_sysfs.c
+++ b/net/atm/atm_sysfs.c
@@ -143,12 +143,13 @@ static struct class atm_class = {
.dev_uevent = atm_uevent,
};
-int atm_register_sysfs(struct atm_dev *adev)
+int atm_register_sysfs(struct atm_dev *adev, struct device *parent)
{
struct device *cdev = &adev->class_dev;
int i, j, err;
cdev->class = &atm_class;
+ cdev->parent = parent;
dev_set_drvdata(cdev, adev);
dev_set_name(cdev, "%s%d", adev->type, adev->number);
diff --git a/net/atm/resources.c b/net/atm/resources.c
index d29e582..23f45ce 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -74,8 +74,9 @@ struct atm_dev *atm_dev_lookup(int number)
}
EXPORT_SYMBOL(atm_dev_lookup);
-struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops,
- int number, unsigned long *flags)
+struct atm_dev *atm_dev_register(const char *type, struct device *parent,
+ const struct atmdev_ops *ops, int number,
+ unsigned long *flags)
{
struct atm_dev *dev, *inuse;
@@ -115,7 +116,7 @@ struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops,
goto out_fail;
}
- if (atm_register_sysfs(dev) < 0) {
+ if (atm_register_sysfs(dev, parent) < 0) {
pr_err("atm_register_sysfs failed for dev %s\n", type);
atm_proc_dev_deregister(dev);
goto out_fail;
diff --git a/net/atm/resources.h b/net/atm/resources.h
index 126fb18..521431e 100644
--- a/net/atm/resources.h
+++ b/net/atm/resources.h
@@ -42,6 +42,6 @@ static inline void atm_proc_dev_deregister(struct atm_dev *dev)
#endif /* CONFIG_PROC_FS */
-int atm_register_sysfs(struct atm_dev *adev);
+int atm_register_sysfs(struct atm_dev *adev, struct device *parent);
void atm_unregister_sysfs(struct atm_dev *adev);
#endif
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: PATCH] filter: fix sk_filter rcu handling
From: Eric Dumazet @ 2010-12-05 21:28 UTC (permalink / raw)
To: Andi Kleen
Cc: netdev, hagen, stable, xiaosuo, wirelesser, Paul E. McKenney,
David Miller, Pavel Emelyanov
In-Reply-To: <20101205210840.GB7668@basil.fritz.box>
Le dimanche 05 décembre 2010 à 22:08 +0100, Andi Kleen a écrit :
> > While working on this, I found an annoying problem with current code.
> >
> > This patch is a stable candidate.
>
> Does this actually fix a real world problem someone is experiencing?
> "Theoretical races" are normally outside stable's scope.
>
> -Andi
I guess its a security problem.
We can probably write a program, run by unpriviledge user to crash the
machine.
I am not sure I want to spend time to write this program, I have other
more interesting topics, but some hackers probably want to.
_______________________________________________
stable mailing list
stable@linux.kernel.org
http://linux.kernel.org/mailman/listinfo/stable
^ permalink raw reply
* Re: PATCH] filter: fix sk_filter rcu handling
From: Andi Kleen @ 2010-12-05 21:08 UTC (permalink / raw)
To: Eric Dumazet
Cc: netdev, hagen, stable, xiaosuo, wirelesser, Paul E. McKenney,
David Miller, Pavel Emelyanov
In-Reply-To: <1291582432.2806.300.camel@edumazet-laptop>
> While working on this, I found an annoying problem with current code.
>
> This patch is a stable candidate.
Does this actually fix a real world problem someone is experiencing?
"Theoretical races" are normally outside stable's scope.
-Andi
^ permalink raw reply
* Re: [PATCH] net: init ingress queue
From: Eric Dumazet @ 2010-12-05 21:05 UTC (permalink / raw)
To: Changli Gao; +Cc: David S. Miller, Tom Herbert, Jiri Pirko, netdev
In-Reply-To: <1291465901-3189-1-git-send-email-xiaosuo@gmail.com>
Le samedi 04 décembre 2010 à 20:31 +0800, Changli Gao a écrit :
> The dev field of ingress queue is forgot to initialized, then NULL
> pointer dereference happens in qdisc_alloc().
>
> Move inits of tx queues to netif_alloc_netdev_queues().
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
> ---
> v2: factorize the two inits in netdev_init_queues() and move inits of
> tx queues to netif_alloc_netdev_queues().
This is a net-next-2.6 patch, you forgot to mention it.
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* PATCH] filter: fix sk_filter rcu handling
From: Eric Dumazet @ 2010-12-05 20:53 UTC (permalink / raw)
To: David Miller
Cc: netdev, hagen, xiaosuo, wirelesser, Paul E. McKenney, stable,
Pavel Emelyanov
In-Reply-To: <1291357953.2854.46.camel@edumazet-laptop>
Le vendredi 03 décembre 2010 à 07:32 +0100, Eric Dumazet a écrit :
> Le mercredi 01 décembre 2010 à 10:18 -0800, David Miller a écrit :
>
> > However, I think it's still valuable to write a few JIT compilers for
> > the existing BPF stuff. I considered working on a sparc64 JIT just to
> > see what it would look like.
> >
> > If people work on the BPF optimizer and BPF JITs in parallel, we'll have
> > both ready at the same time. win++
>
> I began work on implementing a BPF JIT for x86_64
>
> My plan is to use external helpers to load skb data/metadata, to keep
> BPF program very short and have no dependencies against struct layouts.
>
> These helpers would be the three load_word, load_half, load_byte.
>
> In case the bits are in skb head, these helpers should be fast.
>
> For practical reasons, they would be in ASM for their fast path, and C
> for the slow path. They are ASM because they are able to perform the
> shortcut (in case of error, doing the stack unwind to perform the
> "return 0;") so that we dont have to test their return from the JIT
> program.
>
>
While working on this, I found an annoying problem with current code.
This patch is a stable candidate.
Thanks
[PATCH] filter: fix sk_filter rcu handling
Pavel Emelyanov tried to fix a race between sk_filter_(de|at)tach and
sk_clone() in commit 47e958eac280c263397
Problem is we can have several clones sharing a common sk_filter, and
these clones might want to sk_filter_attach() their own filters at the
same time, and can overwrite old_filter->rcu, corrupting RCU queues.
We can not use filter->rcu without being sure no other thread could do
the same thing.
Switch code to a more conventional ref-counting technique : Do the
atomic decrement immediately and queue one rcu call back when last
reference is released.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: stable@kernel.org
---
include/net/sock.h | 4 +++-
net/core/filter.c | 19 ++++++-------------
2 files changed, 9 insertions(+), 14 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index a6338d0..4308af7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1155,6 +1155,8 @@ extern void sk_common_release(struct sock *sk);
/* Initialise core socket variables */
extern void sock_init_data(struct socket *sock, struct sock *sk);
+extern void sk_filter_release_rcu(struct rcu_head *rcu);
+
/**
* sk_filter_release - release a socket filter
* @fp: filter to remove
@@ -1165,7 +1167,7 @@ extern void sock_init_data(struct socket *sock, struct sock *sk);
static inline void sk_filter_release(struct sk_filter *fp)
{
if (atomic_dec_and_test(&fp->refcnt))
- kfree(fp);
+ call_rcu_bh(&fp->rcu, sk_filter_release_rcu);
}
static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
diff --git a/net/core/filter.c b/net/core/filter.c
index c1ee800..ae21a0d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -589,23 +589,16 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
EXPORT_SYMBOL(sk_chk_filter);
/**
- * sk_filter_rcu_release - Release a socket filter by rcu_head
+ * sk_filter_release_rcu - Release a socket filter by rcu_head
* @rcu: rcu_head that contains the sk_filter to free
*/
-static void sk_filter_rcu_release(struct rcu_head *rcu)
+void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
- sk_filter_release(fp);
-}
-
-static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp)
-{
- unsigned int size = sk_filter_len(fp);
-
- atomic_sub(size, &sk->sk_omem_alloc);
- call_rcu_bh(&fp->rcu, sk_filter_rcu_release);
+ kfree(fp);
}
+EXPORT_SYMBOL(sk_filter_release_rcu);
/**
* sk_attach_filter - attach a socket filter
@@ -649,7 +642,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
rcu_assign_pointer(sk->sk_filter, fp);
if (old_fp)
- sk_filter_delayed_uncharge(sk, old_fp);
+ sk_filter_uncharge(sk, old_fp);
return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -663,7 +656,7 @@ int sk_detach_filter(struct sock *sk)
sock_owned_by_user(sk));
if (filter) {
rcu_assign_pointer(sk->sk_filter, NULL);
- sk_filter_delayed_uncharge(sk, filter);
+ sk_filter_uncharge(sk, filter);
ret = 0;
}
return ret;
_______________________________________________
stable mailing list
stable@linux.kernel.org
http://linux.kernel.org/mailman/listinfo/stable
^ permalink raw reply related
* 2.6.37-rc4-git4: Reported regressions 2.6.35 -> 2.6.36
From: Rafael J. Wysocki @ 2010-12-05 20:15 UTC (permalink / raw)
To: Linux Kernel Mailing List
Cc: Linux SCSI List, Linux ACPI, Network Development,
Linux Wireless List, DRI, Florian Mickler, Andrew Morton,
Kernel Testers List, Linus Torvalds, Linux PM List,
Maciej Rutecki
This message contains a list of some post-2.6.35 regressions introduced before
2.6.36, for which there are no fixes in the mainline known to the tracking team.
If any of them have been fixed already, please let us know.
If you know of any other unresolved post-2.6.35 regressions, please let us know
either and we'll add them to the list. Also, please let us know if any
of the entries below are invalid.
Each entry from the list will be sent additionally in an automatic reply to
this message with CCs to the people involved in reporting and handling the
issue.
Listed regressions statistics:
Date Total Pending Unresolved
----------------------------------------
2010-12-05 95 34 31
2010-11-19 92 38 34
2010-10-17 70 27 27
2010-10-10 56 16 15
2010-10-03 52 16 14
2010-09-26 46 15 13
2010-09-20 38 15 15
2010-09-12 28 14 13
2010-08-30 21 16 15
Unresolved regressions
----------------------
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=24022
Subject : wireless no longer works after 1st update of 10.10 [rtl819xE:ERR in init_firmware()]
Submitter : njin <marconifabio@ubuntu-it.org>
Date : 2010-11-29 19:49 (7 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=23812
Subject : HAL does not provide battery information on RHEL5 and CentOS-5
Submitter : Dag Wieers <dag@wieers.com>
Date : 2010-11-26 18:08 (10 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=23302
Subject : alsa stops working after one or more hibernate or suspend cycles
Submitter : Werner Lemberg <wl@gnu.org>
Date : 2010-11-19 16:21 (17 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=23132
Subject : without "pci=nocrs", Dell Inspiron 1545 hangs
Submitter : Bjorn Helgaas <bjorn.helgaas@hp.com>
Date : 2010-11-17 19:18 (19 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22842
Subject : iwl3945 suddenly stops working
Submitter : Felipe Contreras <felipe.contreras@gmail.com>
Date : 2010-11-14 11:14 (22 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22782
Subject : 2.6.36: general protection fault during lockfs lockspace removal
Submitter : nik@linuxbox.cz <nik@linuxbox.cz>
Date : 2010-11-12 12:05 (24 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22732
Subject : 2.6.37-rc1: hibernation breaks swap
Submitter : Zhang Rui <rui.zhang@intel.com>
Date : 2010-11-11 08:38 (25 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22272
Subject : High [extra timer interrupt] count in powertop since 2.6.36
Submitter : Ian Kumlien <pomac@demius.net>
Date : 2010-10-30 23:52 (37 days old)
Message-ID : <alpine.LNX.2.00.1010310148450.24290@twilight.pomac.com>
References : http://marc.info/?l=linux-kernel&m=128848330304431&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22172
Subject : alsa-util.c: snd_pcm_avail_delay() returned strange values: delay 0 is less than avail 32
Submitter : Tobias <devnull@plzk.org>
Date : 2010-11-06 09:33 (30 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=22092
Subject : Kernel v2.6.36 trouble on USB disconnect
Submitter : Ketil Froyn <ketil@froyn.name>
Date : 2010-10-29 8:05 (38 days old)
Message-ID : <AANLkTik5qVxkEGVAA1PSOGk2KTW+ekHpSwttsQEWzWj+@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128833956503607&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=21662
Subject : 2.6.35->2.6.36 regression, vanilla kernel panic, ppp or hrtimers crashing
Submitter : Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Date : 2010-10-25 9:22 (42 days old)
Message-ID : <201010251222.37191.nuclearcat@nuclearcat.com>
References : http://marc.info/?l=linux-kernel&m=128799855826011&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=21652
Subject : several problems with intel graphics since 2.6.36
Submitter : Norbert Preining <preining@logic.at>
Date : 2010-10-27 14:32 (40 days old)
Message-ID : <20101027143252.GA8676@gamma.logic.tuwien.ac.at>
References : http://marc.info/?l=linux-kernel&m=128818998630241&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=21402
Subject : [KVM] Noacpi Windows guest can not boot up on 32bit KVM host
Submitter : xudong <xudong.hao@intel.com>
Date : 2010-10-29 03:01 (38 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=21372
Subject : NULL pointer deference at disk_replace_part_tbl+0x32
Submitter : Luis R. Rodriguez <mcgrof@gmail.com>
Date : 2010-10-28 17:22 (39 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20352
Subject : Fwd: Re: UML kernel crash of v2.6.36-rcX kernel
Submitter : Toralf Förster <toralf.foerster@gmx.de>
Date : 2010-10-13 11:28 (54 days old)
First-Bad-Commit: http://git.kernel.org/linus/365b18189789bfa1acd9939e6312b8a4b4577b28
Message-ID : <201010131328.06465.toralf.foerster@gmx.de>
References : http://marc.info/?l=linux-kernel&m=128696930132503&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20342
Subject : [LogFS] [2.6.36-rc7] Deadlock in logfs_get_wblocks, hold and wait on same lock super->s_write_mutex
Submitter : Prasad Joshi <prasadjoshi124@gmail.com>
Date : 2010-10-13 9:49 (54 days old)
Message-ID : <AANLkTinvsMxTxEbDEFmb5M-6fYjdRvErU==Zs7+qANkV@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128696335024718&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20332
Subject : [LogFS] [2.6.36-rc7] Kernel BUG at lib/btree.c:465!
Submitter : Prasad Joshi <prasadjoshi124@gmail.com>
Date : 2010-10-12 18:56 (55 days old)
Message-ID : <AANLkTimAbCZNhLQ5nADUiAC+7JpAeJBEmjFwdxyZ-FxO@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128690910501830&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20322
Subject : 2.6.36-rc7: inconsistent lock state: inconsistent {IN-RECLAIM_FS-R} -> {RECLAIM_FS-ON-W} usage.
Submitter : Dave Jones <davej@redhat.com>
Date : 2010-10-11 20:10 (56 days old)
Message-ID : <20101011201007.GA29707@redhat.com>
References : http://marc.info/?l=linux-kernel&m=128682782828453&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20232
Subject : kworker consumes ~100% CPU on HP Elitebook 8540w running 2.6.36_rc6-git4
Submitter : Ozan Caglayan <ozan@pardus.org.tr>
Date : 2010-10-13 06:13 (54 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19802
Subject : [drm:init_ring_common] *ERROR* render ring head not reset to zero
Submitter : Thomas Meyer <thomas@m3y3r.de>
Date : 2010-10-04 20:31 (63 days old)
Message-ID : <201010042231.20320.thomas@m3y3r.de>
References : http://marc.info/?l=linux-kernel&m=128622441331199&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19782
Subject : 2.6.36-rc6-git2 -- BUG dentry: Poison overwritten (after resume from hibernation)
Submitter : Miles Lane <miles.lane@gmail.com>
Date : 2010-10-03 3:54 (64 days old)
Message-ID : <AANLkTimrqtzBHAZSuDhEs_3CKA6pCbM35b1BtKH=MvC_@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128607809314079&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19632
Subject : 2.6.36-rc6: modprobe Not tainted warning
Submitter : Heinz Diehl <htd@fritha.org>
Date : 2010-09-30 18:25 (67 days old)
Message-ID : <20100930182516.GA15089@fritha.org>
References : http://marc.info/?l=linux-kernel&m=128587114004680&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19392
Subject : WARNING: at drivers/net/wireless/ath/ath5k/base.c:3475 ath5k_bss_info_changed+0x44/0x168 [ath5k]()
Submitter : Justin Mattock <justinmattock@gmail.com>
Date : 2010-09-28 22:30 (69 days old)
Message-ID : <<AANLkTim5WCGKPvEkOkO_YnMF9pg8mvLfQoFBNUFpfa_k@mail.gmail.com>>
References : http://marc.info/?l=linux-kernel&m=128571307018635&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19372
Subject : 2.6.36-rc6: WARNING: at drivers/gpu/drm/radeon/radeon_fence.c:235 radeon_fence_wait+0x35a/0x3c0
Submitter : Alexey Dobriyan <adobriyan@gmail.com>
Date : 2010-09-29 21:29 (68 days old)
Message-ID : <20100929212923.GA5578@core2.telecom.by>
References : http://marc.info/?l=linux-kernel&m=128579579400315&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19142
Subject : Screen flickers when switching from the console to X
Submitter : Andrey Rahmatullin <wrar@wrar.name>
Date : 2010-09-27 12:05 (70 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19052
Subject : 2.6.36-rc5-git1 -- [drm:i915_report_and_clear_eir] *ERROR* EIR stuck: 0x00000010, masking
Submitter : Miles Lane <miles.lane@gmail.com>
Date : 2010-09-22 23:47 (75 days old)
Message-ID : <AANLkTikWQjUQjFJU9MO1+XbSLAEE-GARz+S+Dz2Fgu4h@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128519926626322&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=19002
Subject : Radeon rv730 AGP/KMS/DRM kernel lockup
Submitter : Duncan <1i5t5.duncan@cox.net>
Date : 2010-09-23 16:48 (74 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=17121
Subject : Two blank rectangles more than 10 cm long when booting
Submitter : Eric Valette <eric.valette@free.fr>
Date : 2010-08-26 17:24 (102 days old)
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=17061
Subject : 2.6.36-rc1 on zaurus: bluetooth regression
Submitter : Pavel Machek <pavel@ucw.cz>
Date : 2010-08-21 15:24 (107 days old)
Message-ID : <20100821152445.GA1536@ucw.cz>
References : http://marc.info/?l=linux-kernel&m=128240433828087&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=16971
Subject : qla4xxx compile failure on 32-bit PowerPC: missing readq and writeq
Submitter : Meelis Roos <mroos@linux.ee>
Date : 2010-08-19 21:03 (109 days old)
Message-ID : <<<alpine.SOC.1.00.1008192359310.19654@math.ut.ee>>>
References : http://marc.info/?l=linux-kernel&m=128225184900892&w=2
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=16951
Subject : hackbench regression with 2.6.36-rc1
Submitter : Zhang, Yanmin <yanmin_zhang@linux.intel.com>
Date : 2010-08-18 6:18 (110 days old)
Message-ID : <1282112318.21202.8.camel@ymzhang.sh.intel.com>
References : http://marc.info/?l=linux-kernel&m=128211235904910&w=2
Regressions with patches
------------------------
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=21092
Subject : Kernel 2.6.36 Bug during quotaon on reiserfs
Submitter : <markus.gapp@gmx.net>
Date : 2010-10-24 16:57 (43 days old)
Handled-By : Jan Kara <jack@suse.cz>
Patch : https://bugzilla.kernel.org/attachment.cgi?id=35292
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20462
Subject : 2.6.36-rc7-git2 - panic/GPF: e1000e/vlans?
Submitter : Nikola Ciprich <extmaillist@linuxbox.cz>
Date : 2010-10-15 7:10 (52 days old)
Message-ID : <20101015071008.GA8714@pcnci.linuxbox.cz>
References : http://marc.info/?l=linux-kernel&m=128712984831303&w=2
Handled-By : Jesse Gross <jesse@nicira.com>
Patch : http://www.spinics.net/lists/netdev/msg146227.html
Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=20162
Subject : [LogFS][2.6.36.rc7+] Kernel BUG at readwrite.c:1193
Submitter : Prasad Joshi <prasadjoshi124@gmail.com>
Date : 2010-10-10 17:44 (57 days old)
Message-ID : <AANLkTi=JkcuWBPo+X-i+9o-BJFVqjea1J3e=Mr=HvAWF@mail.gmail.com>
References : http://marc.info/?l=linux-kernel&m=128673196203340&w=2
Handled-By : Prasad Gajanan Joshi <prasadjoshi124@gmail.com>
Patch : https://bugzilla.kernel.org/show_bug.cgi?id=20162#c1
For details, please visit the bug entries and follow the links given in
references.
As you can see, there is a Bugzilla entry for each of the listed regressions.
There also is a Bugzilla entry used for tracking the regressions introduced
between 2.6.35 and 2.6.36, unresolved as well as resolved, at:
http://bugzilla.kernel.org/show_bug.cgi?id=16444
Please let the tracking team know if there are any Bugzilla entries that
should be added to the list in there.
Thanks!
_______________________________________________
stable mailing list
stable@linux.kernel.org
http://linux.kernel.org/mailman/listinfo/stable
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: Jarek Poplawski @ 2010-12-05 19:09 UTC (permalink / raw)
To: jamal; +Cc: Changli Gao, netdev
In-Reply-To: <1291559231.2159.684.camel@mojatatu>
On Sun, Dec 05, 2010 at 09:27:11AM -0500, jamal wrote:
...
> PS:- We forgot to thank Jarek for pointing out the bug.
Not at all! I only pointed out that Changli didn't point out ;-)
All credits go to him and you for pointing out the appropriate fix.
Cheers,
Jarek P.
^ permalink raw reply
* Re: Question about __alloc_skb() speedup
From: Eric Dumazet @ 2010-12-05 16:49 UTC (permalink / raw)
To: Junchang Wang; +Cc: netdev
In-Reply-To: <20101205105616.GA4770@Desktop-Junchang>
Le dimanche 05 décembre 2010 à 18:56 +0800, Junchang Wang a écrit :
> On Sat, Dec 04, 2010 at 03:47:38PM +0100, Eric Dumazet wrote:
> >
> >Yes I believe so, pktgen being very specific, but I have few questions :
> >
> >Is it with SLUB or SLAB ?
> I had read your discussion about "net: allocate skbs on local node" in
> the list, so SLUB was used.
>
> BTW, what I observed is that network subsystem scales well on NUMA
> systems equipped with a single processor(up to six cores), but the
> performance didn't scale very well if there are two processors.
>
> I have noticed there are a number of discussions in the list. Are
> there any suggestions? I'm very pleasant to do test.
>
> >
> >How many buffers in TX ring on you nic (ethtool -g eth0) ?
> >
> Pre-set maximums:
> RX: 4096
> RX Mini: 0
> RX Jumbo: 0
> TX: 4096
> Current hardware settings:
> RX: 512
> RX Mini: 0
> RX Jumbo: 0
> TX: 512
>
> >What is the datalen value here ? (you prefetch, then advance skb->data)
> >
> 16. But the following skb_push will drawback 14 bytes.
>
> >32 or 64bit kernel ?
> >
> This is a CentOS 5.5 - 64bit distribution with the latest net-next.
>
> >How many pps do you get before and after patch ?
> >
> A Intel SR1625 server with two E5530 quad-core processors and a single
> ixgbe-based NIC.
> Without prefetch: 8.63 Mpps
> With prefetch: 9.03 Mpps
> Improvement: 4.6%
>
>
Thanks Junchang, please submit your pktgen patch with the two added
prefetchw(), I'll Ack it :)
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: jamal @ 2010-12-05 15:31 UTC (permalink / raw)
To: Changli Gao; +Cc: Jarek Poplawski, netdev
In-Reply-To: <AANLkTimLd=d94Cnh8dsX8HFFeYM4mBGH1gpK+p3YT-hm@mail.gmail.com>
On Sun, 2010-12-05 at 23:22 +0800, Changli Gao wrote:
> The current implementation can guarantee it. However, I can't find
> documentation about this 'feature', but I think this behavior should
> not be changed in future since maybe some call sites relay on it.
When you think you are in good shape - please add some debug hooks
so we can verify this especially under a huge traffic input and
I will test it (thats what end of year holidays are for).
cheers,
jamal
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: Changli Gao @ 2010-12-05 15:22 UTC (permalink / raw)
To: hadi; +Cc: Jarek Poplawski, netdev
In-Reply-To: <1291562028.2159.692.camel@mojatatu>
On Sun, Dec 5, 2010 at 11:13 PM, jamal <hadi@cyberus.ca> wrote:
> On Sun, 2010-12-05 at 22:40 +0800, Changli Gao wrote:
>> On Sun, Dec 5, 2010 at 10:30 PM, jamal <hadi@cyberus.ca> wrote:
>
>> > - we use tasklets. When we reschedule we can end up on a differrent
>> > cpu.
>>
>> The tasklets always been scheduled to the current CPU unless it has
>> been schedule already on the other CPU.
>
> I dont think this can be guaranteed - So the potential of packet
> reordering exists.
>
The current implementation can guarantee it. However, I can't find
documentation about this 'feature', but I think this behavior should
not be changed in future since maybe some call sites relay on it.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: Changli Gao @ 2010-12-05 15:16 UTC (permalink / raw)
To: Eric Dumazet; +Cc: hadi, Jarek Poplawski, netdev
In-Reply-To: <1291562016.2806.257.camel@edumazet-laptop>
On Sun, Dec 5, 2010 at 11:13 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le dimanche 05 décembre 2010 à 22:40 +0800, Changli Gao a écrit :
>> On Sun, Dec 5, 2010 at 10:30 PM, jamal <hadi@cyberus.ca> wrote:
>> > On Sun, 2010-12-05 at 09:13 +0800, Changli Gao wrote:
>> >
>> >> BTW: My ultimate goal is making ifb a multi-queue NIC, and the number
>> >> of queues is equal to the number of the possible CPUs.
>> >
>> >
>> > My view is this is going to be tricky because:
>> > - we use tasklets. When we reschedule we can end up on a differrent
>> > cpu.
>>
>> The tasklets always been scheduled to the current CPU unless it has
>> been schedule already on the other CPU.
>>
>> > -I dont see any point in having a separate softIRQ
>> > - and if you do use other mechanisms it would require a lot more
>> > testing since there are quiet a few use cases of ifb
>> >
>>
>> I keep using tasklet. The attachment is the alpha version.
>>
>
> for_each_possible_cpu(cpu) {
> q = per_cpu_ptr(p->q, cpu);
> ...
>
> dev_ifb = alloc_netdev_mq(sizeof(struct ifb_private), "ifb%d",
> ifb_setup, num_possible_cpus());
>
> This is a very usual error.
>
> You can have machines with 2 possibles cpus, numbered 0 and 8
>
> Therere, you must use nr_cpu_ids here instead of num_possible_cpus()
>
Thanks.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: jamal @ 2010-12-05 15:13 UTC (permalink / raw)
To: Changli Gao; +Cc: Jarek Poplawski, netdev
In-Reply-To: <AANLkTimXDTTNcrFPngzEuoDGVgojtBxUZQPOMiSA7yNw@mail.gmail.com>
On Sun, 2010-12-05 at 22:40 +0800, Changli Gao wrote:
> On Sun, Dec 5, 2010 at 10:30 PM, jamal <hadi@cyberus.ca> wrote:
> > - we use tasklets. When we reschedule we can end up on a differrent
> > cpu.
>
> The tasklets always been scheduled to the current CPU unless it has
> been schedule already on the other CPU.
I dont think this can be guaranteed - So the potential of packet
reordering exists.
> I keep using tasklet. The attachment is the alpha version.
>From quick glance I dont see any technicalities - just the
reordering concern.
cheers,
jamal
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: Eric Dumazet @ 2010-12-05 15:13 UTC (permalink / raw)
To: Changli Gao; +Cc: hadi, Jarek Poplawski, netdev
In-Reply-To: <AANLkTimXDTTNcrFPngzEuoDGVgojtBxUZQPOMiSA7yNw@mail.gmail.com>
Le dimanche 05 décembre 2010 à 22:40 +0800, Changli Gao a écrit :
> On Sun, Dec 5, 2010 at 10:30 PM, jamal <hadi@cyberus.ca> wrote:
> > On Sun, 2010-12-05 at 09:13 +0800, Changli Gao wrote:
> >
> >> BTW: My ultimate goal is making ifb a multi-queue NIC, and the number
> >> of queues is equal to the number of the possible CPUs.
> >
> >
> > My view is this is going to be tricky because:
> > - we use tasklets. When we reschedule we can end up on a differrent
> > cpu.
>
> The tasklets always been scheduled to the current CPU unless it has
> been schedule already on the other CPU.
>
> > -I dont see any point in having a separate softIRQ
> > - and if you do use other mechanisms it would require a lot more
> > testing since there are quiet a few use cases of ifb
> >
>
> I keep using tasklet. The attachment is the alpha version.
>
for_each_possible_cpu(cpu) {
q = per_cpu_ptr(p->q, cpu);
...
dev_ifb = alloc_netdev_mq(sizeof(struct ifb_private), "ifb%d",
ifb_setup, num_possible_cpus());
This is a very usual error.
You can have machines with 2 possibles cpus, numbered 0 and 8
Therere, you must use nr_cpu_ids here instead of num_possible_cpus()
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: Changli Gao @ 2010-12-05 14:40 UTC (permalink / raw)
To: hadi; +Cc: Jarek Poplawski, netdev
In-Reply-To: <1291559402.2159.687.camel@mojatatu>
[-- Attachment #1: Type: text/plain, Size: 800 bytes --]
On Sun, Dec 5, 2010 at 10:30 PM, jamal <hadi@cyberus.ca> wrote:
> On Sun, 2010-12-05 at 09:13 +0800, Changli Gao wrote:
>
>> BTW: My ultimate goal is making ifb a multi-queue NIC, and the number
>> of queues is equal to the number of the possible CPUs.
>
>
> My view is this is going to be tricky because:
> - we use tasklets. When we reschedule we can end up on a differrent
> cpu.
The tasklets always been scheduled to the current CPU unless it has
been schedule already on the other CPU.
> -I dont see any point in having a separate softIRQ
> - and if you do use other mechanisms it would require a lot more
> testing since there are quiet a few use cases of ifb
>
I keep using tasklet. The attachment is the alpha version.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
[-- Attachment #2: ifb.c --]
[-- Type: text/x-csrc, Size: 7698 bytes --]
/* drivers/net/ifb.c:
The purpose of this driver is to provide a device that allows
for sharing of resources:
1) qdiscs/policies that are per device as opposed to system wide.
ifb allows for a device which can be redirected to thus providing
an impression of sharing.
2) Allows for queueing incoming traffic for shaping instead of
dropping.
The original concept is based on what is known as the IMQ
driver initially written by Martin Devera, later rewritten
by Patrick McHardy and then maintained by Andre Correa.
You need the tc action mirror or redirect to feed this device
packets.
This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; either version
2 of the License, or (at your option) any later version.
Authors: Jamal Hadi Salim (2005)
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
#define TX_Q_LIMIT 32
struct ifb_q_private {
struct tasklet_struct ifb_tasklet;
struct sk_buff_head rq;
struct u64_stats_sync syncp;
u64 rx_packets;
u64 rx_bytes;
u64 rx_dropped;
};
struct ifb_private {
struct ifb_q_private __percpu *q;
};
static int numifbs = 2;
static void ri_tasklet(unsigned long _dev)
{
struct net_device *dev = (struct net_device *)_dev;
struct ifb_private *p = netdev_priv(dev);
struct ifb_q_private *qp;
struct netdev_queue *txq;
struct sk_buff *skb;
struct sk_buff_head tq;
__skb_queue_head_init(&tq);
txq = netdev_get_tx_queue(dev, raw_smp_processor_id());
qp = per_cpu_ptr(p->q, raw_smp_processor_id());
if (!__netif_tx_trylock(txq)) {
tasklet_schedule(&qp->ifb_tasklet);
return;
}
skb_queue_splice_tail_init(&qp->rq, &tq);
if (netif_tx_queue_stopped(txq))
netif_tx_wake_queue(txq);
__netif_tx_unlock(txq);
while ((skb = __skb_dequeue(&tq)) != NULL) {
u32 from = G_TC_FROM(skb->tc_verd);
skb->tc_verd = 0;
skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
u64_stats_update_begin(&qp->syncp);
txq->tx_packets++;
txq->tx_bytes += skb->len;
rcu_read_lock();
skb->dev = dev_get_by_index_rcu(&init_net, skb->skb_iif);
if (!skb->dev) {
rcu_read_unlock();
txq->tx_dropped++;
u64_stats_update_end(&qp->syncp);
dev_kfree_skb(skb);
continue;
}
rcu_read_unlock();
u64_stats_update_end(&qp->syncp);
skb->skb_iif = dev->ifindex;
if (from & AT_EGRESS) {
dev_queue_xmit(skb);
} else if (from & AT_INGRESS) {
skb_pull(skb, skb->dev->hard_header_len);
netif_rx(skb);
} else
BUG();
}
}
static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ifb_private *p = netdev_priv(dev);
struct ifb_q_private *qp = per_cpu_ptr(p->q,
skb_get_queue_mapping(skb));
u32 from = G_TC_FROM(skb->tc_verd);
u64_stats_update_begin(&qp->syncp);
qp->rx_packets++;
qp->rx_bytes += skb->len;
if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->skb_iif) {
qp->rx_dropped++;
u64_stats_update_end(&qp->syncp);
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
u64_stats_update_end(&qp->syncp);
__skb_queue_tail(&qp->rq, skb);
if (skb_queue_len(&qp->rq) == 1)
tasklet_schedule(&qp->ifb_tasklet);
if (skb_queue_len(&qp->rq) >= dev->tx_queue_len)
netif_stop_queue(dev);
return NETDEV_TX_OK;
}
static int ifb_close(struct net_device *dev)
{
struct ifb_private *p = netdev_priv(dev);
struct ifb_q_private *qp;
int cpu;
for_each_possible_cpu(cpu) {
qp = per_cpu_ptr(p->q, cpu);
tasklet_kill(&qp->ifb_tasklet);
netif_tx_stop_queue(netdev_get_tx_queue(dev, cpu));
__skb_queue_purge(&qp->rq);
}
return 0;
}
static int ifb_open(struct net_device *dev)
{
int cpu;
for_each_possible_cpu(cpu)
netif_tx_start_queue(netdev_get_tx_queue(dev, cpu));
return 0;
}
static int ifb_init(struct net_device *dev)
{
struct ifb_private *p = netdev_priv(dev);
struct ifb_q_private *q;
int cpu;
p->q = alloc_percpu(struct ifb_q_private);
if (!p->q)
return -ENOMEM;
for_each_possible_cpu(cpu) {
q = per_cpu_ptr(p->q, cpu);
tasklet_init(&q->ifb_tasklet, ri_tasklet, (unsigned long)dev);
__skb_queue_head_init(&q->rq);
}
return 0;
}
static void ifb_uninit(struct net_device *dev)
{
struct ifb_private *p = netdev_priv(dev);
free_percpu(p->q);
}
static u16 ifb_select_queue(struct net_device *dev, struct sk_buff *skb)
{
return smp_processor_id();
}
static struct rtnl_link_stats64 *ifb_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct ifb_private *p = netdev_priv(dev);
struct ifb_q_private *q;
struct netdev_queue *txq;
int cpu;
u64 rx_packets, rx_bytes, rx_dropped;
u64 tx_packets, tx_bytes, tx_dropped;
unsigned int start;
for_each_possible_cpu(cpu) {
q = per_cpu_ptr(p->q, cpu);
txq = netdev_get_tx_queue(dev, cpu);
do {
start = u64_stats_fetch_begin_bh(&q->syncp);
rx_packets = q->rx_packets;
rx_bytes = q->rx_bytes;
rx_dropped = q->rx_dropped;
tx_packets = txq->tx_packets;
tx_bytes = txq->tx_bytes;
tx_dropped = txq->tx_dropped;
} while (u64_stats_fetch_retry_bh(&q->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
stats->rx_dropped += rx_dropped;
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
stats->tx_dropped += tx_dropped;
}
return stats;
}
static const struct net_device_ops ifb_netdev_ops = {
.ndo_init = ifb_init,
.ndo_uninit = ifb_uninit,
.ndo_open = ifb_open,
.ndo_stop = ifb_close,
.ndo_start_xmit = ifb_xmit,
.ndo_validate_addr = eth_validate_addr,
.ndo_select_queue = ifb_select_queue,
.ndo_get_stats64 = ifb_get_stats64,
};
static void ifb_setup(struct net_device *dev)
{
/* Initialize the device structure. */
dev->destructor = free_netdev;
dev->netdev_ops = &ifb_netdev_ops;
/* Fill in device structure with ethernet-generic values. */
ether_setup(dev);
dev->tx_queue_len = TX_Q_LIMIT;
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
random_ether_addr(dev->dev_addr);
}
static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
return 0;
}
static struct rtnl_link_ops ifb_link_ops __read_mostly = {
.kind = "ifb",
.priv_size = sizeof(struct ifb_private),
.setup = ifb_setup,
.validate = ifb_validate,
};
/* Number of ifb devices to be set up by this module. */
module_param(numifbs, int, 0);
MODULE_PARM_DESC(numifbs, "Number of ifb devices");
static int __init ifb_init_one(int index)
{
struct net_device *dev_ifb;
int err;
dev_ifb = alloc_netdev_mq(sizeof(struct ifb_private), "ifb%d",
ifb_setup, num_possible_cpus());
if (!dev_ifb)
return -ENOMEM;
err = dev_alloc_name(dev_ifb, dev_ifb->name);
if (err < 0)
goto err;
dev_ifb->rtnl_link_ops = &ifb_link_ops;
err = register_netdevice(dev_ifb);
if (err < 0)
goto err;
return 0;
err:
free_netdev(dev_ifb);
return err;
}
static int __init ifb_init_module(void)
{
int i, err;
rtnl_lock();
err = __rtnl_link_register(&ifb_link_ops);
for (i = 0; i < numifbs && !err; i++)
err = ifb_init_one(i);
if (err)
__rtnl_link_unregister(&ifb_link_ops);
rtnl_unlock();
return err;
}
static void __exit ifb_cleanup_module(void)
{
rtnl_link_unregister(&ifb_link_ops);
}
module_init(ifb_init_module);
module_exit(ifb_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jamal Hadi Salim");
MODULE_ALIAS_RTNL_LINK("ifb");
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: jamal @ 2010-12-05 14:30 UTC (permalink / raw)
To: Changli Gao; +Cc: Jarek Poplawski, netdev
In-Reply-To: <AANLkTimMvb187gOFzZZgWuzWJkk_Z3AOZaoc6M76H-e=@mail.gmail.com>
On Sun, 2010-12-05 at 09:13 +0800, Changli Gao wrote:
> BTW: My ultimate goal is making ifb a multi-queue NIC, and the number
> of queues is equal to the number of the possible CPUs.
My view is this is going to be tricky because:
- we use tasklets. When we reschedule we can end up on a differrent
cpu.
-I dont see any point in having a separate softIRQ
- and if you do use other mechanisms it would require a lot more
testing since there are quiet a few use cases of ifb
cheers,
jamal
^ permalink raw reply
* Re: [PATCH 3/3] ifb: move tq from ifb_private
From: jamal @ 2010-12-05 14:27 UTC (permalink / raw)
To: Changli Gao; +Cc: Jarek Poplawski, netdev
In-Reply-To: <AANLkTimnejoONxGqusiYVWOKbcy2yqbpFH-XyzgG0=87@mail.gmail.com>
On Sun, 2010-12-05 at 08:22 +0800, Changli Gao wrote:
> On Sun, Dec 5, 2010 at 12:56 AM, Jarek Poplawski <jarkao2@gmail.com> wrote:
> >
> > I'm simply not convinced this kind of (fast) throttling can properly
> > fix any of the problems (what about other flows in the queue), while
> > Changli's patch makes this tasklet simpler and a bit faster.
> >
>
> The error case handled currently is the original netdev disappears but
> the corresponding skbs are still in ifb.
>
> I do also think checking the return value of netif_rx() and
> dev_queue_xmit() can fix more 'problems'. :)
Please proceed with a patch for that as well..
cheers,
jamal
PS:- We forgot to thank Jarek for pointing out the bug.
^ permalink raw reply
* Re: [PATCH 3/3 v2] ifb: use the lockless variants of skb_queue
From: jamal @ 2010-12-05 14:26 UTC (permalink / raw)
To: Changli Gao; +Cc: netdev, Jarek Poplawski
In-Reply-To: <1291510912-6979-1-git-send-email-xiaosuo@gmail.com>
On Sun, 2010-12-05 at 09:01 +0800, Changli Gao wrote:
> rq and tq are both protected by tx queue lock, so we can simply use
> the lockless variants of skb_queue.
>
> skb_queue_splice_tail_init() is used instead of the open coded and slow
> one.
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
cheers,
jamal
^ permalink raw reply
* Re: [PATCH net-2.6] ifb: goto resched directly if error happens and dp->tq isn't empty
From: jamal @ 2010-12-05 14:25 UTC (permalink / raw)
To: Changli Gao; +Cc: David S. Miller, Jarek Poplawski, netdev
In-Reply-To: <1291507748-4958-1-git-send-email-xiaosuo@gmail.com>
On Sun, 2010-12-05 at 08:09 +0800, Changli Gao wrote:
> If we break the loop when there are still skbs in tq and no skb in
> rq, the skbs will be left in txq until new skbs are enqueued into rq.
> In rare cases, no new skb is queued, then these skbs will stay in rq
> forever.
>
> After this patch, if tq isn't empty when we break the loop, we goto
> resched directly.
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Dave, this goes to stable as well.
cheers,
jamal
^ permalink raw reply
* Re: kernel panic with time-stamping in phy devices (monitor mode)
From: Eric Dumazet @ 2010-12-05 12:24 UTC (permalink / raw)
To: Andrew Watts; +Cc: Richard Cochran, netdev, David Miller, stable
In-Reply-To: <906429.41845.qm@web111015.mail.gq1.yahoo.com>
Le samedi 04 décembre 2010 à 12:46 -0800, Andrew Watts a écrit :
> Eric, I echo the thanks on the lightning patch.
> Impressive turnaround!
>
> There's an open bug report on the kernel's bugzilla
> for 2.6.36 (#24102). What is the best way to tie these
> together?
Thanks Andy, here is the official patch submission I am going to make.
[PATCH net-2.6] net: fix skb_defer_rx_timestamp()
After commit c1f19b51d1d8 (net: support time stamping in phy devices.),
kernel might crash if CONFIG_NETWORK_PHY_TIMESTAMPING=y and
skb_defer_rx_timestamp() handles a packet without an ethernet header.
Fixes kernel bugzilla #24102
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=24102
Reported-and-tested-by: Andrew Watts <akwatts@ymail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: stable@kernel.org
---
net/core/timestamping.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 0ae6c22..c4fbf85 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -96,11 +96,13 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
struct phy_device *phydev;
unsigned int type;
- skb_push(skb, ETH_HLEN);
+ if (skb->data - ETH_HLEN < skb->head)
+ return false;
+ __skb_push(skb, ETH_HLEN);
type = classify(skb);
- skb_pull(skb, ETH_HLEN);
+ __skb_pull(skb, ETH_HLEN);
switch (type) {
case PTP_CLASS_V1_IPV4:
^ permalink raw reply related
* [PATCH net-2.6] llc: fix a device refcount imbalance
From: Eric Dumazet @ 2010-12-05 12:03 UTC (permalink / raw)
To: Maxim Levitsky, David Miller
Cc: linux1394-devel, Stefan Richter, netdev, Alexey Kuznetsov,
James Morris, Patrick McHardy, Octavian Purdila, stable
In-Reply-To: <1291548233.2806.212.camel@edumazet-laptop>
Le dimanche 05 décembre 2010 à 12:23 +0100, Eric Dumazet a écrit :
> Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit :
>
> > Hmm..
> >
> > If somebody can explain why RTNL is held in arp_ioctl() (and therefore
> > in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
> > that your patch can be applied.
> >
> > Right now it is not good, because RTNL wont be necessarly held when you
> > are going to call arp_invalidate() ?
>
> While doing this analysis, I found a refcount bug in llc, I'll send a
> patch for net-2.6
Oh well, of course I must first fix the bug in net-2.6, and wait David
pull the fix in net-next-2.6 before sending this rcu conversion.
Note: this patch should be sent to stable teams (2.6.34 and up)
[PATCH net-2.6] llc: fix a device refcount imbalance
commit abf9d537fea225 (llc: add support for SO_BINDTODEVICE) added one
refcount imbalance in llc_ui_bind(), because dev_getbyhwaddr() doesnt
take a reference on device, while dev_get_by_index() does.
Fix this using RCU locking. And since an RCU conversion will be done for
2.6.38 for dev_getbyhwaddr(), put the rcu_read_lock/unlock exactly at
their final place.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: stable@kernel.org
Cc: Octavian Purdila <opurdila@ixiacom.com>
---
net/llc/af_llc.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 5826129..e35dbe5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -317,8 +317,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
goto out;
rc = -ENODEV;
rtnl_lock();
+ rcu_read_lock();
if (sk->sk_bound_dev_if) {
- llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+ llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
if (llc->dev) {
if (!addr->sllc_arphrd)
addr->sllc_arphrd = llc->dev->type;
@@ -329,13 +330,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
!llc_mac_match(addr->sllc_mac,
llc->dev->dev_addr)) {
rc = -EINVAL;
- dev_put(llc->dev);
llc->dev = NULL;
}
}
} else
llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd,
addr->sllc_mac);
+ rcu_read_unlock();
rtnl_unlock();
if (!llc->dev)
goto out;
^ permalink raw reply related
* [PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl()
From: Eric Dumazet @ 2010-12-05 11:23 UTC (permalink / raw)
To: Maxim Levitsky
Cc: linux1394-devel, Stefan Richter, netdev, David S. Miller,
Alexey Kuznetsov, James Morris, Patrick McHardy
In-Reply-To: <1291537161.2806.109.camel@edumazet-laptop>
Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit :
> Hmm..
>
> If somebody can explain why RTNL is held in arp_ioctl() (and therefore
> in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
> that your patch can be applied.
>
> Right now it is not good, because RTNL wont be necessarly held when you
> are going to call arp_invalidate() ?
While doing this analysis, I found a refcount bug in llc, I'll send a
patch for net-2.6
Meanwhile, here is the patch for net-next-2.6
Your patch then can be applied after mine.
Thanks
[PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl()
dev_getbyhwaddr() was called under RTNL.
Rename it to dev_getbyhwaddr_rcu() and change all its caller to now use
RCU locking instead of RTNL.
Change arp_ioctl() to use RCU instead of RTNL locking.
Note: this fix a dev refcount bug in llc
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/linux/netdevice.h | 3 ++-
net/core/dev.c | 17 +++++++----------
net/ieee802154/af_ieee802154.c | 6 +++---
net/ipv4/arp.c | 17 +++++++++--------
net/llc/af_llc.c | 11 ++++++-----
5 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a9ac5dc..d31bc3c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1360,7 +1360,8 @@ static inline struct net_device *first_net_device(struct net *net)
extern int netdev_boot_setup_check(struct net_device *dev);
extern unsigned long netdev_boot_base(const char *prefix, int unit);
-extern struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr);
+extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
+ const char *hwaddr);
extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
extern void dev_add_pack(struct packet_type *pt);
diff --git a/net/core/dev.c b/net/core/dev.c
index cd24374..8630142 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -743,34 +743,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
EXPORT_SYMBOL(dev_get_by_index);
/**
- * dev_getbyhwaddr - find a device by its hardware address
+ * dev_getbyhwaddr_rcu - find a device by its hardware address
* @net: the applicable net namespace
* @type: media type of device
* @ha: hardware address
*
* Search for an interface by MAC address. Returns NULL if the device
- * is not found or a pointer to the device. The caller must hold the
- * rtnl semaphore. The returned device has not had its ref count increased
+ * is not found or a pointer to the device. The caller must hold RCU
+ * The returned device has not had its ref count increased
* and the caller must therefore be careful about locking
*
- * BUGS:
- * If the API was consistent this would be __dev_get_by_hwaddr
*/
-struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha)
+struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
+ const char *ha)
{
struct net_device *dev;
- ASSERT_RTNL();
-
- for_each_netdev(net, dev)
+ for_each_netdev_rcu(net, dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
return dev;
return NULL;
}
-EXPORT_SYMBOL(dev_getbyhwaddr);
+EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
index 93c91b6..6df6ecf 100644
--- a/net/ieee802154/af_ieee802154.c
+++ b/net/ieee802154/af_ieee802154.c
@@ -52,11 +52,11 @@ struct net_device *ieee802154_get_dev(struct net *net,
switch (addr->addr_type) {
case IEEE802154_ADDR_LONG:
- rtnl_lock();
- dev = dev_getbyhwaddr(net, ARPHRD_IEEE802154, addr->hwaddr);
+ rcu_read_lock();
+ dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr);
if (dev)
dev_hold(dev);
- rtnl_unlock();
+ rcu_read_unlock();
break;
case IEEE802154_ADDR_SHORT:
if (addr->pan_id == 0xffff ||
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7833f17..ec0966f 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1017,13 +1017,14 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on)
IPV4_DEVCONF_ALL(net, PROXY_ARP) = on;
return 0;
}
- if (__in_dev_get_rtnl(dev)) {
- IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on);
+ if (__in_dev_get_rcu(dev)) {
+ IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on);
return 0;
}
return -ENXIO;
}
+/* must be called with rcu_read_lock() */
static int arp_req_set_public(struct net *net, struct arpreq *r,
struct net_device *dev)
{
@@ -1033,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
if (mask && mask != htonl(0xFFFFFFFF))
return -EINVAL;
if (!dev && (r->arp_flags & ATF_COM)) {
- dev = dev_getbyhwaddr(net, r->arp_ha.sa_family,
+ dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family,
r->arp_ha.sa_data);
if (!dev)
return -ENODEV;
@@ -1225,10 +1226,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (!(r.arp_flags & ATF_NETMASK))
((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr =
htonl(0xFFFFFFFFUL);
- rtnl_lock();
+ rcu_read_lock();
if (r.arp_dev[0]) {
err = -ENODEV;
- dev = __dev_get_by_name(net, r.arp_dev);
+ dev = dev_get_by_name_rcu(net, r.arp_dev);
if (dev == NULL)
goto out;
@@ -1252,12 +1253,12 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
break;
case SIOCGARP:
err = arp_req_get(&r, dev);
- if (!err && copy_to_user(arg, &r, sizeof(r)))
- err = -EFAULT;
break;
}
out:
- rtnl_unlock();
+ rcu_read_unlock();
+ if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r)))
+ err = -EFAULT;
return err;
}
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 5826129..dfd3a64 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -316,9 +316,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
if (unlikely(addr->sllc_family != AF_LLC))
goto out;
rc = -ENODEV;
- rtnl_lock();
+ rcu_read_lock();
if (sk->sk_bound_dev_if) {
- llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+ llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
if (llc->dev) {
if (!addr->sllc_arphrd)
addr->sllc_arphrd = llc->dev->type;
@@ -329,14 +329,15 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
!llc_mac_match(addr->sllc_mac,
llc->dev->dev_addr)) {
rc = -EINVAL;
- dev_put(llc->dev);
llc->dev = NULL;
}
}
} else
- llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd,
+ llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
addr->sllc_mac);
- rtnl_unlock();
+ if (llc->dev)
+ dev_hold(llc->dev);
+ rcu_read_unlock();
if (!llc->dev)
goto out;
if (!addr->sllc_sap) {
^ permalink raw reply related
* Re: Question about __alloc_skb() speedup
From: Junchang Wang @ 2010-12-05 10:56 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev
In-Reply-To: <1291474058.2806.96.camel@edumazet-laptop>
On Sat, Dec 04, 2010 at 03:47:38PM +0100, Eric Dumazet wrote:
>
>Yes I believe so, pktgen being very specific, but I have few questions :
>
>Is it with SLUB or SLAB ?
I had read your discussion about "net: allocate skbs on local node" in
the list, so SLUB was used.
BTW, what I observed is that network subsystem scales well on NUMA
systems equipped with a single processor(up to six cores), but the
performance didn't scale very well if there are two processors.
I have noticed there are a number of discussions in the list. Are
there any suggestions? I'm very pleasant to do test.
>
>How many buffers in TX ring on you nic (ethtool -g eth0) ?
>
Pre-set maximums:
RX: 4096
RX Mini: 0
RX Jumbo: 0
TX: 4096
Current hardware settings:
RX: 512
RX Mini: 0
RX Jumbo: 0
TX: 512
>What is the datalen value here ? (you prefetch, then advance skb->data)
>
16. But the following skb_push will drawback 14 bytes.
>32 or 64bit kernel ?
>
This is a CentOS 5.5 - 64bit distribution with the latest net-next.
>How many pps do you get before and after patch ?
>
A Intel SR1625 server with two E5530 quad-core processors and a single
ixgbe-based NIC.
Without prefetch: 8.63 Mpps
With prefetch: 9.03 Mpps
Improvement: 4.6%
Thanks.
--Junchang
^ permalink raw reply
* Re: [PATCH 2.6.36] vlan: Avoid hwaccel vlan packets when vid not used
From: Michael Leun @ 2010-12-05 9:55 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, Ben Greear, linux-kernel, netdev, Jesse Gross,
stable
In-Reply-To: <1291536233.2806.102.camel@edumazet-laptop>
On Sun, 05 Dec 2010 09:03:53 +0100
Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > But on
> >
> > hpdl320g5:/home/ml # lspci | grep Eth
> > 03:04.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5714
> > Gigabit Ethernet (rev a3) 03:04.1 Ethernet controller: Broadcom
> > Corporation NetXtreme BCM5714 Gigabit Ethernet (rev a3)
> >
> > the good message is that it also does not crash, but with tcpdump I
> > see vlan tags when no vlan devices configured on the respective
> > eth, if so I do not see tags anymore vlan tags on the trunk
> > interface.
> >
>
> For all these very specific needs, you'll have to try 2.6.37 I am
> afraid. Jesse did huge changes to exactly make this working, we wont
> backport this to 2.6.36, but only avoid crashes.
OK, I'm perfectly fine with that, of course, actually nice to hear that
the issue already is addressed.
Likely I'll give some rc an shot on this machine (maybe over christmas),
but it is an production machine (acutally testing other devices is the
"product" produced on this machine), so unfortunately I'm not that free
in when and what I can do (but the possibility to, for example, bridge
the trunk interface would make testing easier, that justifies
something...).
Thank you all very much for your work.
--
MfG,
Michael Leun
^ permalink raw reply
* Re: [PATCH 3/5] NET: IPV4: ARP: allow to invalidate specific ARP entries
From: Eric Dumazet @ 2010-12-05 8:19 UTC (permalink / raw)
To: Maxim Levitsky
Cc: linux1394-devel, Stefan Richter, netdev, David S. Miller,
Alexey Kuznetsov, James Morris, Patrick McHardy
In-Reply-To: <1291504514.1874.92.camel@maxim-laptop>
Le dimanche 05 décembre 2010 à 01:15 +0200, Maxim Levitsky a écrit :
> On Mon, 2010-11-29 at 04:09 +0200, Maxim Levitsky wrote:
> > IPv4 over firewire needs to be able to remove ARP entries
> > from the ARP cache that belong to nodes that are removed, because
> > IPv4 over firewire uses ARP packets for private information
> > about nodes.
> >
> > This information becomes invalid as soon as node drops
> > off the bus and when it reconnects, its only possible
> > to start takling to is after it responded to an ARP packet.
> > But ARP cache prevents such packets from being sent.
> >
> > CC: netdev@vger.kernel.org
> > CC: "David S. Miller" <davem@davemloft.net>
> > CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
> > CC: James Morris <jmorris@namei.org>
> > CC: Patrick McHardy <kaber@trash.net>
>
> Anybody?
>
> Best regards,
> Maxim Levitsky
> >
> >
> > Signed-off-by: Maxim Levitsky <maximlevitsky@gmail.com>
> > ---
> > include/net/arp.h | 1 +
> > net/ipv4/arp.c | 29 ++++++++++++++++++-----------
> > 2 files changed, 19 insertions(+), 11 deletions(-)
> >
> > diff --git a/include/net/arp.h b/include/net/arp.h
> > index f4cf6ce..91f0568 100644
> > --- a/include/net/arp.h
> > +++ b/include/net/arp.h
> > @@ -25,5 +25,6 @@ extern struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
> > const unsigned char *src_hw,
> > const unsigned char *target_hw);
> > extern void arp_xmit(struct sk_buff *skb);
> > +int arp_invalidate(struct net_device *dev, __be32 ip);
> >
> > #endif /* _ARP_H */
> > diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
> > index d8e540c..35b1272 100644
> > --- a/net/ipv4/arp.c
> > +++ b/net/ipv4/arp.c
> > @@ -1142,6 +1142,23 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
> > return err;
> > }
> >
> > +int arp_invalidate(struct net_device *dev, __be32 ip)
> > +{
> > + int err = -ENXIO;
> > + struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
> > +
> > + if (neigh) {
> > + if (neigh->nud_state & ~NUD_NOARP)
> > + err = neigh_update(neigh, NULL, NUD_FAILED,
> > + NEIGH_UPDATE_F_OVERRIDE|
> > + NEIGH_UPDATE_F_ADMIN);
> > + neigh_release(neigh);
> > + }
> > +
> > + return err;
> > +}
> > +EXPORT_SYMBOL(arp_invalidate);
> > +
> > static int arp_req_delete_public(struct net *net, struct arpreq *r,
> > struct net_device *dev)
> > {
> > @@ -1162,7 +1179,6 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
> > {
> > int err;
> > __be32 ip;
> > - struct neighbour *neigh;
> >
> > if (r->arp_flags & ATF_PUBL)
> > return arp_req_delete_public(net, r, dev);
> > @@ -1180,16 +1196,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
> > if (!dev)
> > return -EINVAL;
> > }
> > - err = -ENXIO;
> > - neigh = neigh_lookup(&arp_tbl, &ip, dev);
> > - if (neigh) {
> > - if (neigh->nud_state & ~NUD_NOARP)
> > - err = neigh_update(neigh, NULL, NUD_FAILED,
> > - NEIGH_UPDATE_F_OVERRIDE|
> > - NEIGH_UPDATE_F_ADMIN);
> > - neigh_release(neigh);
> > - }
> > - return err;
> > + return arp_invalidate(dev, ip);
> > }
> >
> > /*
>
Hmm..
If somebody can explain why RTNL is held in arp_ioctl() (and therefore
in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
that your patch can be applied.
Right now it is not good, because RTNL wont be necessarly held when you
are going to call arp_invalidate() ?
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox