* Re: [PATCH net] mscan: zero accidentally copied register content
From: Marc Kleine-Budde @ 2011-10-06 18:25 UTC (permalink / raw)
To: Oliver Hartkopp
Cc: Wolfgang Grandegger, Wolfram Sang, Linux Netdev List,
Andre Naujoks
In-Reply-To: <4E8C78E8.3010605@hartkopp.net>
[-- Attachment #1: Type: text/plain, Size: 896 bytes --]
On 10/05/2011 05:34 PM, Oliver Hartkopp wrote:
> Due to the 16 bit access to mscan registers there's too much data copied to
> the zero initialized CAN frame when having an odd number of bytes to copy.
> This patch clears the data byte read from the invalid register entry.
>
> Reported-by: Andre Naujoks <nautsch@gmail.com>
> Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
This problem have some other drivers, too, e.g. the at91 and the flexcan
driver both copy unconditionally all 8 bytes from the hardware. However,
I don't know if the hardware sets the remaining bytes to zero.
cheers, Marc
--
Pengutronix e.K. | Marc Kleine-Budde |
Industrial Linux Solutions | Phone: +49-231-2826-924 |
Vertretung West/Dortmund | Fax: +49-5121-206917-5555 |
Amtsgericht Hildesheim, HRA 2686 | http://www.pengutronix.de |
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 262 bytes --]
^ permalink raw reply
* Re: [net-next 0/9][pull request] Intel Wired LAN Driver Updates
From: David Miller @ 2011-10-06 18:33 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, sassmann
In-Reply-To: <1317898959-16550-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Thu, 6 Oct 2011 04:02:30 -0700
> The following series contains updates to e1000e, igb and ixgbe. Here
> is a quick summary:
> - e1000e: fixes for 2 WoL issues
> - igb: fix for I2C, and 2 Alt. MAC address updates
> - ixgbe: fix dependencies for 8 traffic classes, add X540 traffic
> class support and a fix for PFC mask generation
>
> The following are changes since commit f0cd7bdc042310b6b104f133bbfd520a72b3c08a:
> bnx2x: remove some dead code
> and are available in the git repository at
> git://github.com/Jkirsher/net-next.git
Pulled, thanks Jeff.
^ permalink raw reply
* [net-next PATCH 1/3] dcb: Use ifindex instead of ifname
From: John Fastabend @ 2011-10-06 18:52 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, gospo
From: Mark Rustad <mark.d.rustad@intel.com>
Use ifindex instead of ifname in the DCB app ring. This makes for a smaller
data structure and faster comparisons. It also avoids possible issues when
a net device is renamed.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/net/dcbnl.h | 2 +-
net/dcb/dcbnl.c | 24 ++++++++++++------------
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index f5aa399..263aa3a 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -23,7 +23,7 @@
#include <linux/dcbnl.h>
struct dcb_app_type {
- char name[IFNAMSIZ];
+ int ifindex;
struct dcb_app app;
struct list_head list;
};
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 3cb56af..e508593 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1255,7 +1255,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
spin_lock(&dcb_lock);
list_for_each_entry(itr, &dcb_app_list, list) {
- if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) {
+ if (itr->ifindex == netdev->ifindex) {
err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app),
&itr->app);
if (err) {
@@ -1412,7 +1412,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
goto dcb_unlock;
list_for_each_entry(itr, &dcb_app_list, list) {
- if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) {
+ if (itr->ifindex == netdev->ifindex) {
struct nlattr *app_nest = nla_nest_start(skb,
DCB_ATTR_APP);
if (!app_nest)
@@ -2050,7 +2050,7 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app)
list_for_each_entry(itr, &dcb_app_list, list) {
if (itr->app.selector == app->selector &&
itr->app.protocol == app->protocol &&
- (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ itr->ifindex == dev->ifindex) {
prio = itr->app.priority;
break;
}
@@ -2073,7 +2073,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
struct dcb_app_type *itr;
struct dcb_app_type event;
- memcpy(&event.name, dev->name, sizeof(event.name));
+ event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
spin_lock(&dcb_lock);
@@ -2081,7 +2081,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
list_for_each_entry(itr, &dcb_app_list, list) {
if (itr->app.selector == new->selector &&
itr->app.protocol == new->protocol &&
- (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ itr->ifindex == dev->ifindex) {
if (new->priority)
itr->app.priority = new->priority;
else {
@@ -2101,7 +2101,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
}
memcpy(&entry->app, new, sizeof(*new));
- strncpy(entry->name, dev->name, IFNAMSIZ);
+ entry->ifindex = dev->ifindex;
list_add(&entry->list, &dcb_app_list);
}
out:
@@ -2127,7 +2127,7 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app)
list_for_each_entry(itr, &dcb_app_list, list) {
if (itr->app.selector == app->selector &&
itr->app.protocol == app->protocol &&
- (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ itr->ifindex == dev->ifindex) {
prio |= 1 << itr->app.priority;
}
}
@@ -2150,7 +2150,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
struct dcb_app_type event;
int err = 0;
- memcpy(&event.name, dev->name, sizeof(event.name));
+ event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
spin_lock(&dcb_lock);
@@ -2159,7 +2159,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
if (itr->app.selector == new->selector &&
itr->app.protocol == new->protocol &&
itr->app.priority == new->priority &&
- (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ itr->ifindex == dev->ifindex) {
err = -EEXIST;
goto out;
}
@@ -2173,7 +2173,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
}
memcpy(&entry->app, new, sizeof(*new));
- strncpy(entry->name, dev->name, IFNAMSIZ);
+ entry->ifindex = dev->ifindex;
list_add(&entry->list, &dcb_app_list);
out:
spin_unlock(&dcb_lock);
@@ -2194,7 +2194,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
struct dcb_app_type event;
int err = -ENOENT;
- memcpy(&event.name, dev->name, sizeof(event.name));
+ event.ifindex = dev->ifindex;
memcpy(&event.app, del, sizeof(event.app));
spin_lock(&dcb_lock);
@@ -2203,7 +2203,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
if (itr->app.selector == del->selector &&
itr->app.protocol == del->protocol &&
itr->app.priority == del->priority &&
- (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ itr->ifindex == dev->ifindex) {
list_del(&itr->list);
kfree(itr);
err = 0;
^ permalink raw reply related
* [net-next PATCH 2/3] dcb: add DCBX mode to event notifier attributes
From: John Fastabend @ 2011-10-06 18:52 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, gospo
In-Reply-To: <20111006185233.2781.80310.stgit@jf-dev1-dcblab>
Add DCBX mode to event notifiers so listeners can learn
currently enabled mode.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/net/dcbnl.h | 1 +
net/dcb/dcbnl.c | 6 ++++++
2 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index 263aa3a..2cd66d0 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -26,6 +26,7 @@ struct dcb_app_type {
int ifindex;
struct dcb_app app;
struct list_head list;
+ u8 dcbx;
};
int dcb_setapp(struct net_device *, struct dcb_app *);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index e508593..9bfbc1d 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -2075,6 +2075,8 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
+ if (dev->dcbnl_ops->getdcbx)
+ event.dcbx = dev->dcbnl_ops->getdcbx(dev);
spin_lock(&dcb_lock);
/* Search for existing match and replace */
@@ -2152,6 +2154,8 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
+ if (dev->dcbnl_ops->getdcbx)
+ event.dcbx = dev->dcbnl_ops->getdcbx(dev);
spin_lock(&dcb_lock);
/* Search for existing match and abort if found */
@@ -2196,6 +2200,8 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
event.ifindex = dev->ifindex;
memcpy(&event.app, del, sizeof(event.app));
+ if (dev->dcbnl_ops->getdcbx)
+ event.dcbx = dev->dcbnl_ops->getdcbx(dev);
spin_lock(&dcb_lock);
/* Search for existing match and remove it. */
^ permalink raw reply related
* [net-next PATCH 3/3] dcb: Add stub routines for !CONFIG_DCB
From: John Fastabend @ 2011-10-06 18:52 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, gospo
In-Reply-To: <20111006185233.2781.80310.stgit@jf-dev1-dcblab>
To avoid ifdefs in the other code that supports DCB notifiers
add stub routines. This method seems popular in other net code
for example 8021Q.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/net/dcbevent.h | 18 ++++++++++++++++++
1 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/include/net/dcbevent.h b/include/net/dcbevent.h
index bc1e7ef..443626e 100644
--- a/include/net/dcbevent.h
+++ b/include/net/dcbevent.h
@@ -24,8 +24,26 @@ enum dcbevent_notif_type {
DCB_APP_EVENT = 1,
};
+#ifdef CONFIG_DCB
extern int register_dcbevent_notifier(struct notifier_block *nb);
extern int unregister_dcbevent_notifier(struct notifier_block *nb);
extern int call_dcbevent_notifiers(unsigned long val, void *v);
+#else
+static inline int
+register_dcbevent_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int unregister_dcbevent_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int call_dcbevent_notifiers(unsigned long val, void *v)
+{
+ return 0;
+}
+#endif /* CONFIG_DCB */
#endif
^ permalink raw reply related
* is PACKET_TX_RING expected to work on loopback?
From: nick black @ 2011-10-06 18:37 UTC (permalink / raw)
To: Vitali Lovitch, Johann Baudy, David Miller; +Cc: linux-net
Hey there. I'm developing an application which makes use of PACKET_TX_RING
(http://dank.qemfd.net/dankwiki/index.php/Omphalos), one mmap'd RX and TX
socket per interface. When I transmit on wireless/ethernet devices, the
packets flow out fine, and I get responses.
When I transmit on loopback, I can see the packets using tcpdump -i lo,
send() returns 0, and the frame is set back to TP_STATUS_AVAILABLE.
Checksums are properly set and the packets appear well-formed in Wireshark.
I can't seem to read the packets, however; neither the intended DNS server
(verified via dnsmasq -d and strace) nor my own socat udp-listen process
seem to get the packets.
Is PACKET_TX_RING expected to work on loopback?
Thanks!
--
nick black <nblack@nvidia.com>
"A main cause of the Roman Empire's fall was that–lacking zero–they had
no way to indicate successful termination of their C programs."
^ permalink raw reply
* [PATCH] fcoe: add DCB notifiers to set skb priority
From: John Fastabend @ 2011-10-06 18:56 UTC (permalink / raw)
To: devel; +Cc: john.r.fastabend, netdev, gospo, davem
Use DCB notifiers to set the skb priority to allow packets
to be steered and tagged correctly over DCB enabled drivers
that setup traffic classes.
This allows queue_mapping() routines to be removed in these
drivers that were previously inspecting the ethertype of
every skb to mark FCoE/FIP frames.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/scsi/fcoe/fcoe.c | 115 +++++++++++++++++++++++++++++++++++++++++
drivers/scsi/fcoe/fcoe_ctlr.c | 4 +
include/scsi/libfcoe.h | 3 +
3 files changed, 122 insertions(+), 0 deletions(-)
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 430b2cd..73d3459 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -32,6 +32,8 @@
#include <linux/sysfs.h>
#include <linux/ctype.h>
#include <linux/workqueue.h>
+#include <net/dcbnl.h>
+#include <net/dcbevent.h>
#include <scsi/scsi_tcq.h>
#include <scsi/scsicam.h>
#include <scsi/scsi_transport.h>
@@ -102,6 +104,8 @@ static int fcoe_ddp_done(struct fc_lport *, u16);
static int fcoe_ddp_target(struct fc_lport *, u16, struct scatterlist *,
unsigned int);
static int fcoe_cpu_callback(struct notifier_block *, unsigned long, void *);
+static int fcoe_dcb_app_notification(struct notifier_block *notifier,
+ ulong event, void *ptr);
static bool fcoe_match(struct net_device *netdev);
static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode);
@@ -130,6 +134,11 @@ static struct notifier_block fcoe_cpu_notifier = {
.notifier_call = fcoe_cpu_callback,
};
+/* notification function for DCB events */
+static struct notifier_block dcb_notifier = {
+ .notifier_call = fcoe_dcb_app_notification,
+};
+
static struct scsi_transport_template *fcoe_nport_scsi_transport;
static struct scsi_transport_template *fcoe_vport_scsi_transport;
@@ -1541,6 +1550,8 @@ int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp)
skb_reset_network_header(skb);
skb->mac_len = elen;
skb->protocol = htons(ETH_P_FCOE);
+ skb->priority = port->priority;
+
if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN &&
fcoe->realdev->features & NETIF_F_HW_VLAN_TX) {
skb->vlan_tci = VLAN_TAG_PRESENT |
@@ -1765,6 +1776,7 @@ int fcoe_percpu_receive_thread(void *arg)
*/
static void fcoe_dev_setup(void)
{
+ register_dcbevent_notifier(&dcb_notifier);
register_netdevice_notifier(&fcoe_notifier);
}
@@ -1773,9 +1785,69 @@ static void fcoe_dev_setup(void)
*/
static void fcoe_dev_cleanup(void)
{
+ unregister_dcbevent_notifier(&dcb_notifier);
unregister_netdevice_notifier(&fcoe_notifier);
}
+static struct fcoe_interface *
+fcoe_hostlist_lookup_realdev_port(struct net_device *netdev)
+{
+ struct fcoe_interface *fcoe;
+ struct net_device *real_dev;
+
+ list_for_each_entry(fcoe, &fcoe_hostlist, list) {
+ if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN)
+ real_dev = vlan_dev_real_dev(fcoe->netdev);
+ else
+ real_dev = fcoe->netdev;
+
+ if (netdev == real_dev)
+ return fcoe;
+ }
+ return NULL;
+}
+
+static int fcoe_dcb_app_notification(struct notifier_block *notifier,
+ ulong event, void *ptr)
+{
+ struct dcb_app_type *entry = ptr;
+ struct fcoe_interface *fcoe;
+ struct net_device *netdev;
+ struct fcoe_port *port;
+ int prio;
+
+ if (entry->app.selector != DCB_APP_IDTYPE_ETHTYPE)
+ return NOTIFY_OK;
+
+ netdev = dev_get_by_index(&init_net, entry->ifindex);
+ if (!netdev)
+ return NOTIFY_OK;
+
+ fcoe = fcoe_hostlist_lookup_realdev_port(netdev);
+ dev_put(netdev);
+ if (!fcoe)
+ return NOTIFY_OK;
+
+ if (entry->dcbx & DCB_CAP_DCBX_VER_CEE)
+ prio = ffs(entry->app.priority) - 1;
+ else
+ prio = entry->app.priority;
+
+ if (prio < 0)
+ return NOTIFY_OK;
+
+ if (entry->app.protocol == ETH_P_FIP ||
+ entry->app.protocol == ETH_P_FCOE)
+ fcoe->ctlr.priority = prio;
+
+ if (entry->app.protocol == ETH_P_FCOE) {
+ port = lport_priv(fcoe->ctlr.lp);
+ port->priority = prio;
+ }
+
+ return NOTIFY_OK;
+}
+
/**
* fcoe_device_notification() - Handler for net device events
* @notifier: The context of the notification
@@ -1984,6 +2056,46 @@ static bool fcoe_match(struct net_device *netdev)
}
/**
+ * fcoe_dcb_create() - Initialize DCB attributes and hooks
+ * @netdev: The net_device object of the L2 link that should be queried
+ * @port: The fcoe_port to bind FCoE APP priority with
+ * @
+ */
+static void fcoe_dcb_create(struct fcoe_interface *fcoe)
+{
+#ifdef CONFIG_DCB
+ int dcbx;
+ u8 fup, up;
+ struct net_device *netdev = fcoe->realdev;
+ struct fcoe_port *port = lport_priv(fcoe->ctlr.lp);
+ struct dcb_app app = {
+ .priority = 0,
+ .protocol = ETH_P_FCOE
+ };
+
+ /* setup DCB priority attributes. */
+ if (netdev && netdev->dcbnl_ops && netdev->dcbnl_ops->getdcbx) {
+ dcbx = netdev->dcbnl_ops->getdcbx(netdev);
+
+ if (dcbx & DCB_CAP_DCBX_VER_IEEE) {
+ app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
+ up = dcb_ieee_getapp_mask(netdev, &app);
+ app.protocol = ETH_P_FIP;
+ fup = dcb_ieee_getapp_mask(netdev, &app);
+ } else {
+ app.selector = DCB_APP_IDTYPE_ETHTYPE;
+ up = dcb_getapp(netdev, &app);
+ app.protocol = ETH_P_FIP;
+ fup = dcb_getapp(netdev, &app);
+ }
+
+ port->priority = ffs(up) ? ffs(up) - 1 : 0;
+ fcoe->ctlr.priority = ffs(fup) ? ffs(fup) - 1 : port->priority;
+ }
+#endif
+}
+
+/**
* fcoe_create() - Create a fcoe interface
* @netdev : The net_device object the Ethernet interface to create on
* @fip_mode: The FIP mode for this creation
@@ -2026,6 +2138,9 @@ static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode)
/* Make this the "master" N_Port */
fcoe->ctlr.lp = lport;
+ /* setup DCB priority attributes. */
+ fcoe_dcb_create(fcoe);
+
/* add to lports list */
fcoe_hostlist_add(lport);
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index c74c4b8..e7522dc 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -320,6 +320,7 @@ static void fcoe_ctlr_solicit(struct fcoe_ctlr *fip, struct fcoe_fcf *fcf)
skb_put(skb, sizeof(*sol));
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
fip->send(fip, skb);
@@ -474,6 +475,7 @@ static void fcoe_ctlr_send_keep_alive(struct fcoe_ctlr *fip,
}
skb_put(skb, len);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
fip->send(fip, skb);
@@ -566,6 +568,7 @@ static int fcoe_ctlr_encaps(struct fcoe_ctlr *fip, struct fc_lport *lport,
cap->fip.fip_dl_len = htons(dlen / FIP_BPW);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
return 0;
@@ -1911,6 +1914,7 @@ static void fcoe_ctlr_vn_send(struct fcoe_ctlr *fip,
skb_put(skb, len);
skb->protocol = htons(ETH_P_FIP);
+ skb->priority = fip->priority;
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h
index 8c1638b..6e4829d 100644
--- a/include/scsi/libfcoe.h
+++ b/include/scsi/libfcoe.h
@@ -147,6 +147,7 @@ struct fcoe_ctlr {
u8 map_dest;
u8 spma;
u8 probe_tries;
+ u8 priority;
u8 dest_addr[ETH_ALEN];
u8 ctl_src_addr[ETH_ALEN];
@@ -296,6 +297,7 @@ struct fcoe_percpu_s {
* @lport: The associated local port
* @fcoe_pending_queue: The pending Rx queue of skbs
* @fcoe_pending_queue_active: Indicates if the pending queue is active
+ * @priority: Packet priority (DCB)
* @max_queue_depth: Max queue depth of pending queue
* @min_queue_depth: Min queue depth of pending queue
* @timer: The queue timer
@@ -311,6 +313,7 @@ struct fcoe_port {
struct fc_lport *lport;
struct sk_buff_head fcoe_pending_queue;
u8 fcoe_pending_queue_active;
+ u8 priority;
u32 max_queue_depth;
u32 min_queue_depth;
struct timer_list timer;
^ permalink raw reply related
* Re: [PATCH] IPv6: DAD from bonding iface is treated as dup address from others
From: Jay Vosburgh @ 2011-10-06 19:05 UTC (permalink / raw)
To: Neil Horman
Cc: Yinglin Sun, David S. Miller, Alexey Kuznetsov, James Morris,
Hideaki YOSHIFUJI, Patrick McHardy, netdev
In-Reply-To: <20111006110047.GA22462@hmsreliant.think-freely.org>
Neil Horman <nhorman@tuxdriver.com> wrote:
>On Wed, Oct 05, 2011 at 08:59:10PM -0700, Yinglin Sun wrote:
>> Steps to reproduce this issue:
>> 1. create bond0 over eth0 and eth1, set the mode to balance-xor
>> 2. add an IPv6 address to bond0
>> 3. DAD packet is sent out from one slave and then is looped back from
>> the other slave. Therefore, it is treated as a duplicate address and
>> stays tentative afterwards:
>> kern.info:
>> Oct 5 11:50:18 testvm1 kernel: [ 129.224353] bond0: IPv6 duplicate address 1234::1 detected!
>>
>> Signed-off-by: Yinglin Sun <Yinglin.Sun@emc.com>
>> ---
>> net/ipv6/ndisc.c | 15 +++++++++++++--
>> 1 files changed, 13 insertions(+), 2 deletions(-)
>>
>> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
>> index 9da6e02..c82f4c7 100644
>> --- a/net/ipv6/ndisc.c
>> +++ b/net/ipv6/ndisc.c
>> @@ -809,9 +809,10 @@ static void ndisc_recv_ns(struct sk_buff *skb)
>>
>> if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
>> if (dad) {
>> + const unsigned char *sadr;
>> + sadr = skb_mac_header(skb);
>> +
>> if (dev->type == ARPHRD_IEEE802_TR) {
>> - const unsigned char *sadr;
>> - sadr = skb_mac_header(skb);
>> if (((sadr[8] ^ dev->dev_addr[0]) & 0x7f) == 0 &&
>> sadr[9] == dev->dev_addr[1] &&
>> sadr[10] == dev->dev_addr[2] &&
>> @@ -821,6 +822,16 @@ static void ndisc_recv_ns(struct sk_buff *skb)
>> /* looped-back to us */
>> goto out;
>> }
>> + } else if (dev->type == ARPHRD_ETHER) {
>> + if (sadr[6] == dev->dev_addr[0] &&
>> + sadr[7] == dev->dev_addr[1] &&
>> + sadr[8] == dev->dev_addr[2] &&
>> + sadr[9] == dev->dev_addr[3] &&
>> + sadr[10] == dev->dev_addr[4] &&
>> + sadr[11] == dev->dev_addr[5]) {
>> + /* looped-back to us */
>> + goto out;
>> + }
>> }
>>
>> /*
>> --
>> 1.7.4.1
>>
>Nack, This seems like it will just completely break DAD. What if theres another
>system out there with the same mac address. A response from that system would
>get dropped by this filter, instead of causing The local system to stop using
>the address. What you really want to do is modify
>bond_should_deliver_exact_match to detect this frame on the inactive slave or
>some such, and drop the frame there.
Also NACK; and adding a bit of information. The balance-xor
mode is nominally expecting to interact with a switch whose ports are
set for etherchannel ("static link aggregation"), in which case the
switch will not loop the packet back around.
If your switch can do etherchannel, then enable it and the
problem should go away. If your switch cannot do this, then you may
have other issues, because all of the multicast or broadcast packets
going out any bonding slave will loop around to another slave. You
could also use 802.3ad / LACP if you switch supports that.
For balance-xor (or balance-rr, for that matter) mode to a
non-etherchannel switch, it's going to be difficult, if not impossible,
to modify bond_should_deliver_exact_match, because there are no inactive
slaves. In this mode, bonding is expecting the switch to balance
incoming traffic across the ports, and not deliver looped back packets
or duplicates. There are no restrictions on what type of traffic
(mcast, bcast, ucast) may arrive on any given port.
I can't think of a way to make the non-etherchannel case work
for balance-xor (or balance-rr) without breaking the DAD functionality
in the case of an actual duplicate. I'm not aware of a way to
distinguish a looped back DAD probe from an actual duplicate address
probe elsewhere on the network.
-J
---
-Jay Vosburgh, IBM Linux Technology Center, fubar@us.ibm.com
^ permalink raw reply
* Re: [PATCH 1/2] bridge: leave carrier on for empty bridge
From: David Miller @ 2011-10-06 19:28 UTC (permalink / raw)
To: shemminger; +Cc: netdev
In-Reply-To: <20111004041509.191082289@vyatta.com>
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Mon, 03 Oct 2011 21:14:45 -0700
> This resolves a regression seen by some users of bridging.
> Some users use the bridge like a dummy device.
> They expect to be able to put an IPv6 address on the device
> with no ports attached. Although there are better ways of doing
> this, there is no reason to not allow it.
>
> Note: the bridge still will reflect the state of ports in the
> bridge if there are any added.
>
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Applied to 'net' and queued up for -stable.
^ permalink raw reply
* Re: [PATCH 2/2] bridge: allow forwarding some link local frames
From: David Miller @ 2011-10-06 19:28 UTC (permalink / raw)
To: shemminger; +Cc: netdev
In-Reply-To: <20111004041509.292932641@vyatta.com>
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Mon, 03 Oct 2011 21:14:46 -0700
> This is based on an earlier patch by Nick Carter with comments
> by David Lamparter but with some refinements. Thanks for their patience
> this is a confusing area with overlap of standards, user requirements,
> and compatibility with earlier releases.
>
> It adds a new sysfs attribute
> /sys/class/net/brX/bridge/group_fwd_mask
> that controls forwarding of frames with address of: 01-80-C2-00-00-0X
> The default setting has no forwarding to retain compatibility.
>
> One change from earlier releases is that forwarding of group
> addresses is not dependent on STP being enabled or disabled. This
> choice was made based on interpretation of tie 802.1 standards.
> I expect complaints will arise because of this, but better to follow
> the standard than continue acting incorrectly by default.
>
> The filtering mask is writeable, but only values that don't forward
> known control frames are allowed. It intentionally blocks attempts
> to filter control protocols. For example: writing a 8 allows
> forwarding 802.1X PAE addresses which is the most common request.
>
> Reported-by: David Lamparter <equinox@diac24.net>
> Original-patch-by: Nick Carter <ncarter100@gmail.com>
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Applied to net-next.
^ permalink raw reply
* Re: [PATCH] Break up the single NBD lock into one per NBD device
From: David Miller @ 2011-10-06 19:37 UTC (permalink / raw)
To: hkchu; +Cc: netdev
In-Reply-To: <1317080052-6052-1-git-send-email-hkchu@google.com>
From: "H.K. Jerry Chu" <hkchu@google.com>
Date: Mon, 26 Sep 2011 16:34:12 -0700
> From: Jerry Chu <hkchu@google.com>
>
> This patch breaks up the single NBD lock into one per
> disk. The single NBD lock has become a serious performance
> bottleneck when multiple NBD disks are being used.
>
> The original comment on why a single lock may be ok no
> longer holds for today's much faster NICs.
>
> Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Acked-by: David S. Miller <davem@davemloft.net>
Even though this is a "networking" block device, I think this change
should go through the Jens Axboe's block layer tree.
Thanks.
^ permalink raw reply
* Re: [PATCH v2 1/2] virtio-net: Verify page list size before fitting into skb
From: David Miller @ 2011-10-06 19:41 UTC (permalink / raw)
To: levinsasha928; +Cc: linux-kernel, rusty, mst, virtualization, netdev, kvm
In-Reply-To: <1317220855-9352-1-git-send-email-levinsasha928@gmail.com>
From: Sasha Levin <levinsasha928@gmail.com>
Date: Wed, 28 Sep 2011 17:40:54 +0300
> This patch verifies that the length of a buffer stored in a linked list
> of pages is small enough to fit into a skb.
>
> If the size is larger than a max size of a skb, it means that we shouldn't
> go ahead building skbs anyway since we won't be able to send the buffer as
> the user requested.
>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: virtualization@lists.linux-foundation.org
> Cc: netdev@vger.kernel.org
> Cc: kvm@vger.kernel.org
> Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
Applied to net-next
^ permalink raw reply
* Re: [PATCH v2 2/2] virtio-net: Prevent NULL dereference
From: David Miller @ 2011-10-06 19:41 UTC (permalink / raw)
To: levinsasha928; +Cc: linux-kernel, rusty, mst, virtualization, netdev, kvm
In-Reply-To: <1317220855-9352-2-git-send-email-levinsasha928@gmail.com>
From: Sasha Levin <levinsasha928@gmail.com>
Date: Wed, 28 Sep 2011 17:40:55 +0300
> This patch prevents a NULL dereference when the user has passed a length
> longer than an actual buffer to virtio-net.
>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: virtualization@lists.linux-foundation.org
> Cc: netdev@vger.kernel.org
> Cc: kvm@vger.kernel.org
> Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
Waiting for a respin of this patch with clarified comments.
^ permalink raw reply
* Re: [net-next PATCH 1/3] dcb: Use ifindex instead of ifname
From: David Miller @ 2011-10-06 19:50 UTC (permalink / raw)
To: john.r.fastabend; +Cc: netdev, gospo
In-Reply-To: <20111006185233.2781.80310.stgit@jf-dev1-dcblab>
From: John Fastabend <john.r.fastabend@intel.com>
Date: Thu, 06 Oct 2011 11:52:33 -0700
> From: Mark Rustad <mark.d.rustad@intel.com>
>
> Use ifindex instead of ifname in the DCB app ring. This makes for a smaller
> data structure and faster comparisons. It also avoids possible issues when
> a net device is renamed.
>
> Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Applied.
^ permalink raw reply
* Re: [net-next PATCH 2/3] dcb: add DCBX mode to event notifier attributes
From: David Miller @ 2011-10-06 19:50 UTC (permalink / raw)
To: john.r.fastabend; +Cc: netdev, gospo
In-Reply-To: <20111006185238.2781.36917.stgit@jf-dev1-dcblab>
From: John Fastabend <john.r.fastabend@intel.com>
Date: Thu, 06 Oct 2011 11:52:38 -0700
> Add DCBX mode to event notifiers so listeners can learn
> currently enabled mode.
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Applied.
^ permalink raw reply
* Re: [net-next PATCH 3/3] dcb: Add stub routines for !CONFIG_DCB
From: David Miller @ 2011-10-06 19:50 UTC (permalink / raw)
To: john.r.fastabend; +Cc: netdev, gospo
In-Reply-To: <20111006185243.2781.67932.stgit@jf-dev1-dcblab>
From: John Fastabend <john.r.fastabend@intel.com>
Date: Thu, 06 Oct 2011 11:52:44 -0700
> To avoid ifdefs in the other code that supports DCB notifiers
> add stub routines. This method seems popular in other net code
> for example 8021Q.
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Applied.
^ permalink raw reply
* Re: [PATCH] Break up the single NBD lock into one per NBD device
From: Eric Dumazet @ 2011-10-06 19:53 UTC (permalink / raw)
To: H.K. Jerry Chu; +Cc: davem, netdev
In-Reply-To: <1317080052-6052-1-git-send-email-hkchu@google.com>
Le lundi 26 septembre 2011 à 16:34 -0700, H.K. Jerry Chu a écrit :
> From: Jerry Chu <hkchu@google.com>
>
> This patch breaks up the single NBD lock into one per
> disk. The single NBD lock has become a serious performance
> bottleneck when multiple NBD disks are being used.
>
> The original comment on why a single lock may be ok no
> longer holds for today's much faster NICs.
>
> Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
> ---
> drivers/block/nbd.c | 22 +++++++++-------------
> 1 files changed, 9 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> index f533f33..355e15c 100644
> --- a/drivers/block/nbd.c
> +++ b/drivers/block/nbd.c
> @@ -58,20 +58,9 @@ static unsigned int debugflags;
>
> static unsigned int nbds_max = 16;
> static struct nbd_device *nbd_dev;
> +static spinlock_t *nbd_locks;
static spinlock_t *nbd_locks __read_mostly;
> static int max_part;
>
> -/*
> - * Use just one lock (or at most 1 per NIC). Two arguments for this:
> - * 1. Each NIC is essentially a synchronization point for all servers
> - * accessed through that NIC so there's no need to have more locks
> - * than NICs anyway.
> - * 2. More locks lead to more "Dirty cache line bouncing" which will slow
> - * down each lock to the point where they're actually slower than just
> - * a single lock.
> - * Thanks go to Jens Axboe and Al Viro for their LKML emails explaining this!
> - */
> -static DEFINE_SPINLOCK(nbd_lock);
> -
> #ifndef NDEBUG
> static const char *ioctl_cmd_to_ascii(int cmd)
> {
> @@ -753,6 +742,12 @@ static int __init nbd_init(void)
> if (!nbd_dev)
> return -ENOMEM;
>
> + nbd_locks = kcalloc(nbds_max, sizeof(*nbd_locks), GFP_KERNEL);
> + if (!nbd_locks) {
> + kfree(nbd_dev);
> + return -ENOMEM;
> + }
> +
Please add loop to init spinlocks to help LOCKDEP...
for (i = 0; i < nbds_max; i++)
spin_lock_init(&nbd_locks[i]);
> part_shift = 0;
> if (max_part > 0) {
> part_shift = fls(max_part);
> @@ -784,7 +779,7 @@ static int __init nbd_init(void)
> * every gendisk to have its very own request_queue struct.
> * These structs are big so we dynamically allocate them.
> */
> - disk->queue = blk_init_queue(do_nbd_request, &nbd_lock);
> + disk->queue = blk_init_queue(do_nbd_request, &nbd_locks[i]);
> if (!disk->queue) {
> put_disk(disk);
> goto out;
> @@ -832,6 +827,7 @@ out:
> put_disk(nbd_dev[i].disk);
> }
> kfree(nbd_dev);
> + kfree(nbd_locks);
> return err;
> }
>
^ permalink raw reply
* radvd 1.8.2 released
From: Reuben Hawkins @ 2011-10-06 19:47 UTC (permalink / raw)
To: radvd-announce-l, radvd Development Discussion, netdev
Hi,
I've just posted a new release of radvd which includes a few bug fixes
and security enhancements. Please update immediately.
Thanks,
Reuben
^ permalink raw reply
* Re: [PATCH] net: fix typos in Documentation/networking/scaling.txt
From: David Miller @ 2011-10-06 20:00 UTC (permalink / raw)
To: benjamin.poirier; +Cc: netdev, linux-doc, willemb
In-Reply-To: <1317736830-4442-1-git-send-email-benjamin.poirier@gmail.com>
From: Benjamin Poirier <benjamin.poirier@gmail.com>
Date: Tue, 4 Oct 2011 10:00:30 -0400
> The second hunk fixes rps_sock_flow_table but has to re-wrap the paragraph.
>
> Signed-off-by: Benjamin Poirier <benjamin.poirier@gmail.com>
Applied, thanks.
^ permalink raw reply
* Re: [PATCH 1/8] vxge: convert to SKB paged frag API.
From: David Miller @ 2011-10-06 20:00 UTC (permalink / raw)
To: Ian.Campbell; +Cc: mirqus, netdev, jdmason
In-Reply-To: <1317916822.21903.252.camel@zakaz.uk.xensource.com>
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Thu, 6 Oct 2011 17:00:22 +0100
> Here it is. David, if you want N separate patches (or a git pull
> request?) let me know.
No, this is fine, applied.
Thanks.
^ permalink raw reply
* [GIT] Networking
From: David Miller @ 2011-10-06 20:23 UTC (permalink / raw)
To: torvalds; +Cc: akpm, netdev, linux-kernel
1) MD5 signature pool leak fix in TCP, from Zheng Yan.
2) Fix carrier state regression in bridging, from Stephen Hemminger.
3) Unicast forwards between macvtap interfaces should use
dev_forward_skb() not the vlan->forward() method. Fix from David
Ward.
4) TCP's lost_cnt_hint is updated one too many times in some situations,
fix from Zheng Yan.
5) netfilter needs to use rwlock_init(), from Thomas Gleixner.
Please pull, thanks a lot!
The following changes since commit 6367f1775ebb66b0f0e9e3512159f3257a6fde0e:
Merge branch 'for-linus' of http://people.redhat.com/agk/git/linux-dm (2011-10-06 08:31:47 -0700)
are available in the git repository at:
git://github.com/davem330/net.git master
Benjamin Poirier (1):
net: fix typos in Documentation/networking/scaling.txt
David Ward (1):
macvlan/macvtap: Fix unicast between macvtap interfaces in bridge mode
Thomas Gleixner (1):
netfilter: Use proper rwlock init function
Yan, Zheng (2):
tcp: properly handle md5sig_pool references
tcp: properly update lost_cnt_hint during shifting
stephen hemminger (1):
bridge: leave carrier on for empty bridge
Documentation/networking/scaling.txt | 10 +++++-----
drivers/net/macvlan.c | 2 +-
net/bridge/br_device.c | 3 ---
net/ipv4/tcp_input.c | 4 +---
net/ipv4/tcp_ipv4.c | 11 +++++++----
net/ipv6/tcp_ipv6.c | 8 +++++---
net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
7 files changed, 20 insertions(+), 20 deletions(-)
^ permalink raw reply
* [PATCH net-next] macvlan: handle fragmented multicast frames
From: Eric Dumazet @ 2011-10-06 20:28 UTC (permalink / raw)
To: Ben Greear; +Cc: netdev
In-Reply-To: <4E8CDB9B.6010900@candelatech.com>
Le mercredi 05 octobre 2011 à 15:35 -0700, Ben Greear a écrit :
> If someone wants to cook up macvlan-ip-defrag patch I'll be happy
> to test it. But, as far as I can tell, this problem can happen on
> any two interfaces. The reason that some of mine work (.1q vlans)
> and macvlan didn't is probably because those were separated by
> some virtual network links that imparted extra delay...so the
> vlan consumed all its fragments and passed the complete pkt up
> the stack before the mac-vlan ever saw the initial frame.
>
> With this in mind, it seems that using multiple udp multicast
> sockets bound to specific devices is fundamentally broken for
> fragmented packets.
>
> I have no pressing need for this feature, so now that I better understand
> the problem I can just document it and move on to other things.
>
> Thanks for all the help.
>
Please test following patch (note I had no time to test it, sorry !)
Based on net-next tree, might apply on 3.0 kernel...
[PATCH net-next] macvlan: handle fragmented multicast frames
Fragmented multicast frames are delivered to a single macvlan port,
because ip defrag logic considers other samples are redundant.
Implement a defrag step before trying to send the multicast frame.
Reported-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
drivers/net/macvlan.c | 3 +++
include/net/ip.h | 9 +++++++++
net/ipv4/ip_fragment.c | 36 ++++++++++++++++++++++++++++++++++++
net/packet/af_packet.c | 39 +--------------------------------------
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b100c90..40366eb 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -169,6 +169,9 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
port = macvlan_port_get_rcu(skb->dev);
if (is_multicast_ether_addr(eth->h_dest)) {
+ skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
+ if (!skb)
+ return RX_HANDLER_CONSUMED;
src = macvlan_hash_lookup(port, eth->h_source);
if (!src)
/* frame comes from an external address */
diff --git a/include/net/ip.h b/include/net/ip.h
index aa76c7a..c7e066a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -406,9 +406,18 @@ enum ip_defrag_users {
IP_DEFRAG_VS_OUT,
IP_DEFRAG_VS_FWD,
IP_DEFRAG_AF_PACKET,
+ IP_DEFRAG_MACVLAN,
};
int ip_defrag(struct sk_buff *skb, u32 user);
+#ifdef CONFIG_INET
+struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
+#else
+static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+{
+ return skb;
+}
+#endif
int ip_frag_mem(struct net *net);
int ip_frag_nqueues(struct net *net);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0e0ab98..763589a 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -682,6 +682,42 @@ int ip_defrag(struct sk_buff *skb, u32 user)
}
EXPORT_SYMBOL(ip_defrag);
+struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+{
+ const struct iphdr *iph;
+ u32 len;
+
+ if (skb->protocol != htons(ETH_P_IP))
+ return skb;
+
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return skb;
+
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 || iph->version != 4)
+ return skb;
+ if (!pskb_may_pull(skb, iph->ihl*4))
+ return skb;
+ iph = ip_hdr(skb);
+ len = ntohs(iph->tot_len);
+ if (skb->len < len || len < (iph->ihl * 4))
+ return skb;
+
+ if (ip_is_fragment(ip_hdr(skb))) {
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (skb) {
+ if (pskb_trim_rcsum(skb, len))
+ return skb;
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ if (ip_defrag(skb, user))
+ return NULL;
+ skb->rxhash = 0;
+ }
+ }
+ return skb;
+}
+EXPORT_SYMBOL(ip_check_defrag);
+
#ifdef CONFIG_SYSCTL
static int zero;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 25e68f5..ff9eed7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1213,43 +1213,6 @@ static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *sk
return f->arr[cpu % num];
}
-static struct sk_buff *fanout_check_defrag(struct sk_buff *skb)
-{
-#ifdef CONFIG_INET
- const struct iphdr *iph;
- u32 len;
-
- if (skb->protocol != htons(ETH_P_IP))
- return skb;
-
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- return skb;
-
- iph = ip_hdr(skb);
- if (iph->ihl < 5 || iph->version != 4)
- return skb;
- if (!pskb_may_pull(skb, iph->ihl*4))
- return skb;
- iph = ip_hdr(skb);
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < (iph->ihl * 4))
- return skb;
-
- if (ip_is_fragment(ip_hdr(skb))) {
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (skb) {
- if (pskb_trim_rcsum(skb, len))
- return skb;
- memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
- if (ip_defrag(skb, IP_DEFRAG_AF_PACKET))
- return NULL;
- skb->rxhash = 0;
- }
- }
-#endif
- return skb;
-}
-
static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
@@ -1268,7 +1231,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
case PACKET_FANOUT_HASH:
default:
if (f->defrag) {
- skb = fanout_check_defrag(skb);
+ skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
if (!skb)
return 0;
}
^ permalink raw reply related
* Re: IPv4 multicast and mac-vlans acting weird on 3.0.4+
From: Eric Dumazet @ 2011-10-06 20:42 UTC (permalink / raw)
To: Ben Greear; +Cc: netdev
In-Reply-To: <1317850603.3457.21.camel@edumazet-laptop>
Le mercredi 05 octobre 2011 à 23:36 +0200, Eric Dumazet a écrit :
> Le mercredi 05 octobre 2011 à 13:56 -0700, Ben Greear a écrit :
>
> > Wouldn't you have the same problem with two real Ethernet interfaces on
> > the same LAN, or two 802.1Q devices for that matter? The addrs will all
> > be the same in that case too?
> >
>
> Usually multicast is coupled with routing.
>
> A JOIN message from your app wont be sent on all interfaces...
>
> But yes, we might have a similar issue with regular vlans.
>
> Probably nobody noticed yet. Just say no to fragments :)
>
> > Also, if I have just a single mac-vlan active (the other 3 are 'ifconfig foo down'),
> > I still see the problem with mcast.
> >
>
> Thats another bug : macvlan doesnt test IFF_UP on broadcasts, only for
> unicast messages. Please test following patch.
>
> > From what you describe, I am thinking I may be hitting a different
> > issue. Any ideas on how to figure out why exactly the NF_HOOK isn't
> > calling the ip_rcv_finish method?
> >
>
> Really I believe I tried to explain the thing already...
>
> ip_local_deliver() -> ip_defrag() :
>
>
> [PATCH] macvlan: dont send frames on DOWN devices
>
> Reported-by: Ben Greear <greearb@candelatech.com>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> ---
> diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
> index b100c90..94a0282 100644
> --- a/drivers/net/macvlan.c
> +++ b/drivers/net/macvlan.c
> @@ -145,7 +145,8 @@ static void macvlan_broadcast(struct sk_buff *skb,
> hlist_for_each_entry_rcu(vlan, n, &port->vlan_hash[i], hlist) {
> if (vlan->dev == src || !(vlan->mode & mode))
> continue;
> -
> + if (!(vlan->dev->flags & IFF_UP))
> + continue;
> nskb = skb_clone(skb, GFP_ATOMIC);
> err = macvlan_broadcast_one(nskb, vlan, eth,
> mode == MACVLAN_MODE_BRIDGE);
>
This one is not needed.
When a port is down, its not in vlan_hash[] table anymore.
(Not sure why we perform the IFF_UP test for unicast frames.)
^ permalink raw reply
* Re: [PATCH 1/8] vxge: convert to SKB paged frag API.
From: Michał Mirosław @ 2011-10-06 20:45 UTC (permalink / raw)
To: Ian Campbell; +Cc: David Miller, netdev@vger.kernel.org, Jon Mason
In-Reply-To: <1317916822.21903.252.camel@zakaz.uk.xensource.com>
W dniu 6 października 2011 18:00 użytkownik Ian Campbell
<Ian.Campbell@citrix.com> napisał:
> On Thu, 2011-10-06 at 08:05 +0100, Ian Campbell wrote:
>> On Wed, 2011-10-05 at 22:03 +0100, Michał Mirosław wrote:
>> > 2011/10/5 Ian Campbell <ian.campbell@citrix.com>:
>> > [...]
>> > > --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
>> > > +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
>> > > @@ -923,9 +923,9 @@ vxge_xmit(struct sk_buff *skb, struct net_device *dev)
>> > > if (!frag->size)
>> > > continue;
>> > >
>> > > - dma_pointer = (u64) pci_map_page(fifo->pdev, frag->page,
>> > > - frag->page_offset, frag->size,
>> > > - PCI_DMA_TODEVICE);
>> > > + dma_pointer = (u64)skb_frag_dma_map(&fifo->pdev->dev, frag,
>> > > + 0, frag->size,
>> > > + PCI_DMA_TODEVICE);
>> >
>> > This should be DMA_TO_DEVICE instead of PCI_DMA_TODEVICE.
>> > > if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer)))
>> > > goto _exit2;
>> > I would also change this to dma_mapping_error() in one go.
>> > Just a random patch check.
>> Thanks Michał.
>> I'm sure I must have made the same mistakes in a whole bunch of patches
>> which have already been applied. I'll knock up a fixup patch.
> Here it is. David, if you want N separate patches (or a git pull
> request?) let me know.
There's a catch there, though:
[...]
> mapping = skb_frag_dma_map(&tp->pdev->dev, frag, 0,
> - len, PCI_DMA_TODEVICE);
> + len, DMA_TO_DEVICE);
>
> tnapi->tx_buffers[entry].skb = NULL;
> dma_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
> mapping);
> - if (pci_dma_mapping_error(tp->pdev, mapping))
> + if (dma_mapping_error(tp->pdev, mapping))
dma_mapping_error() takes struct device *, so those changes should be:
dma_mapping_error(&tp->pdev->dev, mapping)
(Like skb_frag_dma_map()'s first argument).
Best Regards,
Michał Mirosław
^ permalink raw reply
* Re: [PATCH 1/8] vxge: convert to SKB paged frag API.
From: Ian Campbell @ 2011-10-06 21:08 UTC (permalink / raw)
To: Michał Mirosław; +Cc: David Miller, netdev@vger.kernel.org, Jon Mason
In-Reply-To: <CAHXqBFJsGcAdH0zFS_Gd34oR3Ov6ssbXRMzK-KrnSxq8c3=WNg@mail.gmail.com>
On Thu, 2011-10-06 at 21:45 +0100, Michał Mirosław wrote:
> W dniu 6 października 2011 18:00 użytkownik Ian Campbell
> <Ian.Campbell@citrix.com> napisał:
> > On Thu, 2011-10-06 at 08:05 +0100, Ian Campbell wrote:
> >> On Wed, 2011-10-05 at 22:03 +0100, Michał Mirosław wrote:
> >> > 2011/10/5 Ian Campbell <ian.campbell@citrix.com>:
> >> > [...]
> >> > > --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
> >> > > +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
> >> > > @@ -923,9 +923,9 @@ vxge_xmit(struct sk_buff *skb, struct net_device *dev)
> >> > > if (!frag->size)
> >> > > continue;
> >> > >
> >> > > - dma_pointer = (u64) pci_map_page(fifo->pdev, frag->page,
> >> > > - frag->page_offset, frag->size,
> >> > > - PCI_DMA_TODEVICE);
> >> > > + dma_pointer = (u64)skb_frag_dma_map(&fifo->pdev->dev, frag,
> >> > > + 0, frag->size,
> >> > > + PCI_DMA_TODEVICE);
> >> >
> >> > This should be DMA_TO_DEVICE instead of PCI_DMA_TODEVICE.
> >> > > if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer)))
> >> > > goto _exit2;
> >> > I would also change this to dma_mapping_error() in one go.
> >> > Just a random patch check.
> >> Thanks Michał.
> >> I'm sure I must have made the same mistakes in a whole bunch of patches
> >> which have already been applied. I'll knock up a fixup patch.
> > Here it is. David, if you want N separate patches (or a git pull
> > request?) let me know.
>
> There's a catch there, though:
>
> [...]
> > mapping = skb_frag_dma_map(&tp->pdev->dev, frag, 0,
> > - len, PCI_DMA_TODEVICE);
> > + len, DMA_TO_DEVICE);
> >
> > tnapi->tx_buffers[entry].skb = NULL;
> > dma_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
> > mapping);
> > - if (pci_dma_mapping_error(tp->pdev, mapping))
> > + if (dma_mapping_error(tp->pdev, mapping))
>
> dma_mapping_error() takes struct device *, so those changes should be:
>
> dma_mapping_error(&tp->pdev->dev, mapping)
>
> (Like skb_frag_dma_map()'s first argument).
You are absolutely right, I've no idea how I missed the very obvious
warning this produces. Incremental patch is below, sorry about this!
8<-------------------------------------------------------
From 5be2edc6eec5c66b58f4287f1d3ba3637afa7ad6 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Thu, 6 Oct 2011 22:05:41 +0100
Subject: [PATCH] net: fix argument to dma_mapping_error after conversion to skb_frag_dma_map
The recent conversion from pci_dma_mapping_error to dma_mapping_error missed
the change in the exact parameter, which needs to be the struct device * not
the struct pci_device *.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
---
drivers/net/ethernet/broadcom/tg3.c | 2 +-
drivers/net/ethernet/marvell/sky2.c | 4 ++--
drivers/net/ethernet/pasemi/pasemi_mac.c | 2 +-
.../net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 +-
drivers/net/ethernet/qlogic/qla3xxx.c | 2 +-
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +-
drivers/net/ethernet/qlogic/qlge/qlge_main.c | 2 +-
drivers/net/ethernet/sfc/tx.c | 2 +-
8 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3abcb4d..9dbd1af 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6784,7 +6784,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
tnapi->tx_buffers[entry].skb = NULL;
dma_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
mapping);
- if (dma_mapping_error(tp->pdev, mapping))
+ if (dma_mapping_error(&tp->pdev->dev, mapping))
goto dma_error;
if (tg3_tx_frag_set(tnapi, &entry, &budget, mapping,
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 7baff3e..a3ce9b6 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1231,7 +1231,7 @@ static int sky2_rx_map_skb(struct pci_dev *pdev, struct rx_ring_info *re,
frag->size,
DMA_FROM_DEVICE);
- if (dma_mapping_error(pdev, re->frag_addr[i]))
+ if (dma_mapping_error(&pdev->dev, re->frag_addr[i]))
goto map_page_error;
}
return 0;
@@ -1938,7 +1938,7 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
mapping = skb_frag_dma_map(&hw->pdev->dev, frag, 0,
frag->size, DMA_TO_DEVICE);
- if (dma_mapping_error(hw->pdev, mapping))
+ if (dma_mapping_error(&hw->pdev->dev, mapping))
goto mapping_unwind;
upper = upper_32_bits(mapping);
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index d247030..c6f0056 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -1508,7 +1508,7 @@ static int pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev)
map[i + 1] = skb_frag_dma_map(&mac->dma_pdev->dev, frag, 0,
frag->size, DMA_TO_DEVICE);
map_size[i+1] = frag->size;
- if (dma_mapping_error(mac->dma_pdev, map[i + 1])) {
+ if (dma_mapping_error(&mac->dma_pdev->dev, map[i + 1])) {
nfrags = i;
goto out_err_nolock;
}
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index b061c07..e2ba78b 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1907,7 +1907,7 @@ netxen_map_tx_skb(struct pci_dev *pdev,
map = skb_frag_dma_map(&pdev->dev, frag, 0, frag->size,
DMA_TO_DEVICE);
- if (dma_mapping_error(pdev, map))
+ if (dma_mapping_error(&pdev->dev, map))
goto unwind;
nf->dma = map;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 8932265..46f9b64 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2391,7 +2391,7 @@ static int ql_send_map(struct ql3_adapter *qdev,
map = skb_frag_dma_map(&qdev->pdev->dev, frag, 0, frag->size,
DMA_TO_DEVICE);
- err = dma_mapping_error(qdev->pdev, map);
+ err = dma_mapping_error(&qdev->pdev->dev, map);
if (err) {
netdev_err(qdev->ndev,
"PCI mapping frags failed with error: %d\n",
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index c9756e7..eac19e7d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2137,7 +2137,7 @@ qlcnic_map_tx_skb(struct pci_dev *pdev,
map = skb_frag_dma_map(&pdev->dev, frag, 0, frag->size,
DMA_TO_DEVICE);
- if (dma_mapping_error(pdev, map))
+ if (dma_mapping_error(&pdev->dev, map))
goto unwind;
nf->dma = map;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 094ac22..f2d9bb7 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1434,7 +1434,7 @@ static int ql_map_send(struct ql_adapter *qdev,
map = skb_frag_dma_map(&qdev->pdev->dev, frag, 0, frag->size,
DMA_TO_DEVICE);
- err = dma_mapping_error(qdev->pdev, map);
+ err = dma_mapping_error(&qdev->pdev->dev, map);
if (err) {
netif_err(qdev, tx_queued, qdev->ndev,
"PCI mapping frags failed with error: %d.\n",
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 7f47efc..3964a62 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -927,7 +927,7 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
{
st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0,
frag->size, DMA_TO_DEVICE);
- if (likely(!dma_mapping_error(efx->pci_dev, st->unmap_addr))) {
+ if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
st->unmap_single = false;
st->unmap_len = frag->size;
st->in_len = frag->size;
--
1.7.2.5
Ian.
^ 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