linux-toradex.git/drivers/net/xen-netfront.c, branch v3.0.53

xen: netfront: hold RTNL when updating features.

2011-05-25T21:55:32+00:00

Konrad reports:
[    0.930811] RTNL: assertion failed at /home/konrad/ssd/linux/net/core/dev.c (5258)
[    0.930821] Pid: 22, comm: xenwatch Not tainted 2.6.39-05193-gd762f43 #1
[    0.930825] Call Trace:
[    0.930834]  [] __netdev_update_features+0xae/0xe0
[    0.930840]  [] netdev_update_features+0x11/0x30
[    0.930847]  [] netback_changed+0x4e5/0x800 [xen_netfront]
[    0.930854]  [] xenbus_otherend_changed+0xa8/0xb0
[    0.930860]  [] ? _raw_spin_unlock_irqrestore+0x19/0x20
[    0.930866]  [] backend_changed+0xe/0x10
[    0.930871]  [] xenwatch_thread+0xba/0x180
[    0.930876]  [] ? wake_up_bit+0x40/0x40
[    0.930881]  [] ? split+0xf0/0xf0
[    0.930886]  [] kthread+0x96/0xa0
[    0.930891]  [] kernel_thread_helper+0x4/0x10
[    0.930896]  [] ? int_ret_from_sys_call+0x7/0x1b
[    0.930901]  [] ? retint_restore_args+0x5/0x6
[    0.930906]  [] ? gs_change+0x13/0x13

This update happens in xenbus watch callback context and hence does not already
hold the rtnl. Take the lock as necessary.

Signed-off-by: Ian Campbell 
Tested-by: Konrad Rzeszutek Wilk 
Signed-off-by: David S. Miller

xen: netfront: assume all hw features are available until backend connection setup

2011-04-04T18:07:57+00:00

We need to assume that all features will be available when registering the
netdev otherwise they are ommitted from the initial set of
dev->wanted_features. When we connect to the backed we reduce the set as
necessary due to the call to netdev_update_features() in xennet_connect().

Signed-off-by: Ian Campbell 
Signed-off-by: David S. Miller

xen: netfront: fix declaration order

2011-04-04T00:21:00+00:00

Must declare xennet_fix_features() and xennet_set_features() before
using them.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: convert xen-netfront to hw_features

2011-04-02T03:56:29+00:00

Not tested in any way. The original code for offload setting seems broken
as it resets the features on every netback reconnect.

This will set GSO_ROBUST at device creation time (earlier than connect time).

RX checksum offload is forced on - so advertise as it is.

Signed-off-by: Michał Mirosław 
Signed-off-by: David S. Miller

drivers/net: Remove IRQF_SAMPLE_RANDOM flag from network drivers

2011-03-31T05:28:14+00:00

The IRQF_SAMPLE_RANDOM flag is marked as deprecated and will be removed.

Every input point to the kernel's entropy pool have to better document the
type of entropy source it is.

drivers/char/random.c now implements a set of interfaces that can be used for
devices to collect enviromental noise. IRQF_SAMPLE_RANDOM will be replaced
with these add_*_randomness exported functions.

Network drivers are not a good source of entropy. They use as a source of
entropy essentially a remote host. Which means that the source of entropy can
be potentially controlled by an attacker. Also, with heavy workloads the
entropy decreases due to less hardware interrupts happening thanks to irq
mitigation and NAPI.

If a system relies in its network interface as a entropy source it has a false
sense of security. Systems that don't have devices whose drivers are good
sources of entropy, should either use a hardware random number generator or
feed the kernel's entropy pool from userspace using other sources of entropy
such as EGD, video_entropyd, timer_entropyd and audio-entropyd.

Signed-off-by: Javier Martinez Canillas 
Signed-off-by: David S. Miller

xen network backend driver

2011-03-16T02:38:03+00:00

netback is the host side counterpart to the frontend driver in
drivers/net/xen-netfront.c. The PV protocol is also implemented by
frontend drivers in other OSes too, such as the BSDs and even Windows.

The patch is based on the driver from the xen.git pvops kernel tree but
has been put through the checkpatch.pl wringer plus several manual
cleanup passes and review iterations. The driver has been moved from
drivers/xen/netback to drivers/net/xen-netback.

One major change from xen.git is that the guest transmit path (i.e. what
looks like receive to netback) has been significantly reworked to remove
the dependency on the out of tree PageForeign page flag (a core kernel
patch which enables a per page destructor callback on the final
put_page). This page flag was used in order to implement a grant map
based transmit path (where guest pages are mapped directly into SKB
frags). Instead this version of netback uses grant copy operations into
regular memory belonging to the backend domain. Reinstating the grant
map functionality is something which I would like to revisit in the
future.

Note that this driver depends on 2e820f58f7ad "xen/irq: implement
bind_interdomain_evtchn_to_irqhandler for backend drivers" which is in
linux next via the "xen-two" tree and is intended for the 2.6.39 merge
window:
        git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git stable/backends
this branch has only that single commit since 2.6.38-rc2 and is safe for
cross merging into the net branch.

Signed-off-by: Ian Campbell 
Reviewed-by: Ben Hutchings 
Signed-off-by: David S. Miller

xen: netfront: fix xennet_get_ethtool_stats()

2011-03-15T04:05:40+00:00

commit e9a799ea4a5551d2 (xen: netfront: ethtool stats fields should be
unsigned long) made rx_gso_checksum_fixup an unsigned long.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

xen: netfront: ethtool stats fields should be unsigned long

2011-03-14T22:10:10+00:00

Fixup the rx_gso_checksum_fixup field added in e0ce4af920eb to be
unsigned long as suggested by Ben Hutchings in
<1298919198.2569.14.camel@bwh-desktop>

Signed-off-by: Ian Campbell 
Cc: Ben Hutchings 
Signed-off-by: David S. Miller

xen: netfront: handle incoming GSO SKBs which are not CHECKSUM_PARTIAL

2011-01-27T22:17:35+00:00

The Linux network stack expects all GSO SKBs to have ip_summed ==
CHECKSUM_PARTIAL (which implies that the frame contains a partial
checksum) and the Xen network ring protocol similarly expects an SKB
which has GSO set to also have NETRX_csum_blank (which also implies a
partial checksum).

However there have been cases of buggy guests which mark a frame as
GSO but do not set csum_blank. If we detect that we a receiving such a
frame (which manifests as ip_summed != PARTIAL && skb_is_gso) then
force the SKB to partial and recalculate the checksum, since we cannot
rely on the peer having done so if they have not set csum_blank.

Add an ethtool stat to track occurances of this event.

Signed-off-by: Ian Campbell 
Cc: Jeremy Fitzhardinge 
Cc: David Miller 
Cc: xen-devel@lists.xensource.com
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller

net offloading: Pass features into netif_needs_gso().

2011-01-10T07:35:34+00:00

Now that there is a single function that can compute the device
features relevant to a packet, we don't want to run it for each
offload.  This converts netif_needs_gso() to take the features
of the device, rather than computing them itself.

Signed-off-by: Jesse Gross 
Signed-off-by: David S. Miller