The recent patch to fix receive side flow control
(11b57f9025: xen-netback: stop vif thread
spinning if frontend is unresponsive) solved the spinning thread problem,
however caused an another one. The receive side can stall, if:
- [THREAD] xenvif_rx_action sets rx_queue_stopped to true
- [INTERRUPT] interrupt happens, and sets rx_event to true
- [THREAD] then xenvif_kthread sets rx_event to false
- [THREAD] rx_work_todo doesn't return true anymore
Also, if interrupt sent but there is still no room in the ring, it take quite a
long time until xenvif_rx_action realize it. This patch ditch that two variable,
and rework rx_work_todo. If the thread finds it can't fit more skb's into the
ring, it saves the last slot estimation into rx_last_skb_slots, otherwise it's
kept as 0. Then rx_work_todo will check if:
- there is something to send to the ring (like before)
- there is space for the topmost packet in the queue
I think that's more natural and optimal thing to test than two bool which are
set somewhere else.
Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use skb_checksum_setup to set up partial checksum offsets rather
then a private implementation.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The recent patch to improve guest receive side flow control (ca2f09f2) had a
slight flaw in the wait condition for the vif thread in that any remaining
skbs in the guest receive side netback internal queue would prevent the
thread from sleeping. An unresponsive frontend can lead to a permanently
non-empty internal queue and thus the thread will spin. In this case the
thread should really sleep until the frontend becomes responsive again.
This patch adds an extra flag to the vif which is set if the shared ring
is full and cleared when skbs are drained into the shared ring. Thus,
if the thread runs, finds the shared ring full and can make no progress the
flag remains set. If the flag remains set then the thread will sleep,
regardless of a non-empty queue, until the next event from the frontend.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
net/ipv6/ip6_tunnel.c
net/ipv6/ip6_vti.c
ipv6 tunnel statistic bug fixes conflicting with consolidation into
generic sw per-cpu net stats.
qlogic conflict between queue counting bug fix and the addition
of multiple MAC address support.
Signed-off-by: David S. Miller <davem@davemloft.net>
The sizes chosen for the metadata and grant_copy_op arrays on the guest
receive size are wrong;
- The meta array is needlessly twice the ring size, when we only ever
consume a single array element per RX ring slot
- The grant_copy_op array is way too small. It's sized based on a bogus
assumption: that at most two copy ops will be used per ring slot. This
may have been true at some point in the past but it's clear from looking
at start_new_rx_buffer() that a new ring slot is only consumed if a frag
would overflow the current slot (plus some other conditions) so the actual
limit is MAX_SKB_FRAGS grant_copy_ops per ring slot.
This patch fixes those two sizing issues and, because grant_copy_ops grows
so much, it pulls it out into a separate chunk of vmalloc()ed memory.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netback already has code which parses IPv4 and v6 headers to set up checksum
offsets and these are always applied to GSO packets being sent from
frontends. It's therefore suboptimal that GSOs are being marked
SKB_GSO_DODGY to defer the gso_segs calculation when netback already has all
necessary information to hand to do the calculation. This patch adds that
calculation.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'err' is overwrited to 0 after maybe_pull_tail() call, so the error
code was not set if skb_partial_csum_set() call failed. Fix to return
error -EPROTO from those error handling case instead of 0.
Fixes: d52eb0d46f ('xen-netback: make sure skb linear area covers checksum field')
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/intel/i40e/i40e_main.c
drivers/net/macvtap.c
Both minor merge hassles, simple overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix to return -EPROTO error if fragments detected in checksum_setup_ip().
Fixes: 1431fb31ec ('xen-netback: fix fragment detection in checksum setup')
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a mistake in checking the gso_prefix mask when passing large
packets to a guest. The wrong shift is applied to the bit - the raw skb
gso type is used rather then the translated one. This leads to large packets
being handed to the guest without the GSO metadata. This patch fixes the
check.
The mistake manifested as errors whilst running Microsoft HCK large packet
offload tests between a pair of Windows 8 VMs. I have verified this patch
fixes those errors.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch changes the RING_FINAL_CHECK_FOR_REQUESTS in
xenvif_build_tx_gops to a check for RING_HAS_UNCONSUMED_REQUESTS as the
former call has the side effect of advancing the ring event pointer and
therefore inviting another interrupt from the frontend before the napi
poll has actually finished, thereby defeating the point of napi.
The event pointer is updated by RING_FINAL_CHECK_FOR_REQUESTS in
xenvif_poll, the napi poll function, if the work done is less than the
budget i.e. when actually transitioning back to interrupt mode.
Reported-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netback seems to be somewhat confused about the napi budget parameter. The
parameter is supposed to limit the number of skbs processed in each poll,
but netback has this confused with grant operations.
This patch fixes that, properly limiting the work done in each poll. Note
that this limit makes sure we do not process any more data from the shared
ring than we intend to pass back from the poll. This is important to
prevent tx_queue potentially growing without bound.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_partial_csum_set requires that the linear area of the skb covers the
checksum field. The checksum setup code in netback was only doing that
pullup in the case when the pseudo header checksum was being recalculated
though. This patch makes that pullup unconditional. (I pullup the whole
transport header just for simplicity; the requirement is only for the check
field but in the case of UDP this is the last field in the header and in the
case of TCP it's the last but one).
The lack of pullup manifested as failures running Microsoft HCK network
tests on a pair of Windows 8 VMs and it has been verified that this patch
fixes the problem.
Suggested-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The way that flow control works without this patch is that, in start_xmit()
the code uses xenvif_count_skb_slots() to predict how many slots
xenvif_gop_skb() will consume and then adds this to a 'req_cons_peek'
counter which it then uses to determine if the shared ring has that amount
of space available by checking whether 'req_prod' has passed that value.
If the ring doesn't have space the tx queue is stopped.
xenvif_gop_skb() will then consume slots and update 'req_cons' and issue
responses, updating 'rsp_prod' as it goes. The frontend will consume those
responses and post new requests, by updating req_prod. So, req_prod chases
req_cons which chases rsp_prod, and can never exceed that value. Thus if
xenvif_count_skb_slots() ever returns a number of slots greater than
xenvif_gop_skb() uses, req_cons_peek will get to a value that req_prod cannot
possibly achieve (since it's limited by the 'real' req_cons) and, if this
happens enough times, req_cons_peek gets more than a ring size ahead of
req_cons and the tx queue then remains stopped forever waiting for an
unachievable amount of space to become available in the ring.
Having two routines trying to calculate the same value is always going to be
fragile, so this patch does away with that. All we essentially need to do is
make sure that we have 'enough stuff' on our internal queue without letting
it build up uncontrollably. So start_xmit() makes a cheap optimistic check
of how much space is needed for an skb and only turns the queue off if that
is unachievable. net_rx_action() is the place where we could do with an
accurate predicition but, since that has proven tricky to calculate, a cheap
worse-case (but not too bad) estimate is all we really need since the only
thing we *must* prevent is xenvif_gop_skb() consuming more slots than are
available.
Without this patch I can trivially stall netback permanently by just doing
a large guest to guest file copy between two Windows Server 2008R2 VMs on a
single host.
Patch tested with frontends in:
- Windows Server 2008R2
- CentOS 6.0
- Debian Squeeze
- Debian Wheezy
- SLES11
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Annie Li <annie.li@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The code to detect fragments in checksum_setup() was missing for IPv4 and
too eager for IPv6. (It transpires that Windows seems to send IPv6 packets
with a fragment header even if they are not a fragment - i.e. offset is zero,
and M bit is not set).
This patch also incorporates a fix to callers of maybe_pull_tail() where
skb->network_header was being erroneously added to the length argument.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
cc: David Miller <davem@davemloft.net>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We are now using csum_ipv6_magic, include the appropriate header.
Avoids the following error:
drivers/net/xen-netback/netback.c:1313:4: error: implicit declaration of function 'csum_ipv6_magic' [-Werror=implicit-function-declaration]
tcph->check = ~csum_ipv6_magic(&ipv6h->saddr,
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/emulex/benet/be.h
drivers/net/netconsole.c
net/bridge/br_private.h
Three mostly trivial conflicts.
The net/bridge/br_private.h conflict was a function signature (argument
addition) change overlapping with the extern removals from Joe Perches.
In drivers/net/netconsole.c we had one change adjusting a printk message
whilst another changed "printk(KERN_INFO" into "pr_info(".
Lastly, the emulex change was a new inline function addition overlapping
with Joe Perches's extern removals.
Signed-off-by: David S. Miller <davem@davemloft.net>
time_after_eq() only works if the delta is < MAX_ULONG/2.
For a 32bit Dom0, if netfront sends packets at a very low rate, the time
between subsequent calls to tx_credit_exceeded() may exceed MAX_ULONG/2
and the test for timer_after_eq() will be incorrect. Credit will not be
replenished and the guest may become unable to send packets (e.g., if
prior to the long gap, all credit was exhausted).
Use jiffies_64 variant to mitigate this problem for 32bit Dom0.
Suggested-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Jason Luan <jianhai.luan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds code to handle SKB_GSO_TCPV6 skbs and construct appropriate
extra or prefix segments to pass the large packet to the frontend. New
xenstore flags, feature-gso-tcpv6 and feature-gso-tcpv6-prefix, are sampled
to determine if the frontend is capable of handling such packets.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a xenstore feature flag, festure-gso-tcpv6, to advertise
that netback can handle IPv6 TCP GSO packets. It creates SKB_GSO_TCPV6 skbs
if the frontend passes an extra segment with the new type
XEN_NETIF_GSO_TYPE_TCPV6 added to netif.h.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For performance of VM to VM traffic on a single host it is better to avoid
calculation of TCP/UDP checksum in the sending frontend. To allow this this
patch adds the code necessary to set up partial checksum for IPv6 packets
and xenstore flag feature-ipv6-csum-offload to advertise that fact to
frontends.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 4f0581d258.
The named changeset is causing problem. Let's aim to make this part less
fragile before trying to improve things.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Annie Li <annie.li@oracle.com>
Cc: Matt Wilson <msw@amazon.com>
Cc: Xi Xiong <xixiong@amazon.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There was a bug that netback routines netbk/xenvif_skb_count_slots and
netbk/xenvif_gop_frag_copy disagreed with each other, which caused
netback to push wrong number of responses to netfront, which caused
netfront to eventually crash. The bug was fixed in 6e43fc04a
("xen-netback: count number required slots for an skb more carefully").
Commit 6e43fc04a focused on backport-ability. The drawback with the
existing packing scheme is that the ring is not used effeciently, as
stated in 6e43fc04a.
skb->data like:
| 1111|222222222222|3333 |
is arranged as:
|1111 |222222222222|3333 |
If we can do this:
|111122222222|22223333 |
That would save one ring slot, which improves ring effeciency.
This patch effectively reverts 6e43fc04a. That patch made count_slots
agree with gop_frag_copy, while this patch goes the other way around --
make gop_frag_copy agree with count_slots. The end result is that they
still agree with each other, and the ring is now arranged like:
|111122222222|22223333 |
The patch that improves packing was first posted by Xi Xong and Matt
Wilson. I only rebase it on top of net-next and rewrite commit message,
so I retain all their SoBs. For more infomation about the original bug
please refer to email listed below and commit message of 6e43fc04a.
Original patch:
http://lists.xen.org/archives/html/xen-devel/2013-07/msg00760.html
Signed-off-by: Xi Xiong <xixiong@amazon.com>
Reviewed-by: Matt Wilson <msw@amazon.com>
[ msw: minor code cleanups, rewrote commit message, adjusted code
to count RX slots instead of meta structures ]
Signed-off-by: Matt Wilson <msw@amazon.com>
Cc: Annie Li <annie.li@oracle.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
[ liuw: rebased on top of net-next tree, rewrote commit message, coding
style cleanup. ]
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <Ian.Campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a VM is providing an iSCSI target and the LUN is used by the
backend domain, the generated skbs for direct I/O writes to the disk
have large, multi-page skb->data but no frags.
With some lengths and starting offsets, xen_netbk_count_skb_slots()
would be one short because the simple calculation of
DIV_ROUND_UP(skb_headlen(), PAGE_SIZE) was not accounting for the
decisions made by start_new_rx_buffer() which does not guarantee
responses are fully packed.
For example, a skb with length < 2 pages but which spans 3 pages would
be counted as requiring 2 slots but would actually use 3 slots.
skb->data:
| 1111|222222222222|3333 |
Fully packed, this would need 2 slots:
|111122222222|22223333 |
But because the 2nd page wholy fits into a slot it is not split across
slots and goes into a slot of its own:
|1111 |222222222222|3333 |
Miscounting the number of slots means netback may push more responses
than the number of available requests. This will cause the frontend
to get very confused and report "Too many frags/slots". The frontend
never recovers and will eventually BUG.
Fix this by counting the number of required slots more carefully. In
xen_netbk_count_skb_slots(), more closely follow the algorithm used by
xen_netbk_gop_skb() by introducing xen_netbk_count_frag_slots() which
is the dry-run equivalent of netbk_gop_frag_copy().
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As we move to 1:1 model and melt xen_netbk and xenvif together, it would
be better to use single prefix for all functions in xen-netback.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements 1:1 model netback. NAPI and kthread are utilized
to do the weight-lifting job:
- NAPI is used for guest side TX (host side RX)
- kthread is used for guest side RX (host side TX)
Xenvif and xen_netbk are made into one structure to reduce code size.
This model provides better scheduling fairness among vifs. It is also
prerequisite for implementing multiqueue for Xen netback.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The data flow from DomU to DomU on the same host in current copying
scheme with tracking facility:
copy
DomU --------> Dom0 DomU
| ^
|____________________________|
copy
The page in Dom0 is a page with valid MFN. So we can always copy from
page Dom0, thus removing the need for a tracking facility.
copy copy
DomU --------> Dom0 -------> DomU
Simple iperf test shows no performance regression (obviously we copy
twice either way):
W/ tracking: ~5.3Gb/s
W/o tracking: ~5.4Gb/s
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Matt Wilson <msw@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of mixing printk and pr_<level> forms,
just use pr_<level>
Miscellaneous changes around these conversions:
Add a missing newline to avoid message interleaving,
coalesce formats, reflow modified lines to 80 columns.
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a typo here, "i" vs "j", so we would crash on module_exit().
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/wireless/ath/ath9k/Kconfig
drivers/net/xen-netback/netback.c
net/batman-adv/bat_iv_ogm.c
net/wireless/nl80211.c
The ath9k Kconfig conflict was a change of a Kconfig option name right
next to the deletion of another option.
The xen-netback conflict was overlapping changes involving the
handling of the notify list in xen_netbk_rx_action().
Batman conflict resolution provided by Antonio Quartulli, basically
keep everything in both conflict hunks.
The nl80211 conflict is a little more involved. In 'net' we added a
dynamic memory allocation to nl80211_dump_wiphy() to fix a race that
Linus reported. Meanwhile in 'net-next' the handlers were converted
to use pre and post doit handlers which use a flag to determine
whether to hold the RTNL mutex around the operation.
However, the dump handlers to not use this logic. Instead they have
to explicitly do the locking. There were apparent bugs in the
conversion of nl80211_dump_wiphy() in that we were not dropping the
RTNL mutex in all the return paths, and it seems we very much should
be doing so. So I fixed that whilst handling the overlapping changes.
To simplify the initial returns, I take the RTNL mutex after we try
to allocate 'tb'.
Signed-off-by: David S. Miller <davem@davemloft.net>
When putting vif-s on the rx notify list, calling xenvif_put() must be
deferred until after the removal from the list and the issuing of the
notification, as both operations dereference the pointer.
Changing this got me to notice that the "irq" variable was effectively
unused (and was of too narrow type anyway).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Netback and netfront only use one event channel to do TX / RX notification,
which may cause unnecessary wake-up of processing routines. This patch adds a
new feature called feature-split-event-channels to netback, enabling it to
handle TX and RX events separately.
Netback will use tx_irq to notify guest for TX completion, rx_irq for RX
notification.
If frontend doesn't support this feature, tx_irq equals to rx_irq.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables user to unload netback module, which is useful when user
wants to upgrade to a newer netback module without rebooting the host.
Netfront cannot handle netback removal event. As we cannot fix all possible
frontends we add module get / put along with vif get / put to avoid
mis-unloading of netback. To unload netback module, user needs to shutdown all
VMs or migrate them to another host or unplug all vifs before hand.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>¬
Signed-off-by: David S. Miller <davem@davemloft.net>
The array mmap_pages is never touched in the initialization function. This is
remnant of mapping mechanism, which does not exist upstream. In current
upstream code this array only tracks usage of pages inside netback. Those
pages are allocated when contructing a SKB and passed directly to network
subsystem.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch only changes some names to avoid confusion.
In this patch we have:
MAX_SKB_SLOTS_DEFAULT -> FATAL_SKB_SLOTS_DEFAULT
max_skb_slots -> fatal_skb_slots
#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
The fatal_skb_slots is the threshold to determine whether a packet is
malicious.
XEN_NETBK_LEGACY_SLOTS_MAX is the maximum slots a valid packet can have at
this point. It is defined to be XEN_NETIF_NR_SLOTS_MIN because that's
guaranteed to be supported by all backends.
Suggested-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tune xen_netbk_count_requests to not touch working array beyond limit, so that
we can make working array size constant.
Suggested-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tracking down from the caller, first_idx is always equal to vif->tx.req_cons.
Remove it to avoid confusion.
Suggested-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some frontend drivers are sending packets > 64 KiB in length. This length
overflows the length field in the first slot making the following slots have
an invalid length.
Turn this error back into a non-fatal error by dropping the packet. To avoid
having the following slots having fatal errors, consume all slots in the
packet.
This does not reopen the security hole in XSA-39 as if the packet as an
invalid number of slots it will still hit fatal error case.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch tries to coalesce tx requests when constructing grant copy
structures. It enables netback to deal with situation when frontend's
MAX_SKB_FRAGS is larger than backend's MAX_SKB_FRAGS.
With the help of coalescing, this patch tries to address two regressions
avoid reopening the security hole in XSA-39.
Regression 1. The reduction of the number of supported ring entries (slots)
per packet (from 18 to 17). This regression has been around for some time but
remains unnoticed until XSA-39 security fix. This is fixed by coalescing
slots.
Regression 2. The XSA-39 security fix turning "too many frags" errors from
just dropping the packet to a fatal error and disabling the VIF. This is fixed
by coalescing slots (handling 18 slots when backend's MAX_SKB_FRAGS is 17)
which rules out false positive (using 18 slots is legit) and dropping packets
using 19 to `max_skb_slots` slots.
To avoid reopening security hole in XSA-39, frontend sending packet using more
than max_skb_slots is considered malicious.
The behavior of netback for packet is thus:
1-18 slots: valid
19-max_skb_slots slots: drop and respond with an error
max_skb_slots+ slots: fatal error
max_skb_slots is configurable by admin, default value is 20.
Also change variable name from "frags" to "slots" in netbk_count_requests.
Please note that RX path still has dependency on MAX_SKB_FRAGS. This will be
fixed with separate patch.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch to use skb_partial_csum_set() to simplify the codes.
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch to use the new help skb_probe_transport_header() to do the l4 header
probing for untrusted sources. For packets with partial csum, the header should
already been set by skb_partial_csum_set().
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, for the packets receives from netback, before doing header check,
kernel just reset the transport header in netif_receive_skb() which pretends non
l4 header. This is suboptimal for precise packet length estimation (introduced
in 1def9238: net_sched: more precise pkt_len computation) which needs correct l4
header for gso packets.
The patch just reuse the header probed by netback for partial checksum packets
and tries to use skb_flow_dissect() for other cases, if both fail, just pretend
no l4 header.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This variable is never used.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit d37204566a.
This change is incorrect, as per Jan Beulich:
====================
But this is wrong from all we can tell, we discussed this before
(Wei pointed to the discussion in an earlier reply). The core of
it is that the put here parallels the one in netbk_tx_err(), and
the one in xenvif_carrier_off() matches the get from
xenvif_connect() (which normally would be done on the path
coming through xenvif_disconnect()).
====================
And a previous discussion of this issue is at:
http://marc.info/?l=xen-devel&m=136084174026977&w=2
Signed-off-by: David S. Miller <davem@davemloft.net>
netbk_fatal_tx_err() calls xenvif_carrier_off(), which does
a xenvif_put(). As callers of netbk_fatal_tx_err should only
have one reference to the vif at this time, then the xenvif_put
in netbk_fatal_tx_err is one too many.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netbk_count_requests() could detect an error, call
netbk_fatal_tx_error() but return 0. The vif may then be used
afterwards (e.g., in a call to netbk_tx_error().
Since netbk_fatal_tx_error() could set vif->refcnt to 1, the vif may
be freed immediately after the call to netbk_fatal_tx_error() (e.g.,
if the vif is also removed).
Netback thread Xenwatch thread
-------------------------------------------
netbk_fatal_tx_err() netback_remove()
xenvif_disconnect()
...
free_netdev()
netbk_tx_err() Oops!
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reported-by: Christopher S. Aker <caker@theshore.net>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Matthew Daley <mattjd@gmail.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
