A new vhost user message is added to allow QEMU to ask to vhost user backend to
broadcast a fake RARP after live migration for guest without GUEST_ANNOUNCE
capability.
This new message is sent only if the backend supports the new
VHOST_USER_PROTOCOL_F_RARP protocol feature.
The payload of this new message is the MAC address of the guest (not known by
the backend). The MAC address is copied in the first 6 bytes of a u64 to avoid
to create a new payload message type.
This new message has no equivalent ioctl so a new callback is added in the
userOps structure to send the request.
Upon reception of this new message the vhost user backend must generate and
broadcast a fake RARP request to notify the migration is terminated.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
[Rebased and fixed checkpatch errors - Marc-André]
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
Some vhost user backends are able to support live migration.
To provide this service the following features must be added:
1. Add the VIRTIO_NET_F_GUEST_ANNOUNCE capability to vhost-net when netdev
backend is vhost-user.
2. Provide a nop receive callback to vhost-user.
This callback is called by:
* qemu_announce_self after a migration to send fake RARP to avoid network
outage for peers talking to the migrated guest.
- For guest with GUEST_ANNOUNCE capabilities, guest already sends GARP
when the bit VIRTIO_NET_S_ANNOUNCE is set.
=> These packets must be discarded.
- For guest without GUEST_ANNOUNCE capabilities, migration termination
is notified when the guest sends packets.
=> These packets can be discarded.
* virtio_net_tx_bh with a dummy boot to send fake bootp/dhcp request.
BIOS guest manages virtio driver to send 4 bootp/dhcp request in case of
dummy boot.
=> These packets must be discarded.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
Replace the generic vhost_call() by specific functions for each
function call to help with type safety and changing arguments.
While doing this, I found that "unsigned long long" and "uint64_t" were
used interchangeably and causing compilation warnings, using uint64_t
instead, as the vhost & protocol specifies.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
[Fix enum usage and MQ - Thibaut Collet]
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
Version: GnuPG v1
iQEcBAABAgAGBQJWG2e/AAoJEO8Ells5jWIRcYcH/2D11W8cToCBjGDuw/u9K1ht
S3oGyFasOEq3lm3+a3zQE+vDw0RDkjLEMhcTVwNskJQl6k6Ts5JleTZ6wffvUKPM
UCozgPOCt1ZAdGskwdbByc+NhaVBHIiEsmlbDKqP22CENdDx6GWjcFW4brA4tQJQ
AW36EH77j/M+7/KiSukcUfIexILUZJRfN+ICJVyNTpGsqUNJtFqiVPBMPyJhKCEq
3pr3yJ2lf78SAEF5kBeBc9r/PDWUhtqExBsrK0L8Ey1FdrCy8ldqDPGecT4TsxNv
W/KX5AqhKSsMI8DQKdbv/IKaUdjYWNjTRQ2Qjm8Vt0hcW0PhxR0NYi6bV4yjDNM=
=f26Q
-----END PGP SIGNATURE-----
Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging
# gpg: Signature made Mon 12 Oct 2015 08:56:47 BST using RSA key ID 398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg: It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F 3562 EF04 965B 398D 6211
* remotes/jasowang/tags/net-pull-request:
tests: add test cases for netfilter object
netfilter: add a netbuffer filter
net/queue: export qemu_net_queue_append_iov
netfilter: print filter info associate with the netdev
netfilter: add an API to pass the packet to next filter
net/queue: introduce NetQueueDeliverFunc
net: merge qemu_deliver_packet and qemu_deliver_packet_iov
netfilter: hook packets before net queue send
init/cleanup of netfilter object
vl.c: init delayed object after net_init_clients
vmxnet3: Add support for VMXNET3_CMD_GET_ADAPTIVE_RING_INFO command
e1000: use alias for default model
vmxnet3: Support reading IMR registers on bar0
net/vmxnet3: Refine l2 header validation
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Some drivers (e.g. vmware-tools) issue the VMXNET3_CMD_GET_ADAPTIVE_RING_INFO
command.
Currently, due to lack of support, a bogus value (-1) is returned.
Support this command, returning the "adaptive-ring disabled" flag.
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@ravellosystems.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Instead of duplicating the "e1000-82540em" device model as "e1000",
make the latter an alias for the former.
Cc: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Instead of asserting, return the actual IMR register value.
This is aligned with what's returned on ESXi.
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@ravellosystems.com>
Tested-by: Dana Rubin <dana.rubin@ravellosystems.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Validation of l2 header length assumed minimal packet size as
eth_header + 2 * vlan_header regardless of the actual protocol.
This caused crash for valid non-IP packets shorter than 22 bytes, as
'tx_pkt->packet_type' hasn't been assigned for such packets, and
'vmxnet3_on_tx_done_update_stats()' expects it to be properly set.
Refine header length validation in 'vmxnet_tx_pkt_parse_headers'.
Check its return value during packet processing flow.
As a side effect, in case IPv4 and IPv6 header validation failure,
corrupt packets will be dropped.
Signed-off-by: Dana Rubin <dana.rubin@ravellosystems.com>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@ravellosystems.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
g_new(T, n) is neater than g_malloc(sizeof(T) * n). It's also safer,
for two reasons. One, it catches multiplication overflowing size_t.
Two, it returns T * rather than void *, which lets the compiler catch
more type errors.
This commit only touches allocations with size arguments of the form
sizeof(T). Same Coccinelle semantic patchas in commit b45c03f.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
When packet is truncated during receiving, we drop the packets but
neither discard the descriptor nor add and signal used
descriptor. This will lead several issues:
- sg mappings are leaked
- rx will be stalled if a lots of packets were truncated
In order to be consistent with vhost, fix by discarding the descriptor
in this case.
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Originally, timers were ticks based, and it made sense to
add ticks to current time to know when to trigger an alarm.
But since commit:
7447545 change all other clock references to use nanosecond resolution accessors
All timers use nanoseconds and we need to convert ticks to nanoseconds, by
doing something like:
y = muldiv64(x, get_ticks_per_sec(), PCI_FREQUENCY)
where x is the number of device ticks and y the number of system ticks.
y is used as nanoseconds in timer functions,
it works because 1 tick is 1 nanosecond.
(get_ticks_per_sec() is 10^9)
But as PCI frequency is 33 MHz, we can also do:
y = x * 30; /* 33 MHz PCI period is 30 ns */
Which is much more simple.
This implies a 33.333333 MHz PCI frequency,
but this is correct.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Originally, timers were ticks based, and it made sense to
add ticks to current time to know when to trigger an alarm.
But since commit:
7447545 change all other clock references to use nanosecond resolution accessors
All timers use nanoseconds and we need to convert ticks to nanoseconds, by
doing something like:
y = muldiv64(x, get_ticks_per_sec(), PCI_FREQUENCY)
where x is the number of device ticks and y the number of system ticks.
y is used as nanoseconds in timer functions,
it works because 1 tick is 1 nanosecond.
(get_ticks_per_sec() is 10^9)
But as PCI frequency is 33 MHz, we can also do:
y = x * 30; /* 33 MHz PCI period is 30 ns */
Which is much more simple.
This implies a 33.333333 MHz PCI frequency,
but this is correct.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Add a new message, VHOST_USER_SET_VRING_ENABLE, to enable or disable
a specific virt queue, which is similar to attach/detach queue for
tap device.
virtio driver on guest doesn't have to use max virt queue pair, it
could enable any number of virt queue ranging from 1 to max virt
queue pair.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Tested-by: Marcel Apfelbaum <marcel@redhat.com>
This patch is initially based a patch from Nikolay Nikolaev.
This patch adds vhost-user multiple queue support, by creating a nc
and vhost_net pair for each queue.
Qemu exits if find that the backend can't support the number of requested
queues (by providing queues=# option). The max number is queried by a
new message, VHOST_USER_GET_QUEUE_NUM, and is sent only when protocol
feature VHOST_USER_PROTOCOL_F_MQ is present first.
The max queue check is done at vhost-user initiation stage. We initiate
one queue first, which, in the meantime, also gets the max_queues the
backend supports.
In older version, it was reported that some messages are sent more times
than necessary. Here we came an agreement with Michael that we could
categorize vhost user messages to 2 types: non-vring specific messages,
which should be sent only once, and vring specific messages, which should
be sent per queue.
Here I introduced a helper function vhost_user_one_time_request(), which
lists following messages as non-vring specific messages:
VHOST_USER_SET_OWNER
VHOST_USER_RESET_DEVICE
VHOST_USER_SET_MEM_TABLE
VHOST_USER_GET_QUEUE_NUM
For above messages, we simply ignore them when they are not sent the first
time.
Signed-off-by: Nikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Tested-by: Marcel Apfelbaum <marcel@redhat.com>
This is for querying how many queues the backend supports if it has mq
support(when VHOST_USER_PROTOCOL_F_MQ flag is set from the quried
protocol features).
vhost_net_get_max_queues() is the interface to export that value, and
to tell if the backend supports # of queues user requested, which is
done in the following patch.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Tested-by: Marcel Apfelbaum <marcel@redhat.com>
Quote from Michael:
We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Tested-by: Marcel Apfelbaum <marcel@redhat.com>
Support a separate bitmask for vhost-user protocol features,
and messages to get/set protocol features.
Invoke them at init.
No features are defined yet.
[ leverage vhost_user_call for request handling -- Yuanhan Liu ]
Signed-off-by: Michael S. Tsirkin <address@hidden>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Tested-by: Marcel Apfelbaum <marcel@redhat.com>
After commit 019a3edbb2 ("virtio: make
features 64bit wide"). Device's guest_features was actually set after
vdc->load(). This breaks the assumption that device specific load()
function can check guest_features. For virtio-net, self announcement
and guest offloads won't work after migration.
Fixing this by defer them to virtio_net_load() where guest_features
were guaranteed to be set. Other virtio devices looks fine.
Fixes: 019a3edbb2
("virtio: make features 64bit wide")
Cc: qemu-stable@nongnu.org
Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Symptom:
$ qemu-system-x86_64 -m 10000000
Unexpected error in ram_block_add() at /work/armbru/qemu/exec.c:1456:
upstream-qemu: cannot set up guest memory 'pc.ram': Cannot allocate memory
Aborted (core dumped)
Root cause: commit ef701d7 screwed up handling of out-of-memory
conditions. Before the commit, we report the error and exit(1), in
one place, ram_block_add(). The commit lifts the error handling up
the call chain some, to three places. Fine. Except it uses
&error_abort in these places, changing the behavior from exit(1) to
abort(), and thus undoing the work of commit 3922825 "exec: Don't
abort when we can't allocate guest memory".
The three places are:
* memory_region_init_ram()
Commit 4994653 (right after commit ef701d7) lifted the error
handling further, through memory_region_init_ram(), multiplying the
incorrect use of &error_abort. Later on, imitation of existing
(bad) code may have created more.
* memory_region_init_ram_ptr()
The &error_abort is still there.
* memory_region_init_rom_device()
Doesn't need fixing, because commit 33e0eb5 (soon after commit
ef701d7) lifted the error handling further, and in the process
changed it from &error_abort to passing it up the call chain.
Correct, because the callers are realize() methods.
Fix the error handling after memory_region_init_ram() with a
Coccinelle semantic patch:
@r@
expression mr, owner, name, size, err;
position p;
@@
memory_region_init_ram(mr, owner, name, size,
(
- &error_abort
+ &error_fatal
|
err@p
)
);
@script:python@
p << r.p;
@@
print "%s:%s:%s" % (p[0].file, p[0].line, p[0].column)
When the last argument is &error_abort, it gets replaced by
&error_fatal. This is the fix.
If the last argument is anything else, its position is reported. This
lets us check the fix is complete. Four positions get reported:
* ram_backend_memory_alloc()
Error is passed up the call chain, ultimately through
user_creatable_complete(). As far as I can tell, it's callers all
handle the error sanely.
* fsl_imx25_realize(), fsl_imx31_realize(), dp8393x_realize()
DeviceClass.realize() methods, errors handled sanely further up the
call chain.
We're good. Test case again behaves:
$ qemu-system-x86_64 -m 10000000
qemu-system-x86_64: cannot set up guest memory 'pc.ram': Cannot allocate memory
[Exit 1 ]
The next commits will repair the rest of commit ef701d7's damage.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <1441983105-26376-3-git-send-email-armbru@redhat.com>
Reviewed-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
The SOFT_RST or RXEN in the control register can be used as a condition
to unblock the net layer via can_receive(). So check for possible
flushes on RCR changes. This will drop all pending packets on soft
reset or disable which is the functional intent of the can_receive()
logic.
Signed-off-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Tested-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Message-id: b114d4c96f4afbdaa15f1361d9c07e3021755915.1441873621.git.crosthwaite.peter@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Return false from can_receive() when the FIFO doesn't have a free RX
slot. This fixes a bug in the current code where the allocated buffer
is freed before the fifo pop, triggering a premature flush of queued RX
packets. It also will handle a corner case, where the guest manually
frees the allocated buffer before popping the rx FIFO (hence it is not
enough to just delay the flush_queued_packets()).
Reported-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Signed-off-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Tested-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Message-id: 97bfdfc5cbce0bd5e0cbbbff35ce7a1bf6f8603d.1441873621.git.crosthwaite.peter@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Check that the core can once again receive packets before asking the
net layer to do a flush. This will make it more convenient to flush
packets when adding new conditions to can_receive.
Add missing if braces while moving the can_receive() core code.
Signed-off-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Tested-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Message-id: 92e15e12a6964274f4bc0eb71b61a7d94326f6c6.1441873621.git.crosthwaite.peter@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Ne2000 NIC uses ring buffer of NE2000_MEM_SIZE(49152)
bytes to process network packets. While receiving packets
via ne2000_receive() routine, a local 'index' variable
could exceed the ring buffer size, leading to an infinite
loop situation.
Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: P J P <pjp@fedoraproject.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Ne2000 NIC uses ring buffer of NE2000_MEM_SIZE(49152)
bytes to process network packets. While receiving packets
via ne2000_receive() routine, a local 'index' variable
could exceed the ring buffer size, which could lead to a
memory buffer overflow. Added other checks at initialisation.
Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: P J P <pjp@fedoraproject.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
While processing transmit descriptors, it could lead to an infinite
loop if 'bytes' was to become zero; Add a check to avoid it.
[The guest can force 'bytes' to 0 by setting the hdr_len and mss
descriptor fields to 0.
--Stefan]
Signed-off-by: P J P <pjp@fedoraproject.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-id: 1441383666-6590-1-git-send-email-stefanha@redhat.com
My Coccinelle semantic patch finds a few more, because it also fixes up
the equally pointless conditional
if (foo) {
free(foo);
foo = NULL;
}
Result (feel free to squash it into your patch):
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
The free() and g_free() functions both happily accept
NULL on any platform QEMU builds on. As such putting a
conditional 'if (foo)' check before calls to 'free(foo)'
merely serves to bloat the lines of code.
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
A number of files were including signal.h but not using any
of the functions it provides
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Many source files have doubled words (eg "the the", "to to",
and so on). Most of these can simply be removed, but a couple
were actual mis-spellings (eg "to to" instead of "to do").
There was even one triple word score "to to to" :-)
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Commit ef546f1275 ("virtio: add
feature checking helpers") introduced a helper __virtio_has_feature.
We don't want to use reserved identifiers, though, so let's
rename __virtio_has_feature to virtio_has_feature and virtio_has_feature
to virtio_vdev_has_feature.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Bit 15 of the PHY Specific Status Register is reserved and
should remain 0. Fix the reset value to ensure that the 15th
bit is not set.
Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Message-id: c795069e49040ff770fe2ece19dfe1791b729e22.1441316450.git.alistair.francis@xilinx.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This is based on mcf_fec.c FEC implementation for Coldfire
* A generic PHY was added (borrowwed from LAN9118)
* The buffer management is also modified as buffers are
slightly different between Coldfire and i.MX
Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net>
Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Message-id: fb314f8a120aa49f8f6ad886f312c649b484fb5a.1441057361.git.jcd@tribudubois.net
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
ne2000_receive already checks the same conditions and drops the packet
if it's not ready, removing the .can_receive callback avoids the
necessity to add explicit flushes when the conditions turn true (which
is required by the new semantics of .can_receive since 6e99c63
"net/socket: Drop net_socket_can_send").
Plus the "return 1" if E8390_STOP is also suspicious.
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Commit 6e99c63 ("net/socket: Drop net_socket_can_send") changed the
semantics around .can_receive for sockets to now require the device to
flush queued pkts when transitioning to a .can_receive=true state. But
it's OK to drop incoming packets when the link is not active.
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
When operation in standard mode, we currently return the size
of packet during buffer overflow. This consumes the overflow
packet. Return 0 instead so we can re-process the overflow packet
when we have room.
This fixes issues with lost/dropped fragments of large messages.
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Message-id: 1441121206-6997-3-git-send-email-vyasevic@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
rtl8139_do_receive() tries to check for the overflow condition
by making sure that packet_size + 8 does not exceed the
available buffer space. The issue here is that RxBuffAddr,
used to calculate available buffer space, is aligned to a
a 4 byte boundry after every update. So it is possible that
every packet ends up being slightly padded when written
to the receive buffer. This padding is not taken into
account when checking for overflow and we may end up missing
the overflow condition can causing buffer overwrite.
This patch takes alignment into consideration when
checking for overflow condition.
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Message-id: 1441121206-6997-2-git-send-email-vyasevic@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The tx offload feature accesses a 16-bit aligned TCP header struct. The
32-bit fields must be accessed using ldl/stl wrappers since some host
architectures fault on unaligned access.
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Message-id: 1438604157-29664-4-git-send-email-stefanha@redhat.com
Eliminate the following "custom" macros since they are just duplicates
of net/eth.h macros under a different name:
ETHER_ADDR_LEN -> ETH_ALEN
ETH_P_8021Q -> ETH_P_VLAN
IP_HEADER_LENGTH -> IP_HDR_GET_LEN
TCP_FLAG_FIN -> TH_FIN
TCP_FLAG_PUSH -> TH_PUSH
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Message-id: 1438604157-29664-3-git-send-email-stefanha@redhat.com
The transmit offload features inspect Ethernet, IP, TCP, and UDP
headers. Avoid redefining these net/eth.h structs.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Message-id: 1438604157-29664-2-git-send-email-stefanha@redhat.com
After commit 40bad8f3deba15e2074ff34cfe923c12916b1cc5("virtio-net: fix
used len for tx"), async_tx.len was no longer used afterwards. So
remove useless codes with it.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
From: Dana Rubin <dana.rubin@ravellosystems.com>
In commit 80da311d81,
"net/vmxnet3: Fix RX TCP/UDP checksum on partially summed packets"
a debug message was introduced in vmxnet3_rx_need_csum_calculate() for
an unlikely input condition.
The message accidentally printed 'len' variable instead of 'pkt_len'.
Fix, providing the correct argument.
Signed-off-by: Dana Rubin <dana.rubin@ravellosystems.com>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@ravellosystems.com>
Message-id: 1438109090-18957-1-git-send-email-shmulik.ladkani@ravellosystems.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The TCP Data Offset field contains the length of the header. Make sure
it is valid and does not exceed the IP data length.
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
TCP Large Segment Offload accesses the TCP header in the packet. If the
packet is too short we must not attempt to access header fields:
tcp_header *p_tcp_hdr = (tcp_header*)(eth_payload_data + hlen);
int tcp_hlen = TCP_HEADER_DATA_OFFSET(p_tcp_hdr);
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The IP Total Length field includes the IP header and data. Make sure it
is valid and does not exceed the Ethernet payload size.
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The IP Header Length field was only checked in the IP checksum case, but
is used in other cases too.
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Transmit offload features access Ethernet and IP headers the packet. If
the packet is too short we must not attempt to access header fields:
int proto = be16_to_cpu(*(uint16_t *)(saved_buffer + 12));
...
eth_payload_data = saved_buffer + ETH_HLEN;
...
ip = (ip_header*)eth_payload_data;
if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The previous patch stopped using the ip pointer as an indicator that the
IP header is present. When we reach the if (ip) {...} statement we know
ip is always non-NULL.
Remove the if statement to reduce nesting.
Reported-by: 朱东海(启路) <donghai.zdh@alibaba-inc.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
