TX/RX callback handlers (ntb_netdev_tx_handler(),
ntb_netdev_rx_handler()) can be called in interrupt
context via the DMA framework when the respective
DMA operations have completed. As such, any calls
by these routines to free skb's, should use the
interrupt context safe dev_kfree_skb_any() function.
Previously, these callback handlers would call the
interrupt unsafe version of dev_kfree_skb(). This has
not presented an issue on Intel IOAT DMA engines as
that driver utilizes tasklets rather than a hard
interrupt handler, like the AMD PTDMA DMA driver.
On AMD systems, a kernel WARNING message is
encountered, which is being issued from
skb_release_head_state() due to in_hardirq()
being true.
Besides the user visible WARNING from the kernel,
the other symptom of this bug was that TCP/IP performance
across the ntb_netdev interface was very poor, i.e.
approximately an order of magnitude below what was
expected. With the repair to use dev_kfree_skb_any(),
kernel WARNINGs from skb_release_head_state() ceased
and TCP/IP performance, as measured by iperf, was on
par with expected results, approximately 20 Gb/s on
AMD Milan based server. Note that this performance
is comparable with Intel based servers.
Fixes: 765ccc7bc3 ("ntb_netdev: correct skb leak")
Fixes: 548c237c0a ("net: Add support for NTB virtual ethernet device")
Signed-off-by: Eric Pilmore <epilmore@gigaio.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/20221209000659.8318-1-epilmore@gigaio.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The ntb_netdev_init_module() returns the ntb_transport_register_client()
directly without checking its return value, if
ntb_transport_register_client() failed, the NTB client device is not
unregistered.
Fix by unregister NTB client device when ntb_transport_register_client()
failed.
Fixes: 548c237c0a ("net: Add support for NTB virtual ethernet device")
Signed-off-by: Yuan Can <yuancan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dave suggested a while ago (eleven years by now) "Let's make netif_rx()
work in all contexts and get rid of netif_rx_ni()". Eric agreed and
pointed out that modern devices should use netif_receive_skb() to avoid
the overhead.
In the meantime someone added another variant, netif_rx_any_context(),
which behaves as suggested.
netif_rx() must be invoked with disabled bottom halves to ensure that
pending softirqs, which were raised within the function, are handled.
netif_rx_ni() can be invoked only from process context (bottom halves
must be enabled) because the function handles pending softirqs without
checking if bottom halves were disabled or not.
netif_rx_any_context() invokes on the former functions by checking
in_interrupts().
netif_rx() could be taught to handle both cases (disabled and enabled
bottom halves) by simply disabling bottom halves while invoking
netif_rx_internal(). The local_bh_enable() invocation will then invoke
pending softirqs only if the BH-disable counter drops to zero.
Eric is concerned about the overhead of BH-disable+enable especially in
regard to the loopback driver. As critical as this driver is, it will
receive a shortcut to avoid the additional overhead which is not needed.
Add a local_bh_disable() section in netif_rx() to ensure softirqs are
handled if needed.
Provide __netif_rx() which does not disable BH and has a lockdep assert
to ensure that interrupts are disabled. Use this shortcut in the
loopback driver and in drivers/net/*.c.
Make netif_rx_ni() and netif_rx_any_context() invoke netif_rx() so they
can be removed once they are no more users left.
Link: https://lkml.kernel.org/r/20100415.020246.218622820.davem@davemloft.net
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use dev_addr_set() instead of writing directly to netdev->dev_addr
in various misc and old drivers.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace the elaborate private structure global linked-list used in
ntb_netdev_probe() and ntb_netdev_remove() by stashing our private
data in the NTB transport client device.
Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The tx_time should be in usecs (according to the comment above the
variable), but the setting of the timer during the rearming is done in
msecs. Change it to match the expected units.
Fixes: e74bfeedad ("NTB: Add flow control to the ntb_netdev")
Suggested-by: Gerd W. Haeussler <gerd.haeussler@cesys-it.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Acked-by: Dave Jiang <dave.jiang@intel.com>
random_ether_addr is a #define for eth_random_addr which is
generally preferred in kernel code by ~3:1
Convert the uses of random_ether_addr to enable removing the #define
Miscellanea:
o Convert &vfmac[0] to equivalent vfmac and avoid unnecessary line wrap
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Jon Mason <jdmason@kudzu.us>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Allen Hubbe <Allen.Hubbe@emc.com>
Cc: linux-ntb@googlegroups.com
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
At present, ntb_netdev devices end up under /sys/devices/virtual/net
completely unconnected to the ntb trees below them. This patch sets the
parent of the net_device (using SET_NETDEV_DEV) to the client_dev
device. This results in a better connected sysfs path for the network
device:
/sys/devices/pci0000:00/0000:00:03.0/0000:03:00.1/0000:03:00.1/ntb_netdev0/net/eth2
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The ethtool api {get|set}_settings is deprecated.
We move this driver to new api {get|set}_link_ksettings.
As I don't have the hardware, I'd be very pleased if
someone may test this patch.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
geneve:
- Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu
- This one isn't quite as straight-forward as others, could use some
closer inspection and testing
macvlan:
- set min/max_mtu
tun:
- set min/max_mtu, remove tun_net_change_mtu
vxlan:
- Merge __vxlan_change_mtu back into vxlan_change_mtu
- Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in
change_mtu function
- This one is also not as straight-forward and could use closer inspection
and testing from vxlan folks
bridge:
- set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in
change_mtu function
openvswitch:
- set min/max_mtu, remove internal_dev_change_mtu
- note: max_mtu wasn't checked previously, it's been set to 65535, which
is the largest possible size supported
sch_teql:
- set min/max_mtu (note: max_mtu previously unchecked, used max of 65535)
macsec:
- min_mtu = 0, max_mtu = 65535
macvlan:
- min_mtu = 0, max_mtu = 65535
ntb_netdev:
- min_mtu = 0, max_mtu = 65535
veth:
- min_mtu = 68, max_mtu = 65535
8021q:
- min_mtu = 0, max_mtu = 65535
CC: netdev@vger.kernel.org
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
CC: Hannes Frederic Sowa <hannes@stressinduktion.org>
CC: Tom Herbert <tom@herbertland.com>
CC: Daniel Borkmann <daniel@iogearbox.net>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
CC: Paolo Abeni <pabeni@redhat.com>
CC: Jiri Benc <jbenc@redhat.com>
CC: WANG Cong <xiyou.wangcong@gmail.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
CC: Pravin B Shelar <pshelar@ovn.org>
CC: Sabrina Dubroca <sd@queasysnail.net>
CC: Patrick McHardy <kaber@trash.net>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Pravin Shelar <pshelar@nicira.com>
CC: Maxim Krasnyansky <maxk@qti.qualcomm.com>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Right now if we push the NTB really hard, we start dropping packets due
to not able to process the packets fast enough. We need to st:qop the
upper layer from flooding us when that happens.
A timer is necessary in order to restart the queue once the resource has
been processed on the receive side. Due to the way NTB is setup, the
resources on the tx side are tied to the processing of the rx side and
there's no async way to know when the rx side has released those
resources.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
ntb_netdev is allowing the link to come up even when -ENOMEM is returned
from ntb_transport_rx_enqueue. Fix to cover all possible errors.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
It was possible for a synchronous update of the RX index in the error
case to get ahead of the asynchronous RX index update in the normal
case. Change the RX processing to preserve an RX completion order.
There were two error cases. First, if a buffer is not present to
receive data, there would be no queue entry to preserve the RX
completion order. Instead of dropping the RX frame, leave the RX frame
in the ring. Schedule RX processing when RX entries are enqueued, in
case there are RX frames waiting in the ring to be received.
Second, if a buffer is too small to receive data, drop the frame in the
ring, mark the RX entry as done, and indicate the error in the RX entry
length. Check for a negative length in the receive callback in
ntb_netdev, and count occurrences as rx_length_errors.
Signed-off-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Change ntb_hw_intel to use the new NTB hardware abstraction layer.
Split ntb_transport into its own driver. Change it to use the new NTB
hardware abstraction layer.
Signed-off-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
This patch only moves files to their new locations, before applying the
next two patches adding the NTB Abstraction layer. Splitting this patch
from the next is intended make distinct which code is changed only due
to moving the files, versus which are substantial code changes in adding
the NTB Abstraction layer.
Signed-off-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
net: get rid of SET_ETHTOOL_OPS
Dave Miller mentioned he'd like to see SET_ETHTOOL_OPS gone.
This does that.
Mostly done via coccinelle script:
@@
struct ethtool_ops *ops;
struct net_device *dev;
@@
- SET_ETHTOOL_OPS(dev, ops);
+ dev->ethtool_ops = ops;
Compile tested only, but I'd seriously wonder if this broke anything.
Suggested-by: Dave Miller <davem@davemloft.net>
Signed-off-by: Wilfried Klaebe <w-lkml@lebenslange-mailadresse.de>
Acked-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In ntb_netdev_open, when ntb_transport_rx_enqueue fails the skb that was
attempting to be enqueued is not freed. Free this skb on the
ntb_transport_rx_enqueue error.
Signed-off-by: Jon Mason <jon.mason@intel.com>
If list_for_each_entry exits without finding the ntb_device, the dev
pointer will not be NULL. Thus the check will never be true and the
code will not exit when it should. Correct this by adding a bool to
determine when the device is found, otherwise exit in good fashion.
Signed-off-by: Jon Mason <jon.mason@intel.com>
The ntb_netdev device is not removed from the global list of devices
upon device removal. If the device is re-added, the removal code would
find the first instance and try to remove an already removed device.
Signed-off-by: Jon Mason <jon.mason@intel.com>
Improve driver logging to be more helpful
Signed-off-by: Jon Mason <jon.mason@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There is a race between disabling and enabling the tx queue, resulting
in tx timeouts. Since all the tx timeout does is re-enable the tx
queue, simple remove the start/stop of the queue and the tx timeout
routine.
Signed-off-by: Jon Mason <jon.mason@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If ntb_netdev is unable to pass a new skb to the ntb transport for
future rx packets, it should free the newly alloc'ed skb in the error
case. Found by Kernel memory leak detector.
Signed-off-by: Jon Mason <jon.mason@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove init/exit from probe/remove routines to correct warnings of
"Section mismatch".
Signed-off-by: Jon Mason <jon.mason@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
These are now gone from the kernel, so remove them from the newly-added
drivers before they start to cause build errors for people.
Cc: Jon Mason <jon.mason@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A virtual ethernet device that uses the NTB transport API to
send/receive data.
Signed-off-by: Jon Mason <jon.mason@intel.com>
Reviewed-by: Nicholas Bellinger <nab@linux-iscsi.org>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
