Willem noticed that we could avoid an rbtree lookup if the
the attempt to coalesce incoming skb to the last skb failed
for some reason.

Since most ooo additions are at the tail, this is definitely
worth adding a test and fast path.
Suggested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

When userspace tries to create datapaths and the module is not loaded,
it will simply fail. With this patch, the module will be automatically
loaded.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

These functions are used by other code misc-next tree.

This reverts commit 30d1de08.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Saeed Mahameed says:

====================
Mellanox 100G mlx5 seamless error recovery

This series from Mohamad improves the driver load/unload flows
to seamlessly handle pci errors and device internal errors recovery
reset flows.

Current pci and internal error handling is too heavy and is done
with a full restart of the driver by unregistering mlx5 interfaces
(mlx5e netedevs and mlx5_ib) which will cause losing all the current
interfaces and mlx5 core configurations.

To improve this, we add new callback functions of mlx5 interface
object (attach/detach) to be called upon reset flows when errors are
detected rather than calling register and unregister interfaces.

On their side, interfaces such as (mlx5e and mlx5_ib) can choose to implement
those callback, if not, the old heavy reset will be called for that interface.

For non-interface mlx5 modules such as sriov and eswitch, we refactored
and reorganized the code in a way that the software state objects are created
only once on driver load.  Those software state objects are kept upon reset recovery
flows and only freed once on driver unload. On seamless soft reset flows, only
hardware resources are released on stop and re-allocated on start according to the
current soft state.

In this series only mlx5e interface implements attach/detach callbacks
so that the netdevice will be kept alive on reset. On detach only hardware resources
are released and the netdevice will be marked as detached to the stack. Once
attached again it will re-allocate the hardware resources according to the current
netdevice state, and all the configurations and the software state will be kept or restored
after recovery.

Note: I will be out of office all next week, in case of any updates
or V2 is required, Tariq will post the new series, I hope it is ok.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Hide the exposed (external) mlx5_dev_list and mlx5_intf_mutex and expose
an organized modular API to manage and manipulate mlx5 devices list.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When detaching the mlx5e interface clear all the vlans rules from the
vlan flow table.
When attaching it back restore all the active vlans rules to the HW.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Needed to support seamless and lightweight PCI/Internal error recovery.
Implement the attach/detach interface callbacks.
In attach callback we only allocate HW resources.
In detach callback we only deallocate HW resources.
All SW/kernel objects initialzing/destroying is kept in add/remove
callbacks.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Save the user configuration in the vport sturct.
Restore saved old configuration upon vport enable.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Init/cleanup sriov/eswitch in the core software context init/cleanup
flows.
Attach/detach sriov/eswitch in the core load/unload flows.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Needed for lightweight and modular internal/pci error handling.
Implement eswitch attach function which allocates/starts hw related
resources.
Implement eswitch detach function which releases/stops hw related
resources.
Init/cleanup function only handle eswitch software context allocation
and destruction.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Needed for lightweight and modular internal/pci error handling.
Implement sriov attach function which enables pre-saved number of vfs on
the device side.
Implement sriov detach function which disable the current vfs on the
device side.
Init/cleanup function only handles sriov software context allocation and
destruction.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Gather all software context creating/destroying in one function and call
it once in the first load and in the last unload.
load/unload functions will now receive indication if we need to
create/destroy the software contexts.
In internal/pci error do the unload/load flows without releasing the
software objects.
In this way we perserve the sw core state and it help us restoring old
driver state after PCI error/shutdown.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add attach/detach callbacks to interface API.
This is crucial for implementing seamless reset flow which releases the
hardware and it's resources upon detach while keeping software
structures and state (e.g netdev) then reset and reallocate the hardware
needed resources upon attach.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Simplify the code and makes it look modular and symmetric.
Split sriov enable/disable to two levels: device level and pci level.
When user enable/disable sriov (via sriov_configure driver callback) we
will enable/disable both device and pci sriov.
When driver load/unload we will enable/disable (on demand) only device
sriov while keeping the PCI sriov enabled for next driver load.
On internal/pci error, VFs will be kept enabled on PCI and the reset
is done only in device level.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In case of device in internal error state there is no need to wait for
vf pages since they will be reclaimed manually later in the unload flow.
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Javier Martinez Canillas says:

====================
net: use IS_ENABLED() instead of checking for built-in or module

This trivial series replace the open coding to check for a Kconfig symbol
being built-in or module, with IS_ENABLED() macro that does exactly that.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: Javier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Christophe Leroy says:

====================
Optimisation of fs_enet ethernet driver

This set optimises the freescale fs_enet ethernet driver:
1/ Merge of RX and TX NAPI functions in order to limit the amount of
interrupts
2/ Do not unmap DMA when packets len is below copybreak, otherwise there
is no benefit in copying the skb instead of allocating a new one
3/ Make copybreak value configurable as the optimised value is not the
same on all targets
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Measurement shows that on a MPC8xx running at 132MHz, the optimal
limit is 112:
* 114 bytes packets are processed in 147 TB ticks with higher copybreak
* 114 bytes packets are processed in 148 TB ticks with lower copybreak
* 128 bytes packets are processed in 154 TB ticks with higher copybreak
* 128 bytes packets are processed in 148 TB ticks with lower copybreak
* 238 bytes packets are processed in 172 TB ticks with higher copybreak
* 238 bytes packets are processed in 148 TB ticks with lower copybreak

However it might be different on other processors
and/or frequencies. So it is useful to make it configurable.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

When the length of the packet is below the defined copybreak limit,
the received packet is copied into a newly allocated skb in order
to reuse the skb. This is only interesting if it allow us to avoid
a new DMA mapping. We shall therefore not DMA unmap and remap the
skb->data. Instead, we invalidate the cache
with dma_sync_single_for_cpu() once the received data has been
copied into the new skb.

The following measures have been obtained on a mpc885 running at 132Mhz.
Measurement is done using the timebase with packets sent to the target
with 'ping -s 1' (packet len is 60):
* Without this patch: 182 TB ticks
* With this patch: 143 TB ticks

As a comparison, if we set the copybreak limit to 0, then we get
148 TB ticks. It means that without this patch, duration is even
worse when copying received data to a new skb instead of
allocating a new skb for next packet to be received
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

Initially, a NAPI TX routine has been implemented separately from
NAPI RX, as done on the freescale/gianfar driver.

By merging NAPI RX and NAPI TX, we reduce the amount of TX completion
interrupts.

Handling of the budget in association with TX interrupts is based on
indications provided at https://wiki.linuxfoundation.org/networking/napi
We never proceed more than the complete TX ring on a single run.

At the same time, we fix an issue in the handling of fep->tx_free:

It is only when fep->tx_free goes up to MAX_SKB_FRAGS that
we need to wake up the queue. There is no need to call
netif_wake_queue() at every packet successfully transmitted.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

Hadar Hen Zion says:

====================
net/sched: ip tunnel metadata set/release/classify by using TC

This patchset introduces ip tunnel manipulation support using the TC subsystem.

In the decap flow, it enables the user to redirect packets from a shared tunnel
device and classify by outer and inner headers. The outer headers are extracted
from the metadata and used by the flower filter. A new action act_tunnel_key,
releases the metadata.

In the encap flow, act_tunnel_key creates a metadata object to be used by the
shared tunnel device. The actual redirection to the tunnel device is done using
act_mirred.

For example:
$ tc qdisc add dev vnet0 ingress
$ tc filter add dev vnet0 protocol ip parent ffff: \
	flower \
	 ip_proto 1 \
	action tunnel_key set \
	 src_ip 11.11.0.1 \
	 dst_ip 11.11.0.2 \
	 id 11 \
	action mirred egress redirect dev vxlan0

$ tc qdisc add dev vxlan0 ingress
$ tc filter add dev vxlan0 protocol ip parent ffff: \
	flower \
	 enc_src_ip 11.11.0.2 \
	 enc_dst_ip 11.11.0.1 \
	 enc_key_id 11 \
	action tunnel_key release \
	action mirred egress redirect dev vnet0

Amir & Hadar

Changes from V6:
- Add kfree_rcu to tunnel_key_release function
- Use reverse Christmas tree order in tunnel_key_init function

Changes from V5:
- Add __rcu notation to struct tcf_tunnel_key_params in struct tcf_tunnel_key
- Fix indentation in include/net/dst_metadata.h
- Fix syntx error in commit message

Changes from V4:
- Fix tunnel_key_init function error flow.
- Add 'action' variable to struct tcf_tunnel_key_params and use it instead of
  tcf_action variable which is not protected by rcu lock.

Changes from V3:
- Use percpu stats
- No spinlock on datapatch - protecting parameters with rcu
- Fix buggy handling of set/release dst
- Use nla_get_in_addr and nla_put_in_addr
- Fix change logs
- Pass in6_addr by pointer
- Rename utility functions to start with double underscore

Changes from V2:
- Use union in struct fl_flow_key for enc_ipv6 and enc_ipv4.
- Rename functions _ip_tun_rx_dst and _ipv6_tun_rx_dst to _ip_tun_set_dst and
  _ipv6_tun_set_dst accordingly.
- Remove local parameter 'encapdecap' from tunnel_key_init function.
- Don't copy in6_addr values in tunnel_key_dump_addresses function, use pointers.

Changes from V1:
- More cleanups to key32_to_tunnel_id() and tunnel_id_to_key32()
- IPv6 Support added
- Set TUNNEL_KEY flag to make GRE work
- Handle zero tunnel id properly in act_tunnel_key
- Don't leave junk in decap action
- Fix bug in act_tunnel_key initialization where (exists & ocr) is true
- Remove BUG() from code
- Rename action to tunnel_key
- Improve grep-ability of code
- Reuse code from ip_tun_rx_dst() and ipv6_tun_rx_dst()

Changes from RFC:
- Add a new action instead of making mirred too complex
- No need to specify UDP port in action - it is already in the tunnel device
  configuration
- Added a decap operation to drop tunnel metadata
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

This action could be used before redirecting packets to a shared tunnel
device, or when redirecting packets arriving from a such a device.

The action will release the metadata created by the tunnel device
(decap), or set the metadata with the specified values for encap
operation.

For example, the following flower filter will forward all ICMP packets
destined to 11.11.11.2 through the shared vxlan device 'vxlan0'. Before
redirecting, a metadata for the vxlan tunnel is created using the
tunnel_key action and it's arguments:

$ tc filter add dev net0 protocol ip parent ffff: \
    flower \
      ip_proto 1 \
      dst_ip 11.11.11.2 \
    action tunnel_key set \
      src_ip 11.11.0.1 \
      dst_ip 11.11.0.2 \
      id 11 \
    action mirred egress redirect dev vxlan0
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Introduce classifying by metadata extracted by the tunnel device.
Outer header fields - source/dest ip and tunnel id, are extracted from
the metadata when classifying.

For example, the following will add a filter on the ingress Qdisc of shared
vxlan device named 'vxlan0'. To forward packets with outer src ip
11.11.0.2, dst ip 11.11.0.1 and tunnel id 11. The packets will be
forwarded to tap device 'vnet0' (after metadata is released):

$ tc filter add dev vxlan0 protocol ip parent ffff: \
    flower \
      enc_src_ip 11.11.0.2 \
      enc_dst_ip 11.11.0.1 \
      enc_key_id 11 \
      dst_ip 11.11.11.1 \
    action tunnel_key release \
    action mirred egress redirect dev vnet0

The action tunnel_key, will be introduced in the next patch in this
series.
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Extract __ip_tun_set_dst() and __ipv6_tun_set_dst() out of
ip_tun_rx_dst() and ipv6_tun_rx_dst(), to be used without supplying an
skb.
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add utility functions to convert a 32 bits key into a 64 bits tunnel and
vice versa.
These functions will be used instead of cloning code in GRE and VXLAN,
and in tc act_iptunnel which will be introduced in a following patch in
this patchset.
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

* Multiplications for the size determination of memory allocations
  indicated that array data structures should be processed.
  Thus use the corresponding function "kmalloc_array".

  This issue was detected by using the Coccinelle software.

* Replace the specification of data types by pointer dereferences
  to make the corresponding size determination a bit safer according to
  the Linux coding style convention.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Tobias Regnery says:

====================
alx: add msi-x support

This patchset adds msi-x support to the alx driver. It is a preparatory
series for multi queue support, which I am currently working on. As there
is no advantage over msi interrupts without multi queue support, msi-x
interrupts are disabled by default. In order to test for regressions, a
new module parameter is added to enable msi-x interrupts.

Based on information of the downstream driver at github.com/qca/alx
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

msi-x support is default disabled in the alx driver. In order to test msi-x
interrupts for regressions add a module parameter to the driver.
Signed-off-by: Tobias Regnery <tobias.regnery@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add msi-x support to the alx driver. This is in preparation for multi queue
support.

msi-x interrupts are disabled by default because without multi queue support
there is no advantage over msi interrupts. The performance numbers observed
with iperf stay the same.

Based on information of the downstream driver at github.com/qca/alx
Signed-off-by: Tobias Regnery <tobias.regnery@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Factor out the handling of misc interrupts into a new function.
This function can be reused later for msi-x interrupts.
Signed-off-by: Tobias Regnery <tobias.regnery@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Introduce a new flag field for the advanced interrupt capatibilities and add
new functions to enable and disable msi interrupts. These functions will be
extended later to cover msi-x interrupts.

We enable msi interrupts earlier in alx_init_intr because with msi-x and multi
queue support the number of queues must be set before we allocate resources for
the rx and tx paths.
Signed-off-by: Tobias Regnery <tobias.regnery@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We get a few warnings when building kernel with W=1:
drivers/net/ethernet/qlogic/qed/qed_l2.c:112:5: warning: no previous prototype for 'qed_sp_vport_start' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:110:6: warning: no previous prototype for 'qed_iov_is_valid_vfid' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:188:5: warning: no previous prototype for 'qed_iov_post_vf_bulletin' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:578:6: warning: no previous prototype for 'qed_iov_set_vfs_to_disable' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:1135:28: warning: no previous prototype for 'qed_iov_get_public_vf_info' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:1148:6: warning: no previous prototype for 'qed_iov_clean_vf' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:2444:5: warning: no previous prototype for 'qed_iov_chk_ucast' [-Wmissing-prototypes]
drivers/net/ethernet/qlogic/qed/qed_sriov.c:2762:5: warning: no previous prototype for 'qed_iov_vf_flr_cleanup' [-Wmissing-prototypes]
....

In fact, these functions are only used in the file in which they are
declared and don't need a declaration, but can be made static.
so this patch marks these functions with 'static'.
Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>