dpdk.git
8 years agomlx4: support setting primary MAC address
David Marchand [Tue, 5 Jan 2016 18:00:08 +0000 (19:00 +0100)]
mlx4: support setting primary MAC address

Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
8 years agomlx4: ensure number of Rx queues is a power of 2
Robin Jarry [Thu, 3 Mar 2016 14:27:40 +0000 (15:27 +0100)]
mlx4: ensure number of Rx queues is a power of 2

In the documentation it is specified that the hardware only supports a
number of RX queues if it is a power of 2.

Since ibv_exp_create_qp may not return an error when the number of
queues is unsupported by hardware, sanitize the value in dev_configure.

Signed-off-by: Robin Jarry <robin.jarry@6wind.com>
8 years agomlx4: fix unneeded function error with clang 3.6
Bruce Richardson [Mon, 8 Feb 2016 22:11:49 +0000 (22:11 +0000)]
mlx4: fix unneeded function error with clang 3.6

When compiling with clang 3.6, the mlx4 driver gives the following error
message about an unneeded function.

  CC mlx4.o
.../drivers/net/mlx4/mlx4.c:136:20: fatal error: function
      'wr_id_t_check' is not needed and will not be emitted
[-Wunneeded-internal-declaration]
static inline void wr_id_t_check(void)
                   ^
1 error generated.

The function is to compile-time check the size of wr_id_t, so use
the standard DPDK BUILD_BUG_ON macro to do so in the init function
instead.

Fixes: 7fae69eeff13 ("mlx4: new poll mode driver")

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
8 years agofm10k: enable FTAG based forwarding
Xiao Wang [Wed, 2 Mar 2016 11:19:13 +0000 (19:19 +0800)]
fm10k: enable FTAG based forwarding

This patch enables reading sglort (global resource tag) info into the
mbuf for RX and inserting an FTAG (Fabric Tag) at the beginning of the
packet for TX. The vlan_tci_outer field selected from rte_mbuf structure
for sglort is not used in fm10k now.
In FTAG based forwarding mode, the switch will forward packets according
to glort info in FTAG rather than mac and vlan table.

To activate this feature, user needs to pass a devargs parameter to eal
for fm10k device like "-w 0000:84:00.0,enable_ftag=1". Currently this
feature is supported only on PF, because FM10K_PFVTCTL register is
read-only for VF.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
8 years agofm10k/base: remove unused struct element
Xiao Wang [Fri, 19 Feb 2016 11:07:05 +0000 (19:07 +0800)]
fm10k/base: remove unused struct element

Remove the unused element request_lport_map in struct fm10k_mac_ops.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: minor cleanups
Xiao Wang [Fri, 19 Feb 2016 11:07:04 +0000 (19:07 +0800)]
fm10k/base: minor cleanups

Some cleanups to better reflect the code that was actually pushed out to
the upstream Linux community.

Among the above cleanups, a few macros such as FM10K_RXINT_TIMER_SHIFT are
removed, but they are needed in dpdk/fm10k, so we have to put all these
necessary macros into fm10k_osdep.h.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: move constants on right of binary operators
Xiao Wang [Fri, 19 Feb 2016 11:07:03 +0000 (19:07 +0800)]
fm10k/base: move constants on right of binary operators

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: fix TLV structures alignment
Xiao Wang [Fri, 19 Feb 2016 11:07:02 +0000 (19:07 +0800)]
fm10k/base: fix TLV structures alignment

Per comments from an upstream kernel patch, and looking at how TLV
LE_STRUCT code works, we actually want these structures to be 4byte
aligned, not 1byte aligned.

In practice, 1byte alignment has worked so far because all our
structures end up being a multiple of 4. But if a future TLV
structure were added that had a u8 or similar sticking on the end things
would break. Fix this by using 4byte alignment which will prevent the
TLV LE_STRUCT code from breaking. Update the comment explaining that we
need 4byte alignment of our structures.

Fixes: 925c862cbc21 ("fm10k/base: pack TLV overlay structures")

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: improve comments
Xiao Wang [Fri, 19 Feb 2016 11:07:01 +0000 (19:07 +0800)]
fm10k/base: improve comments

The comment for fm10k_iov_msg_lport_state_pf was changed during
review of kernel driver, and the new wording is slightly clearer.
Re-write the comment in base code based on this new wording.

Fix a number of mailbox comment issues with function header comments,
lower-case acronyms (i.e. FIFO, TLV), incorrect function names in
DEBUGFUNC(), duplicate comments and a stubbed-out header comment for
fm10k_sm_mbx_init.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: expand VID to VLAN ID in comments
Xiao Wang [Fri, 19 Feb 2016 11:07:00 +0000 (19:07 +0800)]
fm10k/base: expand VID to VLAN ID in comments

The vid variable name is shorthand for VLAN ID, so we should use this in
comments explaining what is happening.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: allow removal of slot appropriate check
Xiao Wang [Fri, 19 Feb 2016 11:06:59 +0000 (19:06 +0800)]
fm10k/base: allow removal of slot appropriate check

The Linux Kernel provides the OS a call "pcie_get_minimum_link" which
can crawl the PCIe tree and determine the actual minimum link speed of a
device which is a more general check than provided by
is_slot_appropriate. Thus, the kernel driver does not use or want the
is_slot_appropriate function call. Add a NO_IS_SLOT_APPROPRIATE_CHECK
definition which can be defined to remove the code.
If left undefined (the default) then the code will all be active and no
driver changes should be necessary.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: use memcpy for MAC address copy
Xiao Wang [Fri, 19 Feb 2016 11:06:58 +0000 (19:06 +0800)]
fm10k/base: use memcpy for MAC address copy

Use memcpy instead of copying MAC address byte-by-byte.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: remove CamelCase
Xiao Wang [Fri, 19 Feb 2016 11:06:57 +0000 (19:06 +0800)]
fm10k/base: remove CamelCase

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: add bit macro
Xiao Wang [Fri, 19 Feb 2016 11:06:56 +0000 (19:06 +0800)]
fm10k/base: add bit macro

Using the BIT macro can simplify the bit-shifting operation and make the
code look clean. Similar to how this is handled in the i40e base code,
define a macro for it in DPDK, so it can be used here too.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: remove useless else
Xiao Wang [Fri, 19 Feb 2016 11:06:55 +0000 (19:06 +0800)]
fm10k/base: remove useless else

"else" is not generally useful after a break or return.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: wrap long lines
Xiao Wang [Fri, 19 Feb 2016 11:06:54 +0000 (19:06 +0800)]
fm10k/base: wrap long lines

Recommended line length maximum is 80 characters

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: document ITR scale workaround
Xiao Wang [Fri, 19 Feb 2016 11:06:53 +0000 (19:06 +0800)]
fm10k/base: document ITR scale workaround

Add comments which properly explain the undocumented use of bits in
TDLEN register prior to VF initializing it to the correct value. Note
that the mechanism is entirely software-defined and explain its purpose
to help reduce confusion in the future.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: fix max queues on VF initialization failure
Xiao Wang [Fri, 19 Feb 2016 11:06:52 +0000 (19:06 +0800)]
fm10k/base: fix max queues on VF initialization failure

VF drivers must detect how many queues are available. Previously, the
driver assumed that each VF has at minimum 1 queue. This assumption is
incorrect, since it is possible that the PF has not yet assigned the
queues to the VF by the time the VF checks.

To resolve this, we added a check first to ensure that the first queue
is, in fact, owned by the VF at init_hw_vf time.
However, the code flow did not reset hw->mac.max_queues to 0.
In some cases, such as during reinit flows, we call init_hw_vf
without clearing the previous value of hw->mac.max_queues. Due to this,
when init_hw_vf errors out, if its error code is not properly handled
the VF driver may still believe it has queues which no longer belong to
it. Fix this by clearing the hw->mac.max_queues on exit due to errors.

Fixes: 8b8264bdb90d ("fm10k/base: check VF has a queue")

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: use bit shift for ITR scale
Xiao Wang [Fri, 19 Feb 2016 11:06:51 +0000 (19:06 +0800)]
fm10k/base: use bit shift for ITR scale

Use bitshift instead of a divisor, because this is faster, and
eliminates any need for a '0' check. In our case, this even works
out because default Gen3 will be 0.

Because of this, we are also able to remove the check for non-zero value
in the VF code path since that will already be the default Gen3 case.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: clean up namespace pollution
Xiao Wang [Fri, 19 Feb 2016 11:06:50 +0000 (19:06 +0800)]
fm10k/base: clean up namespace pollution

Make functions that are only referenced locally static.

Wrap fm10k_msg_data fm10k_iov_msg_data_pf[] in the new ifndef
NO_DEFAULT_SRIOV_MSG_HANDLERS so that drivers with custom SR-IOV
message handlers can strip it.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k/base: fix typecast
Xiao Wang [Fri, 19 Feb 2016 11:06:49 +0000 (19:06 +0800)]
fm10k/base: fix typecast

Since the resultant data type of the mac_update.mac_upper field is u16,
it does not make sense to typecast u8 variables to u32 first.

Fixes: 7223d200c227 ("fm10k: add base driver")

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k: use default mailbox message handler for PF
Xiao Wang [Fri, 19 Feb 2016 11:06:48 +0000 (19:06 +0800)]
fm10k: use default mailbox message handler for PF

The new share code makes fm10k_msg_update_pvid_pf function static, so we
can not refer to it now in fm10k_ethdev.c. The registered PF handler is
almost the same as the default PF handler, removing it has no impact on
mailbox.

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k: handle error flags in vector Rx
Chen Jing D(Mark) [Sat, 6 Feb 2016 06:49:25 +0000 (14:49 +0800)]
fm10k: handle error flags in vector Rx

Using SSE instructions to parse error flags in HW Rx descriptor,
then set corresponding bits of mbuf.

Signed-off-by: Chen Jing D(Mark) <jing.d.chen@intel.com>
Acked-by: Cunming Liang <cunming.liang@intel.com>
8 years agofm10k: optimize mbuf freeing in non-vector Tx
Chen Jing D(Mark) [Thu, 28 Jan 2016 09:45:59 +0000 (17:45 +0800)]
fm10k: optimize mbuf freeing in non-vector Tx

When the TX function tries to free a bunch of mbufs, it will free
them one by one. This change will scan the free list and merge the
requests in case they belongs to same pool, then free once, which
will reduce cycles on freeing mbufs.

Signed-off-by: Chen Jing D(Mark) <jing.d.chen@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
8 years agofm10k: fix switch manager high CPU usage
Shaopeng He [Fri, 5 Feb 2016 02:46:11 +0000 (10:46 +0800)]
fm10k: fix switch manager high CPU usage

fm10k switch core uses source MAC + VID + SGLORT to do
look up in MAC table. If no match, an exception interrupt
will be sent to the switch manager. Too much of this kind
of exception interrupts cause switch manager side high CPU
usage.
To reproduce this issue, one DPDK testpmd runs on a server
with one fm10k NIC, mac forwards test traffic from one of
fm10k ports to another port. The CPU usage for the switch
manager will go up to about 20% for test traffic rate at
10G bps, comparing to near 0% for no test traffic.

This patch fixes this issue. A default SGLORT is assigned
to each TX queue. This default value works for non-VMDq mode
and current VMDq example. For advanced VMDq usage, e.g.
different source MAC address for different TX queue, FTAG
forwarding function could be used to change this default
SGLORT value.

Fixes: 9ae6068c86da ("fm10k: add dev start/stop")

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agofm10k: enable broadcast loopback suppression
Shaopeng He [Thu, 4 Feb 2016 12:43:21 +0000 (20:43 +0800)]
fm10k: enable broadcast loopback suppression

In FM10K, a single PCIe port can derive out a few logical ports,
like SRIOV PF/VF devices, VMDQ objects. To better manage them, FM10K
silicon assigns a Unique GLORT ID to each logical port.

When a logical port sends a broadcast packet, the silicon will flood
it to all logical ports, including the one that sent the broadcast packet.
To prevent this, silicon has an rxq register to store the glort id of
the logical port that queue binds to.

FM10K has a switch core inside, which has a loopback suppression
mechanism in the switch level. Switch level loopback suppression mostly
works for the ether port traffic.

This patch assigns a SGLORT for each RX queue, and enables PCIe port
level loopback suppression.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
8 years agoexamples/l3fwd-power: fix memory leak for non-IP packets
Shaopeng He [Fri, 5 Feb 2016 04:57:50 +0000 (12:57 +0800)]
examples/l3fwd-power: fix memory leak for non-IP packets

Previous l3fwd-power only processes IP and IPv6 packets, other
packets' mbufs are not freed, and this causes a memory leak.
This patch fixes this issue.

Fixes: 3c0184cc0c60 ("examples: replace some offload flags with packet type")

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: make default VID available in initialization
Shaopeng He [Fri, 5 Feb 2016 04:57:49 +0000 (12:57 +0800)]
fm10k: make default VID available in initialization

When the PF establishes a connection with Switch Manager(SM), it receives
a logical port range from SM, and registers certain logical ports from
that range. Then a default VID will be sent back from the SM.

This whole transaction - finishing with the default VID being set -
needs to be completed before dev_init returns. If not, the interrupt
setting will subsequently be changed in dev_start according to the RX
queue number, and that can cause this transaction to fail.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: add Rx queue interrupt enable/disable functions
Shaopeng He [Fri, 5 Feb 2016 04:57:48 +0000 (12:57 +0800)]
fm10k: add Rx queue interrupt enable/disable functions

Interrupt mode framework has per-queue enable/disable functions.
Implement these two functions for fm10k driver.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: remove Rx queue interrupts when stopping
Shaopeng He [Fri, 5 Feb 2016 04:57:47 +0000 (12:57 +0800)]
fm10k: remove Rx queue interrupts when stopping

Previous dev_stop function stops the rx/tx queues. This patch adds logic
to disable rx queue interrupt, clean the datapath event and queue/vector
map.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: setup Rx interrupt for PF and VF
Shaopeng He [Fri, 5 Feb 2016 04:57:46 +0000 (12:57 +0800)]
fm10k: setup Rx interrupt for PF and VF

In interrupt mode, each rx queue can have one interrupt to notify the
application when packets are available in that queue. Some queues
also can share one interrupt.
Currently, fm10k needs one separate interrupt for mailbox. So, only those
drivers which support multiple interrupt vectors e.g. vfio-pci can work
in fm10k interrupt mode.
This patch uses the RXINT/INT_MAP registers to map interrupt causes
(rx queue and other events) to vectors, and enable these interrupts
through kernel drivers like vfio-pci.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: support Rx descriptor check
Shaopeng He [Fri, 5 Feb 2016 04:57:45 +0000 (12:57 +0800)]
fm10k: support Rx descriptor check

rx_descriptor_done is used by interrupt mode example application
(l3fwd-power) to check rxd DD bit to decide the RX trend,
then l3fwd-power will adjust the cpu frequency according to
the result.

Signed-off-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: Michael Qiu <michael.qiu@intel.com>
8 years agofm10k: allocate logical ports for flow director
Chen Jing D(Mark) [Wed, 30 Dec 2015 08:35:35 +0000 (16:35 +0800)]
fm10k: allocate logical ports for flow director

In fm10k, PF, VF, VMDQ or queues binding to flow director rule can
be considered as a logical port. Original implementation only creates
a single port for all cases. This change creates 128 logical ports;
first 64 for PF and VMDQ, second 64 for flow director.

Registers DGLORTDEC/DGLORTMAP define rules for how to classify packets
into different queues. Currently only PF and VMDQ cases are considered.
This change add rules for flow director.

Signed-off-by: Chen Jing D(Mark) <jing.d.chen@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
8 years agofm10k: fix VLAN flag in scattered Rx
Xiao Wang [Fri, 18 Dec 2015 03:09:18 +0000 (11:09 +0800)]
fm10k: fix VLAN flag in scattered Rx

In fm10k_recv_scattered_pkts function, a packet is stored in a linked list,
offload flags such as PKT_RX_VLAN_PKT should be set in the first segment.

Fixes: 6b59a3bc82b1 ("fm10k: fix VLAN in Rx mbuf")

Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
8 years agoi40e: support default MAC address setting
Remy Horton [Wed, 9 Mar 2016 13:29:24 +0000 (13:29 +0000)]
i40e: support default MAC address setting

Signed-off-by: Remy Horton <remy.horton@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
8 years agoi40e: add EEPROM and registers dumping
Remy Horton [Wed, 9 Mar 2016 13:29:24 +0000 (13:29 +0000)]
i40e: add EEPROM and registers dumping

Signed-off-by: Remy Horton <remy.horton@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
8 years agoi40e: support setting VF MAC address
Jingjing Wu [Wed, 9 Mar 2016 08:22:46 +0000 (16:22 +0800)]
i40e: support setting VF MAC address

This patch implemented the ops of adding and removing mac
address in i40evf driver. Functions are assigned like:
  .mac_addr_add    =  i40evf_add_mac_addr,
  .mac_addr_remove = i40evf_del_mac_addr,
To support multiple mac addresses setting, this patch also
extended the mac addresses adding and deletion when device
start and stop. Each VF can have a maximum of 64 mac
addresses.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Zhe Tao <zhe.tao@intel.com>
8 years agoi40e: add VEB switching support
Zhe Tao [Wed, 9 Mar 2016 05:38:43 +0000 (13:38 +0800)]
i40e: add VEB switching support

VEB switching feature for i40e is used to enable the switching between the
VSIs connect to the virtual bridge. The old implementation is setting the
virtual bridge mode as VEPA which is port aggregation. Enable the switching
ability by setting the loop back mode for the specific VSIs which connect
to PF or VFs.

VEB/VSI/VEPA are concepts not specific to the i40e HW, the concepts are
from 802.1qbg spec
IEEE EVB tutorial:
http://www.ieee802.org/802_tutorials/2009-11/evb-tutorial-draft-20091116_v09.pdf

VEB: a virtual switch can forward the packet based on the specific match
field.
VSI: a virtual interface connect between the VEB/VEPA and virtual machine.
VEPA: a virtual Ethernet port aggregator will upstream the packets from
VSI to the LAN port.

Signed-off-by: Zhe Tao <zhe.tao@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
8 years agoi40e: fix typo in a comment
Rami Rosen [Fri, 26 Feb 2016 18:33:54 +0000 (20:33 +0200)]
i40e: fix typo in a comment

This patch fixes a typo in a comment in the definition of
the i40e_pf struct.

Fixes: 4861cde46116 ("i40e: new poll mode driver")

Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoexamples/vmdq_dcb: support X710
Jingjing Wu [Thu, 25 Feb 2016 07:33:35 +0000 (15:33 +0800)]
examples/vmdq_dcb: support X710

Currently, the example vmdq_dcb only works on Intel(R) 82599 NICs.
This patch extends this sample to make it work both on Intel(R) 82599
and X710/XL710 NICs by making the following changes:
  1. add VMDQ base queue checking to avoid forwarding on PF queues.
  2. assign each VMDQ pool to a MAC address.
  3. add more arguments (nb-tcs, enable-rss) to change the default
     setting
  4. extend the max number of queues from 128 to 1024.
This patch also reworks the user guide for the vmdq_dcb sample.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoi40e: enable DCB in VMDQ VSIs
Jingjing Wu [Thu, 25 Feb 2016 07:33:33 +0000 (15:33 +0800)]
i40e: enable DCB in VMDQ VSIs

Previously, DCB(Data Center Bridging) is only enabled on PF,
queue mapping and BW configuration is only done on PF.
This patch enables DCB for VMDQ VSIs(Virtual Station Interfaces)
by following steps:
  1. Take BW and ETS(Enhanced Transmission Selection)
     configuration on VEB(Virtual Ethernet Bridge).
  2. Take BW and ETS configuration on VMDQ VSIs.
  3. Update TC(Traffic Class) and queues mapping on VMDQ VSIs.
To enable DCB on VMDQ, the number of TCs should not be larger than
the number of queues in VMDQ pools, and the number of queues per
VMDQ pool is specified by CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM
in config/common_* file.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoi40evf: use base driver defined interface
Helin Zhang [Tue, 8 Mar 2016 08:14:37 +0000 (16:14 +0800)]
i40evf: use base driver defined interface

It removes the i40evf_set_mac_type() defined in PMD, and reuses
i40e_set_mac_type() defined in base driver.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add base driver release info
Helin Zhang [Tue, 8 Mar 2016 08:14:36 +0000 (16:14 +0800)]
i40e/base: add base driver release info

It adds base driver release information such as release date,
for better tracking in the future.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: update AQ command structures and macros
Helin Zhang [Tue, 8 Mar 2016 08:14:35 +0000 (16:14 +0800)]
i40e/base: update AQ command structures and macros

Several structures and macros are added or updated, such
as 'struct i40e_aqc_get_link_status',
'struct i40e_aqc_run_phy_activity' and
'struct i40e_aqc_lldp_set_local_mib_resp'.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add AQ thermal sensor control struct
Helin Zhang [Tue, 8 Mar 2016 08:14:34 +0000 (16:14 +0800)]
i40e/base: add AQ thermal sensor control struct

It adds the new AQ command and struct for managing a
thermal sensor.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add virtchnl offload for X722 PCTYPES
Helin Zhang [Tue, 8 Mar 2016 08:14:33 +0000 (16:14 +0800)]
i40e/base: add virtchnl offload for X722 PCTYPES

X722 supports Expanded version of TCP, UDP PCTYPES for RSS.
Add a Virtchnl offload to support this.
Without this patch VF drivers will not be able to support
the correct PCTYPES for X722 and UDP flows will not fan out.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add some register definitions
Helin Zhang [Tue, 8 Mar 2016 08:14:32 +0000 (16:14 +0800)]
i40e/base: add some register definitions

This patch adds 7 new register definitions for programming the
parser, flow director and RSS blocks in the HW.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e: use AQ for Rx control register read/write
Helin Zhang [Tue, 8 Mar 2016 08:14:31 +0000 (16:14 +0800)]
i40e: use AQ for Rx control register read/write

RX control register read/write functions are added, as directly
read/write may fail when under stress small traffic. After the
adminq is ready, all rx control registers should be read/written
by dedicated functions.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix coding style
Helin Zhang [Tue, 8 Mar 2016 08:14:30 +0000 (16:14 +0800)]
i40e/base: fix coding style

Clean up coding style in base code

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: save VSI resource count on update
Helin Zhang [Tue, 8 Mar 2016 08:14:29 +0000 (16:14 +0800)]
i40e/base: save VSI resource count on update

When updating a VSI, save off the number of allocated and
unallocated VSIs as we do when adding a VSI.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix driver load failure
Helin Zhang [Tue, 8 Mar 2016 08:14:28 +0000 (16:14 +0800)]
i40e/base: fix driver load failure

Fix the driver load failure with linking with some
PHY types, as the amount of time it takes for the
GLGEN_RSTAT_DEVSTATE to be set increases greatly on those PHY
types, which can lead to a timeout.

Fixes: 9aeefed05538 ("i40e/base: support ESS")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: avoid unwanted Tx traffic mirroring
Helin Zhang [Tue, 8 Mar 2016 08:14:27 +0000 (16:14 +0800)]
i40e/base: avoid unwanted Tx traffic mirroring

In Multi-Function Mode (MFP) particularly when the PF VSI is set
in limited promiscuous mode, the HW switch was still mirroring the
outgoing packets from other VSIs (VF/VMdq) onto the PF VSI.

This sets a new bit to avoid above mirroring, and it is in limited
promiscuous on the PF VSI in MFP which is similar to default port
VSI.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: support LED blinking with new PHY
Helin Zhang [Tue, 8 Mar 2016 08:14:26 +0000 (16:14 +0800)]
i40e/base: support LED blinking with new PHY

This patch adds functions to blink led on devices using a new
PHY since MAC registers used in other designs do not work in
this device configuration.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add AQ switch configuration
Helin Zhang [Tue, 8 Mar 2016 08:14:25 +0000 (16:14 +0800)]
i40e/base: add AQ switch configuration

Add the support code for calling the AdminQ API call
aq_set_switch_config.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add VEB statistics control
Helin Zhang [Tue, 8 Mar 2016 08:14:24 +0000 (16:14 +0800)]
i40e/base: add VEB statistics control

With the latest firmware, statistics gathering can now be enabled and
disabled in the HW switch, so we need to add a parameter to allow the
driver to set it as desired. At the same time, the L2 cloud filtering
parameter has been removed as it was never used.

Older drivers working with the newer firmware and newer drivers working
with older firmware will not run into problems with these bits as the
defaults are reasonable and there is no overlap in the bit definitions.
Also, newer drivers will be forced to update because of the change in
function call parameters, a reminder that the functionality exists.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: support mirroring rules
Helin Zhang [Tue, 8 Mar 2016 08:14:23 +0000 (16:14 +0800)]
i40e/base: support mirroring rules

This patch implements necessary functions related to port
mirroring features such as add/delete mirror rule, function
to set promiscuous VLAN mode for VSI if mirror rule_type is
"VLAN Mirroring".

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: set shared bit for multicast filters
Helin Zhang [Tue, 8 Mar 2016 08:14:22 +0000 (16:14 +0800)]
i40e/base: set shared bit for multicast filters

Add the use of the new shared MAC filter bit for multicast
and broadcast filters in order to make better use of the
filters available from the device.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix PHY NVM interaction
Helin Zhang [Tue, 8 Mar 2016 08:14:21 +0000 (16:14 +0800)]
i40e/base: fix PHY NVM interaction

This patch fixes a problem where the NVMUpdate Tool, when
using the PHY NVM feature, gets bad data from the PHY because
of contention on the MDIO interface from get phy capability
calls from the driver during regular operations. The problem
is fixed by adding a check if media is available before calling
get phy capability function because that bit is not set when
device is in PHY interaction mode.

Fixes: 842ea1996335 ("i40e/base: save link module type")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: unify the capability function
Helin Zhang [Tue, 8 Mar 2016 08:14:20 +0000 (16:14 +0800)]
i40e/base: unify the capability function

The device capabilities were defined in two places, and neither had
all the definitions. It really belongs with the AQ API definition,
so this patch removes the other set of definitions and fills out the
missing item.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix proxy for X722
Helin Zhang [Tue, 8 Mar 2016 08:14:19 +0000 (16:14 +0800)]
i40e/base: fix proxy for X722

The recently added proxy opcodes should be available only with
X722_SUPPORT, so move them into the #ifdef, and reorder these
to be in numerical order with the rest of the opcodes. Several
structs that were added are unnecessary, so they are removed
here.

Fixes: 788fc17b2dec ("i40e/base: support proxy config for X722")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix wake on lan for X722
Helin Zhang [Tue, 8 Mar 2016 08:14:18 +0000 (16:14 +0800)]
i40e/base: fix wake on lan for X722

The recently added Wakeup On Line (WOL) opcodes should be
available only with X722_SUPPORT, so move them into the #ifdef,
and reorder these to be in numerical order with the rest of the
opcodes. Several structs that were added are unnecessary, so
they are removed here.

Fixes: 3c89193a36fd ("i40e/base: support WOL config for X722")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e: update device ids
Helin Zhang [Tue, 8 Mar 2016 08:14:17 +0000 (16:14 +0800)]
i40e: update device ids

Add new Device ID's for backplane and QSFP+ adapters, and delete
deprecated one for backplane.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix uncertain event descriptor issue
Helin Zhang [Tue, 8 Mar 2016 08:14:16 +0000 (16:14 +0800)]
i40e/base: fix uncertain event descriptor issue

In one obscure corner case, it was possible to clear the NVM update
wait flag when no update_done message was actually received. This
patch cleans the event descriptor before use, and moves the opcode
check to where it won't get done if there was no event to clean.

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: set AQ count after memory allocation
Helin Zhang [Tue, 8 Mar 2016 08:14:15 +0000 (16:14 +0800)]
i40e/base: set AQ count after memory allocation

The standard way to check if the AQ is enabled is to look at
the count field. So it should only set this field after it has
successfully allocated memory.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix missing check for stopped admin queue
Helin Zhang [Tue, 8 Mar 2016 08:14:14 +0000 (16:14 +0800)]
i40e/base: fix missing check for stopped admin queue

It's possible that while waiting for the spinlock, another
entity (that owns the spinlock) has shut down the admin queue.
If it then attempts to use the queue, it will panic.
It adds a check for this condition on the receive side. This
matches an existing check on the send queue side.

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: limit version check of DCB
Helin Zhang [Tue, 8 Mar 2016 08:14:13 +0000 (16:14 +0800)]
i40e/base: limit version check of DCB

XL710/X710 devices requires FW version checks to properly handle
DCB configurations from the FW while other devices (e.g. X722)
do not, so limit these checks to XL710/X710 only.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: support NVM read on X722
Helin Zhang [Tue, 8 Mar 2016 08:14:12 +0000 (16:14 +0800)]
i40e/base: support NVM read on X722

In X722, NVM reads can't be done through SRCTL registers.
And require AQ calls, which require grabbing the NVM lock.
Unfortunately some paths need the lock to be acquired once
and do a whole bunch of stuff and then release it.
This patch creates an unsafe version of the read calls, so
that it can be called from the paths that need the bulk access.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: add flag for X722 register access
Helin Zhang [Tue, 8 Mar 2016 08:14:11 +0000 (16:14 +0800)]
i40e/base: add flag for X722 register access

Instead of doing the MAC check, use a flag that gets set per
MAC. This way there are less chances of user error and it
can enable multiple MACs with the capability in a single place
rather than cluttering the code with MAC checks.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: acquire NVM ownership before reading it
Helin Zhang [Tue, 8 Mar 2016 08:14:10 +0000 (16:14 +0800)]
i40e/base: acquire NVM ownership before reading it

SW needs to acquire the NVM ownership before issuing an AQ read
to the X722 NVM otherwise it will get EBUSY from the firmware.
Also it should be released when done.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40e/base: fix compilation warnings
Helin Zhang [Tue, 8 Mar 2016 08:14:09 +0000 (16:14 +0800)]
i40e/base: fix compilation warnings

Fix compilation warnings in base code on some platforms.

Fixes: bd6651c2d2d7 ("i40e/base: use bit shift macros")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
8 years agoi40evf: rework MAC address validation
Helin Zhang [Tue, 8 Mar 2016 06:42:09 +0000 (14:42 +0800)]
i40evf: rework MAC address validation

Use ether API of 'is_valid_assigned_ether_addr' to validate
MAC address.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Zhe Tao <zhe.tao@intel.com>
8 years agoi40e: generate MAC address for VF
Helin Zhang [Tue, 8 Mar 2016 06:42:08 +0000 (14:42 +0800)]
i40e: generate MAC address for VF

Generate a MAC address for each VF during PF host
initialization.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Zhe Tao <zhe.tao@intel.com>
8 years agoi40e: fix VLAN filtering
Julien Meunier [Thu, 4 Feb 2016 11:02:16 +0000 (12:02 +0100)]
i40e: fix VLAN filtering

VLAN filtering was always performed, even if hw_vlan_filter was
disabled. During device initialization, default filter
RTE_MACVLAN_PERFECT_MATCH was applied. In this situation, all incoming
VLAN frames were dropped by the card (increase of the register RUPP - Rx
Unsupported Protocol).

In order to restore default behavior, if HW VLAN filtering is activated,
set a filter to match MAC and VLAN. If not, set a filter to only match
MAC.

Fixes: 4861cde46116 ("i40e: new poll mode driver")
Fixes: 912b595146d6 ("i40e: mac vlan filter")

Signed-off-by: Julien Meunier <julien.meunier@6wind.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoi40e: fix inverted check for no refcount
Rich Lane [Wed, 23 Dec 2015 08:08:00 +0000 (00:08 -0800)]
i40e: fix inverted check for no refcount

The no-refcount path was being taken without the application opting
in to it.

Fixes: 4861cde46116 ("i40e: new poll mode driver")

Reported-by: Mike Stolarchuk <mike.stolarchuk@bigswitch.com>
Signed-off-by: Rich Lane <rich.lane@bigswitch.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoixgbe: disallow unsupported Rx mode
Jingjing Wu [Thu, 25 Feb 2016 07:33:34 +0000 (15:33 +0800)]
ixgbe: disallow unsupported Rx mode

The multi queue mode ETH_MQ_RX_VMDQ_DCB_RSS is not supported in
ixgbe driver.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoixgbe: fix VF close to remove MAC address
Bernard Iremonger [Tue, 8 Mar 2016 17:10:27 +0000 (17:10 +0000)]
ixgbe: fix VF close to remove MAC address

Call the ixgbevf_remove_mac_addr() function in the ixgbevf_dev_close()
function to ensure that the VF traffic goes to the PF after stop,
close and detach of the VF.

Fixes: af75078fece3 ("first public release")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
8 years agoixgbe: add more information to multiqueue error message
Bernard Iremonger [Tue, 8 Mar 2016 17:10:26 +0000 (17:10 +0000)]
ixgbe: add more information to multiqueue error message

Add the nb_rx_q and nb_tx_q values to the error message
to give details about the error.

Fixes: 27b609cbd1c6 ("ethdev: move the multi-queue mode check to specific drivers")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
8 years agoixgbe: fix releasing queues twice when detaching VF
Bernard Iremonger [Tue, 8 Mar 2016 17:10:25 +0000 (17:10 +0000)]
ixgbe: fix releasing queues twice when detaching VF

Releasing the rx and tx queues is already done in ixgbe_dev_close()
so it does not need to be done in eth_ixgbevf_dev_uninit().

Fixes: 2866c5f1b87e ("ixgbe: support port hotplug")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
8 years agoixgbe: fix VF Rx/Tx function assignment
Zhe Tao [Thu, 10 Mar 2016 15:26:22 +0000 (15:26 +0000)]
ixgbe: fix VF Rx/Tx function assignment

For the secondary process of DPDK to initialize ixgbevf, it will always
use the simple RX function or LRO RX function, and this behavior is not
the same RX/TX function selection logic as it is for the primary process.
Use the ixgbe_set_tx_function and ixgbe_set_rx_function to select the
RX/TX function when secondary process calls the init function for eth dev.

Fixes: 9d8a92628f21 ("ixgbe: remove simple scalar scattered Rx method")

Signed-off-by: Zhe Tao <zhe.tao@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoixgbe: support link speed auto-negotiation on X550em_x
Wenzhuo Lu [Fri, 26 Feb 2016 03:05:29 +0000 (11:05 +0800)]
ixgbe: support link speed auto-negotiation on X550em_x

Normally the auto-negotiation is supported by FW. SW need not care about
that. But on x550em_x, FW doesn't support auto-neg. As the x550em_x ports
are 10G, if we connect the port will a peer which is 1G, the link will
always be down.
We need support auto-neg by SW to avoid this link down issue. As we already
have the code to handle the link speed setting, what we need is a trigger.
When the advertised link speed changes, a PHY interruption will be
triggered. So, we should handle this interrupt and call ixgbe_handle_lasi
to set the link speed correctly.

Please be aware it's working when auto-neg is on. If the auto-neg of the
peer port is turned off and its speed is indicated manually, we should also
set the speed of our own port manually.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
8 years agoixgbe: support multicast promiscuous mode on VF
Wenzhuo Lu [Sun, 14 Feb 2016 06:24:47 +0000 (14:24 +0800)]
ixgbe: support multicast promiscuous mode on VF

Add multicast promiscuous mode support on ixgbe VF driver.

Please note if we want to use this promiscuous mode, we need both PF
and VF driver to support it. The reason is this VF feature is
configged on PF.
If use kernel PF driver + dpdk VF driver, make sure kernel PF driver
support VF multicast promiscuous mode. If use dpdk PF + dpdk VF,
better make sure PF driver is the same version as VF.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Xiao Wang <xiao.w.wang@intel.com>
8 years agoixgbe: support new devices and MAC types
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:06 +0000 (16:55 +0800)]
ixgbe: support new devices and MAC types

Add the support for new devices and mac types, as supported by the base
code update.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: update readme
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:05 +0000 (16:55 +0800)]
ixgbe/base: update readme

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: abstract out link read/write
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:04 +0000 (16:55 +0800)]
ixgbe/base: abstract out link read/write

It's more valuable to abstract the link read/write interface. As such,
change the following method names, and add them to a new link info
structure:
  read_i2c_combined               => read_link
  read_i2c_combined_unlocked      => read_link_unlocked
  write_i2c_combined              => write_link
  write_i2c_combined_unlocked     => write_link_unlocked

This will allow X550EM_a to override these methods for MDIO access
while X550EM_x provides methods to use I2C combined access.
Initially the structure is just method pointers and a bus
address.

Two functions involved in combined I2C accesses were moved from
ixgbe_phy.c to ixgbe_x550.c. The underlying functions that carry
out the combined I2C accesses were left in ixgbe_phy.c because
they share some functions with other I2C methods.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: set MDIO speed after MAC reset
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:03 +0000 (16:55 +0800)]
ixgbe/base: set MDIO speed after MAC reset

The MDIO clock speed must be reconfigured after the MAC reset.
The MDIO clock speed becomes invalid, therefore the driver reads
invalid PHY register values. The driver now set the MDIO clock
speed prior to initializing PHY ops and again after the MAC reset.

As now the MDIO speed gets set in more than one place, make a
function for it so it will always be done correctly.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: fix setting flow director flag twice
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:02 +0000 (16:55 +0800)]
ixgbe/base: fix setting flow director flag twice

Do not set FDIRCTRL.DROP_NO_MATCH in ixgbe_init_fdir_perfect_82599(),
this bit is already set in ixgbe_set_fdir_drop_queue_82599() which
makes more sense for drivers that call that function.

This resolves an issue where packets were being dropped when switching
to perfect filters mode.

Setting this bit makes no sense in perfect filters mode for the
driver as we do not want to route all packets that don't match an FDIR
rule to a single queue and instead fall back to RSS.
Drivers that need this bit set can call ixgbe_set_fdir_drop_queue_82599()
and the ones that don't, can preserve the old behavior.

Fixes: 2241ce281646 ("ixgbe/base: add flow director drop queue")
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: add register definition for SGMII busy
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:01 +0000 (16:55 +0800)]
ixgbe/base: add register definition for SGMII busy

The X550EM_a device provides the MAC_SGMII_BUSY register to
indicate when slow SGMII register writes complete. Add
definitions for the register. No definitions are provided for
the individual bits under the theory that it is better to wait
for everything to complete when needed rather than try to map
out which reads need to wait for which writes. So we should wait
when anything is marked as "busy".

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: ignore manageability for PHY power on
Wenzhuo Lu [Sun, 14 Feb 2016 08:55:00 +0000 (16:55 +0800)]
ixgbe/base: ignore manageability for PHY power on

Instead of not defining the callback for set_phy_power when
manageability is enabled, put the check in the set_phy_power
function so that only turning the power off is conditional on
management, but not turning the PHY on.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: set VF MAC address only when acked by PF
Wenzhuo Lu [Sun, 14 Feb 2016 08:54:59 +0000 (16:54 +0800)]
ixgbe/base: set VF MAC address only when acked by PF

This patch resolves an issue where VF mac address is zeroed out
in cases where the VF driver is loaded while the PF interface
is down.
The solution is to only set it when we get an ACK from the PF.

Fixes: 6202266e5680 ("ixgbe/base: vf changes")
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: add sw-firmware sync for resource sharing on X550em_a
Wenzhuo Lu [Sun, 14 Feb 2016 08:54:58 +0000 (16:54 +0800)]
ixgbe/base: add sw-firmware sync for resource sharing on X550em_a

Use a PHY token, shared between sw-fw for PHY access on X550EM_a.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: support X550em_x V2 device
Wenzhuo Lu [Sun, 14 Feb 2016 08:54:57 +0000 (16:54 +0800)]
ixgbe/base: support X550em_x V2 device

Only x550em_x V1 was supported before. Now V2 is supported.
A mask for V1 and V2 is defined and used to support both.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe/base: support X550em_a device
Wenzhuo Lu [Sun, 14 Feb 2016 08:54:56 +0000 (16:54 +0800)]
ixgbe/base: support X550em_a device

Add new X550EM_a devices and their mac types, X550EM_a
and X550EM_a_vf.
Update the code to use the new devices and mac types.

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoixgbe: fix disable interrupt twice
Michael Qiu [Fri, 29 Jan 2016 05:58:10 +0000 (13:58 +0800)]
ixgbe: fix disable interrupt twice

Currently, ixgbe vf and pf will disable interrupt twice in
stop stage and uninit stage. It will cause an error:

    testpmd> quit

    Shutting down port 0...
    Stopping ports...
    Done
    Closing ports...
    EAL: Error disabling MSI-X interrupts for fd 26
    Done

because the interrupt has already been disabled in stop stage.
Since it is enabled in init stage, better remove from
stop stage.

Fixes: 0eb609239efd ("ixgbe: enable Rx queue interrupts for PF and VF")

Signed-off-by: Michael Qiu <michael.qiu@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoixgbe: fix whitespace
Stephen Hemminger [Wed, 13 Jan 2016 04:54:10 +0000 (20:54 -0800)]
ixgbe: fix whitespace

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Helin Zhang <helin.zhang@intel.com>
8 years agoixgbe: speed up non-vector Tx
Stephen Hemminger [Fri, 13 Nov 2015 16:10:13 +0000 (08:10 -0800)]
ixgbe: speed up non-vector Tx

The freeing of mbuf's in ixgbe is one of the observable hot spots
under load. Optimize it by doing bulk free of mbufs using code similar
to i40e and fm10k.

Drop the no longer needed micro-optimization for the no refcount flag.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
8 years agoigb: set default thresholds based on MAC type
Stephen Hemminger [Fri, 22 Jan 2016 01:38:37 +0000 (17:38 -0800)]
igb: set default thresholds based on MAC type

This brings the DPDK igb driver inline with the behavior used by
the current Linux driver. The IGB hardware has several different
MAC types and the threshold values that work vary based on the hardware.

Since DPDK 1.8 it has been up to devices to provide the correct default
configuration parameter. But the igb driver gives values that are broken
on some devices, and always causes a warning message at startup.

Please test this on real hardware, I don't have the luxury of a
hardware lab full of variations of this chip.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoe1000: fix VF MAC address on close
Bernard Iremonger [Wed, 2 Mar 2016 16:09:06 +0000 (16:09 +0000)]
e1000: fix VF MAC address on close

Allow reprogramming of the RAR with a zero mac address,
to ensure that the VF traffic goes to the PF after
stop, close and detach of the VF.

Fixes: be2d648a2dd3 ("igb: add PF support")
Fixes: d82170d27918 ("igb: add VF support")

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoe1000: support VF promiscuous and allmulticast
Yury Kylulin [Tue, 9 Feb 2016 09:09:43 +0000 (12:09 +0300)]
e1000: support VF promiscuous and allmulticast

Enable promiscuous and allmulticast mode control from the VF using
rte_eth_promiscuous_enable()/rte_eth_promiscuous_disable() and
rte_eth_allmulticast_enable()/rte_eth_allmulticast_disable().

For promiscuous mode host/PF igb driver should be built with
IGB_ENABLE_VF_PROMISC.

For allmulticast mode "allmulti" flag should be set for appropriate PF
ifconfig eth0 allmulti

Signed-off-by: Yury Kylulin <yury.kylulin@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoe1000: support I217 and I218 devices
Ravi Kerur [Wed, 2 Mar 2016 13:59:34 +0000 (05:59 -0800)]
e1000: support I217 and I218 devices

Modified driver and eal code to support I217 and I218 Intel NICs.

Compiled and tested (via testpmd) on Ubuntu 14.04 for target
x86_64-native-linuxapp-gcc
Compiled for target x86_64-native-linuxapp-clang

Signed-off-by: Ravi Kerur <rkerur@gmail.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
8 years agoenic: fix last packet not being sent
John Daley [Tue, 8 Mar 2016 18:49:07 +0000 (10:49 -0800)]
enic: fix last packet not being sent

The last packet of the tx burst function array was not being
emitted until the subsequent call.  The nic descriptor index
was being set to the current tx descriptor instead of one past
the descriptor as required by the nic.

Fixes: d739ba4c6abf ("enic: improve Tx packet rate")

Signed-off-by: John Daley <johndale@cisco.com>