dpdk.git
9 years agoconfig: increase max queues per port
Jijiang Liu [Thu, 28 May 2015 01:36:18 +0000 (09:36 +0800)]
config: increase max queues per port

The default value of RTE_MAX_QUEUES_PER_PORT is 256, which is too small
for some configurations for i40e. There will return an error when
configured queue number is larger than 256 in rte_eth_dev_configure().

For example, in vHost sample, PF queue number: 64,
configured vmdq pool number: 63, each vmdq pool has 4 queues,
there will be required 316 queues in a port.

Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
9 years agofm10k: fix maximum VF number
Michael Qiu [Tue, 2 Jun 2015 02:28:48 +0000 (10:28 +0800)]
fm10k: fix maximum VF number

In DPDK, max_vfs means vf numbers created, not the max number vfs
the device supported.

Signed-off-by: Michael Qiu <michael.qiu@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
9 years agoi40e: fix condition to get VMDQ infos
Jijiang Liu [Tue, 19 May 2015 05:55:39 +0000 (13:55 +0800)]
i40e: fix condition to get VMDQ infos

To get device VMDQ info when only i40e VMDQ feature is enabled.

Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
9 years agokni: fix missing header dependencies
Bruce Richardson [Mon, 25 May 2015 12:23:54 +0000 (13:23 +0100)]
kni: fix missing header dependencies

The file rte_kni.h depends upon a number of other headers, some of which
are missing from the #include lines. The following #includes are added:
 * rte_memory.h - for the definition of phys_addr_t
 * rte_mempool.h - for the definition of mempool struct and the mempool
   create function.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Marc Sune <marc.sune@bisdn.de>
9 years agoeal: fix missing header dependency
Bruce Richardson [Mon, 25 May 2015 12:23:53 +0000 (13:23 +0100)]
eal: fix missing header dependency

rte_pci.h depends upon stdio.h for the definition of the FILE type. Add
in #include <stdio.h> to the file to satisfy this dependency in cases
where the including C file does not already include stdio.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Marc Sune <marc.sune@bisdn.de>
9 years agoapp/testpmd: compute checksum in ICMP reply
Adrien Mazarguil [Fri, 22 May 2015 17:03:12 +0000 (19:03 +0200)]
app/testpmd: compute checksum in ICMP reply

ICMP echo replies with invalid checksums may be dropped by network nodes or
ignored by the ping utility.

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Ivan Boule <ivan.boule@6wind.com>
9 years agoapp/testpmd: fix MAC address in ARP reply
Adrien Mazarguil [Fri, 22 May 2015 11:07:31 +0000 (13:07 +0200)]
app/testpmd: fix MAC address in ARP reply

In the icmpecho forwarding mode, ARP replies from testpmd contain
invalid zero-filled MAC addresses. This is broken since the commit below.

Fixes: 31db4d38de72 ("net: change arp header struct declaration")

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Ivan Boule <ivan.boule@6wind.com>
9 years agomempool: fix pages computation to determine number of objects
Konstantin Ananyev [Wed, 27 May 2015 08:40:05 +0000 (09:40 +0100)]
mempool: fix pages computation to determine number of objects

In rte_mempool_obj_iter(), when element boundary coincides with page boundary,
even if a single page is required per object, a loop checks that the next page
is contiguous and drops the first one otherwise.
This commit checks subsequent pages only when several are required per object.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reviewed-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
9 years agomempool: fix returned value after counting objects
Adrien Mazarguil [Mon, 25 May 2015 16:27:45 +0000 (18:27 +0200)]
mempool: fix returned value after counting objects

rte_mempool_xmem_usage()'s return type is ssize_t which has the same
architecture-dependent width as size_t but is signed.

On 64-bit architectures, returning a negative uint32_t value without casting
to ssize_t first does not work as intended, the sign bit is lost and the
returned value is garbage.

This commit fixes an assertion failure in testpmd on 64 bit architectures
when combining --no-huge and --mp-anon outside of Xen Dom0:

 PANIC in mempool_anon_create():
 line 170        assert "elt_num == mp->size" failed

Fixes: 148f963fb532 ("xen: core library changes")

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
9 years agocmdline: fix small memory leak
Erik Ziegenbalg [Wed, 20 May 2015 00:04:55 +0000 (17:04 -0700)]
cmdline: fix small memory leak

A function in cmdline.c has a return that does not free buf properly.

Signed-off-by: Erik Ziegenbalg <eziegenb@brocade.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: John McNamara <john.mcnamara@intel.com>
9 years agodoc: refactor table numbers into references
John McNamara [Mon, 18 May 2015 11:34:07 +0000 (12:34 +0100)]
doc: refactor table numbers into references

This change adds automatic table references to the docs. The
table numbers in the generated Html and PDF docs are now
automatically numbered based on section.

Requires Sphinx >= 1.3.1.

This change:

* Adds a RST table:: directive to each table caption.

* Indents the tables to the required directive level.

Signed-off-by: John McNamara <john.mcnamara@intel.com>
9 years agodoc: refactor figure numbers into references
John McNamara [Mon, 18 May 2015 11:34:06 +0000 (12:34 +0100)]
doc: refactor figure numbers into references

This change adds automatic figure references to the docs. The
figure numbers in the generated Html and PDF docs are now
automatically numbered based on section.

Requires Sphinx >= 1.3.1.

The patch makes the following changes.

* Changes image:: tag to figure:: and moves image caption
  to the figure.

* Adds captions to figures that didn't previously have any.

* Un-templates the |image-name| substitution definitions
  into explicit figure:: tags. They weren't used more
  than once anyway and Sphinx doesn't support them
  for figure.

* Adds a target to each image that didn't previously
  have one so that they can be cross-referenced.

* Renamed existing image target to match the image
  name for consistency.

* Replaces the Figures lists with automatic :numref:
  :ref: entries to generate automatic numbering
  and captions.

* Replaces "Figure" references with automatic :numref:
  references.

Signed-off-by: John McNamara <john.mcnamara@intel.com>
9 years agodoc: add sphinx numref compatibility fallback
John McNamara [Mon, 18 May 2015 11:34:08 +0000 (12:34 +0100)]
doc: add sphinx numref compatibility fallback

This change adds some simple handling for the :numref: directive
for Sphinx versions prior to 1.3.1. This allows the Guides
documentation to be built with older versions of Sphinx and still
produce reasonable results.

The patch replaces the :numref: reference with a link to the
target (for all Sphinx doc types). It doesn't try to label
figures/tables.

Full numref support with automatic figure/table numbering and
links can be obtained by upgrading to Sphinx 1.3.1 or later.

Signed-off-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoxenvirt: move drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:57:00 +0000 (16:57 +0100)]
xenvirt: move drivers/net/

Move xenvirt PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agovmxnet3: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:59 +0000 (16:56 +0100)]
vmxnet3: move to drivers/net/

Move vmxnet3 PMD to drivers/net directory.
As part of the move, rename the "vmxnet3" subdirectory, containing the
original FreeBSD drivers, from "vmxnet3" to the more standard name
"base", to indicate it contains the base drivers used for the
implementation.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agovirtio: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:58 +0000 (16:56 +0100)]
virtio: move to drivers/net/

Move virtio PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoring: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:57 +0000 (16:56 +0100)]
ring: move to drivers/net/

Move ring PMD to drivers directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agopcap: move drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:56 +0000 (16:56 +0100)]
pcap: move drivers/net/

Move pcap pmd to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agonull: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:55 +0000 (16:56 +0100)]
null: move to drivers/net/

Move null PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agomlx4: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:54 +0000 (16:56 +0100)]
mlx4: move to drivers/net/

move mlx4 PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoixgbe: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:53 +0000 (16:56 +0100)]
ixgbe: move to drivers/net/

move ixgbe PMD to drivers/net directory.
As part of the move, we rename the ixgbe directory, containing the
ixgbe "base driver" code, from "ixgbe" to "base".

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoi40e: move to drivers/net/
Bruce Richardson [Mon, 18 May 2015 11:05:12 +0000 (12:05 +0100)]
i40e: move to drivers/net/

Move i40e PMD to drivers/net directory.
As part of the move, rename the "i40e" directory, containing the "base
driver" code, from "i40e" to "base".

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agofm10k: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:51 +0000 (16:56 +0100)]
fm10k: move to drivers/net/

move fm10k PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoenic: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:50 +0000 (16:56 +0100)]
enic: move to drivers/net/

move enic PMD to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
[Thomas: move vnic/ to base/]
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoe1000: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:49 +0000 (16:56 +0100)]
e1000: move to drivers/net/

Move e1000 pmd to drivers/net directory
As part of move, rename "e1000" subdirectory, which contains the code
from the "base driver", to "base".

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agobond: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:48 +0000 (16:56 +0100)]
bond: move to drivers/net/

Move bonded ethdev pmd to drivers/net

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoaf_packet: move to drivers/net/
Bruce Richardson [Fri, 15 May 2015 15:56:47 +0000 (16:56 +0100)]
af_packet: move to drivers/net/

move af_packet pmd to drivers/net directory

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agodrivers: create new directory
Bruce Richardson [Fri, 15 May 2015 15:56:46 +0000 (16:56 +0100)]
drivers: create new directory

Add a new top-level "drivers" directory to which all PMDs will be moved
for easier maintenance of both lib folder and drivers themselves. This
new directory is a dependency of all the apps in the app folder, so
the makefiles for each app are updated.
To the new top-level directory add a "net" subdirectory to classify
more specifically our existing PMDs as ethernet drivers

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
[Thomas: fix dependencies and merge several patches]
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agomk: use relative rather than absolute pmd paths
Bruce Richardson [Fri, 15 May 2015 15:56:45 +0000 (16:56 +0100)]
mk: use relative rather than absolute pmd paths

In the Makefiles for the PMDs, the paths to the files are often
specified using the full path from $(RTE_SDK) variable. These paths can
be shortened, and make more flexible in case of a future path change by
specifying the paths using $(SRCDIR) instead.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
9 years agomempool: limit cache size
Zoltan Kiss [Mon, 18 May 2015 15:35:14 +0000 (16:35 +0100)]
mempool: limit cache size

Otherwise cache_flushthresh can be bigger than n, and
a consumer can starve others by keeping every element
either in use or in the cache.

Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agolib: fix 32-bit build with debug enabled
Olivier Matz [Mon, 18 May 2015 08:18:00 +0000 (10:18 +0200)]
lib: fix 32-bit build with debug enabled

When debug is enabled for 32 bits targets, it triggers some format
errors that are not visible in 64 bits. Fix them by using the proper
format from inttypes.h or the proper cast.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoexamples: add dependencies for timer and vm_power_manager
Olivier Matz [Mon, 18 May 2015 08:18:01 +0000 (10:18 +0200)]
examples: add dependencies for timer and vm_power_manager

Do not compile these examples if the related dpdk option is not
enabled, as it's done for other examples. It allows to build
the examples directory with a reduced dpdk configuration.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoexamples/netmap: fix build for x32 ABI
Olivier Matz [Mon, 18 May 2015 08:17:59 +0000 (10:17 +0200)]
examples/netmap: fix build for x32 ABI

Fix a cast issue:
examples/netmap_compat/lib/compat_netmap.c:827:10: error: cast to
  pointer from integer of different size [-Werror=int-to-pointer-cast]

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoexamples/bond: fix build with clang
Olivier Matz [Mon, 18 May 2015 08:17:58 +0000 (10:17 +0200)]
examples/bond: fix build with clang

Fix the following compilation error:

examples/bond/main.c:717:1: error: control reaches end of
  non-void function [-Werror,-Wreturn-type]

The prompt() function does not return anything, so fix its prototype
to be void.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoexamples/ip_pipeline: fix build with clang 3.6
Thomas Monjalon [Tue, 19 May 2015 09:34:16 +0000 (11:34 +0200)]
examples/ip_pipeline: fix build with clang 3.6

This error is detected:
    examples/ip_pipeline/cmdline.c:272:15: error: address of array
          'params->file_path' will always evaluate to 'true'
            if (!params->file_path) {
                ~~~~~~~~~^~~~~~~~~

file_path is an array in a structure so it's unneeded to check it.

Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
9 years agoi40e/base: fix build with clang
Helin Zhang [Mon, 18 May 2015 15:40:56 +0000 (23:40 +0800)]
i40e/base: fix build with clang

When compiling with clang, it detects that a variable used for debug
is unused (debug_mask is never set):
    lib/librte_pmd_i40e/i40e/i40e_nvm.c:708:20: error: unused variable
          'i40e_nvm_update_state_str' [-Werror,-Wunused-variable]
    STATIC const char *i40e_nvm_update_state_str[] = {
                       ^
As we are not supposed to modify the base driver (except for update
synchronization from Intel), it was ignored with GCC thanks to the
option -Wno-unused-variable but clang was forgotten.

Fixes: 6b5aaf47d571 ("i40e/base: replace NVM debug logs")

Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Tetsuya Mukawa <mukawa@igel.co.jp>
9 years agoi40e/base: fix build with icc
Helin Zhang [Mon, 18 May 2015 15:40:55 +0000 (23:40 +0800)]
i40e/base: fix build with icc

Below compile error can be found on ICC 13.0.0, which is a warning
treated as error. Forcedly disabling the warning can fix it.

Error log:
lib/librte_pmd_i40e/i40e/i40e_nvm.c(1022): error #188: enumerated
type mixed with another type
hw->aq.asq_last_status = old_asq_status;
                       ^

Fixes: 3b7271f3958a ("i40e/base: catch NVM write semaphore timeout and retry")

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Tetsuya Mukawa <mukawa@igel.co.jp>
9 years agocmdline: add polling mode
Pawel Wodkowski [Wed, 13 May 2015 12:00:01 +0000 (14:00 +0200)]
cmdline: add polling mode

This patch adds the ability to process console input in the same thread
as packet processing by using poll() function.

Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agocmdline: fix missing includes
Pawel Wodkowski [Wed, 13 May 2015 12:00:00 +0000 (14:00 +0200)]
cmdline: fix missing includes

When including only some of library headers some definitions
are missing and build fails.

Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoport: add IPv6 reassembly port
Maciej Gajdzica [Thu, 30 Apr 2015 12:02:34 +0000 (14:02 +0200)]
port: add IPv6 reassembly port

Added new port type - IPv6 reassembly port.

Signed-off-by: Maciej Gajdzica <maciejx.t.gajdzica@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
9 years agoport: add IPv6 fragmentation port
Maciej Gajdzica [Thu, 30 Apr 2015 12:02:33 +0000 (14:02 +0200)]
port: add IPv6 fragmentation port

Added new port type - IPv6 Fragmentation port

Signed-off-by: Maciej Gajdzica <maciejx.t.gajdzica@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
9 years agoport: remove constant default MTU
Maciej Gajdzica [Thu, 30 Apr 2015 12:02:32 +0000 (14:02 +0200)]
port: remove constant default MTU

p->mtu field should be used instead.

Signed-off-by: Maciej Gajdzica <maciejx.t.gajdzica@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
9 years agoi40e/base: update adminq commands
Helin Zhang [Thu, 30 Apr 2015 15:03:39 +0000 (23:03 +0800)]
i40e/base: update adminq commands

Miscellaneous modifications are added as follows for future use.
- Admin queue command opcodes
- struct i40e_aqc_arp_proxy_data
- struct i40e_aq_set_phy_config
- struct i40e_aqc_nvm_config_data_immediate_field
- struct i40e_aqc_oem_param_change
- struct i40e_aqc_opc_oem_ocsd_initialize
- struct i40e_aqc_opc_oem_ocbb_initialize
In addition, sturcture and command length check at compile time
are added for each admin queue opcodes in order to report any
potential issues as early as possible.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: rework structures and macros
Helin Zhang [Thu, 30 Apr 2015 15:03:38 +0000 (23:03 +0800)]
i40e/base: rework structures and macros

Several structures as follows were modified for future use.
- struct i40e_link_status
- struct i40e_nvm_info
- struct i40e_veb_tc_stats
In addition, shadow RAM macros and enum were modified for future
use as well.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: future proof some sizeof calls
Helin Zhang [Thu, 30 Apr 2015 15:03:36 +0000 (23:03 +0800)]
i40e/base: future proof some sizeof calls

Make sure the sizeof() calls are taking the size of the actual
struct that we care about. By using the pointer variable, it will
always get the right struct size, even if the variable type
changes sometime in the future.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: add new interfaces
Helin Zhang [Thu, 30 Apr 2015 15:03:27 +0000 (23:03 +0800)]
i40e/base: add new interfaces

Four new interfaces are added for future use, as follows, together
with their relevant strucure and macro definitions.
- i40e_aq_read_nvm_config()
- i40e_aq_write_nvm_config()
- i40e_aq_set_lldp_mib()
- i40e_read_pba_string()
In addition, removed i40e_read_nvm_srrd() as needed.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: add more virtual channel operations
Helin Zhang [Thu, 30 Apr 2015 15:03:37 +0000 (23:03 +0800)]
i40e/base: add more virtual channel operations

Virtual channel operations of I40E_VIRTCHNL_OP_EVENT and
I40E_VIRTCHNL_OP_CONFIG_RSS are added for future use.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: add iSCSI capability
Helin Zhang [Thu, 30 Apr 2015 15:03:34 +0000 (23:03 +0800)]
i40e/base: add iSCSI capability

Add parsing and reporting of iSCSI capability for a given device
or function.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: add AOC PHY types
Helin Zhang [Thu, 30 Apr 2015 15:03:33 +0000 (23:03 +0800)]
i40e/base: add AOC PHY types

Add the 10G and 40G AOC phy types to the case statement in
get_media_type so that the correct information gets reported back
to the user.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: workaround for PHY type with firmware < 4.4
Helin Zhang [Thu, 30 Apr 2015 15:03:32 +0000 (23:03 +0800)]
i40e/base: workaround for PHY type with firmware < 4.4

The FW for SW3E is incorrectly reporting a breakout cable as PHY
type 0x3 when it should be 0x16 (I40E_PHY_TYPE_10GBASE_SFPP_CU).
As this is supposed to be fixed in the next FW version
(FW versions >= 4.4), if we get this value back from FW and the
version is < 4.4, reassign it to I40E_PHY_TYPE_10GBASE_SFPP_CU.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: find partition id in NPAR mode and disable FCoE
Helin Zhang [Thu, 30 Apr 2015 15:03:31 +0000 (23:03 +0800)]
i40e/base: find partition id in NPAR mode and disable FCoE

In NPAR mode the driver instance might be controlling the base
partition or one of the other "fake" PFs. There are some things
that can only be done by the base partition, aka partition_id 1.
This code does a bit of work to find how many partitions are there
in per port and what is the current partition_id. In addition,
FCOE is disabled by default, as it was pushed out from the firmware.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: fix hardware port number for pass-thru
Helin Zhang [Thu, 30 Apr 2015 15:03:30 +0000 (23:03 +0800)]
i40e/base: fix hardware port number for pass-thru

Getting the pf_id from the function number was a good place to
start, but when the PF was setup in pass-thru mode, the PCI
bus/device/function was virtualized and the number in the VM is
different from the number in the bare metal. This caused HW
configuration issues when the wrong pf_id was used to set up the
HMC and other structures. The PF_FUNC_RID register has the real
bus/device/function information as configured by the BIOS, so use
that for a better number.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: update LED blinking
Helin Zhang [Thu, 30 Apr 2015 15:03:28 +0000 (23:03 +0800)]
i40e/base: update LED blinking

As it is requried to blink the LEDs only, it should ignore the
activity LEDs. Also a fix is added to clear the GPIO blink field
specifically.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: remove useless wrapper for link info
Helin Zhang [Thu, 30 Apr 2015 15:03:26 +0000 (23:03 +0800)]
i40e/base: remove useless wrapper for link info

As i40e_update_link_info() is just a simple wrapper of AQ command
interface of i40e_aq_get_link_info(), the AQ command interface
should be used directly.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: clean adminq debug
Helin Zhang [Thu, 30 Apr 2015 15:03:29 +0000 (23:03 +0800)]
i40e/base: clean adminq debug

A sparse complaint in i40e_debug_aq in a funky buffer write goes
away by straightening out the code out to something less convoluted.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: enhance adminq init and ASQ send
Helin Zhang [Thu, 30 Apr 2015 15:03:25 +0000 (23:03 +0800)]
i40e/base: enhance adminq init and ASQ send

The timeout of ASQ command is enlarged from 100 ms to 250 ms to
wait longer time for the response. nvm_busy is not needed anymore.
Also nvm_release_on_done and nvmupd_state will be set during
adminq init.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: use FLAG_RD when sending driver version to firmware
Helin Zhang [Thu, 30 Apr 2015 15:03:35 +0000 (23:03 +0800)]
i40e/base: use FLAG_RD when sending driver version to firmware

When sending driver version to FW, FLAG_SI is not needed as it is
done as part of i40e_fill_default_descriptor function call, and it
should be replaced by FLAG_BUF and FLAG_RD.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: grab NVM devstarter version instead of image version
Helin Zhang [Thu, 30 Apr 2015 15:03:24 +0000 (23:03 +0800)]
i40e/base: grab NVM devstarter version instead of image version

The NVM image version has useful data but it is a per image version,
and every image can have a different one. While for the dev starter
version, all the images for release will have the same version. So
it would be better to use dev starter version number.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: store firmware version
Helin Zhang [Thu, 30 Apr 2015 15:03:22 +0000 (23:03 +0800)]
i40e/base: store firmware version

Since the FW build number is available in the AQ response, save it
off for future use.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: enhance NVM checksum calculation
Helin Zhang [Thu, 30 Apr 2015 15:03:20 +0000 (23:03 +0800)]
i40e/base: enhance NVM checksum calculation

The data buffer for i40e_calc_nvm_checksum() is too big, so move
it off and allocate separately. In addition, use
i40e_read_nvm_buffer() to get the whole shadow RAM, together with
minor enhancements.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: enhance polling of NVM semaphore
Helin Zhang [Thu, 30 Apr 2015 15:03:19 +0000 (23:03 +0800)]
i40e/base: enhance polling of NVM semaphore

Only poll on the NVM semaphore if there's time left on a previous
reservation.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: fix error handling of NVM state update
Helin Zhang [Thu, 30 Apr 2015 15:03:18 +0000 (23:03 +0800)]
i40e/base: fix error handling of NVM state update

The state transitions after an error were not managed well, so
these changes get us back to the INIT state or don't transit
out of the INIT state after most errors.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: replace NVM debug logs
Helin Zhang [Thu, 30 Apr 2015 15:03:21 +0000 (23:03 +0800)]
i40e/base: replace NVM debug logs

To support better debug information printing, all DEBUGOUT() are
replaced by i40e_debug(). In addition, the NVM update state strings
are added in debug information.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: check for AQ timeout
Helin Zhang [Thu, 30 Apr 2015 15:03:17 +0000 (23:03 +0800)]
i40e/base: check for AQ timeout

Decoding the AQ return code is great except when the AQ send timed
out and there's no return code set. This changes the handy decoder
interface to help catch and properly report the condition as an
useful error number rather than returning a misleading '0'.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: catch NVM write semaphore timeout and retry
Helin Zhang [Thu, 30 Apr 2015 15:03:16 +0000 (23:03 +0800)]
i40e/base: catch NVM write semaphore timeout and retry

In some circumstances, a multi-write transaction takes longer than
the default 3 minutes timeout on the write semaphore. If the write
failed with an EBUSY status, this is likely the problem. So here
it tries to reacquire the semaphore and then retry the write.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: update shadow RAM read/write
Helin Zhang [Thu, 30 Apr 2015 15:03:15 +0000 (23:03 +0800)]
i40e/base: update shadow RAM read/write

To support different hardware, shadow RAM read should be done via
SRCTL register or AQ command, and shadow RAM write should be done
via AQ command only.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: rework virtual address retrieval for lan queue
Helin Zhang [Thu, 30 Apr 2015 15:03:14 +0000 (23:03 +0800)]
i40e/base: rework virtual address retrieval for lan queue

To simplify the usage of invoking 'i40e_hmc_get_object_va', input
parameters of it were reworked. In addition, minor code style fixes
were added as well.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: move register debug function
Helin Zhang [Thu, 30 Apr 2015 15:03:13 +0000 (23:03 +0800)]
i40e/base: move register debug function

As base driver provides 'i40e_aq_debug_read_register()', the same
functional interface of 'i40e_debug_read_register()' can be replaced.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: support CEE DCBX
Helin Zhang [Thu, 30 Apr 2015 15:03:12 +0000 (23:03 +0800)]
i40e/base: support CEE DCBX

Recent firmware versions support CEE DCBX, while old firmware
versions support IEEE DCBX only. So firmware version needs to be
checked during getting DCB configurations. To support CEE DCBX,
AQ commands of 'i40e_aq_get_cee_dcb_config' and
'i40e_aq_start_stop_dcbx' were implemented.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: skip some hardware init for VF
Helin Zhang [Thu, 30 Apr 2015 15:03:23 +0000 (23:03 +0800)]
i40e/base: skip some hardware init for VF

This patch is useful for future expansion when new VF MAC types get
added. It also helps with cleaning up VF driver flow.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: support building both PF and VF driver together
Helin Zhang [Thu, 30 Apr 2015 15:03:11 +0000 (23:03 +0800)]
i40e/base: support building both PF and VF driver together

Macros of PF_DRIVER, VF_DRIVER and INTEGRATED_VF were defined to
support building both PF and VF driver together. PF_DRIVER needs
to be defined if a build is for PF only, while VF_DRIVER for VF
only. PF_DRIVER, VF_DRIVER and INTEGRATED_VF are all needed for
building both PF and VF driver together.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: rename err to perrno
Helin Zhang [Thu, 30 Apr 2015 15:03:10 +0000 (23:03 +0800)]
i40e/base: rename err to perrno

To be consistent with the original base driver, the variable name
of 'err' should be renamed to 'perrno'.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e/base: adjust register definitions and relevant
Helin Zhang [Thu, 30 Apr 2015 15:03:09 +0000 (23:03 +0800)]
i40e/base: adjust register definitions and relevant

Some macros of register definitions or relevant are added, modified
or deleted. In detail, they are as follows.
- I40E_PRTDCB_RUPTQ
- I40E_GLGEN_GPIO_CTL
- I40E_GLGEN_MDIO_CTRL
- I40E_GLGEN_RSTENA_EMP
- I40E_GLPCI_LATCT
- I40E_GLTPH_CTRL
- I40E_GLPRT_BPRCH
- I40E_GLPRT_TDPC
- I40E_GLSCD_QUANTA
Also reading the register of I40E_GLPRT_TDPC is deleted as its
definition is deleted.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agoi40e: update copyright
Helin Zhang [Thu, 30 Apr 2015 15:03:07 +0000 (23:03 +0800)]
i40e: update copyright

Copyright is updated.

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
9 years agoi40e: disable setting of PHY configuration
Helin Zhang [Thu, 30 Apr 2015 15:03:08 +0000 (23:03 +0800)]
i40e: disable setting of PHY configuration

There was a known link issue on 40G ports on NVM version (FVL3E),
when setting phy configuration. As a workaround, setting of phy
configuration should be disabled. The impact is that the link cannot
be forcedly configured, which doesn't affect any feature functions.
The workaround can be removed when a formal fix is ready later.

Test report: http://www.dpdk.org/ml/archives/dev/2015-May/017384.html

Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Jijiang Liu <jijiang.liu@intel.com>
Tested-by: Min Cao <min.cao@intel.com>
9 years agomk: introduce EXTRA_LDLIBS variable
Keith Wiles [Thu, 14 May 2015 14:21:32 +0000 (09:21 -0500)]
mk: introduce EXTRA_LDLIBS variable

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agomk: simplify conditions for libs to link
Keith Wiles [Thu, 14 May 2015 14:21:31 +0000 (09:21 -0500)]
mk: simplify conditions for libs to link

Simplify the ifdefs in rte.app.mk to make the code more
readable and maintainable by introducing a internal
_LDLIBS-y variable to build up the LDLIBS variable.

The new internal variable _LDLIBS-y should not be
used outside of the rte.app.mk file.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agomaintainers: claim responsibility for docs
John McNamara [Wed, 13 May 2015 13:08:28 +0000 (14:08 +0100)]
maintainers: claim responsibility for docs

Signed-off-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agovhost: fix virtio freeze due to missed interrupt
Huawei Xie [Wed, 29 Apr 2015 11:11:24 +0000 (19:11 +0800)]
vhost: fix virtio freeze due to missed interrupt

Update of used->idx and read of avail->flags could be reordered.
Memory fence should be used to ensure the order, otherwise guest could see
a stale used->idx value after it toggles the interrupt suppression flag.
After guest sets the interrupt suppression flag, it will check if there
is more buffer to process through used->idx. If it sees a stale value,
it will exit the processing while host won't send interrupt to guest.

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Reviewed-by: Luke Gorrie <luke@snabb.co>
9 years agoeal/linux: fix irq handling with igb_uio
Stephen Hemminger [Tue, 28 Apr 2015 16:36:38 +0000 (09:36 -0700)]
eal/linux: fix irq handling with igb_uio

The introduction of uio_pci_generic broke interrupt handling with
igb_uio. The igb_uio device uses the kernel read/write method to
enable disable IRQ's; the uio_pci_generic has to use PCI intx
config read/write to enable disable interrupts.

Since igb_uio uses MSI-X the PCI intx config read/write won't
work.

Fixes: c112df6875a5 ("eal/linux: toggle interrupt for uio_pci_generic")

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
9 years agomk: remove NO_AUTOLIBS option
Keith Wiles [Fri, 1 May 2015 14:29:47 +0000 (09:29 -0500)]
mk: remove NO_AUTOLIBS option

NO_AUTOLIBS is not required as it was not used or defined in the config files.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
9 years agoscripts: fix build in a symlinked directory
Olivier Matz [Tue, 5 May 2015 09:00:09 +0000 (11:00 +0200)]
scripts: fix build in a symlinked directory

The script relpath.sh returns the relative path of the first directory
from the second directory. It is used to generate relative symlinks,
which can be useful if the build directory is embedded in the dpdk
directory: the whole dpdk can be moved without breaking the links,
which is helpful for an installation.

In case the build directory is a symlink, the script was not generating
the proper relative path. Fix this by calling "readlink -f" on the
arguments.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Tested-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
9 years agopcap: fix storage of name and type in queues
Konstantin Ananyev [Thu, 23 Apr 2015 14:32:48 +0000 (15:32 +0100)]
pcap: fix storage of name and type in queues

pcap_rx_queue/pcap_tx_queue should store it's own copy of name/type values,
not the pointer to temporary allocated space.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: John Mcnamara <john.mcnamara@intel.com>
9 years agoexamples/vhost: fix build with debug enabled
Ouyang Changchun [Mon, 4 May 2015 07:15:19 +0000 (15:15 +0800)]
examples/vhost: fix build with debug enabled

Minor fix for the referring of a pointer when debug and dump is enabled.

Fixes: 72ec8d77ac68 ("examples/vhost: rework duplicated code")

Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
9 years agovfio: set eventfd non-blocking and not inherited
Stephen Hemminger [Wed, 29 Apr 2015 15:15:45 +0000 (08:15 -0700)]
vfio: set eventfd non-blocking and not inherited

Set internal event file descriptor to be non-block and not
inherited across exec.  This prevents accidental hangs and
passing in another thread.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
9 years agoapps: fix default mbuf size
Konstantin Ananyev [Wed, 29 Apr 2015 23:31:51 +0000 (00:31 +0100)]
apps: fix default mbuf size

Latest mbuf changes (priv_size addition and related fixes)
exposed small problem with testpmd and few other sample apps:
when mbuf size is exaclty 2KB or less, that causes
ixgbe PMD to select scattered RX even for configs with 'normal'
max packet length (max_rx_pkt_len == ETHER_MAX_LEN).
To overcome that problem and unify the code, new macro was created
to represent recommended minimal buffer length for mbuf.
When appropriate, samples are updated to use that macro.

Fixes: dfb03bbe2b ("app/testpmd: use standard functions to initialize
mbufs and mbuf pool")

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoeal/bsd: fix build on FreeBSD
Bruce Richardson [Tue, 5 May 2015 12:47:34 +0000 (13:47 +0100)]
eal/bsd: fix build on FreeBSD

Compilation on FreeBSD with clang was broken, giving the error message:

lib/librte_eal/bsdapp/eal/eal_pci.c:438:16: fatal error: assigning to
  'struct rte_pci_id *' from 'const struct rte_pci_id *' discards qualifiers
  [-Wincompatible-pointer-types-discards-qualifiers]
    for (id_table = dr->id_table ; id_table->vendor_id != 0; id_table++) {
                  ^ ~~~~~~~~~~~~

This patch fixes the issue by adding "const" to the type of id_table.

Fixes: 6065355a03fc ("pci: make device id tables const")

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
9 years agokni: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:52 +0000 (14:03 +0100)]
kni: remove inclusion of mbuf header

The kni header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agopipeline: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:54 +0000 (14:03 +0100)]
pipeline: remove inclusion of mbuf header

The pipeline header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agotable: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:56 +0000 (14:03 +0100)]
table: remove inclusion of mbuf header

The rte_table header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agodistributor: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:50 +0000 (14:03 +0100)]
distributor: remove inclusion of mbuf header

The distributor header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoip_frag: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:53 +0000 (14:03 +0100)]
ip_frag: remove inclusion of mbuf header

The ip_frag header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agovhost: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:57 +0000 (14:03 +0100)]
vhost: remove inclusion of mbuf header

The virtio_net header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agovirtio: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:55 +0000 (14:03 +0100)]
virtio: remove inclusion of mbuf header

The virtqueue header files include the mbuf header file, but they do not
need to do so as they only use pointers to the struct rte_mbuf type, and
do not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoethdev: remove inclusion of mbuf header
Bruce Richardson [Thu, 23 Apr 2015 13:03:51 +0000 (14:03 +0100)]
ethdev: remove inclusion of mbuf header

The ethdev header file includes the mbuf header file, but it does not
need to do so as it only uses pointers to the struct rte_mbuf type, and
does not use any of the mbuf internals, nor any of the mbuf functions or
macros. Therefore the inclusion is unnecessary, and can be replaced by a
forward declaration of the mbuf type.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
9 years agoenic: add device ids
Sujith Sankar [Thu, 7 May 2015 03:49:09 +0000 (09:19 +0530)]
enic: add device ids

This patch adds support for enic in the nic_uio driver so that enic
could be used on FreeBSD.

Signed-off-by: Sujith Sankar <ssujith@cisco.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
9 years agokni: fix vhost build with kernels 3.19 and 4.0
Pablo de Lara [Tue, 5 May 2015 14:08:00 +0000 (15:08 +0100)]
kni: fix vhost build with kernels 3.19 and 4.0

Due to commit c0371da6 in kernel 3.19, which removed msg_iov
and msg_iovlen from struct msghdr, DPDK would not build.
Also, functions memcpy_toiovecend and memcpy_fromiovecend
were removed in commits ba7438ae and 57dd8a07, being substituted by
copy_from_iter and copy_to_iter.

This patch makes use of struct iov_iter, which has references
to msg_iov and msg_iovln, and makes use of copy_from_iter
and copy_to_iter.

Reported-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
9 years agokni: fix build with kernel 4.0
Pablo de Lara [Tue, 28 Apr 2015 17:37:42 +0000 (18:37 +0100)]
kni: fix build with kernel 4.0

Due to API changes in function pointer ndo_bridge_setlink
(commit ad41faa8) and the rename of functions vlan_tx_*
(commit df8a39de) in kernel 4.0, DPDK would not build.

This patch adds the properly checks to fix the compilation.

Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
9 years agoixgbe: use scattered Rx with bulk allocation
Vlad Zolotarov [Wed, 29 Apr 2015 08:38:17 +0000 (11:38 +0300)]
ixgbe: use scattered Rx with bulk allocation

Simply initialze rx_pkt_burst callback to ixgbe_recv_pkts_lro_bulk_alloc()
if the conditions are right.

This is possible because work against HW in LRO and scattered cases is
exactly the same and LRO callback already supports the bulk allocation.

Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
9 years agoixgbe: remove simple scalar scattered Rx method
Vlad Zolotarov [Wed, 29 Apr 2015 08:38:16 +0000 (11:38 +0300)]
ixgbe: remove simple scalar scattered Rx method

Kill ixgbe_recv_scattered_pkts() - use ixgbe_recv_pkts_lro_single_alloc()
instead.

Work against HW queues in LRO and scattered Rx cases is exactly the same.
Therefore we may drop the inferior callback.

This patch also changes the sw_rsc_ring allocation in the
ixgbe_dev_rx_queue_setup() to always allocate sw_rsc_ring instead of
explicitly allocating it in all possible cases when it may be needed:
LRO and/or scattered Rx.

This will only impose sizeof(void*) * IXGBE_MAX_RING_DESC = 32KB overhead
per Rx queue as a price for a much simpler code, which seems reasonable.

Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>