I'm not sure why this has not caused an issue before, perhaps
missing -Werror=unused-parameter or super-set
and subsequently fixed.
This patch adds __rte_unused to
pci_unbind_kernel_driver(struct rte_pci_device *dev)
Signed-off-by: Alan Carew
---
lib/librte_eal/bsdapp/eal/eal_pci.c | 2 +-
1
Recent change to rte_dump_tailq, which now uses a FILE parameter
causes compilation to fail under FreeBSD and sourced to a
missing include of stdio.h
This and next patch(both small) allows to compile without error.
Signed-off-by: Alan Carew
---
lib/librte_eal/common/include/rte_tailq.h | 1 +
Hi,
We are running the sample DPDK KNI application on a single physical port.
We are able to see the vETH interface getting created via IFCONFIG.
However the vETH interface is DOWN by default despite the physical
interface being UP and RUNNING. Only when we configured IP address via
IFCONFIG, the
On 06/04/2014 08:08 PM, Cristian Dumitrescu wrote:
> (Version 2 changes are exclusively style changes (checkpatch.pl) and patch
> consolidation, no functional change)
>
> Intel DPDK Packet Framework provides a standard methodology (logically
> similar to OpenFlow) for rapid development of
This final patch address the issue of not being able to determine the correct
offet when MSI-X is disabled.
Signed-off-by: Alan Carew
---
lib/librte_pmd_virtio/virtio_ethdev.c |1 +
lib/librte_pmd_virtio/virtio_pci.h|4 +++-
2 files changed, 4 insertions(+), 1 deletions(-)
diff
This patch adds a shared enum between user and kernel space to rte_pci_device.
The value of intr_mode is parsed by eal_pci during pci_uio_map_resource
Signed-off-by: Alan Carew
---
lib/librte_eal/common/Makefile |1 +
lib/librte_eal/common/include/rte_pci.h |2 +
This patch adds an "interrupt_mode" sysfs entry for igb_uio devices,
allowing userspace eal_pci to track which interrupt mode has been enabled in
kernel space.
The sysfs entry can be inspected via
/sys/bus/pci/devices/
---
.../common/include/rte_pci_dev_feature_defs.h | 85
Acked-by: Pablo de Lara Guarch
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Konstantin Ananyev
> Sent: Wednesday, May 28, 2014 3:47 PM
> To: dev at dpdk.org; dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] fix for eth_pcap_tx() can cause mbuf corruption
>
Hey all-
One of the things that came up during the dpdk package review for Fedora
was the inconsistency of License reporting in the upstream project. DPDK is
triple licensed, whcih isn't in and of itself a big deal, but indications of
which file(s) are under which license is fairly
Hi,
In order to minimize the number of iterations, Ivan and I had an offline
discussion on this.
Ivan is concerned with the way the mbuf cloning/scatter-gather feature is
currently implemented in DPDK, and not with this particular patch.
We agreed to take the discussion on
Sys files of 'extended_tag' and 'max_read_request_size' are
supported by igb_uio. Reading or writing them to enable/disable
'Extended Tag' or reset 'Max Read Request Size' automatically
according to the configurations are added.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by:
Enabling 'Extended Tag' and resetting 'Max Read Request Size' in PCI
config space have big impacts to i40e performance. They cannot be
changed on some BIOS implementations, though can on others. Two sys
files of 'extended_tag' and 'max_read_request_size' are added to
support changing them by
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in qos_meter example application to
support all PMDs.
Signed-off-by: Helin Zhang
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in multi_process example application to
support all PMDs.
Signed-off-by: Helin
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in load_balancer example application to
support all PMDs.
Signed-off-by: Helin
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in l3fwd example application to support
all PMDs.
Signed-off-by: Helin Zhang
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in l3fwd-power example application to
support all PMDs.
Signed-off-by: Helin Zhang
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in ip_reassembly example application to
support all PMDs.
Signed-off-by: Helin
As hash flags of RSS have been enlarged from 16 bits to 64 bits to
support more possible types in all PMDs, and new macro of
ETH_RSS_IP has been defined to cover all IP hash flags of RSS.
That macro should be used in dpdk_qat example application to
support all PMDs.
Signed-off-by: Helin Zhang
As i40e PMD need to know the L3 packet type for TX checksum offloading,
the packet type has been added in rte_mbuf offload flags.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
As the hash flags of RSS has been enlarged from 16 bits to 64 bits in
'struct rte_eth_rss_conf' in rte_ethdev.h, the size of it in testpmd
should be enlarged as well. In addition, macro of ETH_RSS_IP is used
to replace all IP hash flags of RSS.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
New command of 'tx_vlan set pvid port_id vlan_id (on|off)' has been
added in test-pmd to configure port based vlan insertion.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
i40e supports both 16 and 32 bytes RX descriptors, while ixgbe and
igb support 16 bytes size only. Code changes have been made in
test-pmd to support both 16 and 32 bytes RX descriptors according
to the configuration in config files.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by:
configurations for i40e have been added in both common_bsdapp
and common_linuxapp.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
config/common_bsdapp | 20
i40e support has been added in lib/Makefile and mk/rte.app.mk.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
lib/Makefile | 1 +
mk/rte.app.mk | 4
2 files changed, 5 insertions(+)
As the hash flags of RSS has been enlarged from 16 bits to 64 bits
in 'struct rte_eth_rss_conf' in rte_ethdev.h, the size of it in
igb has to be enlarged as well. In addition, the flags for igb
only are masked, as there are flags for others in those 64 bits.
Signed-off-by: Helin Zhang
As the hash flags of RSS has been enlarged from 16 bits to 64 bits
in 'struct rte_eth_rss_conf' in rte_ethdev.h, the size of it in
ixgbe has to be enlarged as well. In addition, the flags for ixgbe
only are masked, as there are flags for others in those 64 bits.
Signed-off-by: Helin Zhang
As the hash flags of RSS has been enlarged from 16 bits to 64 bits
in 'struct rte_eth_rss_conf' in rte_ethdev.h, the size of it in
vmxnet3 has to be enlarged as well. In addition, the flags for
vmxnet3 only are masked, as there are flags for others in that
64 bits.
Signed-off-by: Helin Zhang
In ethdev, it ignores setting maximum packet length to less than
1518. The changes is to remove this limitation and let less than
1518 can be set for 'maximum packet length'.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing
To support i40e,
- New link speeds have been defined.
- New ops has been added to support setting port based vlan insertion.
- i40e RSS flags have been added.
- A generic function of is_same_ether_addr() has been added to
compare two ethernet address.
- A new configuration of 'uint8_t
New packet flags of both RX and TX have been added to support i40e.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
lib/librte_mbuf/rte_mbuf.h | 8
1 file changed, 8 insertions(+)
The definitions have been added to support i40e devices.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
lib/librte_eal/linuxapp/igb_uio/igb_uio.c | 2 ++
1 file changed, 2 insertions(+)
The pci device IDs of i40e have been added. The new macros have been
added in rte_pci_dev_ids.h to support i40e.
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
Acked-by: Jingjing Wu
Tested-by: Waterman Cao
---
Add PMD source files to support Intel(R) 40G Ethernet Controllers.
The new files are,
i40e_osdep.h
i40e_ethdev.c
i40e_ethdev.h
i40e_ethdev_vf.c
i40e_logs.h
i40e_pf.c
i40e_pf.h
i40e_rxtx.c
i40e_rxtx.h
Makefile
Signed-off-by: Helin Zhang
Signed-off-by: Jing Chen
Acked-by: Cunming Liang
Acked-by:
Add shared code source files to support basic operations to be
called in poll mode driver. The new files are,
- i40e_adminq.c
- i40e_adminq.h
- i40e_adminq_cmd.h
- i40e_alloc.h
- i40e_common.c
- i40e_dcb.c
- i40e_dcb.h
- i40e_diag.c
- i40e_diag.h
- i40e_hmc.c
- i40e_hmc.h
-
Summary:
The 2nd version of series of patches are to add i40e PMD support.
It contains the updated basic shared code, and some other enhancements.
It adds the support of the latest version of firmware.
* Add new PMD driver of i40e in the folder of librte_pmd_i40e
* Add some neccessary definitions,
Tested-by: Waterman Cao
This patch bug fix has been tested by Intel.
Please see information as the following:
Fedora 20 x86_64, Linux Kernel 3.13.9-200, GCC 4.8.2
Intel Xeon CPU E5-2680 v2 @ 2.80GHz
NIC: Intel Niantic 82599, Intel i350, Intel 82580 and Intel 82576
Tested-by: Waterman Cao
Totally this patch is composed of 24 files including cover letter, and has been
tested by Intel.
We verified packet framework patch with ip pipeline example and unit test, all
cases passed.
Please see test result as the following:
test_flow_management Passed
Acked-by: Pablo de Lara Guarch
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Cristian Dumitrescu
> Sent: Wednesday, June 04, 2014 7:08 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [v2 00/23] Packet Framework
>
> (Version 2 changes are exclusively style
On Thu, 5 Jun 2014 15:39:16 +0100
Alan Carew wrote:
> This patch adds an "interrupt_mode" sysfs entry for igb_uio devices,
> allowing userspace eal_pci to track which interrupt mode has been enabled in
> kernel space.
> The sysfs entry can be inspected via
> /sys/bus/pci/devices/
>
On Thu, 5 Jun 2014 13:08:49 +0800
Helin Zhang wrote:
> +#define PKT_RX_EIP_CKSUM_BAD 0x /**< External IP header checksum error.
> */
> +#define PKT_RX_OVERSIZE 0x /**< Num of desc of an RX pkt oversize.
> */
> +#define PKT_RX_HBUF_OVERFLOW 0x /**< Header buffer overflow. */
>
On Thu, 5 Jun 2014 15:39:15 +0100
Alan Carew wrote:
> This series addresses an issue with librte_pmd_virtio where the offset to the
> virtio device specific header may be incorrect depending on whether MSI-X has
> been enabled or not.
>
> If MSI-X is configured the device specific header is
On Wed, 4 Jun 2014 16:18:02 +0100
declan.doherty at intel.com wrote:
> From: Declan Doherty
>
> - Broadcast TX burst broadcast bug fix
> - Add/remove slave behavior fix
> - Checkpatch fixes
>
> Signed-off-by: Declan Doherty
There are some pretty weak hash functions in there.
What about
Acked-by: Pablo de Lara Guarch
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of
> declan.doherty at intel.com
> Sent: Wednesday, June 04, 2014 4:18 PM
> To: dev at dpdk.org; dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v2 0/4] Link Bonding Library
>
> From:
On Wed, Jun 04, 2014 at 04:18:01PM +0100, declan.doherty at intel.com wrote:
> From: Declan Doherty
>
> v2 patch additions,
> fix for tx burst broadcast, incrementing the reference count on each mbuf by
> the number of slaves - 1
> add/remove slave behavior chnange to fix primary slave port
On Thu, Jun 05, 2014 at 03:11:46AM +, Ouyang, Changchun wrote:
> Hi, Neil
>
> " but you're implementaiton requires that it be re-implemented for each PMD "
>
> [Changchun]: Different PMD(corresponding diff NIC) has different register to
> set.
> It makes sense to me has different
Acked-by: Jijiang Liu
-Original Message-
From: Ouyang, Changchun
Sent: Monday, May 26, 2014 3:45 PM
To: dev at dpdk.org
Cc: Ouyang, Changchun
Subject: [PATCH v2 0/3] Support setting TX rate for queue and VF
This patch v2 fixes some errors and warnings reported by checkpatch.pl.
This
Acked-by: Helin Zhang
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jijiang Liu
Sent: Thursday, May 15, 2014 10:18 AM
To: dev at dpdk.org
Subject: [dpdk-dev] [PATCH 0/3] *** Upgrade NIC share codes ***
This patchset upgrades NIC share code in ixgbe & e1000
Hi Thomas,
As we can see below, There are already 4 existing functions for vf in the
header file:
rte_ethdev.h:int rte_eth_dev_set_vf_rxmode(uint8_t port, uint16_t vf, uint16_t
rx_mode,
rte_ethdev.h:rte_eth_dev_set_vf_tx(uint8_t port,uint16_t vf, uint8_t on);
Hi, Neil
" but you're implementaiton requires that it be re-implemented for each PMD "
[Changchun]: Different PMD(corresponding diff NIC) has different register to
set.
It makes sense to me has different implementation to support limit tx rate.
" Why not just export max tx rates from the PMD
50 matches
Mail list logo
