Bug: When a timer is running
- if rte_timer_stop is called, the pending decrement is
skipped (decremented only if the timer is pending) and due
to the update flag the future processing is skipped so the
timer is counted as pending while it is stopped. - the same
applies when rte_timer_reset is
In ethdev, it will ignore setting maximum packet length to less than 1518.
The changes is to fix it and let less than 1518 can be really set for
maximum packet length.
Signed-off-by: Helin Zhang
Signed-off-by: Mark Chen
---
lib/librte_ether/rte_ethdev.c | 10 +++---
1 file changed, 7 insert
Sys files of 'extended_tag' and 'max_read_request_size' have been
supported in igb_uio, and can be changed during probing PCI. Three
items in configuration files are needed to support them at compile
time. Those three items are,
- CONFIG_RTE_PCI_CONFIG
- CONFIG_RTE_PCI_EXTENDED_TAG
- CONFIG_RTE_
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: Mark Chen
---
lib/librte
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 'echo
As i40e support port based VLAN ID insertion offloading, new command
'tx_vlan set pvid port_id vlan_id (on|off)' is added to support that
setting.
Signed-off-by: Helin Zhang
Signed-off-by: Mark Chen
---
app/test-pmd/cmdline.c | 61 ++
app/test-pmd
As i40e support both 16 and 32 bytes RX descriptors, modifications should be
done to support 32 bytes RX descriptors according to the configuration.
Signed-off-by: Helin Zhang
Signed-off-by: Mark Chen
---
app/test-pmd/config.c | 36 +---
1 file changed, 33 insert
As i40e PMD need to know the L3 packet type for TX checksum offloading,
modifications in testpmd should be done for that.
Signed-off-by: Helin Zhang
Signed-off-by: Mark Chen
---
app/test-pmd/csumonly.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/
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 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 dpdk_qat
example application to support all PMDs.
Signed-off-by: Helin Zhang
Sig
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 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 l3fwd-vf
example application to support all PMDs.
Signed-off-by: Helin Zhang
Sig
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
Signed
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 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 qos_meter
example application to support all PMDs.
Signed-off-by: Helin Zhang
Si
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: Mark Chen
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 should
be enlarged as well. In addition, the flags for vmxnet3 only should be masked,
as there are flags for others in that 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 should be
enlarged as well. In addition, the flags for ixgbe only should be masked,
as there are flags for others in that 64 bits.
Signed-off-by: Helin Zhang
Si
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 e1000 should be
enlarged as well. In addition, the flags for e1000 only should be masked,
as there are flags for others in that 64 bits.
Signed-off-by: Helin Zhang
Si
Add i40e support by modifying neccessary source files.
The componets modified are,
- Add configurations for i40e in config/
- Modified neccessary makefiles in both k/ and lib/
- Modified neccessary source files in librte_ether/
- Add more packet bit flags in rte_mbuf.h
- Add i40e support in ig
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: Mark Chen
---
lib/librte_pmd_i40e/Makefile
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
i40e_lan_hmc.c
i40e_lan_hmc.h
i40e_nvm.c
i40e_pr
Summary:
The series of patches are to add i40e PMD support.
* Add new PMD driver of i40e in the folder of librte_pmd_i40e
* Add some neccessary definitions, changes in rte_mbuf.h and eth_dev
* Add new configurations for i40e
* Add or modifiy makefiles to support i40e compilation
* Add neccessary ch
Bug: when a periodic timer's callback is running, if another
timer is manipulated, the periodic timer is not reloaded.
Solution: set the update flag only is the modified timer is
in RUNNING state
Signed-off-by: Vadim Suraev
---
lib/librte_timer/rte_timer.c |8 ++--
1 file changed, 6 i
Hi , we re implementing bandwith controller per user with the dpdk qos
scheduler framework.
I want to know if the framework support dynamic changes in the
rte_sched_port structure.
For example, we want to give the possibility to change the configuration
of the different bucket rates int the port
2014-05-19 16:51, Anatoly Burakov:
> Creating code to handle VFIO interrupts in EAL interrupts, and also
> adding a header eal_vfio.h.
Maybe it's better to have 2 patches here.
> This header checks two things:
> * checks if CONFIG_RTE_EAL_VFIO was enabled during build time
> * checks that kernel
Hi Stephen,
Looking more precisely to your patch, I think that your requirement can
beaddressed without adding
a new `mac_addr_set` function into the [already overloaded] set of
operations exported by a PMD.
In fact, changing the default MAC address used by a port consists in
executingthe foll
> > The "default" part in configuration filenames is misleading.
> > Rename this as "native", as this is the RTE_MACHINE that is set in these
> > files. This should make it clearer for people who build DPDK on a system
> > then run it on another one.
> >
> > Signed-off-by: David Marchand
>
> Ack
2014-05-14 15:10, Richardson, Bruce:
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of David Marchand
> > Sent: Wednesday, May 14, 2014 3:58 PM
> > To: dev at dpdk.org
> > Subject: [dpdk-dev] [PATCH 1/3] config: factorize configurations
> >
> > linux and bs
Hi Vadim,
On 05/16/2014 12:15 PM, Vadim Suraev wrote:
> Description: while running a periodic timer's callback, if another
> timer is manipulated, the updated flag is raised
> preventing the periodic timer to reload.
> Fix: move
> updated flag from priv_timer to rte_timer stucture (one
> p
Few more comments from checkpatch.pl on this patch:
ERROR: else should follow close brace '}'
#252: FILE: lib/librte_eal/linuxapp/igb_uio/igb_uio.c:225:
}
+ else if (udev->mode == RTE_INTR_MODE_LEGACY) {
WARNING: suspect code indent for conditional statements (8, 8)
#316: FILE: lib/
2014-05-19 16:51, Anatoly Burakov:
> Moving interrupt type enum out of igb_uio and renaming it to be more
> generic. Such a strange header naming and separation is done mostly to
> make coming virtio patches easier to port to dpdk.org tree.
>
> Signed-off-by: Anatoly Burakov
> +++ b/lib/librte_
2014-05-19 16:51, Anatoly Burakov:
> Rename the RTE_PCI_DRV_NEED_IGB_UIO to be more generic,
> retain old macro for backwards compatibility. Probably should
> be removed in one of the next releases.
>
> Signed-off-by: Anatoly Burakov
[...]
> +/** Retain the old name for backwards-compatibility *
Hi Anatoly,
2014-05-19 16:51, Anatoly Burakov:
> In order to make the code a bit more clean while using multiple
> drivers, IGB_UIO mapping has been separated into its own file.
>
> Signed-off-by: Anatoly Burakov
[...]
> /* map a particular resource from a file */
> -static void *
> -pci_map_r
Hi Thomas,
> Why are you splitting things in 2 files?
>
The commit message explains it. Initially this work was based off our internal
tree, which had a few virtio-related changes, including these two files. I
stripped out most of the virtio stuff and left only things relevant to VFIO,
but ke
On Wed, May 21, 2014 at 10:21:26AM +, Richardson, Bruce wrote:
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Tuesday, May 20, 2014 7:19 PM
> > To: Richardson, Bruce
> > Cc: dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH 2/4] distributor: ne
> -Original Message-
> From: Neil Horman [mailto:nhorman at tuxdriver.com]
> Sent: Tuesday, May 20, 2014 7:19 PM
> To: Richardson, Bruce
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 2/4] distributor: new packet distributor
> library
>
> On Tue, May 20, 2014 at 11:00:55AM +0100,
Originally igb_uio had code for MSI, but it was broken.
See my patches which fixed that and several other bugs.
On Tue, May 20, 2014 at 8:26 PM, Burakov, Anatoly wrote:
> Hi Stephen,
>
> > I am not sure that MSI-X has any advantage with only one IRQ, so MSI
> would
> > do.
>
> Igb_uio doesn't s
39 matches
Mail list logo
