The workaround for Tx tunnel offloading can now be replaced with packet
type flag checking.
The ol_flags for IPv4/IPv6 and tunnel Rx offloading are replaced with
packet type flags.
Signed-off-by: Thomas Monjalon
Acked-by: Adrien Mazarguil
---
On Rx side, the tunnel type cannot be set.
So
Documentation update about implementation details and requirements for
Dynamic RSS Configuration for Bonding.
Signed-off-by: Tomasz Kulasek
---
.../prog_guide/link_bonding_poll_mode_drv_lib.rst | 34 ++--
1 file changed, 32 insertions(+), 2 deletions(-)
diff --git
Signed-off-by: Tomasz Kulasek
---
.../prog_guide/link_bonding_poll_mode_drv_lib.rst |8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/doc/guides/prog_guide/link_bonding_poll_mode_drv_lib.rst
b/doc/guides/prog_guide/link_bonding_poll_mode_drv_lib.rst
index
This patch adds propagation of mapping over the slaves, and fills bonding
port's stats with a sum of corresponding values taken from bonded slaves,
when stats are requested for bonding port.
Signed-off-by: Tomasz Kulasek
---
drivers/net/bonding/rte_eth_bond_pmd.c | 34
This test module uses modified null device to check right RSS configuration
propagation.
1) Propagation test
a) Set RSS hash function for bonding, fetch RSS hash function from
bonded slave, check if same. Do it for all slaves.
b) Repeat above for RSS key and RETA.
2)Dynamic adding slave
To use eth_dev_null_create in application this method needs to be exported.
Signed-off-by: Tomasz Kulasek
---
drivers/net/null/Makefile |2 +-
drivers/net/null/rte_eth_null.c |3 ++-
drivers/net/null/rte_eth_null.h | 40 +
This implementation allows to set and read RSS configuration for null
device, and is used to validate right values propagation over the slaves,
in test units for dynamic RSS configuration for bonding.
Signed-off-by: Tomasz Kulasek
---
drivers/net/null/rte_eth_null.c | 116
This patch adds a possibility to configure more than one queue on null
device.
Signed-off-by: Tomasz Kulasek
---
drivers/net/null/rte_eth_null.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/net/null/rte_eth_null.c
When device is added to the bonding, the link status callback is added to
the slave's eth_dev->link_intr_cbs list. This list is not initialized for
null pmd and adding it to the bonding segfaults application.
This patch allocates and sets up required structures.
Signed-off-by: Tomasz Kulasek
Bonding device implements independent management of RSS settings. It
stores its own copies of settings i.e. RETA, RSS hash function and RSS
key. It?s required to ensure consistency.
1) RSS hash function set for bonding device is maximal set of RSS hash
functions supported by all bonded devices.
OVERVIEW
1) Setting .rxmode.mq_mode for bonding device to ETH_MQ_RX_RSS makes bonding
device fully RSS-capable, so all slaves are synchronized with its configuration.
This mode is intended to provide RSS configuration as known from "dynamic RSS
configuration for one port" and made slaves
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, July 15, 2015 10:32 AM
> To: Zhang, Helin
> Cc: dev at dpdk.org
> Subject: [PATCH] mlx4: replace some offload flags with packet type
>
> The workaround for Tx tunnel offloading can now
Hi Sy Jong,
If I load "rte_kni.ko" driver, the net_device structs will be initialled by
KNI, right?
If yes, how can I handle these net_device structs in other driver,
because I using "for_each_netdev()" kernel API can't find the net_device
structs which KNI initialled.
Or these structs have not
Update malloc documentation to reflect new implementation details.
Signed-off-by: Sergio Gonzalez Monroy
---
doc/guides/prog_guide/env_abstraction_layer.rst | 220 -
doc/guides/prog_guide/img/malloc_heap.png | Bin 81329 -> 0 bytes
doc/guides/prog_guide/img/malloc_heap.svg |
Announce the creation of dummy malloc library for 2.1 and removal of
such library, now integrated in librte_eal, for 2.2 release.
Signed-off-by: Sergio Gonzalez Monroy
---
doc/guides/rel_notes/abi.rst | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git
Add new unit test for rte_memzone_free API.
Signed-off-by: Sergio Gonzalez Monroy
---
app/test/test_memzone.c | 82 +++--
1 file changed, 80 insertions(+), 2 deletions(-)
diff --git a/app/test/test_memzone.c b/app/test/test_memzone.c
index
Implement rte_memzone_free which, as its name implies, would free a
memzone.
Currently memzone are tracked in an array and cannot be free.
To be able to reuse the same array to track memzones, we have to
change how we keep track of reserved memzones.
With this patch, any memzone with addr NULL
Remove free_memseg field from internal mem config structure as it is
not used anymore.
Also remove code in ivshmem that was setting up free_memseg on init.
Signed-off-by: Sergio Gonzalez Monroy
---
lib/librte_eal/common/include/rte_eal_memconfig.h | 3 ---
During initializaio malloc sets all available memory as part of the heaps.
CONFIG_RTE_MALLOC_MEMZONE_SIZE was used to specify the default memory
block size to expand the heap. The option is not used/relevant anymore,
so we remove it.
Signed-off-by: Sergio Gonzalez Monroy
---
Some unit test are not relevant anymore. It is the case of those malloc
UTs that checked corner cases when allocating MALLOC_MEMZONE_SIZE
chunks, and the case of those memzone UTs relaying of specific free
memsegs of rhte reserved memzone.
Other UTs just need to be update, for example, to
In the current memory hierarchy, memsegs are groups of physically
contiguous hugepages, memzones are slices of memsegs and malloc further
slices memzones into smaller memory chunks.
This patch modifies malloc so it partitions memsegs instead of memzones.
Thus memzones would call malloc internally
Move malloc inside eal and create a new section in MAINTAINERS file for
Memory Allocation in EAL.
Create a dummy malloc library to avoid breaking applications that have
librte_malloc in their DT_NEEDED entries.
This is the first step towards using malloc to allocate memory directly
from memsegs.
Current implemetation allows reserving/creating memzones but not the opposite
(unreserve/free). This affects mempools and other memzone based objects.
>From my point of view, implementing free functionality for memzones would look
like malloc over memsegs.
Thus, this approach moves malloc inside
2015-07-15 15:11, Gonzalez Monroy, Sergio:
> On 15/07/2015 15:07, Thomas Monjalon wrote:
> > 2015-07-15 09:26, Sergio Gonzalez Monroy:
> >> Update malloc documentation to reflect new implementation details.
> >>
> >> doc/guides/prog_guide/img/malloc_heap.png | Bin 81329 -> 80952
> >>
add function bond_ethdev_free_queues() and call from the bond_ethdev_stop()
function.
Signed-off-by: Bernard Iremonger
---
drivers/net/bonding/rte_eth_bond_pmd.c | 20
1 file changed, 20 insertions(+)
diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c
When the bonded port is started it also starts the slave port,
but the slave port status is not set. A slave_flag has been
added to struct rte_port to resolve this issue.
Signed-off-by: Bernard Iremonger
---
app/test-pmd/cmdline.c | 4 +++-
app/test-pmd/testpmd.c | 24 +---
This patch depends on the Port Hotplug Framework.
It implements the rte_dev_uninit_t() function for the link bonding pmd.
Signed-off-by: Bernard Iremonger
---
drivers/net/bonding/rte_eth_bond.h | 13 -
drivers/net/bonding/rte_eth_bond_api.c | 78 +++---
Changes in V5:
Rebase.
Refactor initialisation of static structures.
Changes in V4:
Rebase to latest code.
Move freeing of queue memory from uninit() function to close() function.
Changes in V3:
Rebase to latest code.
Modified testpmd to handle attach/detach of bonding pmd.
Changes in V2:
SLES 12 has kernel 3.12, which original does not have skb_set_hash,
but SuSE has added that function to the kernel integrated on it.
Therefore, the function is not declared when compiling on this OS.
Reported-by: Sotiris Salloumis
Signed-off-by: Pablo de Lara
---
2015-07-15 09:26, Sergio Gonzalez Monroy:
> Update malloc documentation to reflect new implementation details.
>
> doc/guides/prog_guide/img/malloc_heap.png | Bin 81329 -> 80952 bytes
Sorry, you cannot update a PNG file without converting it as a SVG file.
Some PNG files were allowed when
Hi,
Today I tried no-huge option with app/test, the test app crashed.
It seems that memory can not be allocated.
I think it could be this change causing the panic. Can someone check it?
commit 2d65283c259616a5643599ce32d7a62d174ec49e
Author: Cyril Chemparathy
Date: Thu Jul 9 16:25:14 2015
Hi Pablo,
I did the modifications manually on the dpdk 2.0.0
(http://dpdk.org/browse/dpdk/snapshot/dpdk-2.0.0.tar.gz) as per your email.
DPDK build was complete successfully.
I will perform tests on my test app tomorrow and in case of issues will use
this thread.
Thanks for the support
commit 7c5d0cc91579 added const in prefetch functions for
X86 and PPC. This patch does the same for Tile arch.
Fixes: 7c5d0cc91579 ("eal: add const in prefetch functions")
Signed-off-by: Zhigang Lu
---
lib/librte_eal/common/include/arch/tile/rte_prefetch.h | 6 +++---
1 file changed, 3
Hi Sotiris,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Sotiris Salloumis
> Sent: Wednesday, July 15, 2015 2:15 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] Dpdk 2.0.0 error with Suse Linux Enterprise 12
>
> Dear all,
>
> I?m trying to build dpdk
Hi all,
It is with great excitement and delight that I welcome you, the DPDK.org
development community, to register your attendance for DPDK Userspace 2015 -
October 8th and 9th 2015, Ballsbridge Hotel, Pembroke Road, Dublin 4, Ireland.
Userspace 2015 is a developer forum which will focus on
At this point the stop() and close() functions have already been called.
The rte_eth_promiscuous_disable() function does not return on the VM.
Signed-off-by: Bernard Iremonger
---
app/test-pmd/testpmd.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git
Signed-off-by: Bernard Iremonger
---
drivers/net/virtio/virtio_ethdev.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev.c
index b992898..9ca9bb2 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++
Add functions virtio_dev_queue_release(), virtio_dev_rx_queue_release() and
virtio_dev_tx_queue_release().
Signed-off-by: Stephen Hemminger
Signed-off-by: Bernard Iremonger
---
drivers/net/virtio/virtio_ethdev.c | 32 ++--
drivers/net/virtio/virtio_ethdev.h | 8
If vq is NULL, there is a segmentation fault.
Signed-off-by: Bernard Iremonger
---
drivers/net/virtio/virtqueue.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/net/virtio/virtqueue.c b/drivers/net/virtio/virtqueue.c
index 8a3005f..7f60e3e 100644
---
This patch depends on the Port Hotplug Framework.
It implements the eth_dev_uninit_t() function for virtio pmd.
Signed-off-by: Bernard Iremonger
---
drivers/net/virtio/virtio_ethdev.c | 72 ++
1 file changed, 65 insertions(+), 7 deletions(-)
diff --git
Changes in V6:
Rebase.
Use queue_release function in dev_uninit function (patch 5)
Set vq to NULL in queue release function.
Move previous patch 5 to patch 6.
Changes in V5:
Rebase.
Add proper queue release patch (patch 3).
Reorder patches, moved previous patch 3 to patch 4,
moved previous patch
2015-07-15 11:12, Sergio Gonzalez Monroy:
> After code rework from bellow commit, logic expects hugepage_sz field to
> always be set (ie. not zero value).
> When using --no-huge, this field was left unset defaulting to zero.
>
> Set hugepage_sz to RTE_PGSIZE_4K when using --no-huge.
>
> Fixes:
2015-07-15 15:26, Zhigang Lu:
> commit 7c5d0cc91579 added const in prefetch functions for
> X86 and PPC. This patch does the same for Tile arch.
>
> Fixes: 7c5d0cc91579 ("eal: add const in prefetch functions")
>
> Signed-off-by: Zhigang Lu
Applied, thanks
2015-07-15 23:00, Rahul Lakkireddy:
> Fix spelling and grammar errors. Re-organize sections for better explanation
> in the documentation. Add a section describing compilation of CXGBE with
> DPDK.
> Add a note describing that CXGBE currently only supports binding to PF4.
>
> Signed-off-by:
Add a guide for the proc_info application.
Signed-off-by: Maryam Tahhan
---
doc/guides/sample_app_ug/index.rst | 1 +
doc/guides/sample_app_ug/proc_info.rst | 71 ++
2 files changed, 72 insertions(+)
create mode 100644 doc/guides/sample_app_ug/proc_info.rst
proc_info displays statistics information including extended stats for
given DPDK ports and dumps the memory information for DPDK.
Signed-off-by: Maryam Tahhan
---
MAINTAINERS| 4 +
app/Makefile | 1 +
app/proc_info/Makefile | 45 +++
app/proc_info/main.c | 354
Remove the dump_cfg application, this will be replaced by a new app
called proc_info that will implement the same functionality as dump_cfg
and extend it to retrieve statistics for DPDK ports.
Signed-off-by: Maryam Tahhan
---
app/Makefile | 1 -
app/dump_cfg/Makefile | 45
ierrors only included a base set of error statistics, this patch adds
additional error registers to ierrors.
Signed-off-by: Maryam Tahhan
---
drivers/net/ixgbe/ixgbe_ethdev.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c
Add the NIC/HW specific stats that were removed from rte_ethdev.c to
the extended stats in ixgbe.
Signed-off-by: Maryam Tahhan
---
drivers/net/ixgbe/ixgbe_ethdev.c | 31 ++-
1 file changed, 14 insertions(+), 17 deletions(-)
diff --git
Remove non generic stats in rte_stats_strings and mark the relevant
fields in struct rte_eth_stats as deprecated.
Signed-off-by: Maryam Tahhan
---
doc/guides/rel_notes/abi.rst | 12
lib/librte_ether/rte_ethdev.c | 9 -
lib/librte_ether/rte_ethdev.h | 30
Extend rte_eth_xstats_get to retrieve additional stats from the device
driver as well the ethdev generic stats.
Signed-off-by: Maryam Tahhan
---
lib/librte_ether/rte_ethdev.c | 31 ---
1 file changed, 20 insertions(+), 11 deletions(-)
mode change 100644 => 100755
Implement ixgbe_dev_xstats_reset and ixgbe_dev_xstats_get.
Signed-off-by: Maryam Tahhan
---
drivers/net/ixgbe/ixgbe_ethdev.c | 87
1 file changed, 87 insertions(+)
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index
Move stats register reads to ixgbe_read_stats_registers() as it will be
used by the functions to retrieve stats and extended stats.
Signed-off-by: Maryam Tahhan
---
drivers/net/ixgbe/ixgbe_ethdev.c | 64 +++-
1 file changed, 44 insertions(+), 20 deletions(-)
This patch set implements xstats_get() and xstats_reset() in dev_ops for
ixgbe to expose detailed error statistics to DPDK applications. The
dump_cfg application was extended to demonstrate the usage of
retrieving statistics for DPDK interfaces and renamed to proc_info
in order reflect this new
2015-07-15 11:36, Wang, Liang-min:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2015-07-15 10:48, Wang, Liang-min:
> > > > > > What means magic? Is it always a device id?
> > > > > This field is the same as defined in kernel ethtool data structure.
> > > >
> > > > Not an
_mm_test_all_zeros is not available for CPUs with no SSE4.1,
therefore, DPDK would not build.
This patch adds an alternative for this, using _mm_cmpeq_epi32 and
_mm_movemask_epi8.
Fixes: 48a399119619 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara
---
gcc 4.4 and 4.5 throws following error:
rte_cuckoo_hash.c:145: error: flexible array member in otherwise empty struct.
This is due to empty length in flexible array, which has been changed to use
size 0 in the declaration of the array.
Fixes: 48a399119619 ("hash: replace with cuckoo hash
When encountering a loop while adding a new entry,
element out of bounds of array was being unnecessarily resetted.
Fixes: 48a399119619 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara
---
lib/librte_hash/rte_cuckoo_hash.c | 5 +
1 file changed, 1
fix return value, using the macro input instead of -EINVAL.
Signed-off-by: Liang-Min Larry Wang
---
lib/librte_ether/rte_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index ddf3658..a957d9a 100644
---
2015-07-15 10:48, Wang, Liang-min:
> > > > What means magic? Is it always a device id?
> > > This field is the same as defined in kernel ethtool data structure.
> >
> > Not an excellent argument :)
> > Actually you didn't answer.
> >
> I could not speak for other devices. For igb and ixgbe, it's
Dear all,
I?m trying to build dpdk with Suse 12 but I receive the following error:
from
/home/Downloads/dpdk-2.0.0/lib/librte_eal/linuxapp/kni/ethtool/igb/e1000_api.h:31,
from
/home/Downloads/dpdk-2.0.0/x86_64-native-linuxapp-gcc/build/lib/librte_eal/linuxapp/kni/e1000_82575.c:38:
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Wednesday, July 15, 2015 10:19 AM
> To: Tahhan, Maryam; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v4 3/8] ethdev: expose extended error stats
>
> Hi Maryam,
>
> The API of the driver-specific function should be the same than
2015-07-15 10:15, Wang, Liang-min:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > 2015-07-14 20:56, Wang, Liang-min:
> > > Thomas,
> > > The mac_addr_set is needed for ethtool net-op as described in
> > > examples/ethtool-ethtool/lib/rte_ethtool.c
> >
2015-07-15 10:07, Wang, Liang-min:
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > Please precise offset from which point?
> > Why offset is needed?
> >
> Is C always 0-base?
> The offset is introduced because one of the review requesting to support
> partial register read,
>
On 07/09/2015 06:31 PM, Helin Zhang wrote:
> As there are only 6 bit flags in ol_flags for indicating packet
> types, which is not enough to describe all the possible packet
> types hardware can recognize. For example, i40e hardware can
> recognize more than 150 packet types. Unified packet type
On 07/09/2015 03:22 PM, Bruce Richardson wrote:
> The comment for TX offload flags stated that those flags started at bit
> 55 and then were added to the right of that, leaving 8 bits reserved for
> generic mbuf (i.e. non-offload) use. This comment may not have been
> clear as 5 of the 8 flags
On 07/10/2015 01:37 AM, Stephen Hemminger wrote:
> From: Stephen Hemminger
>
> Added rte_pktmbuf_copy() function since copying multi-part
> segments is common issue and can be problematic.
>
> Signed-off-by: Mike Davison
> Reviewed-by: Stephen Hemminger
> ---
> lib/librte_mbuf/rte_mbuf.h | 59
On 07/10/2015 05:43 PM, Stephen Hemminger wrote:
> On Fri, 10 Jul 2015 10:32:17 +0100
> Bruce Richardson wrote:
>
>> On Thu, Jul 09, 2015 at 04:37:48PM -0700, Stephen Hemminger wrote:
>>> From: Stephen Hemminger
>>>
>>> For applications that use m->userdata the initialization can
>>> be a
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, July 15, 2015 7:21 AM
> To: Wang, Liang-min
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v15 1/4] ethdev: add apis to support access
> device info
>
> 2015-07-15 10:48, Wang,
On 07/07/15 11:21, Bernard Iremonger wrote:
> This patch depends on the Port Hotplug Framework.
> It implements the rte_dev_uninit_t() function for the link bonding pmd.
>
> Signed-off-by: Bernard Iremonger
> ---
...
>
I think we can clean up the create function a bit further as the
After code rework from bellow commit, logic expects hugepage_sz field to
always be set (ie. not zero value).
When using --no-huge, this field was left unset defaulting to zero.
Set hugepage_sz to RTE_PGSIZE_4K when using --no-huge.
Fixes: b3dfffd962ecd ("mem: allow multiple page sizes to be
On 15/07/2015 08:34, damu wrote:
> Hi,
>
> Today I tried no-huge option with app/test, the test app crashed.
> It seems that memory can not be allocated.
> I think it could be this change causing the panic. Can someone check it?
>
>
Hi Damu,
Actually it is the following commit causing the panic:
Hi,
On 07/07/2015 07:17 PM, Zoltan Kiss wrote:
>
>
> On 02/07/15 18:07, Ananyev, Konstantin wrote:
>>
>>
>>> -Original Message-
>>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zoltan Kiss
>>> Sent: Wednesday, July 01, 2015 10:04 AM
>>> To: dev at dpdk.org
>>> Subject:
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, July 15, 2015 6:27 AM
> To: Wang, Liang-min
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v15 1/4] ethdev: add apis to support access
> device info
>
> 2015-07-15 10:07, Wang,
The read for events in the interrupt thread may get interrupted
by signals from application. Avoid generating stray log message.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, July 15, 2015 1:53 AM
> To: Wang, Liang-min
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v16 0/6] User-space Ethtool
>
> 2015-07-14 20:56, Wang, Liang-min:
> > Thomas,
> >
On Tue, Jul 14, 2015 at 06:21:33PM +, Polevoy, Igor wrote:
> Hi,
> We are developing an application that uses DPDK PMD functionality .
> We are using a linux shared library which contains the network packets
> processing code and it is statically linked with all the necessary DPDK libs.
> The
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Wednesday, July 15, 2015 2:16 AM
> To: Wang, Liang-min
> Cc: dev at dpdk.org; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v15 1/4] ethdev: add apis to support access
> device info
>
>
Hi Scott,
You will need to start KNI sample app, it will create the vEth interface. After
kni app, it will be there, kni app is the datapath, it get the packet into the
kernel.
http://dpdk.org/doc/guides/prog_guide/kernel_nic_interface.html
1. Insert the KNI kernel module:
2. insmod
Announce the creation of dummy malloc library for 2.1 and removal of
such library, now integrated in librte_eal, for 2.2 release.
Signed-off-by: Sergio Gonzalez Monroy
---
doc/guides/rel_notes/abi.rst | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git
Add new unit test for rte_memzone_free API.
Signed-off-by: Sergio Gonzalez Monroy
---
app/test/test_memzone.c | 82 +++--
1 file changed, 80 insertions(+), 2 deletions(-)
diff --git a/app/test/test_memzone.c b/app/test/test_memzone.c
index
Implement rte_memzone_free which, as its name implies, would free a
memzone.
Currently memzone are tracked in an array and cannot be free.
To be able to reuse the same array to track memzones, we have to
change how we keep track of reserved memzones.
With this patch, any memzone with addr NULL
Remove free_memseg field from internal mem config structure as it is
not used anymore.
Also remove code in ivshmem that was setting up free_memseg on init.
Signed-off-by: Sergio Gonzalez Monroy
---
lib/librte_eal/common/include/rte_eal_memconfig.h | 3 ---
During initializaio malloc sets all available memory as part of the heaps.
CONFIG_RTE_MALLOC_MEMZONE_SIZE was used to specify the default memory
block size to expand the heap. The option is not used/relevant anymore,
so we remove it.
Signed-off-by: Sergio Gonzalez Monroy
---
Some unit test are not relevant anymore. It is the case of those malloc
UTs that checked corner cases when allocating MALLOC_MEMZONE_SIZE
chunks, and the case of those memzone UTs relaying of specific free
memsegs of rhte reserved memzone.
Other UTs just need to be update, for example, to
In the current memory hierarchy, memsegs are groups of physically
contiguous hugepages, memzones are slices of memsegs and malloc further
slices memzones into smaller memory chunks.
This patch modifies malloc so it partitions memsegs instead of memzones.
Thus memzones would call malloc internally
Move malloc inside eal and create a new section in MAINTAINERS file for
Memory Allocation in EAL.
Create a dummy malloc library to avoid breaking applications that have
librte_malloc in their DT_NEEDED entries.
This is the first step towards using malloc to allocate memory directly
from memsegs.
Current implemetation allows reserving/creating memzones but not the opposite
(unreserve/free). This affects mempools and other memzone based objects.
>From my point of view, implementing free functionality for memzones would look
like malloc over memsegs.
Thus, this approach moves malloc inside
> -Original Message-
> From: Ouyang, Changchun
> Sent: Wednesday, July 15, 2015 9:39 AM
> To: Iremonger, Bernard; Stephen Hemminger
> Cc: dev at dpdk.org; Ouyang, Changchun
> Subject: RE: [PATCH 4/5] virtio: free queue memory in virtio_dev_close()
>
>
>
> > -Original Message-
> -Original Message-
> From: Iremonger, Bernard
> Sent: Wednesday, July 15, 2015 4:27 PM
> To: Stephen Hemminger
> Cc: dev at dpdk.org; Ouyang, Changchun
> Subject: RE: [PATCH 4/5] virtio: free queue memory in virtio_dev_close()
>
> > -Original Message-
> > From: Stephen
Hi, Bernard
> -Original Message-
> From: Iremonger, Bernard
> Sent: Wednesday, July 15, 2015 4:02 PM
> To: Ouyang, Changchun; dev at dpdk.org
> Cc: Xu, Qian Q; stephen at networkplumber.org
> Subject: RE: [PATCH 4/5] virtio: free queue memory in virtio_dev_close()
>
> Hi Ouyang,
>
>
>
> -Original Message-
> From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> Sent: Tuesday, July 14, 2015 7:28 PM
> To: Iremonger, Bernard
> Cc: dev at dpdk.org; Ouyang, Changchun
> Subject: Re: [PATCH 4/5] virtio: free queue memory in virtio_dev_close()
>
> On Tue, 14 Jul 2015
Hi Olga,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olga Shern
> Sent: Wednesday, July 15, 2015 9:08 AM
> To: Richardson, Bruce; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] hash: rename unused field to "reserved"
>
> Hi,
>
> I see the
2015-07-13 22:18, Liang-Min Larry Wang:
> --- a/lib/librte_ether/Makefile
> +++ b/lib/librte_ether/Makefile
> @@ -51,6 +51,7 @@ SRCS-y += rte_ethdev.c
> SYMLINK-y-include += rte_ether.h
> SYMLINK-y-include += rte_ethdev.h
> SYMLINK-y-include += rte_eth_ctrl.h
> +SYMLINK-y-include +=
Hi,
I see the following compilation error :
dpdk/lib/librte_hash/rte_cuckoo_hash.c:145: error: flexible array member in
otherwise empty struct
when compiling on RH6.5
Best Regards,
Olga
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson
Sent:
Hi Ouyang,
> > --- a/drivers/net/virtio/virtio_ethdev.c
> > +++ b/drivers/net/virtio/virtio_ethdev.c
> > @@ -438,6 +438,24 @@ virtio_dev_cq_queue_setup(struct rte_eth_dev
> > *dev, uint16_t vtpci_queue_idx, }
> >
> > static void
> > +virtio_free_queues(struct rte_eth_dev *dev) {
> > +
2015-07-14 20:56, Wang, Liang-min:
> Thomas,
> The mac_addr_set is needed for ethtool net-op as described in
> examples/ethtool-ethtool/lib/rte_ethtool.c
> (rte_ethtool_net_set/get_mac_addr).
That's why it should be the first patch of this series.
You probably misread "another patch"
Did you tried 'mk/rte_app.mk' to build you application?
Simply including -lrte_pmd_xxx may cause problem because
PMD_REGISTER_DRIVER uses 'init' attribute,
which is called before the 'main' function.
See the 'start-group' and 'whole-archive' linker options.
Keunhong.
2015-07-15 3:21 GMT+09:00
> -Original Message-
> From: Iremonger, Bernard
> Sent: Tuesday, July 14, 2015 9:11 PM
> To: dev at dpdk.org
> Cc: Ouyang, Changchun; stephen at networkplumber.org; Iremonger, Bernard
> Subject: [PATCH 4/5] virtio: free queue memory in virtio_dev_close()
>
> Add function
> -Original Message-
> From: Tao, Zhe
> Sent: Tuesday, July 14, 2015 6:37 PM
> To: dev at dpdk.org
> Cc: Tao, Zhe; Wu, Jingjing
> Subject: [PATCH] i40e: Fix the endian issue for the i40e read registers
> functions
>
> Linux kernel uses the writel and readl related functions to perform
1 - 100 of 101 matches
Mail list logo
