Thanks, PSB.
> -Original Message-
> From: Yongseok Koh
> Sent: Tuesday, October 2, 2018 4:03 AM
> To: Dekel Peled
> Cc: dev@dpdk.org; Shahaf Shuler ; Ori Kam
>
> Subject: Re: [PATCH 1/4] net/mlx5: add flow action functions to glue
>
> On Thu, Sep 27, 2018 at 05:50:42PM +0300, Dekel Pele
On Thu, Sep 27, 2018 at 05:50:44PM +0300, Dekel Peled wrote:
> This patch adds support for Direct Verbs encap operations, L2 and L3.
>
> Signed-off-by: Dekel Peled
> ---
> drivers/net/mlx5/mlx5_flow_dv.c | 249
> +++-
> 1 file changed, 244 insertions(+), 5 de
Thanks, PSB.
> -Original Message-
> From: Yongseok Koh
> Sent: Saturday, September 29, 2018 12:24 PM
> To: Dekel Peled
> Cc: dev@dpdk.org; Shahaf Shuler ; Ori Kam
>
> Subject: Re: [PATCH] net/mlx5: allow flow rule with attribute egress
>
> On Thu, Sep 27, 2018 at 05:25:30PM +0300, Dekel
Thanks, PSB.
> -Original Message-
> From: Yongseok Koh
> Sent: Saturday, September 29, 2018 12:09 PM
> To: Dekel Peled
> Cc: dev@dpdk.org; Shahaf Shuler ; Ori Kam
>
> Subject: Re: [PATCH v2] net/mlx5: support metadata as flow rule criteria
>
> On Thu, Sep 27, 2018 at 05:18:55PM +0300, D
> >> + while (last_bkt->next) {
> >> + prev_bkt = last_bkt;
> >> + last_bkt = last_bkt->next;
> >> + }
> >Minor: We are trying to find the last bucket here, along with its previous.
> May be we can modify 'rte_hash_get_last_bkt' instead?
> >
> [Wang, Yipeng] Then there will be o
On Thu, Sep 27, 2018 at 05:50:43PM +0300, Dekel Peled wrote:
> This patch add the required definitions for DV encap/decap actions.
> It also adds usage of the new actions definition in validation
> function of existing drop operation.
>
> Signed-off-by: Dekel Peled
> ---
> drivers/net/mlx5/mlx5_
In accordance with
"[RFC] net/mlx5: support multiple groups and jump action" [1].
[1] https://mails.dpdk.org/archives/dev/2018-September/40.html
Yongseok Koh (2):
ethdev: add jump action to description table
net/mlx5: support multiple groups and jump action
app/test-pmd/config.c
rte_flow has 'group' attribute and 'jump' action in order to support
multiple groups. This feature is known as multi-table support ('chain' in
linux TC flower) in general because a group means a table of flows. Example
commands are:
flow create 0 transfer priority 1 ingress
pa
Signed-off-by: Yongseok Koh
---
app/test-pmd/config.c| 2 +-
lib/librte_ethdev/rte_flow.c | 1 +
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index 794aa5268..641ac5e17 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/con
I am sorry that I did not clearly say in the cover letter that this patch set is
depending on another bug-fix patch set (http://patchwork.dpdk.org/cover/45611/)
we submitted. I will update the cover letter in next version.
They were in the same patch set and I separated them because one is dedicat
>-Original Message-
>[Wang, Yipeng] I was thinking about another corner case and wondering if the
>version counter needs to be done on key deletion as
>well.
>For example, a reader reads out the index and falsely matches a signature,
>before it reads out the data and the key, the key-data
>-Original Message-
>From: Van Haaren, Harry
>> > > > > /**
>> > > > > * Add a key to an existing hash table.
>> > > > >@@ -222,7 +222,7 @@ rte_hash_add_key(const struct rte_hash *h,
>> > > > >const void
>> > > *key);
>> > > > > * array of user data. This value is unique for this k
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>> >> /* Get position of entry in key table */
>> >> position = h->buckets[bucket_idx].key_idx[idx];
>> >If we change the while loop as I suggested as above, we can remove this
>> >line.
>> >
>> >>
Hi Jerin,
> > > > > > >
> > > > > > > Anyway, let's pretend we found some smart way to distribute
> > > > > > > inbound packets for the same SA to multiple HW queues/CPU
> > > > > cores.
> > > > > > > To make ipsec processing for such case to work correctly just
> > > > > > > atomicity on check/
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>> +
>> +for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
>> +if (last_bkt->key_idx[i] != EMPTY_SLOT) {
>> +cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
>> +
Hi Akhil,
>
> Hi Konstantin,
>
> On 10/1/2018 2:30 AM, Ananyev, Konstantin wrote:
> >
> > Hi Akhil,
> >
> >> Hi Konstantin,
> >>
> >> On 9/24/2018 4:21 PM, Ananyev, Konstantin wrote:
> >>> Hi Akhil,
> >>>
> Hi Konstantin,
>
> On 9/18/2018 6:12 PM, Ananyev, Konstantin wrote:
>
Hi, Ferruh,
On 10/02, Ferruh Yigit wrote:
>On 9/28/2018 10:47 PM, Xiaolong Ye wrote:
>> The vdpa sample application creates vhost-user sockets by using the
>> vDPA backend. vDPA stands for vhost Data Path Acceleration which utilizes
>> virtio ring compatible devices to serve virtio driver directly
Hi, Ferruh,
On 10/02, Ferruh Yigit wrote:
>On 9/28/2018 10:47 PM, Xiaolong Ye wrote:
>> It's used to get number of available registered vDPA devices.
>>
>> Signed-off-by: Xiaolong Ye
>> Acked-by: Xiao Wang
>> Reviewed-by: Maxime Coquelin
>> ---
>> lib/librte_vhost/rte_vdpa.h| 3 ++
02/10/2018 18:33, Alejandro Lucero:
> As I was told, I sent this patchset early September (actually it was still
> October) for making it for 18.11.
>
> I wonder if this will be applied when doing the integration phase or it
> will need to wait until 19.02.
Such patchset cannot be applied after -
I am attempting to test the patch on an Arm machine, but it failed to apply.
I’m getting the following error:
error: patch failed: test/test/test_hash_perf.c:18
error: test/test/test_hash_perf.c: patch does not apply
Patch failed at 0003 test/hash: implement extendable bucket hash test
> On Oct
Signed-off-by: Junxiao Shi
---
lib/librte_cryptodev/rte_cryptodev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/librte_cryptodev/rte_cryptodev.c
b/lib/librte_cryptodev/rte_cryptodev.c
index 63ae23f..3d6f474 100644
--- a/lib/librte_cryptodev/rte_cryptodev.c
+++ b/lib/librte_cryptode
Signed-off-by: Junxiao Shi
---
lib/librte_cryptodev/rte_cryptodev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/librte_cryptodev/rte_cryptodev.c
b/lib/librte_cryptodev/rte_cryptodev.c
index 63ae23f..3d6f474 100644
--- a/lib/librte_cryptodev/rte_cryptodev.c
+++ b/lib/librte_cryptode
On 10/02/2018 05:59 AM, Burakov, Anatoly wrote:
Hi Eric,
Ferruh has already mention that this should be part of the patch
adding the --iova-mode flag, not separate (or at the very least be in
the same patchset!).
OK. I will generate version 3 which has one patchset includes code and
docume
IPsec requires truncated HMAC operations support. Extend OpenSSL crypto
PMD to support truncated HMAC operations necessary for IPsec.
Signed-off-by: Dmitry Eremin-Solenikov
---
Changes since V2:
- support all digest sizes from 1 up to full digest length.
drivers/crypto/openssl/rte_openssl_pmd.
Introduced DEV_RX_OFFLOAD_OUTER_UDP_CKSUM Rx offload flag and
PKT_RX_EL4_CKSUM_BAD mbuf ol_flags to detect outer UDP checksum
failure.
- To use hardware Rx outer UDP checksum offload, the user needs to
configure DEV_RX_OFFLOAD_OUTER_UDP_CKSUM offload flags in slowpath.
- Driver updates the PKT_RX
Collect and prints the statistics for PKT_RX_EL4_CKSUM_BAD
errors.
Signed-off-by: Jerin Jacob
---
v2:
- added PKT_RX_EL4_CKSUM_BAD statistics
---
app/test-pmd/csumonly.c | 6 ++
app/test-pmd/testpmd.c | 22 +-
app/test-pmd/testpmd.h | 4
3 files changed, 27 ins
Added outer-udp Tx HW checksum support for csum forward engine
if device supports DEV_TX_OFFLOAD_OUTER_UDP_CKSUM.
Signed-off-by: Jerin Jacob
---
v2:
- Added outer-udp support for csum engine
---
app/test-pmd/cmdline.c | 24 ++---
app/test-pmd/csumonly.c
Introduced DEV_TX_OFFLOAD_OUTER_UDP_CKSUM offload flags and
PKT_TX_OUTER_TCP_CKSUM mbuf ol_flags to enable Tx outer UDP
checksum offload.
To use hardware Tx outer UDP checksum offload, the user needs to,
- enable following in mbuff:
a) fill outer_l2_len and outer_l3_len in mbuf
b) set the PKT_TX_
> -Original Message-
> From: Yipeng Wang
> Sent: Monday, October 1, 2018 1:35 PM
> To: bruce.richard...@intel.com
> Cc: konstantin.anan...@intel.com; dev@dpdk.org;
> yipeng1.w...@intel.com; Honnappa Nagarahalli
> ; sameh.gobr...@intel.com
> Subject: [PATCH v5 1/4] hash: fix race conditi
Hi all,
I got a huge problem: I found that using normal hashing and
configuration on X710 hardware is not sufficient, so I followed some
threads and read the code inside the testpmd application to configure a
symmetric hashing for IP src / IP dst on TCP packets so that all packets
in a flow a
On 9/27/2018 11:49 AM, Kiran Kumar wrote:
> With current KNI implementation kernel module will work only in
> IOVA=PA mode. This patch will add support for kernel module to work
> with IOVA=VA mode.
>
> The idea is to maintain a mapping in KNI module between user pages and
> kernel pages and in fa
On 9/27/2018 1:02 AM, Igor Ryzhov wrote:
> Signed-off-by: Igor Ryzhov
Hi Igor,
What is the motivation to add this support? What is enabled by this?
Meanwhile, why we are not using eth_header_ops, which is already set by
ether_setup().
To disable .cache & .cache_update?
If so why not using rel
>
>
> > net/bnxt: update HWRM version
> > net/bnxt: update HWRM version part 2
> > net/bnxt: update HWRM version part 3
>
> Is there a logical to separation of part 1,2 & 3?
> Commit logs are empty and there is nothing distinctive from commits. If the
> separation is not logical but just phys
As I was told, I sent this patchset early September (actually it was still
October) for making it for 18.11.
I wonder if this will be applied when doing the integration phase or it
will need to wait until 19.02.
On Fri, Aug 31, 2018 at 1:51 PM Alejandro Lucero <
alejandro.luc...@netronome.com> wr
On Tue, Oct 02, 2018 at 05:20:46PM +0100, Luca Boccassi wrote:
> Allow users and packagers to override the default dpdk/drivers
> subdirectory where the PMDs get installed under $lib.
>
> Signed-off-by: Luca Boccassi
> ---
Acked-by: Bruce Richardson
On Tue, Oct 02, 2018 at 05:20:45PM +0100, Luca Boccassi wrote:
> As part of the effort of consolidating the DPDK installation bits and
> pieces across distros, set the default directory of lib/ where PMDs get
> installed to dpdk/pmds-XX.YY. It's necessary to have a versioned
> subdirectory as multi
Allow users and packagers to override the default dpdk/drivers
subdirectory where the PMDs get installed under $lib.
Signed-off-by: Luca Boccassi
---
v3: changed default value to and use string.contains rather
than exact equivalence
v4: further optimisations suggested by review
meson.build
On Tue, 2018-10-02 at 16:58 +0100, Bruce Richardson wrote:
> On Tue, Oct 02, 2018 at 04:25:56PM +0100, Luca Boccassi wrote:
> > Allow users and packagers to override the default dpdk/drivers
> > subdirectory where the PMDs get installed under $lib.
> >
> > Signed-off-by: Luca Boccassi
> > ---
> >
As part of the effort of consolidating the DPDK installation bits and
pieces across distros, set the default directory of lib/ where PMDs get
installed to dpdk/pmds-XX.YY. It's necessary to have a versioned
subdirectory as multiple ABI revisions might be installed at the same
time, so having a fixe
On 9/28/2018 8:25 PM, John Daley wrote:
> From: Hyong Youb Kim
>
> Add the vectorized version of the no-scatter Rx handler. It aims to
> process 8 descriptors per loop using AVX2 SIMD instructions. This
> handler is in its own file enic_rxtx_vec_avx2.c, and makefile and
> meson.build are modified
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, October 2, 2018 4:54 PM
> To: Guo, Jia ; step...@networkplumber.org; Richardson,
> Bruce ; Yigit, Ferruh
> ; Ananyev, Konstantin ;
> gaetan.ri...@6wind.com; Wu, Jingjing
> ; tho...@monjalon.net; mo...@mellanox.com;
> ma...@
On Tue, Oct 02, 2018 at 04:25:56PM +0100, Luca Boccassi wrote:
> Allow users and packagers to override the default dpdk/drivers
> subdirectory where the PMDs get installed under $lib.
>
> Signed-off-by: Luca Boccassi
> ---
> v3: changed default value to and use string.contains rather
> than
18/09/2018 18:19, Ferruh Yigit:
> On 9/13/2018 10:46 PM, Dan Gora wrote:
> > Modify kni_net_ioctl() to return -EOPNOTSUPP for all ioctls instead
> > of 0.
> >
> > This is necessary because the Wicked (and possibly other) network
> > interface managers will perform the SIOCGIWNAME ioctl to check if
On 02-Oct-18 1:35 PM, Jeff Guo wrote:
The mechanism can initially register the sigbus handler after the device
event monitor is enabled. When a sigbus event is captured, it will check
the failure address and accordingly handle the memory failure of the
corresponding device by invoke the hot-unplu
Hi Jerin
> > Subject: [dpdk-dev] [PATCH] app/testpmd: add commands for TM to mark
> > pkts
> > X-Mailer: git-send-email 2.18.0
> >
> > Add following testpmd run-time commands to support test of TM packet
> > marking:
> >
> > set port tm mark ip_ecn
> > set port tm mark ip_dscp set por
26/09/2018 18:21, Igor Ryzhov:
> Long time ago preallocation of memory for KNI was introduced in commit
> 0c6bc8e. It was done because of lack of ability to free previously
> allocated memzones, which led to memzone exhaustion. Currently memzones
> can be freed and this patch uses this ability for
On Tue, 2018-10-02 at 16:19 +0100, Bruce Richardson wrote:
> On Tue, Oct 02, 2018 at 03:59:48PM +0100, Luca Boccassi wrote:
> > On Tue, 2018-10-02 at 15:28 +0100, Bruce Richardson wrote:
> > > On Tue, Oct 02, 2018 at 02:06:46PM +0100, Luca Boccassi wrote:
> > > > Allow users and packagers to overri
Allow users and packagers to override the default dpdk/drivers
subdirectory where the PMDs get installed under $lib.
Signed-off-by: Luca Boccassi
---
v3: changed default value to and use string.contains rather
than exact equivalence
meson.build | 10 --
meson_options.txt | 2
As part of the effort of consolidating the DPDK installation bits and
pieces across distros, set the default directory of lib/ where PMDs get
installed to dpdk/pmds-XX.YY. It's necessary to have a versioned
subdirectory as multiple ABI revisions might be installed at the same
time, so having a fixe
Hi Jeff,
> Subject: [PATCH v12 7/7] testpmd: use hot-unplug failure handle mechanism
./devtools/check-git-log.sh -1
Wrong headline label:
testpmd: use hot-unplug failure handle mechanism
> This patch use testpmd for example, to show how an app smoothly handle
> failure when device be
02/10/2018 14:50, Jerin Jacob:
> Santosh Shukla no longer associated with Cavium.
> Update the octeontx driver code maintainership.
>
> Signed-off-by: Jerin Jacob
Applied
On Tue, Oct 02, 2018 at 03:59:48PM +0100, Luca Boccassi wrote:
> On Tue, 2018-10-02 at 15:28 +0100, Bruce Richardson wrote:
> > On Tue, Oct 02, 2018 at 02:06:46PM +0100, Luca Boccassi wrote:
> > > Allow users and packagers to override the default dpdk/drivers
> > > subdirectory where the PMDs get i
On Tue, 2018-10-02 at 15:28 +0100, Bruce Richardson wrote:
> On Tue, Oct 02, 2018 at 02:06:46PM +0100, Luca Boccassi wrote:
> > Allow users and packagers to override the default dpdk/drivers
> > subdirectory where the PMDs get installed under $lib.
> >
> > Signed-off-by: Luca Boccassi
> > ---
> >
> -Original Message-
> From: Jerin Jacob [mailto:jerin.ja...@caviumnetworks.com]
> Sent: Tuesday, October 2, 2018 2:36 PM
> To: Lu, Wenzhuo ; Wu, Jingjing
> ; Iremonger, Bernard
> Cc: dev@dpdk.org; Jerin Jacob ;
> olivier.m...@6wind.com; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] app
On 9/28/2018 4:08 AM, John Daley wrote:
> rte_flow structures were not being freed when destroyed or flushed.
>
> Fixes: 6ced137607d0 ("net/enic: flow API for NICs with advanced filters
> enabled")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Hyong Youb Kim
> Signed-off-by: John Daley
Series appl
On 9/21/2018 12:55 AM, Ferruh Yigit wrote:
> On 9/10/2018 12:01 PM, Xiao Wang wrote:
>> IFCVF can help to log dirty page in live migration stage,
>> each queue's index can be read and configured to support
>> VHOST_USER_GET_VRING_BASE and VHOST_USER_SET_VRING_BASE.
>>
>> Signed-off-by: Xiao Wang
>
On 02-Oct-18 1:35 PM, Jeff Guo wrote:
This patch implements the ops for the PCI bus sigbus handler. It finds the
PCI device that is being hot-unplugged and calls the relevant ops of the
hot-unplug handler to handle the hot-unplug failure of the device.
Signed-off-by: Jeff Guo
Acked-by: Shaopeng
On 02-Oct-18 1:35 PM, Jeff Guo wrote:
When a device is hot-unplugged, a sigbus error will occur of the datapath
can still read/write to the device. A handler is required here to capture
the sigbus signal and handle it appropriately.
This patch introduces a bus ops to handle sigbus errors. Each b
Hi Qi Zhang,
From: Qi Zhang
> v16:
> - rebase to patch "simplify parameters of hotplug functions"
Seems that we have some issues in applying this series such as following and it
continues with the rest of the patches
Applying: eal: enable hotplug on multi-process
fatal: sha1 information is lack
On Tue, Oct 02, 2018 at 02:06:46PM +0100, Luca Boccassi wrote:
> Allow users and packagers to override the default dpdk/drivers
> subdirectory where the PMDs get installed under $lib.
>
> Signed-off-by: Luca Boccassi
> ---
> meson.build | 10 --
> meson_options.txt | 2 ++
> 2 fil
Add rte flow flush api for flushing
all the flows of the port.
Signed-off-by: Reshma Pattan
---
v2: Use TAILQ_FOREACH_SAFE instead of TAILQ_FOREACH
for safe removal using TAILQ_REMOVAL.
Corrected indentation and other style related nits.
---
drivers/net/softnic/rte_eth_softnic_flow.c | 46 +
On 2/10/2018 2:48 PM, Liang Ma wrote:
Add empty poll mode command line example
ChangeLogs:
v9: update the document
Signed-off-by: Liang Ma
---
Acked-by: David Hunt
On 2/10/2018 2:48 PM, Liang Ma wrote:
Update the document for empty poll API.
Change Logs:
v9: minor changes for syntax. Update document.
Signed-off-by: Liang Ma
---
Acked-by: David Hunt
On 2/10/2018 2:48 PM, Liang Ma wrote:
Add the support for new traffic pattern aware power control
power management API.
Example:
./l3fwd-power -l xxx -n 4 -w :xx:00.0 -w :xx:00.1 -- -p 0x3
-P --config="(0,0,xx),(1,0,xx)" --empty-poll="0,0,0" -l 14 -m 9 -h 1
Please Reference l3fwd-
On 2/10/2018 2:48 PM, Liang Ma wrote:
1. Abstract
For packet processing workloads such as DPDK polling is continuous.
This means CPU cores always show 100% busy independent of how much work
those cores are doing. It is critical to accurately determine how busy
a core is hugely important for th
On 02-Oct-18 1:58 PM, Jeff Guo wrote:
When device is be hot-unplugged, the vfio kernel module will sent req
notifier to request user space to release the allocated resources at
first. After that, vfio kernel module will detect the device disappear,
and then delete the device in kernel.
This patc
On 02.10.2018 12:36, Maxime Coquelin wrote:
> The master sends this message before stopping handling
> userfaults, so that the backend closes the userfaultfd.
>
> The master waits for the slave to acknowledge the request
> with an empty 64bits payload for synchronization purpose.
>
> Signed-off-b
On 02.10.2018 12:36, Maxime Coquelin wrote:
> Return of message handling has now changed to an enum that can
> take non-negative value that is not zero in case a reply is
> needed. But the code checking the variable afterwards has not
> been updated, leading to success messages handling being
> tre
On 02.10.2018 12:36, Maxime Coquelin wrote:
> Signed-off-by: Dr. David Alan Gilbert
> Signed-off-by: Maxime Coquelin
> ---
> lib/librte_vhost/vhost.h | 1 +
> lib/librte_vhost/vhost_user.c | 19 +++
> lib/librte_vhost/vhost_user.h | 4 +++-
> 3 files changed, 23 insertions
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, October 2, 2018 2:35 PM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo ; Wu, Jingjing
> ; Iremonger, Bernard ;
> Mcnamara, John ; Kovacevic, Marko
> ; laszlo.madara...@ericsson.com;
> laszlo.vadke...@ericsson.com; andras.kov...@ericsson.c
On 9/28/2018 10:47 PM, Xiaolong Ye wrote:
> The vdpa sample application creates vhost-user sockets by using the
> vDPA backend. vDPA stands for vhost Data Path Acceleration which utilizes
> virtio ring compatible devices to serve virtio driver directly to enable
> datapath acceleration. As vDPA dri
Update the document for empty poll API.
Change Logs:
v9: minor changes for syntax. Update document.
Signed-off-by: Liang Ma
---
doc/guides/prog_guide/power_man.rst | 86 +
1 file changed, 86 insertions(+)
diff --git a/doc/guides/prog_guide/power_man.rst
b/d
Add the support for new traffic pattern aware power control
power management API.
Example:
./l3fwd-power -l xxx -n 4 -w :xx:00.0 -w :xx:00.1 -- -p 0x3
-P --config="(0,0,xx),(1,0,xx)" --empty-poll="0,0,0" -l 14 -m 9 -h 1
Please Reference l3fwd-power document for full parameter usage
T
1. Abstract
For packet processing workloads such as DPDK polling is continuous.
This means CPU cores always show 100% busy independent of how much work
those cores are doing. It is critical to accurately determine how busy
a core is hugely important for the following reasons:
* No indication o
Add empty poll mode command line example
ChangeLogs:
v9: update the document
Signed-off-by: Liang Ma
---
doc/guides/sample_app_ug/l3_forward_power_man.rst | 69 +++
1 file changed, 69 insertions(+)
diff --git a/doc/guides/sample_app_ug/l3_forward_power_man.rst
b/doc/guides
On 9/18/2018 1:45 PM, Mattias Rönnblom wrote:
> This patch contains the Meson and GNU Make build system extensions
> required for the Distributed Event Device, and also the initialization
> code for the driver itself.
>
> Signed-off-by: Mattias Rönnblom
<...>
> @@ -0,0 +1,26 @@
> +# SPDX-Licens
In order to use external memory in multiple processes, we need to
attach to primary process's memseg lists, so add a new API to do
that. It is the responsibility of the user to ensure that memory
is accessible and that it has been previously added to the malloc
heap by another process.
Signed-off-
Add an API to add externally allocated memory to malloc heap. The
memory will be stored in memseg lists like regular DPDK memory.
Multiple segments are allowed within a heap. If IOVA table is
not provided, IOVA addresses are filled in with RTE_BAD_IOVA.
Signed-off-by: Anatoly Burakov
---
lib/lib
Based on the documentation and help print, the sub command
for csum suppose to be "parse-tunnel" instead of "parse_tunnel".
Cc: olivier.m...@6wind.com
Cc: sta...@dpdk.org
Fixes: 64fc36064dc3 ("app/testpmd: add csum parse-tunnel command")
Signed-off-by: Jerin Jacob
---
app/test-pmd/cmdline.c | 4
Currently, mempools can only be allocated either using native
DPDK memory, or anonymous memory. This patch will add two new
methods to allocate mempool using external memory (regular or
hugepage memory), and add documentation about it to testpmd
user guide.
It adds a new flag "--mp-alloc", with fo
Hi Jeff,
Looks ok to me in general, just one thing I missed before:
> +static void sigbus_handler(int signum, siginfo_t *info,
> + void *ctx __rte_unused)
> +{
> + int ret;
> +
> + RTE_LOG(INFO, EAL, "Thread[%d] catch SIGBUS, fault address:%p\n",
> +
Hi Raslan,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Raslan Darawsheh
> Sent: Monday, September 24, 2018 1:49 PM
> To: Wu, Jingjing
> Cc: Thomas Monjalon ; dev@dpdk.org; Shahaf Shuler
> ; Raslan Darawsheh ;
> Xueming(Steven) Li ; Ori Katz ;
> jerin.ja...@
Add API to allow creating new malloc heaps. They will be created
with socket ID's going above RTE_MAX_NUMA_NODES, to avoid clashing
with internal heaps.
This breaks the ABI, so document the change.
Signed-off-by: Anatoly Burakov
---
doc/guides/rel_notes/release_18_11.rst| 2 +
.../comm
An API is needed to check whether a particular socket ID belongs
to an internal or external heap. Prime user of this would be
mempool allocator, because normal assumptions of IOVA
contiguousness in IOVA as VA mode do not hold in case of
externally allocated memory.
Signed-off-by: Anatoly Burakov
Document the addition of external memory support to DPDK.
Signed-off-by: Anatoly Burakov
---
doc/guides/rel_notes/release_18_11.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_11.rst
b/doc/guides/rel_notes/release_18_11.rst
index e7674adb9..8fe463d7
We will be assigning "invalid" socket ID's to external heap, and
malloc will now be able to verify if a supplied socket ID is in
fact a valid one, rendering parameter checks for sockets
obsolete.
Signed-off-by: Anatoly Burakov
Acked-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_pipeline.c
Previously, to calculate length of memory area covered by a memseg
list, we would've needed to multiply page size by length of fbarray
backing that memseg list. This is not obvious and unnecessarily
low level, so store length in the memseg list itself.
This breaks ABI, so bump the EAL ABI version
When we will be creating external heaps, they will have their own
"fake" socket ID, so add a function that will map the heap name
to its socket ID.
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/include/rte_malloc.h | 14
lib/librte_eal/common/rte_malloc.c | 37 +++
We will be assigning "invalid" socket ID's to external heap, and
malloc will now be able to verify if a supplied socket ID is in
fact a valid one, rendering parameter checks for sockets
obsolete.
Signed-off-by: Anatoly Burakov
Acked-by: Bernard Iremonger
---
lib/librte_flow_classify/rte_flow_cl
Add a short chapter on usage of external memory in DPDK to the
Programmer's Guide.
Signed-off-by: Anatoly Burakov
---
.../prog_guide/env_abstraction_layer.rst | 37 +++
1 file changed, 37 insertions(+)
diff --git a/doc/guides/prog_guide/env_abstraction_layer.rst
b/doc/guid
Add simple unit tests to test external memory support.
The tests are pretty basic and mostly consist of checking
if invalid API calls are handled correctly, plus a simple
allocation/deallocation test for malloc and memzone.
Signed-off-by: Anatoly Burakov
---
test/test/Makefile| 1 +
When adding or removing external memory from the memory map, there
may be actions that need to be taken on account of this memory (e.g.
DMA mapping). Add support for triggering callbacks when adding,
removing, attaching or detaching external memory.
Some memory event callback handlers will need ad
This is a proposal to enable using externally allocated memory
in DPDK.
In a nutshell, here is what is being done here:
- Index internal malloc heaps by NUMA node index, rather than NUMA
node itself (external heaps will have ID's in order of creation)
- Add identifier string to malloc heap, to
Add an API to destroy specified heap.
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/include/rte_malloc.h | 23 +
lib/librte_eal/common/malloc_heap.c| 22
lib/librte_eal/common/malloc_heap.h| 3 ++
lib/librte_eal/common/rte_malloc.c | 58 ++
Add API to detach from existing chunk of external memory in a
process.
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/include/rte_malloc.h | 27 +++
lib/librte_eal/common/rte_malloc.c | 31 +-
lib/librte_eal/rte_eal_version.map | 1 +
Add an API to remove memory from specified heaps. This will first
check if all elements within the region are free, and that the
region is the original region that was added to the heap (by
comparing its length to length of memory addressed by the
underlying memseg list).
Signed-off-by: Anatoly Bu
We will be assigning "invalid" socket ID's to external heap, and
malloc will now be able to verify if a supplied socket ID is in
fact a valid one, rendering parameter checks for sockets
obsolete.
Signed-off-by: Anatoly Burakov
Acked-by: Cristian Dumitrescu
---
lib/librte_sched/rte_sched.c | 2 +
When we allocate and use DPDK memory, we need to be able to
differentiate between DPDK hugepage segments and segments that
were made part of DPDK but are externally allocated. Add such
a property to memseg lists.
This breaks the ABI, so document the change in release notes.
This also breaks a few
We will need to refer to external heaps in some way. While we use
heap ID's internally, for external API use it has to be something
more user-friendly. So, we will be using a string to uniquely
identify a heap.
This breaks the ABI, so document the change.
Signed-off-by: Anatoly Burakov
---
doc/
Switch over all parts of EAL to use heap ID instead of NUMA node
ID to identify heaps. Heap ID for DPDK-internal heaps is NUMA
node's index within the detected NUMA node list. Heap ID for
external heaps will be order of their creation.
This breaks the ABI, so document the changes.
Signed-off-by:
1 - 100 of 226 matches
Mail list logo
