06/11/2019 06:50, David Marchand:
> On Wed, Nov 6, 2019 at 12:14 AM Thomas Monjalon wrote:
> > Applied, thanks
>
> The added tests are timeouting:
> https://travis-ci.com/DPDK/dpdk/jobs/253293904
> 47/86 DPDK:fast-tests / rib_autotest TIMEOUT 30.01 s
> 48/86 DPDK:fast-tests / rib6_autote
Hi Stephen,
Many thanks for your reviewing and comments. PSB.
BR. Bing
> -Original Message-
> From: Stephen Hemminger
> Sent: Wednesday, November 6, 2019 1:25 AM
> To: Bing Zhao
> Cc: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/m
Hi Artur,
> > > --
> > > Core engine refactoring (test_deflate_comp_decomp function).
> > > Smaller specialized functions created.
> > >
> > > Signed-off-by: Artur Trybula
> > > ---
Could you please close these comments by today?
> -Original Message-
> From: Andrew Rybchenko
> Sent: Wednesday, November 6, 2019 8:41 AM
> To: Ori Kam ; Thomas Monjalon
>
> Cc: dev@dpdk.org; pbhagavat...@marvell.com; ferruh.yi...@intel.com;
> jer...@marvell.com; John McNamara ; Marko
> Kovacevic ; Adrien Mazarguil
> ; david.march...
On Wed, Nov 6, 2019 at 7:16 AM Wangyu (Eric) wrote:
>
>
> In 64K pagesize system, DPDK will read the size NIC need in
> uio/uio1/maps/map1/size, when the size small than pagesize(e.g.,82599 is
> 16K), dev->mem_resource[i].len will be 16K, but the mmap function applies for
> at least 1 page siz
This patch adds retry in the DPAA2 SEC packet enqueue API
Signed-off-by: Nipun Gupta
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 27 +++--
1 file changed, 20 insertions(+), 7 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_sec/
This patch fixes core dump issue when entering safe mode
with a wrong package file.
Fixes: 5ad3db8d4bdd ("net/ice: enable advanced RSS")
Signed-off-by: Simei Su
---
drivers/net/ice/ice_hash.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ice/ice_hash.c b/driver
>
> This patch usages the anti replay window size to config
> the anti replay checking in decap path for lookaside
> IPSEC offload
>
> Signed-off-by: Hemant Agrawal
> ---
Acked-by: Akhil Goyal
Hi Konstantin,
I had requested some changes in v5 which are there in this patch.
Could you please review this again? I plan to merge it today.
Thanks,
Akhil
> The rte_security lib has introduced replay_win_sz,
> so it can be removed from the rte_ipsec lib.
>
> The relaved tests,app are also upd
From: Andrew Rybchenko
> On 11/5/19 5:05 PM, Matan Azrad wrote:
> > From: Andrew Rybchenko
> >> On 11/3/19 6:16 PM, Matan Azrad wrote
> >>> From: Andrew Rybchenko
> On 11/3/19 9:57 AM, Matan Azrad wrote:
> > Hi
> >
> > From: Andrew Rybchenko
> >> On 10/31/19 7:33 PM, Pavan Ni
This patch usages the anti replay window size to config
the anti replay checking in decap path for lookaside
IPSEC offload
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 21 +
drivers/crypto/dpaa2_sec/dpaa2_sec_priv.h | 6 --
drivers/c
The rte_security lib has introduced replay_win_sz,
so it can be removed from the rte_ipsec lib.
The relaved tests,app are also update to reflect
the usages.
Note that esn and anti-replay fileds were earlier used
only for ipsec library, they were enabling the libipsec
by default. With this change
At present the ipsec xfrom is missing the important step
to configure the anti replay window size.
The newly added field will also help in to enable or disable
the anti replay checking, if available in offload by means
of non-zero or zero value.
Signed-off-by: Hemant Agrawal
Acked-by: Konstantin
On Wed, Oct 30, 2019 at 7:38 PM Subrahmanyam Nilla wrote:
>
> System DPI Packet Interface Unit (SDP) is a co-processor
> of OCTEON TX2 which provides PCIe endpoint support for a
> remote host to DMA packets into and out of the OCTEON TX2 SoC.
> SDP interface comes in to live only when it is connec
On 11/5/19 7:37 PM, Ori Kam wrote:
>
>
>> -Original Message-
>> From: Andrew Rybchenko
>> Sent: Tuesday, November 5, 2019 1:31 PM
>> To: Ori Kam ; Thomas Monjalon
>>
>> Cc: dev@dpdk.org; pbhagavat...@marvell.com; ferruh.yi...@intel.com;
>> jer...@marvell.com; John McNamara ; Marko
>> Ko
On Wed, Nov 6, 2019 at 6:13 AM Gavin Hu (Arm Technology China)
wrote:
>
> Reviewed-by: Gavin Hu
Applied to dpdk-next-net-mrvl/master. Thanks
In 64K pagesize system, DPDK will read the size NIC need in
uio/uio1/maps/map1/size, when the size small than pagesize(e.g.,82599 is 16K),
dev->mem_resource[i].len will be 16K, but the mmap function applies for at
least 1 page size, which is 64K.
Then second NIC mmap, start address is first N
The ptype bitmap calculation for GRE packet is modified by misktake due to
commit fc845a9d78ce
("net/ice/base: fix ptype mapping pollution from GTP flow")
which is target for GTP packet. The patch rollback that part of code.
Fixes: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP
The ptype bitmap calculation for GRE packet is modified by misktake due to
commit: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP flow")
which is target for GTP packet. The patch rollback that part of code.
Fixes: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP
testpmd will occur infinite loops when device hotplug remove.
We can fix the issue by using the pci generic remove function
Fixes: f2f4990eff94 ("net/ixgbe: release port upon close")
Signed-off-by: Di ChenxuX
---
drivers/net/ixgbe/ixgbe_ethdev.c | 11 +--
1 file changed, 1 insertion(+),
testpmd will occur infinite loops when device hotplug remove.
We can fix the issue by using the pci generic remove function
Fixes: ac89d46096d5 ("net/i40e: release port upon close")
Signed-off-by: Di ChenxuX
v2:
change the code in driver.
---
drivers/net/i40e/i40e_ethdev.c | 12 +---
1
The ptype bitmap calculation for GRE packet is modified by misktake due to
commit: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP flow")
which is target for GTP packet. The patch rollback that part of code.
Fixes: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP
On Wed, Nov 6, 2019 at 12:14 AM Thomas Monjalon wrote:
>
> 01/11/2019 16:21, Vladimir Medvedkin:
> > This is heavily reworked version of previous RIB library series:
> > https://mails.dpdk.org/archives/dev/2018-April/099492.html
> >
> > app/test/Makefile | 7 +
> > app/test/aut
The ptype bitmap calculation for GRE packet is modified by misktake due to
commit: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP flow")
which is target for GTP packet. The patch rollback that part of code.
Fixes: fc845a9d78ce ("net/ice/base: fix ptype mapping pollution from GTP
Use kernel headers for __le* types to avoid potential conflicts
resulting in redefinition errors for Linux build environments.
Add check for FreeBSD execution environments.
Without this fix, aarch64 builds can fail with error [1] below.
[1]
In file included from ../drivers/net/bnx2x/bnx2x.h:22,
> -Original Message-
> From: dev On Behalf Of Stephen Hemminger
> Sent: Tuesday, November 5, 2019 9:39 PM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Ferruh Yigit
>
> Subject: [dpdk-dev] [PATCH] examples/l3fwd: use correct IP reserved
> address range
>
> The original patch used incorrec
This patch throw the warning when using truncted digest
len for SHA256 case.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 4
drivers/crypto/dpaa_sec/dpaa_sec.c | 4
2 files changed, 8 insertions(+)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2
This patch enables short buffer and 12 bit IV AES-CTR cases
for dpaax_sec pmds.
Signed-off-by: Vakul Garg
Signed-off-by: Hemant Agrawal
---
app/test/test_cryptodev_aes_test_vectors.h | 24 +++---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/app/test/test_crypto
From: Gagandeep Singh
This patch remove redundant checks.
Signed-off-by: Gagandeep Singh
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 17 ++---
1 file changed, 6 insertions(+), 11 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_se
From: Vakul Garg
The protocol aware ipsec descriptor has been modified to
use ctr_initial value of 1 and salt configured for ipsec SA.
Signed-off-by: Hemant Agrawal
Signed-off-by: Vakul Garg
---
drivers/common/dpaax/caamflib/desc/ipsec.h | 18 --
drivers/crypto/dpaa2_sec/dpaa
From: Vakul Garg
As per RFC3686, the initial aes-ctr counter value should be '1' for use
in ipsec. The patches changes SEC descriptor for using correct counter
value. In addition, it drops a redundant parameter for passing IV while
creating the descriptor.
Signed-off-by: Vakul Garg
---
drivers
From: Gagandeep Singh
Align the cleanup and allocation for the queues.
Signed-off-by: Gagandeep Singh
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/crypto/dpaa_sec/dpaa_sec.c
ind
These are supported when using protocol offload mode or in chain mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 22 +++
drivers/crypto/dpaa2_sec/dpaa2_sec_priv.h | 41 +
2 files changed, 56 insertions(+), 7 deletions(-)
diff -
set the pdcp capa_flags to 0 by default.
Fixes: a1173d55598c ("crypto/dpaa_sec: support PDCP offload")
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.h
b/drivers/crypto/dpaa_sec/dpaa_se
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 60 +++--
1 file changed, 56 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
index dd80e6dc5..173ec8095 100644
---
Check if the session is not null during processing.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/crypto/dpaa_sec/dpaa_sec.c
index 6c186338f..343a565a2 100644
--- a/dr
This patch add support for AES-128-GCM, when used in
proto lookaside mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 309 -
1 file changed, 211 insertions(+), 98 deletions(-)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/cryp
Check if the session is not null during processing.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
index b04890a48..7d5
These are supported when using protocol offload mode or when
in chain mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 33 ++--
drivers/crypto/dpaa_sec/dpaa_sec.h | 41 ++
2 files changed, 66 insertions(+), 8 deletions(-
> -Original Message-
> From: Akhil Goyal
> Sent: Wednesday, November 6, 2019 3:32 AM
> To: Hemant Agrawal ; dev@dpdk.org
> Cc: konstantin.anan...@intel.com; ano...@marvell.com; Hemant Agrawal
>
> Subject: RE: [PATCH v5 2/3] ipsec: remove redundant replay_win_sz
> Importance: High
>
>
Hi Akhil,
> -Original Message-
> From: Akhil Goyal
> Sent: Wednesday, November 6, 2019 3:38 AM
> To: Hemant Agrawal ; dev@dpdk.org
> Cc: konstantin.anan...@intel.com; ano...@marvell.com; Hemant Agrawal
>
> Subject: RE: [PATCH v5 3/3] crypto/dpaa2_sec: enable anti replay window
> config
>
Hi Eelco
> -Original Message-
> From: Eelco Chaudron [mailto:echau...@redhat.com]
> Sent: Friday, November 1, 2019 4:13 PM
> To: Xing, Beilei ; Zhang, Xiao
> Cc: Zhang, Qi Z ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: force promiscuous state after VF
> reset
>
>
>
> On 1
>
> Originally both SW and HW crypto PMDs use rte_crypot_op based API to
> process the crypto workload asynchronously. This way provides uniformity to
> both PMD types, but also introduce unnecessary performance penalty to SW
> PMDs that have to "simulate" HW async behavior (crypto-ops
> enqueue
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, November 6, 2019 09:22
> To: Thomas Monjalon
> Cc: dev@dpdk.org; jerinjac...@gmail.com; Yigit, Ferruh
> ;
> arybche...@solarflare.com; viachesl...@mellanox.com; damar...@cisco.com; Ye,
> Xiaolong
> ; Sun, Chenmin ; Kinsella, Ra
This patch changes RSS rule destroy API from ice_rem_vsi_rss_cfg()
to ice_rem_rss_cfg(). ice_rem_vsi_rss_cfg() removes RSS configurations
associated with VSI. ice_rem_rss_cfg() remove an existing RSS configuration
with matching hashed fields. To support input set change, we should adopt
ice_rem_rss
Change the type of burst mode information from bit field to free string
data, so that each PMD can describe the Rx/Tx busrt functions flexibly.
Signed-off-by: Haiyue Wang
Acked-by: Ray Kinsella
---
v3: - Fix one doxygen issue.
v2: - http://patchwork.dpdk.org/patch/62368/
- Drop the bit fiel
As doc mentioned, Rx/Mac/vlan filters are all supported by best effort.
These control commands should return success.
Fixes: f9b9d1a55775 ("net/virtio-user: add multiple queues in device emulation")
Cc: sta...@dpdk.org
Signed-off-by: Marvin Liu
---
drivers/net/virtio/virtio_user/virtio_user_dev
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, November 6, 2019 08:34
> To: Wang, Haiyue
> Cc: dev@dpdk.org; jerinjac...@gmail.com; Yigit, Ferruh
> ;
> arybche...@solarflare.com; viachesl...@mellanox.com; damar...@cisco.com; Ye,
> Xiaolong
> ; Sun, Chenmin ;
Reviewed-by: Gavin Hu
04/11/2019 11:39, Haiyue Wang:
> Change the type of burst mode information from bit field to free string
> data, so that each PMD can describe the Rx/Tx busrt functions flexibly.
>
> Signed-off-by: Haiyue Wang
> ---
>
> v2: - Drop the bit field for burst mode information handling.
Please use --
05/11/2019 15:23, Nipun Gupta:
> Hemant Agrawal (1):
> bus/dpaa: moving qbman global init to bus
>
> Nipun Gupta (7):
> net/dpaa: fix supported RSS types
> net/dpaa: fix LS1043 alignment check
> common/dpaax: fallback to check separate memory node for VM
> net/dpaa2: add retry and timeou
I'm sorry I still have some comments.
But on the positive side, you can see that I carefuly read this doc.
05/11/2019 16:24, Ray Kinsella:
> +#. Major ABI versions are declared every **year** and are then supported for
> one
> + year, typically aligned with the :ref:`LTS release `.
As discusse
Hi, Ferruh
On 11/05, Ferruh Yigit wrote:
>On 10/28/2019 5:51 AM, Yang, Qiming wrote:
>> Hi,
>>
>>> -Original Message-
>>> From: Di, ChenxuX
>>> Sent: Thursday, October 24, 2019 9:03 AM
>>> To: dev@dpdk.org
>>> Cc: Lu, Wenzhuo ; Yang, Qiming
>>> ; Di, ChenxuX
>>> Subject: [PATCH] app/test
01/11/2019 16:21, Vladimir Medvedkin:
> This is heavily reworked version of previous RIB library series:
> https://mails.dpdk.org/archives/dev/2018-April/099492.html
>
> app/test/Makefile | 7 +
> app/test/autotest_data.py | 48 +++
> app/test/meson.build
> IPSec Multi buffer library supports encryption on multiple segments.
> When dealing with chained buffers (multiple segments), as long as
> the operation is in-place, the destination buffer does not have to
> be contiguous (unlike in the case of out-of-place operation).
> Therefore, the limitati
> Updated AESNI MB and AESNI GCM PMD documentation guides
> with information about the latest Intel IPSec Multi-buffer
> library supported.
>
> Signed-off-by: Pablo de Lara
Applied to dpdk-next-crypto
Thanks
>
> The example IPsec application does not work properly when using
> AES-GCM with crypto_openssl.
>
> ESP with AES-GCM uses standard 96bit long algorithm IV ([1]) which
> later concatenated with be32(1) forms a J0 block. GCM specification
> ([2], chapter 7.1) states that when length of IV is
> FD retreived from SEC after crypto processing provides
> an updated length of the buffer which need to be updated
> in mbuf. The difference in length can be negative hence
> changing diff to int32_t from uint32_t.
>
> Fixes: 0a23d4b6f4c2 ("crypto/dpaa2_sec: support protocol offload IPsec")
>
>
> Coverity reported about two division by zero:
> *** CID 350344: Incorrect expression (DIVIDE_BY_ZERO)
> Although in fact these dividers will never be equal to 0,
> adding explicit checks in lookup() to make coverity happy
> will not affect the execution speed.
>
> Signed-off-by: Vladimir
Hi Hemant,
>
> This patch usages the anti replay window size to config
> the anti replay checking in decap path for lookaside
> IPSEC offload
>
> Signed-off-by: Hemant Agrawal
> ---
> drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 24 +++
> drivers/crypto/dpaa2_sec/dpaa2_sec_pri
Hi Hemant,
>
> The rte_security lib has introduced replay_win_sz,
> so it can be removed from the rte_ipsec lib.
>
> Also, the relaved tests,app are also update to reflect
> the usages.
>
> Signed-off-by: Hemant Agrawal
> Acked-by: Konstantin Ananyev
> ---
> app/test/test_ipsec.c
Hi Konstantin,
>
> This patch extends rte_cryptodev API with CPU-CRYPTO mode.
> This is done by reusing existing rte_crypto_sym_session structure itself
> and related control-path cryptodev API (init/clear/get_size/etc.)
> For data-path new sym_cpu_ process() function is added into
> rte_cryptod
FD retreived from SEC after crypto processing provides
an updated length of the buffer which need to be updated
in mbuf. The difference in length can be negative hence
changing diff to int32_t from uint32_t.
Fixes: 0a23d4b6f4c2 ("crypto/dpaa2_sec: support protocol offload IPsec")
Cc: sta...@dpdk.o
On Tue, Nov 5, 2019 at 1:36 PM David Marchand
wrote:
> Hello,
>
> On Tue, Nov 5, 2019 at 7:17 PM wrote:
> >
> > From: Devyn Collier Johnson
> >
> > Signed-off-by: Devyn Collier Johnson
> > ---
> > lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
> > lib/librte_eal/common/eal_common_cpuf
>From: Thomas Monjalon
>Sent: Tuesday, November 05, 2019 10:15 AM
>
>01/11/2019 07:02, Rasesh Mody:
>> Use kernel headers for __le* types to avoid potential conflicts
>> resulting in redefinition errors during Linux builds. Add check for
>> BSD builds.
>
>I don't see the error with my test builds.
Hello,
On Tue, Nov 5, 2019 at 7:17 PM wrote:
>
> From: Devyn Collier Johnson
>
> Signed-off-by: Devyn Collier Johnson
> ---
> lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
> lib/librte_eal/common/eal_common_cpuflags.c | 4 ++--
> lib/librte_eal/common/eal_common_errno.c| 2 +-
>
This commit introduce the hairpin queues to the testpmd.
the hairpin queue is configured using --hairpinq=
the hairpin queue adds n queue objects for both the total number
of TX queues and RX queues.
The connection between the queues are 1 to 1, first Rx hairpin queue
will be connected to the first
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, November 5, 2019 19:21
> To: Bing Zhao
> Cc: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: introduce mlx5 hash list
>
> On Tue, 5 Nov 2019 17:28:00 +0200
> Bing
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
lib/librte_mbuf/rte_mbuf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/librte_mbuf/rte_mbuf.c
index f3fe16eb0..305084531 100644
--- a/lib/librte_mbuf/rte_mbuf.c
+++ b/li
This patch extends rte_security API with CPU-CRYPTO mode.
Crypto PMD that wants to support that functionality would need to:
1. claim RTE_CRYPTODEV_FF_SECURITY capability supported.
2. at device .probe() allocate and initialize security context (dev->
security_ctx).
3. implement at least the follo
Introduce basic data strucure to be used with cpu-crypto data-path.
Signed-off-by: Konstantin Ananyev
---
lib/librte_cryptodev/rte_crypto_sym.h | 52 +--
lib/librte_security/rte_security.h| 6 +++-
2 files changed, 54 insertions(+), 4 deletions(-)
diff --git a/lib/l
This patch extends rte_cryptodev API with CPU-CRYPTO mode.
This is done by reusing of existing rte_crypto_sym_xform data structures
and introducing new opaque rte_crypto_cpu_sym_session data structure
and related control and data path API.
Crypto PMD that wants to support that functionality would
This patch extends rte_cryptodev API with CPU-CRYPTO mode.
This is done by reusing existing rte_crypto_sym_session structure itself
and related control-path cryptodev API (init/clear/get_size/etc.)
For data-path new sym_cpu_ process() function is added into
rte_cryptodev dev_ops.
Crypto PMD t
Originally both SW and HW crypto PMDs use rte_crypot_op based API to
process the crypto workload asynchronously. This way provides uniformity
to both PMD types, but also introduce unnecessary performance penalty to
SW PMDs that have to "simulate" HW async behavior
(crypto-ops enqueue/dequeue, HW ad
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
app/test/test_cmdline_portlist.c| 2 +-
examples/vmdq_dcb/main.c| 2 +-
lib/librte_cryptodev/rte_cryptodev.c| 2 +-
lib/librte_eal/common/eal_common_tailqs.c | 2 +-
lib/librte_eal/com
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
lib/librte_eal/common/eal_common_cpuflags.c | 4 ++--
lib/librte_eal/common/eal_common_errno.c| 2 +-
lib/librte_eal/common/eal_common_hexdump.c | 4 ++--
lib/libr
01/11/2019 07:02, Rasesh Mody:
> Use kernel headers for __le* types to avoid potential conflicts
> resulting in redefinition errors during Linux builds. Add check
> for BSD builds.
I don't see the error with my test builds.
Please could you describe a case where it happens?
And please provide an e
On Tue, 5 Nov 2019 15:24:15 +
Ray Kinsella wrote:
> Separate versioning.rst into abi versioning and abi policy guidance, in
> preparation for adding more detail to the abi policy.
>
> Signed-off-by: Ray Kinsella
> ---
> doc/guides/contributing/abi_policy.rst | 167
> doc/guid
On Tue, 5 Nov 2019 15:24:17 +
Ray Kinsella wrote:
> Updates to the ABI versioning guide, to account for the changes to the DPDK
> ABI/API policy. Fixes for references to abi versioning and policy guides.
>
> Signed-off-by: Ray Kinsella
> ---
Acked-by: Stephen Hemminger
On Tue, 5 Nov 2019 15:24:16 +
Ray Kinsella wrote:
> This policy change introduces major ABI versions, these are
> declared every year, typically aligned with the LTS release
> and are supported by subsequent releases in the following year.
> This change is intended to improve ABI stabilty fo
On 11/5/2019 3:32 PM, Ori Kam wrote:
> This patch solves a compilation issue that is caused due to using
> internal function (is_rx_hairpin_queue) inside inline function.
>
> The solution is to remove the usage of the functions
> from the burst functions.
>
> Fixes: 60b476d5da3c ("ethdev: add sup
On Tue, 5 Nov 2019 16:02:18 +
Raslan Darawsheh wrote:
> Hi,
>
> > -Original Message-
> > From: Bing Zhao
> > Sent: Tuesday, November 5, 2019 5:28 PM
> > To: Ori Kam ; Slava Ovsiienko
> > ; Raslan Darawsheh ;
> > dev@dpdk.org
> > Subject: [PATCH] net/mlx5: introduce mlx5 hash list
>
On Tue, 5 Nov 2019 17:28:00 +0200
Bing Zhao wrote:
> +struct mlx5_hlist *
> +mlx5_hlist_create(char *name, uint64_t size, mlx5_hlist_destroy_callback_fn
> cb)
Name is unused in rte_malloc, so why bother with it here?
> +{
> + struct mlx5_hlist *h;
> + uint64_t act_size;
> + uint64_
On Tue, 5 Nov 2019 17:28:00 +0200
Bing Zhao wrote:
> Introduce simple hash list to the mlx5 utilities. User can define
> its own data structure containing the mlx5_hlist_entry and create
> the hash list table via the creation interface. Then the entry will
> be inserted into the table and linked
On 05-Nov-19 3:15 PM, Anatoly Burakov wrote:
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the tim
On 05-Nov-19 3:18 PM, Burakov, Anatoly wrote:
On 05-Nov-19 2:10 PM, Rajesh Ravi wrote:
Thanks a lot Anatoly.
Will the same solution work with DPDK 19.02 as well? We 're actually
using DPDK 19.02 for memory allocations for SPDK 19.07.
DPDK 19.11 may not be supported by SPDK 19.07 we 're curren
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the time of heap creation (or
if devices were availabl
> -Original Message-
> From: Kevin Traynor
> Sent: Tuesday 5 November 2019 16:41
> To: David Marchand
> Cc: dev ; Ferriter, Cian ; dpdk
> stable ; Yigit, Ferruh
> Subject: Re: [dpdk-dev] [PATCH 1/9] net/pcap: fix argument checks
>
> On 30/10/2019 07:52, David Marchand wrote:
> > On Tu
On 30/10/2019 07:52, David Marchand wrote:
> On Tue, Oct 1, 2019 at 2:54 PM Kevin Traynor wrote:
>>
>> Previously rx/tx_queues were passed into eth_from_pcaps_common()
>> as ptrs and were checked for being NULL.
>>
>> In commit da6ba28f0540 ("net/pcap: use a struct to pass user options")
>> that c
> -Original Message-
> From: Andrew Rybchenko
> Sent: Tuesday, November 5, 2019 1:31 PM
> To: Ori Kam ; Thomas Monjalon
>
> Cc: dev@dpdk.org; pbhagavat...@marvell.com; ferruh.yi...@intel.com;
> jer...@marvell.com; John McNamara ; Marko
> Kovacevic ; Adrien Mazarguil
> ; david.march...@r
On 11/1/2019 5:04 PM, Wang, Yipeng1 wrote:
> Hi, Amit,
>
> I think I acked this patch. But from patchwork seems you superseded this
> patch set accidentally. So Thomas might have missed it.
> To make his life easier, you may submit a newer version with my acked. I
> believe Thomas will see it.
On Tue, 5 Nov 2019 16:12:31 +
Ferruh Yigit wrote:
> On 11/5/2019 4:09 PM, Stephen Hemminger wrote:
> > The original patch used incorrect subnet range for testing.
> >
> > Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
> > Reported-by: Ferruh Yigit
>
> I guess this is:
On 11/5/2019 4:13 PM, Shah, Rahul R wrote:
> No, As Bruce explained I confirmed it is being already built before
> librte_port
> library as highlighted below.
Got it, so meson doesn't need fixing. Can you please fix the make part?
No, As Bruce explained I confirmed it is being already built before librte_port
library as highlighted below.
# process all libraries equally, as far as possible
# "core" libs first, then others alphebetically as far as possible
# NOTE: for speed of meson runs, the dependencies in the subdire
On 11/5/2019 4:09 PM, Stephen Hemminger wrote:
> The original patch used incorrect subnet range for testing.
>
> Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
> Reported-by: Ferruh Yigit
I guess this is:
Reported-by: Hemant Agrawal
> Signed-off-by: Stephen Hemminger
> ---
On 11/4/2019 11:24 AM, Shah, Rahul R wrote:
> Hi Ferruh,
>
> I was checking the lib/Makefile for cryptodev example which is similar to
> eventdev patch I have added (i.e. there is a dependency on librte_cryptodev
> library)
>
> DIRS-$(CONFIG_RTE_LIBRTE_PORT) += librte_port
> DEPDIRS-librte_port
The original patch used incorrect subnet range for testing.
Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
Reported-by: Ferruh Yigit
Signed-off-by: Stephen Hemminger
---
doc/guides/testpmd_app_ug/run_app.rst | 6 +++---
examples/l3fwd/l3fwd_lpm.c| 18 +---
On Tue, Nov 05, 2019 at 04:36:59PM +0100, Olivier Matz wrote:
> KNI supposes that mbufs are contiguous in kernel virtual memory. This
> may not be true when using the IOVA=VA mode. To fix this, a possibility
> is to ensure that objects do not cross page boundaries in mempool. This
> patchset implem
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Tuesday, November 5, 2019 5:28 PM
> To: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh ;
> dev@dpdk.org
> Subject: [PATCH] net/mlx5: introduce mlx5 hash list
>
> Introduce simple hash list to the mlx5 utilities. User can define its own d
On 11/4/2019 11:06 AM, Bruce Richardson wrote:
> On Tue, Oct 29, 2019 at 09:27:22AM +, Ferruh Yigit wrote:
>> On 10/28/2019 5:18 PM, Stephen Hemminger wrote:
>>> On Mon, 26 Aug 2019 18:32:35 +0530
>>> Gagandeep Singh wrote:
>>>
--- a/config/common_base
+++ b/config/common_base
@
1 - 100 of 231 matches
Mail list logo
