On Mon, Jun 26, 2023 at 12:04 PM Thomas Monjalon
wrote:
> 26/06/2023 11:13, Didier Pallard:
> > HI,
> > not sure to understand how it is possible.
> > If build OPENSSL_VERSION_NUMBER < 0x1010L, linker should link
> binary
> > with libcrypto.so.1.0.0.
sed
at build time, no?
didier
On Sun, Jun 25, 2023 at 9:22 PM Thomas Monjalon wrote:
> 18/04/2023 16:56, Didier Pallard:
> > This workaround was needed before version 1.0.1f. Do not build it for
> > versions >= 1.1.
> >
> > Fixes: d61f70b4c918 ("crypto/lib
This workaround was needed before version 1.0.1f. Do not build it for
versions >= 1.1.
Fixes: d61f70b4c918 ("crypto/libcrypto: add driver for OpenSSL library")
Signed-off-by: Didier Pallard
Cc: sta...@dpdk.org
---
drivers/crypto/openssl/rte_openssl_pmd.c | 14 --
1 fil
quot;)
Signed-off-by: Didier Pallard
Cc: sta...@dpdk.org
---
drivers/crypto/openssl/rte_openssl_pmd.c | 7 ---
1 file changed, 7 deletions(-)
diff --git a/drivers/crypto/openssl/rte_openssl_pmd.c
b/drivers/crypto/openssl/rte_openssl_pmd.c
index 384d26262105..e00db0facba5 100644
--- a/dr
SOCKET_ID_ANY
is converted to 255, causing rte_cryptodev_socket_id to return
an incorrect value.
Fixes: 7dcd73e37965 ("drivers/bus: set device NUMA node to unknown by default")
Signed-off-by: Didier Pallard
---
lib/cryptodev/cryptodev_pmd.h | 4 ++--
1 file changed, 2 insertions(+), 2
Hi slava,
Is this fixed in main branch now?
If yes could you please point me out the proper commit?
Thanks
Didier
On 3/17/20 10:25 AM, Slava Ovsiienko wrote:
*From:* Didier Pallard
*Sent:* Tuesday, March 17, 2020 11:19
*To:* Slava Ovsiienko
*Cc:* dev@dpdk.org; sta...@dpdk.org; Matan Azrad
Out of place with linear buffers is supported by octeontx2
while not advertised.
Fixes: 6aa9ceaddf1d ("crypto/octeontx2: add symmetric capabilities")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
v2:
* Add documentation.
doc/guides/cryptodevs/features/octeontx2.ini | 1
Out of place with linear buffers is supported by octeontx
while not advertised.
Fixes: 0dc1cffa4d33 ("crypto/octeontx: add hardware init routine")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
v2:
* Add documentation.
doc/guides/cryptodevs/features/octeontx.ini | 1 +
driv
Out of place with linear buffers is supported by octeontx2
while not advertised.
Cc: sta...@dpdk.org
Fixes: 6aa9ceaddf1d ("crypto/octeontx2: add symmetric capabilities")
Signed-off-by: Didier Pallard
---
drivers/crypto/octeontx2/otx2_cryptodev.c | 1 +
1 file changed, 1 insertion(+)
Out of place with linear buffers is supported by octeontx
while not advertised.
Cc: sta...@dpdk.org
Fixes: 0dc1cffa4d33 ("crypto/octeontx: add hardware init routine")
Signed-off-by: Didier Pallard
---
drivers/crypto/octeontx/otx_cryptodev_ops.c | 1 +
1 file changed, 1 insertion(+)
Dependency on kmod needed to manage crypto devices is missing
in qat crypto pmd.
Cc: sta...@dpdk.org
Fixes: 0880c40113ef ("drivers: advertise kmod dependencies in pmdinfo")
Signed-off-by: Didier Pallard
---
drivers/common/qat/qat_device.c | 1 +
1 file changed, 1 insertion(+)
di
OK, thank you
best regards
didier
On Tue, Mar 17, 2020 at 10:25 AM Slava Ovsiienko
wrote:
> *From:* Didier Pallard
> *Sent:* Tuesday, March 17, 2020 11:19
> *To:* Slava Ovsiienko
> *Cc:* dev@dpdk.org; sta...@dpdk.org; Matan Azrad
> *Subject:* Re: [dpdk-dev] [PATCH] n
t 9:33 AM Slava Ovsiienko
wrote:
> >> From: Didier Pallard
> >> Sent: Monday, March 16, 2020 19:24
> >> To: Slava Ovsiienko
> >> Cc: dev@dpdk.org; sta...@dpdk.org; Matan Azrad
> >> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: fix Rx descriptor status
>
orrespond the requested packets
> in case of multi-segment packets (requested desc is divided by
> (1<
> With best regards, Slava
>
> > -Original Message-
> > From: dev On Behalf Of Didier Pallard
> > Sent: Friday, March 13, 2020 11:57
> > To: dev@
s in queue, not this number minus
one.
Fixes: 8788fec1f269 ("net/mlx5: implement descriptor status API")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers/net/mlx5/mlx5_rxtx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_rxtx.
rroneously includes all PKT_RX_OFFLOAD_ bits in the
I40E_TX_OFFLOAD_NOTSUP_MASK, this is not what is expected.
Restore the initial xor that gives the expected result.
Fixes: 09a62d75691f ("net/i40e: fix offload not supported mask")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
-
.
So any packet sent to those drivers with a L4 checksum request and
one of PKT_TX_IPVx bit set is rejected by the tx prepare function.
Fixes: 1037ed842c37 ("mbuf: fix Tx offload mask")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers/net/atlantic/atl_rxtx.c| 2 ++
d
t for representor ports")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers/net/ixgbe/ixgbe_vf_representor.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/ixgbe_vf_representor.c
b/drivers/net/ixgbe/ixgbe_vf_representor.c
index db
t for representor ports")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers/net/i40e/i40e_vf_representor.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/i40e/i40e_vf_representor.c
b/drivers/net/i40e/i40e_vf_representor.c
index f9f131611016..0bfbb4f6011f 100644
---
advertise it and
expect to never receive fragmented packets (octeontx, axgbe)
So an ethdev that supports multisegmented packets should properly
advertise it.
Didier Pallard (4):
net/e1000: fix missing Tx multi segs capability
net/fm10k: fix missing Tx multi segs capability
net/i40e: fix
s API")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers/net/fm10k/fm10k_ethdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/fm10k/fm10k_ethdev.c b/drivers/net/fm10k/fm10k_ethdev.c
index 3359df3c8b9c..7cf5b0314c75 100644
--- a/drivers/net/fm10k/fm10k_ethd
advertise it and
expect to never receive fragmented packets (octeontx, axgbe)
So an ethdev that supports multisegmented packets should properly
advertise it.
Fixes: e5c05e6590ea ("net/e1000: convert to new Tx offloads API")
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
drivers
;)
Cc: sta...@dpdk.org
Signed-off-by: Didier Pallard
---
lib/librte_net/rte_net.h | 20
1 file changed, 8 insertions(+), 12 deletions(-)
diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
index b6ab6e1d57b2..e59760a0a108 100644
--- a/lib/librte_net/rte_net.h
t the same
than before the
patch.
Didier
On 04/16/2018 09:46 PM, Yong Wang wrote:
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Didier Pallard
Sent: Wednesday, March 28, 2018 8:44 AM
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 2/8] net/vmxnet3: return unknown
t the following numbers using 2 cores for
our DPDK app:
- with LRO enabled on the DPDK app ports: 40 Gbps
- with LRO disabled on the DPDK app ports: 20 Gbps
Didier
/*
*/
On 04/13/2018 06:44 AM, Yong Wang wrote:
On 3/28/18, 8:44 AM, "dev on behalf of Didier Pallard" wrote:
This
Packets containing empty segments are dropped by hypervisor, prevent
this case by skipping empty segments in transmission.
Also drop empty mbufs to be sure that at least one segment is transmitted
for each mbuf.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 13
receiving buffers, they may
generate unneeded extra processing in the upper application.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 13 +
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c
b/drivers/net/vmxnet3
Not so old variants of vmxnet3 do not provide MSS value along with
LRO packet. When this case happens, try to guess MSS value with
information at hand.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/Makefile | 1 +
drivers/net/vmxnet3/vmxnet3_ethdev.c | 2 ++
drivers/net
Add support for IPv6, LRO and properly set packet type in all
supported cases.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/base/vmxnet3_defs.h | 27 ++-
drivers/net/vmxnet3/vmxnet3_rxtx.c | 82 +++--
2 files changed, 93 insertions(+), 16
In case we are working on a multisegment buffer, most bit are set
in last segment of the buffer. Correctly look at those bits in eop part
of the rx_offload function.
Fixes: 2fdd835f992c ("vmxnet3: support jumbo frames")
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/vmxnet3_r
skip_ip6_ext function can be exported as a helper, it may be used
by some PMD to skip IPv6 header extensions.
Signed-off-by: Didier Pallard
---
lib/librte_net/Makefile| 1 +
lib/librte_net/rte_net.c | 21 ++---
lib/librte_net/rte_net.h | 27
be later used for TSO offloads.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 56 +-
1 file changed, 31 insertions(+), 25 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c
b/drivers/net/vmxnet3/vmxnet3_rxtx.c
index
segment, and is
propagated as is to the application. But if the application
sends back to the hypervisor a mbuf with an empty
segment, this mbuf is dropped by the hypervisor.
Didier Pallard (8):
net: export IPv6 header extensions skip function
net/vmxnet3: return unknown IPv4 extension len
Rather than parsing IP header to get proper ptype to return, just return
RTE_PTYPE_L3_IPV4_EXT_UNKNOWN, that tells application that we have an IP
packet with unknown header length.
Signed-off-by: Didier Pallard
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 8 +---
1 file changed, 1 insertion
Fix crc32c hash functions to return a valid crc32c value for
data lengthes not multiple of 4 bytes.
ARM code is not tested.
Signed-off-by: Didier Pallard
Acked-by: David Marchand
---
doc/guides/rel_notes/release_16_04.rst | 5 ++
lib/librte_hash/rte_crc_arm64.h| 64
Add some small key lengthes (below 4 bytes), and fix odd key lengthes
expected returned values for CRC computation to match real CRC values.
Signed-off-by: Didier Pallard
---
app/test/test_hash_functions.c | 17 +++--
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a
computation.
Didier Pallard (2):
test: fix CRC hash function autotest
hash: fix CRC32c computation
app/test/test_hash_functions.c | 17 +++--
doc/guides/rel_notes/release_16_04.rst | 5 ++
lib/librte_hash/rte_crc_arm64.h| 64 +
lib/librte_hash/rte_hash_crc.h
Ok, i will fix the typo and propose a second serie of patch including
unit tests.
thanks
On 02/10/2016 03:35 PM, Pattan, Reshma wrote:
> Hi,
>
> Small typo.
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Didier Pallard
>&
quot;, ~rte_hash_crc(null_test, 3, 0x));
printf("CRC of 4 nul bytes expected: 0x48674bc7\n");
printf("soft: %08x\n", crc32c_trivial(null_test, 4, 0));
rte_hash_crc_init_alg();
printf("rte accelerated: %08x\n", ~rte_hash_crc(null_test, 4,
0xF
\n", ~rte_hash_crc(null_test, 3, 0x));
printf("CRC of 4 nul bytes expected: 0x48674bc7\n");
printf("soft: %08x\n", crc32c_trivial(null_test, 4, 0));
rte_hash_crc_init_alg();
printf("rte accelerated: %08x\n", ~rte_ha
is locked)
to be inaccessible from DPDK application until reboot of the
hardware.
This patch release locks that are supposed to be locked due to
an improper exit of the application.
Signed-off-by: Didier Pallard
---
v3: Move code outside from base driver
lib/librte_pmd_e1000/igb_ethdev.c | 69
is locked)
to be inaccessible from DPDK application until reboot of the
hardware.
This patch release locks that are supposed to be locked due to
an improper exit of the application.
Signed-off-by: Didier Pallard
---
v3: Move code outside from base driver
lib/librte_pmd_ixgbe/ixgbe_ethdev.c
barrier before rdtsc to
synchronize operations and ensure that the TSC read is done at the expected
place.
Signed-off-by: Didier Pallard
---
Call rte_mb() and rte_rdtsc() rather than duplicating rte_rdtsc function.
Use r/w memory barrier instead of lfence to serialize both load and stores.
lib/li
is locked)
to be inaccessible from DPDK application until reboot of the
hardware.
This patch release locks that are supposed to be locked due to
an improper exit of the application.
Signed-off-by: Didier Pallard
---
lib/librte_pmd_ixgbe/ixgbe/ixgbe_82598.c | 30 +++
lib
e1000_init_mac_params_82571 function. Since I have no mean to test this
implementation, code is not modified for this hardware.
Signed-off-by: Didier Pallard
---
lib/librte_pmd_e1000/e1000/e1000_80003es2lan.c | 29 +
lib/librte_pmd_e1000/e1000/e1000_82575.c | 33
truction before rdtsc to
synchronize read operations and ensure that the TSC read is done at the expected
place.
Signed-off-by: Didier Pallard
---
Introduce a rte_rdtsc_precise function that adds lfence before reading tsc
counter.
lib/librte_eal/common/include/rte_
read operations and
ensure
that the read is done at the expected instant.
Signed-off-by: Didier Pallard
---
lib/librte_eal/common/include/rte_cycles.h |3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/librte_eal/common/include/rte_cycles.h
b/lib/librte_eal/common/include/rte_cycles.
malloc_elem structure adds a dependency between
rte_malloc.h and rte_memory.h; test source code are modified to
include both files in correct order.
Signed-off-by: Didier Pallard
---
app/test/test_hash.c|2 +-
app/test/test_hash_perf.c |2 +-
app/test/test_memcpy.c
48 matches
Mail list logo
