Dmitry Eremin-Solenikov(lumag) replied on github web page:
configure.ac
@@ -172,6 +172,16 @@ AS_IF([test "${with_platform}" = "linux-generic"],
AC_DEFINE_UNQUOTED([IMPLEMENTATION_NAME], ["$IMPLEMENTATION_NAME"],
[Define to the name of the implementation])
From: Michal Mazur
Implement support in dpdk_pool_info function to provide
address range of pool data available for application.
Pull request of related API change:
https://github.com/Linaro/odp/pull/200
Signed-off-by: Michal Mazur
---
/** Email created
From: Ilias Apalodimas
* typedef struct { } ODP_ALIGN() test_t; is correct
* typedef struct ODP_ALIGN() {} test_t; is correct and
preferred from gcc standards
* typedef struct {} test_t ODP_ALIGN() discards align
Had segfauls
From: Matias Elo
odp_pktio_stats_t.out_octets was updated incorrectly if all packets were
not successfully enqueued.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
**
From: Matias Elo
Some NICs do not automatically drop packets which exceed MTU.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
Enable Linux helpers by default as e.g. OFP uses those. Build
and test helper code does not add significant overhead, but
catches potential issues early.
Signed-off-by: Petri Savolainen petri.savolai...@linaro.org
github
/** Email created from pull request
Refresh Linaro copyrights to more indicate in source code that ODP code is
freshly maintained and developed.
Signed-off-by: Maxim Uvarov maxim.uva...@linaro.org
github
/** Email created from pull request 399 (muvarov:api-next_copyrights)
**
From: Dmitry Eremin-Solenikov
Distributions won't like statically-linked binaries. Provide configure
switch to link examples and tests dynamically.
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull
Distributions won't like statically-linked binaries. Provide configure switch
to link examples and tests dynamically.
github
/** Email created from pull request 390 (lumag:dynamic-link-tests)
** https://github.com/Linaro/odp/pull/390
** Patch:
From: Matias Elo
Drop truncated packets received from kernel during sock_mmsg_recv() call.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
From: Dmitry Eremin-Solenikov
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull request 390 (lumag:dynamic-link-tests)
** https://github.com/Linaro/odp/pull/390
** Patch:
From: Petri Savolainen
Enable Linux helpers by default as e.g. OFP uses those. Build
and test helper code does not add significant overhead, but
catches potential issues early.
Signed-off-by: Petri Savolainen
---
/** Email created from
* typedef struct { } ODP_ALIGN() test_t; is correct
* typedef struct ODP_ALIGN() {} test_t; is correct and
preferred from gcc standards
* typedef struct {} test_t ODP_ALIGN() discards align
Had segfaults on gcc-7 using that
Signed-off-by: Ilias Apalodimas ilias.apalodi...@linaro.org
From: Matias Elo
Allocating enough memory for storing each packet in the packet pool in each
RX/TX block wastes a lot of memory. Also, the following mmap() call in
mmap_sock() can start failing when the number of memory blocks increases
(large number of CPU cores). Reduce
From: Matias Elo
Use more realistic MTU value. The value is also checked in TX.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
github
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch: https://github.com/Linaro/odp/pull/397.patch
** Base sha: 520c170d758f2d37554631bf1467ec50e027cd3e
** Merge commit sha:
From: Matias Elo
Some NICs do not automatically drop packets which exceed MTU.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
From: Matias Elo
During sock_mmap_send() when all packets are not transmitted by sendto()
call the used ring slots have to be marked as TP_STATUS_AVAILABLE or they
will be transmitted during the next sock_mmap_send() call, thus breaking
the function logic.
To reduce the
From: Matias Elo
The maximum frame length should include Ethernet header.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
From: Ilias Apalodimas
Signed-off-by: Ilias Apalodimas
Signed-off-by: Mykyta Iziumtsev
---
/** Email created from pull request 383 (MykytaI:caterpillar_mdev_cxgb4)
** https://github.com/Linaro/odp/pull/383
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
Dmitry Eremin-Solenikov(lumag) replied on github web page:
include/odp/api/spec/ipsec.h
line 8
@@ -232,6 +232,12 @@ typedef struct odp_ipsec_capability_t {
*/
odp_support_t pipeline_cls;
+ /** Implementation will automatically truncate TFC padding in received
+*
From: Dmitry Eremin-Solenikov
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull request 342 (lumag:openssl-ctx)
** https://github.com/Linaro/odp/pull/342
** Patch:
Dmitry Eremin-Solenikov(lumag) replied on github web page:
include/odp/api/spec/ipsec.h
line 36
@@ -1223,9 +1223,12 @@ typedef struct odp_ipsec_status_t {
* Each successfully transformed packet has a valid value for these metadata
* regardless of the inner packet parse configuration
*
This PR is basically cxgb4 driver + PR380. As soon as PR380 gets merged -- this
PR will be rebased so that only one patch remains for the merge.
github
/** Email created from pull request 383 (MykytaI:caterpillar_mdev_cxgb4)
**
https://bugs.linaro.org/show_bug.cgi?id=3576
Bug ID: 3576
Summary: classification: CoS queues in invalid table index
Product: OpenDataPlane - linux- generic reference
Version: master
Hardware: Other
OS: Linux
From: Dmitry Eremin-Solenikov
Per idea of Janne Peltonen, do not allocate/free crypto contexts for
each operation, providing significant speed increase. Each thread
on startup allocates hmac+cipher contexts pair for each crypto session.
Then they are
From: Dmitry Eremin-Solenikov
There is no point in having odp_crypto_generic_session_t definition in
global include file. Move it to odp_crypto module.
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
Branch: refs/heads/master
Home: https://github.com/Linaro/odp
Commit: e3cef11dd0161d49dddc09d8e6263722825953f7
https://github.com/Linaro/odp/commit/e3cef11dd0161d49dddc09d8e6263722825953f7
Author: Juha-Matti Tilli
Date: 2018-01-17 (Wed, 17 Jan 2018)
From: Mykyta Iziumtsev
Signed-off-by: Mykyta Iziumtsev
---
/** Email created from pull request 380 (MykytaI:caterpillar_mdev_i40e)
** https://github.com/Linaro/odp/pull/380
** Patch: https://github.com/Linaro/odp/pull/380.patch
**
@JannePeltonen
This is the promised OpenSSL CTX rework, bringing significant crypto speedup
github
/** Email created from pull request 342 (lumag:openssl-ctx)
** https://github.com/Linaro/odp/pull/342
** Patch: https://github.com/Linaro/odp/pull/342.patch
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Add mediated i40e driver along with common mdev code.
github
/** Email created from pull request 380 (MykytaI:caterpillar_mdev_i40e)
** https://github.com/Linaro/odp/pull/380
** Patch: https://github.com/Linaro/odp/pull/380.patch
** Base sha:
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-generic/odp_ipsec_sad.c
line 12
@@ -303,13 +303,15 @@ odp_ipsec_sa_t odp_ipsec_sa_create(const
odp_ipsec_sa_param_t *param)
case ODP_CIPHER_ALG_3DES_CBC:
ipsec_sa->esp_iv_len = 8;
GBalakrishna replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
+"crypto_openssl" --vdev
As discussed during yesterdays ODP call, these are the capabilities of Inside
Secure IPsec hardware.
First, it's important to establish that we don't have just 1 IPsec solution, we
have a whole family of solutions spanning various cost/performance/feature
trade-offs.
In least-to-most
Petri Savolainen(psavol) replied on github web page:
platform/linux-generic/odp_packet.c
line 51
@@ -1259,7 +1260,15 @@ int odp_packet_input_index(odp_packet_t pkt)
void odp_packet_user_ptr_set(odp_packet_t pkt, const void *ptr)
{
- packet_hdr(pkt)->buf_hdr.user_ptr = ptr;
+
Petri Savolainen(psavol) replied on github web page:
platform/linux-generic/include/odp/api/plat/packet_types.h
line 6
@@ -67,101 +67,89 @@ typedef enum {
#endif
-/** @internal Packet field accessor */
+/** @cond _ODP_HIDE_FROM_DOXYGEN_ */
+
Comment:
This a section label for doxygen. We'll
bogdanPricope replied on github web page:
example/Makefile.inc
line 7
@@ -13,4 +13,8 @@ AM_CFLAGS = \
-I$(top_srcdir)/platform/@with_platform@/arch/@ARCH_DIR@ \
-I$(top_builddir)/include
+if STATIC_LINK
AM_LDFLAGS = -L$(LIB) -static
+else
+AM_LDFLAGS =
Comment:
I am using
Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page:
platform/linux-dpdk/pool/dpdk.c
line 15
@@ -538,13 +538,19 @@ static void dpdk_pool_print(odp_pool_t pool_hdl)
static int dpdk_pool_info(odp_pool_t pool_hdl, odp_pool_info_t *info)
{
pool_entry_cp_t *pool_cp =
From: Dmitry Eremin-Solenikov
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull request 402 (lumag:travis-upd)
** https://github.com/Linaro/odp/pull/402
** Patch:
From: Dmitry Eremin-Solenikov
Add testcase compiling and running ODP with shared DPDK lib
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull request 402 (lumag:travis-upd)
**
From: Dmitry Eremin-Solenikov
All other tests do not use doxygen. So let's compile doxygen only for
doxygen test, saving few minutes.
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email created from pull request 402
From: Dmitry Eremin-Solenikov
If installation of cross-packages fails, installation will abort with
obscure error message. Stop early providing more precise "error" point.
Signed-off-by: Dmitry Eremin-Solenikov
---
/** Email
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Branch: refs/heads/caterpillar
Home: https://github.com/Linaro/odp
Commit: 944c6bf6c2eaea883ba943fa1513d1f3e5c7c334
https://github.com/Linaro/odp/commit/944c6bf6c2eaea883ba943fa1513d1f3e5c7c334
Author: Mykyta Iziumtsev
Date: 2018-01-18 (Thu, 18
From: Matias Elo
odp_pktio_stats_t.out_octets was updated incorrectly if all packets were
not successfully enqueued.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
**
From: Matias Elo
The maximum frame length should include Ethernet header.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
muvarov replied on github web page:
platform/linux-generic/pktio/socket.c
line 14
@@ -643,6 +643,10 @@ static int sock_mmsg_recv(pktio_entry_t *pktio_entry, int
index ODP_UNUSED,
uint16_t pkt_len = msgvec[i].msg_len;
int ret;
+ if
muvarov replied on github web page:
platform/linux-generic/pktio/socket_mmap.c
line 46
@@ -202,6 +202,12 @@ static inline unsigned pkt_mmap_v2_rx(pktio_entry_t
*pktio_entry,
pkt_buf = (uint8_t *)ppd.raw + ppd.v2->tp_h.tp_mac;
pkt_len = ppd.v2->tp_h.tp_snaplen;
+
Stanislaw Kardach(semihalf-kardach-stanislaw) replied on github web page:
include/odp/api/spec/packet_io.h
line 25
@@ -884,14 +887,19 @@ int odp_pktin_recv(odp_pktin_queue_t queue, odp_packet_t
packets[], int num);
* @param numMaximum number of packets to receive
* @param
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 41
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 171
@@ -663,76 +666,105 @@ int odp_crypto_auth_capability(odp_auth_alg_t auth,
return idx;
}
-static int get_crypto_dev(struct rte_crypto_sym_xform *cipher_xform,
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 238
@@ -784,8 +832,9 @@ int odp_crypto_session_create(odp_crypto_session_param_t
*param,
uint8_t cdev_id = 0;
struct rte_crypto_sym_xform cipher_xform;
struct
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 26
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
GBalakrishna replied on github web page:
platform/linux-generic/odp_ipsec_sad.c
line 12
@@ -303,13 +303,15 @@ odp_ipsec_sa_t odp_ipsec_sa_create(const
odp_ipsec_sa_param_t *param)
case ODP_CIPHER_ALG_3DES_CBC:
ipsec_sa->esp_iv_len = 8;
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 171
@@ -663,76 +666,105 @@ int odp_crypto_auth_capability(odp_auth_alg_t auth,
return idx;
}
-static int get_crypto_dev(struct rte_crypto_sym_xform *cipher_xform,
-
GBalakrishna replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
+"crypto_openssl" --vdev
Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page:
include/odp/api/spec/ipsec.h
@@ -1206,6 +1210,14 @@ typedef struct odp_ipsec_status_t {
* restored. The amount and content of packet data before the IP header is
* undefined.
*
+ * Additional TFC padding might be present
Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page:
include/odp/api/spec/ipsec.h
@@ -1293,6 +1297,10 @@ int odp_ipsec_in(const odp_packet_t pkt_in[], int num_in,
* with IPSEC, etc headers constructed according to the standards. The amount
* and content of packet data before the
Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page:
include/odp/api/spec/ipsec.h
line 8
@@ -232,6 +232,12 @@ typedef struct odp_ipsec_capability_t {
*/
odp_support_t pipeline_cls;
+ /** Implementation will automatically truncate TFC padding in received
+
Bill Fischofer(Bill-Fischofer-Linaro) replied on github web page:
include/odp/api/spec/ipsec.h
line 36
@@ -1223,9 +1223,12 @@ typedef struct odp_ipsec_status_t {
* Each successfully transformed packet has a valid value for these metadata
* regardless of the inner packet parse configuration
Pascal Van Leeuwen wrote:
> I get the impression that
> the IPsec payload can just be random garbage, i.e. it doesn't have to decrypt
> to anything
> that makes sense and it doesn't have to authenticate properly (to facilitate
> fast
> generation of such packets by skipping actual cryptographic
> Pascal Van Leeuwen wrote:
> > I get the impression that
> > the IPsec payload can just be random garbage, i.e. it doesn't have to
> > decrypt to anything that makes sense and it doesn't have to
> > authenticate properly (to facilitate fast generation of such packets by
> skipping actual
From: Matias Elo
Allocating enough memory for storing each packet in the packet pool in each
RX/TX block wastes a lot of memory. Also, the following mmap() call in
mmap_sock() can start failing when the number of memory blocks increases
(large number of CPU cores). Reduce
From: Matias Elo
Use more realistic MTU value. The value is also checked in TX.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
Petri Savolainen(psavol) replied on github web page:
helper/m4/configure.m4
@@ -8,14 +8,13 @@ AC_ARG_ENABLE([test-helper],
AM_CONDITIONAL([test_helper], [test x$test_helper = xyes ])
##
-# Enable/disable helper-ext
-#
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 26
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
test/performance/odp_crypto.c
line 17
@@ -45,6 +45,21 @@ static uint8_t test_key24[24] = { 0x01, 0x02, 0x03, 0x04,
0x05,
0x15, 0x16, 0x17, 0x18
};
+static uint8_t test_key64[64] = { 0x01, 0x02, 0x03,
GBalakrishna replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
+"crypto_openssl" --vdev
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 41
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 171
@@ -663,76 +666,105 @@ int odp_crypto_auth_capability(odp_auth_alg_t auth,
return idx;
}
-static int get_crypto_dev(struct rte_crypto_sym_xform *cipher_xform,
- struct
muvarov replied on github web page:
platform/linux-generic/pktio/null.c
line 97
@@ -0,0 +1,214 @@
+/* Copyright (c) 2017, Linaro Limited
+ * All rights reserved.
+ *
+ * SPDX-License-Identifier: BSD-3-Clause
+ */
+
+#include "config.h"
+
+#include
+
+#include
+#include
+#include
+#include
GBalakrishna replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
muvarov replied on github web page:
platform/linux-generic/pktio/null.c
line 97
@@ -0,0 +1,214 @@
+/* Copyright (c) 2017, Linaro Limited
+ * All rights reserved.
+ *
+ * SPDX-License-Identifier: BSD-3-Clause
+ */
+
+#include "config.h"
+
+#include
+
+#include
+#include
+#include
+#include
From: Matias Elo
Drop truncated packets received from kernel during sock_mmsg_recv() call.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
From: Matias Elo
Some NICs do not automatically drop packets which exceed MTU.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
muvarov replied on github web page:
helper/m4/configure.m4
@@ -8,14 +8,13 @@ AC_ARG_ENABLE([test-helper],
AM_CONDITIONAL([test_helper], [test x$test_helper = xyes ])
##
-# Enable/disable helper-ext
-# platform specific
Petri Savolainen(psavol) replied on github web page:
helper/m4/configure.m4
@@ -8,14 +8,13 @@ AC_ARG_ENABLE([test-helper],
AM_CONDITIONAL([test_helper], [test x$test_helper = xyes ])
##
-# Enable/disable helper-ext
-#
bogdanPricope replied on github web page:
configure.ac
line 7
@@ -172,6 +172,16 @@ AS_IF([test "${with_platform}" = "linux-generic"],
AC_DEFINE_UNQUOTED([IMPLEMENTATION_NAME], ["$IMPLEMENTATION_NAME"],
[Define to the name of the implementation])
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 62
@@ -615,7 +618,7 @@ int odp_crypto_auth_capability(odp_auth_alg_t auth,
while (cap->op != RTE_CRYPTO_OP_TYPE_UNDEFINED) {
cap_auth_algo = cap->sym.auth.algo;
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 333
@@ -855,48 +924,51 @@ int odp_crypto_session_create(odp_crypto_session_param_t
*param,
auth_xform.auth.key.length = 0;
}
+ auth_xform.auth.digest_length = 0;
+
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 215
@@ -776,6 +808,22 @@ static int get_crypto_dev(struct rte_crypto_sym_xform
*cipher_xform,
return -1;
}
+static void set_chain_order(struct rte_crypto_sym_xform **first_xform,
+
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-generic/odp_ipsec_sad.c
line 12
@@ -303,13 +303,15 @@ odp_ipsec_sa_t odp_ipsec_sa_create(const
odp_ipsec_sa_param_t *param)
case ODP_CIPHER_ALG_3DES_CBC:
ipsec_sa->esp_iv_len = 8;
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Petri Savolainen(psavol) replied on github web page:
helper/m4/configure.m4
line 14
@@ -8,14 +8,13 @@ AC_ARG_ENABLE([test-helper],
AM_CONDITIONAL([test_helper], [test x$test_helper = xyes ])
##
-# Enable/disable
github
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch: https://github.com/Linaro/odp/pull/397.patch
** Base sha: 520c170d758f2d37554631bf1467ec50e027cd3e
** Merge commit sha:
From: Matias Elo
During sock_mmap_send() when all packets are not transmitted by sendto()
call the used ring slots have to be marked as TP_STATUS_AVAILABLE or they
will be transmitted during the next sock_mmap_send() call, thus breaking
the function logic.
To reduce the
From: Matias Elo
Some NICs do not automatically drop packets which exceed MTU.
Signed-off-by: Matias Elo
---
/** Email created from pull request 397 (matiaselo:dev/pktio_fixes)
** https://github.com/Linaro/odp/pull/397
** Patch:
Petri Savolainen(psavol) replied on github web page:
include/odp/api/spec/packet_io.h
line 25
@@ -884,14 +887,19 @@ int odp_pktin_recv(odp_pktin_queue_t queue, odp_packet_t
packets[], int num);
* @param numMaximum number of packets to receive
* @param wait Wait time
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/odp_crypto.c
line 19
@@ -122,29 +130,24 @@ static int auth_alg_odp_to_rte(odp_auth_alg_t auth_alg,
case ODP_AUTH_ALG_MD5_96:
#endif
auth_xform->auth.algo = RTE_CRYPTO_AUTH_MD5_HMAC;
-
Dmitry Eremin-Solenikov(lumag) replied on github web page:
platform/linux-dpdk/test/wrapper-script.sh
line 5
@@ -1,6 +1,7 @@
#!/bin/bash
-export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 --vdev "crypto_openssl"}
+export ODP_PLATFORM_PARAMS=${ODP_PLATFORM_PARAMS:--n 4 "--vdev \
Dmitry Eremin-Solenikov(lumag) replied on github web page:
test/performance/odp_crypto.c
line 35
@@ -226,6 +241,18 @@ static crypto_alg_config_t algs_config[] = {
.auth_digest_len = 12,
},
},
+ {
+ .name = "null-hmac-md5-96",
+
98 matches
Mail list logo