Re: [PATCH v2] eal: allow worker lcore stacks to be allocated from hugepage memory

On Fri, 13 May 2022 13:58:22 -0400 Don Wallwork wrote: > + if (internal_conf->huge_worker_stack_size == 0) { > + ret = pthread_create(&lcore_config[i].thread_id, NULL, > + eal_thread_loop, > +

Re: [PATCH v2] eal: allow worker lcore stacks to be allocated from hugepage memory

On Fri, 13 May 2022 13:58:22 -0400 Don Wallwork wrote: > +static int > +eal_parse_huge_worker_stack(const char *arg, size_t *huge_worker_stack_size) > +{ > + size_t worker_stack_size; > + if (arg == NULL) { > + *huge_worker_stack_size = USE_OS_STACK_SIZE; > + retur

Re: [PATCH v7] eal: fix rte_memcpy strict aliasing/alignment bugs

Hi David, > > Actually, looking again at the history, it fixes: > > Fixes: f5472703c0bd ("eal: optimize aligned memcpy on x86") > > Nop, that's probably even older, could you double check? > I'll hold on pushing this fix. It seems you still haven't received a response. I'll take a stab at this.

[PATCH v9 2/2] hash: unify crc32 selection for x86 and Arm

From: Pavan Nikhilesh Merge crc32 hash calculation public API implementation for x86 and Arm. Select the best available CRC32 algorithm when unsupported algorithm on a given CPU architecture is requested by an application. Previously, if an application directly includes `rte_crc_arm64.h` without

[PATCH v9 1/2] hash: split x86 and SW hash CRC intrinsics

From: Pavan Nikhilesh Split x86 and SW hash crc intrinsics into separate files. Signed-off-by: Pavan Nikhilesh Reviewed-by: Ruifeng Wang Acked-by: Yipeng Wang --- v9 Changes: - Fix forcing CRC32_SSE42_x64 as CRC alg even when CRC32_SSE42 is requested (Yipeng Wang). v8 Changes: - Instal

[PATCH v3 1/3] eventdev: add function to quiesce an event port

From: Pavan Nikhilesh Add function to quiesce any core specific resources consumed by the event port. When the application decides to migrate the event port to another lcore or teardown the current lcore it may to call `rte_event_port_quiesce` to make sure that all the data associated with the e

[PATCH v3 3/3] event/cnxk: implement event port quiesce function

From: Pavan Nikhilesh Implement event port quiesce function to clean up any lcore resources used. Signed-off-by: Pavan Nikhilesh --- drivers/event/cnxk/cn10k_eventdev.c | 78 ++--- drivers/event/cnxk/cn9k_eventdev.c | 60 +- 2 files changed, 130 ins

[PATCH v3 2/3] eventdev: update examples to use port quiesce

From: Pavan Nikhilesh Quiesce event ports used by the workers core on exit to free up any outstanding resources. Signed-off-by: Pavan Nikhilesh --- app/test-eventdev/test_perf_common.c | 8 app/test-eventdev/test_pipeline_common.c | 12 examples/eventdev_pipe

[PATCH v2] eal: allow worker lcore stacks to be allocated from hugepage memory

Add support for using hugepages for worker lcore stack memory. The intent is to improve performance by reducing stack memory related TLB misses and also by using memory local to the NUMA node of each lcore. EAL option '--huge-worker-stack [stack-size-in-KiB]' is added to allow the feature to be e

[PATCH v2 6/6] examples/ipsec-secgw: cleanup worker state before exit

From: Pavan Nikhilesh Event ports are configured to implicitly release the scheduler contexts currently held in the next call to rte_event_dequeue_burst(). A worker core might still hold a scheduling context during exit as the next call to rte_event_dequeue_burst() is never made. This might lead

[PATCH v2 5/6] examples/l2fwd-event: clean up worker state before exit

From: Pavan Nikhilesh Event ports are configured to implicitly release the scheduler contexts currently held in the next call to rte_event_dequeue_burst(). A worker core might still hold a scheduling context during exit, as the next call to rte_event_dequeue_burst() is never made. This might lead

[PATCH v2 4/6] examples/l3fwd: clean up worker state before exit

From: Pavan Nikhilesh Event ports are configured to implicitly release the scheduler contexts currently held in the next call to rte_event_dequeue_burst(). A worker core might still hold a scheduling context during exit, as the next call to rte_event_dequeue_burst() is never made. This might lead

[PATCH v2 3/6] examples/eventdev: clean up worker state before exit

From: Pavan Nikhilesh Event ports are configured to implicitly release the scheduler contexts currently held in the next call to rte_event_dequeue_burst(). A worker core might still hold a scheduling context during exit, as the next call to rte_event_dequeue_burst() is never made. This might lead

[PATCH v2 2/6] app/eventdev: clean up worker state before exit

From: Pavan Nikhilesh Event ports are configured to implicitly release the scheduler contexts currently held in the next call to rte_event_dequeue_burst(). A worker core might still hold a scheduling context during exit, as the next call to rte_event_dequeue_burst() is never made. This might lead

[PATCH v2 1/6] app/eventdev: simplify signal handling and teardown

From: Pavan Nikhilesh Remove rte_*_dev calls from signal handler callback as signal handlers are supposed to be light weight. Split ethernet device teardown into Rx and Tx sections, wait for workers to finish processing after disabling Rx to allow workers to complete processing currently held pa

Re: [PATCH v7 12/18] vdpa/ifc: add some log at vDPA launch before qemu connect

On Fri, 13 May 2022 08:34:38 + "Pei, Andy" wrote: > Hi Chenbo, > > Thanks for your reply. > My reply is inline. > > > -Original Message- > > From: Xia, Chenbo > > Sent: Thursday, May 12, 2022 9:53 PM > > To: Pei, Andy ; dev@dpdk.org > > Cc: maxime.coque...@redhat.com; Cao, Gang ; L

Re: [PATCH v3 1/8] eal: add initial support for RISC-V architecture

On Fri, 13 May 2022 08:50:34 +0200 Heinrich Schuchardt wrote: > On 5/10/22 17:48, Stanislaw Kardach wrote: > > From: Michal Mazurek > > > > Add all necessary elements for DPDK to compile and run EAL on SiFive > > Freedom U740 SoC which is based on SiFive U74-MC (ISA: rv64imafdc) > > core comple

Re: [PATCH v3 8/8] ci: add RISCV64 cross compilation job

Stanisław Kardach writes: > On Thu, 12 May 2022, 17:47 Aaron Conole, wrote: > > Stanislaw Kardach writes: > > > Checks cross-compilation using Ubuntu 20.04 x86. > > > > Signed-off-by: David Marchand > > Signed-off-by: Stanislaw Kardach > > --- > > .ci/linux-build.sh | 4

Re: [PATCH 6/6] examples/ipsec-secgw: cleanup worker state before exit

On Wed, Apr 27, 2022 at 2:45 AM Pavan Nikhilesh wrote: > > Event ports are configured to implicitly release the scheduler contexts > currently held in the next call to rte_event_dequeue_burst(). > A worker core might still hold a scheduling context during exit as the > next call to rte_event_deque

Re: [PATCH 2/6] app/eventdev: clean up worker state before exit

On Wed, Apr 27, 2022 at 2:44 AM Pavan Nikhilesh wrote: > > Event ports are configured to implicitly release the scheduler contexts > currently held in the next call to rte_event_dequeue_burst(). > A worker core might still hold a scheduling context during exit, as the > next call to rte_event_dequ

Re: [PATCH 1/6] app/eventdev: simplify signal handling and teardown

On Wed, Apr 27, 2022 at 2:44 AM Pavan Nikhilesh wrote: > > Remove rte_*_dev calls from signal handler callback. Pease adds the reason. > Split ethernet device teardown into Rx and Tx sections, wait for > workers to finish processing after disabling Rx to allow workers > to complete processing cu

Re: [PATCH 1/6] app/eventdev: simplify signal handling and teardown

On Wed, Apr 27, 2022 at 2:44 AM Pavan Nikhilesh wrote: > > Remove rte_*_dev calls from signal handler callback. > Split ethernet device teardown into Rx and Tx sections, wait for > workers to finish processing after disabling Rx to allow workers > to complete processing currently held packets. > >

Re: [PATCH v3 1/8] eal: add initial support for RISC-V architecture

On Fri, May 13, 2022 at 12:52 PM Heinrich Schuchardt wrote: > > On 5/13/22 10:42, Stanisław Kardach wrote: > > On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt > > wrote: > > > >>> +Linux kernel > >>> + > >>> + > >>> +It is recommended to use Linux kernel built from > >>> +`SiFive

Re: [PATCH] event/cnxk: fix base pointer for SSO head wait

On Fri, Mar 25, 2022 at 4:30 PM Volodymyr Fialko wrote: > > Function roc_sso_hws_head_wait() expects a base as input pointer, and it > will itself get tag_op from the base. By passing tag_op instead of base > pointer to this function will add SSOW_LF_GWS_TAG register offset twice, > which will lea

Re: [PATCH v3 1/8] eal: add initial support for RISC-V architecture

On 5/13/22 10:42, Stanisław Kardach wrote: On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt wrote: +Linux kernel + + +It is recommended to use Linux kernel built from +`SiFive Freedom Unleashed SDK `_. How would the Unleashed SDK help o

RE: [EXT] [PATCH 8/8] test/crypto: add short MAC-I test vector for zuc

> Add a ZUC based short MAC-I test vector. > > Signed-off-by: Gagandeep Singh Only test vector, where is the test case calling this? > --- > ...est_cryptodev_security_pdcp_test_vectors.h | 20 +-- > 1 file changed, 18 insertions(+), 2 deletions(-) > > diff --git a/app/test/test

Re: OVS DPDK DMA-Dev library/Design Discussion

On Fri, May 13, 2022 at 05:48:35PM +0800, fengchengwen wrote: > On 2022/5/13 17:10, Bruce Richardson wrote: > > On Fri, May 13, 2022 at 04:52:10PM +0800, fengchengwen wrote: > >> On 2022/4/8 14:29, Pai G, Sunil wrote: > -Original Message- > From: Richardson, Bruce > Sent: Tu

Re: [RFC PATCH 1/4] app/testpmd: register driver specific commands

On Fri, May 13, 2022 at 9:57 AM David Marchand wrote: > + TAILQ_FOREACH(parser, &cmdline_parsers, next) { > + for (i = 0; parser->ctx[i] != NULL; i++) { > + ctx = realloc(main_ctx, (count + i + 1) * > sizeof(*ctx)); > + if (ctx == NU

RE: [EXT] [PATCH 7/8] test/crypto: add external buffer test case

> Add a test case to verify crypto functionality > with external buffer. > > Signed-off-by: Gagandeep Singh > --- > app/test/test_cryptodev.c | 163 ++ > 1 file changed, 163 insertions(+) > > diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c

RE: [PATCH v7 14/18] vdpa/ifc: add interrupt and handle for virtio blk

HI Chenbo, Thanks for your reply. My reply is inline. > -Original Message- > From: Xia, Chenbo > Sent: Friday, May 13, 2022 10:53 AM > To: Pei, Andy ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Cao, Gang ; Liu, > Changpeng > Subject: RE: [PATCH v7 14/18] vdpa/ifc: add interrupt and

RE: [PATCH 1/1] drivers: define OPENSSL_API_COMPAT

> -Original Message- > From: Heinrich Schuchardt > Sent: 2022年5月10日 23:07 > To: Zhang, Roy Fan > Cc: Chandubabu Namburu ; dev@dpdk.org; Heinrich > Schuchardt > Subject: [PATCH 1/1] drivers: define OPENSSL_API_COMPAT > > The API of the OpenSSL library has changed with version 3.0. This

RE: [PATCH v2] net/ice: fix DCF state checking mechanism

> -Original Message- > From: peng1x.zh...@intel.com > Sent: Wednesday, May 11, 2022 4:50 PM > To: Yang, Qiming ; Zhang, Qi Z > ; dev@dpdk.org > Cc: Zhang, Peng1X ; sta...@dpdk.org > Subject: [PATCH v2] net/ice: fix DCF state checking mechanism > > From: Peng Zhang > > DCF state previous

RE: [EXT] [PATCH 3/8] examples/ipsec-secgw: support XCBC-MAC/DES-CBC

> ipsec-secgw application is updated to support > DES-CBC ciphering and XCBC-MAC authentication > based IPsec functionality. > > Signed-off-by: Gagandeep Singh > --- > examples/ipsec-secgw/esp.c | 5 + > examples/ipsec-secgw/sa.c | 8 > 2 files changed, 13 insertions(+) Documentati

RE: [EXT] [PATCH 2/8] app/test-crypto-perf: support SDAP for PDCP operations

> Add a command line option "--enable-sdap" to enable > Service Data Adaptation Protocol. > > example command: > ./dpdk-test-crypto-perf -c 0xc --log-level=8 -- > --devtype crypto_dpaa2_sec --optype pdcp --cipher-algo aes-ctr > --cipher-op encrypt --auth-algo zuc-eia3 --auth-op generate > --auth-

RE: [EXT] [PATCH 1/8] app/test-crypto-perf: improve dequeue logic

Hi Gagan, > Issue more dequeue commands if the gap between enqueued > and dequeued packets is more than burst size *8 > > Signed-off-by: Gagandeep Singh > --- Why is this change required? What gain are we getting? I see a performance drop due to this patch. > app/test-crypto-perf/cperf_test_thr

Re: OVS DPDK DMA-Dev library/Design Discussion

On Fri, May 13, 2022 at 04:52:10PM +0800, fengchengwen wrote: > On 2022/4/8 14:29, Pai G, Sunil wrote: > >> -Original Message- > >> From: Richardson, Bruce > >> Sent: Tuesday, April 5, 2022 5:38 PM > >> To: Ilya Maximets ; Chengwen Feng > >> ; Radha Mohan Chintakuntla ; > >> Veerasenareddy

Minutes of Technical Board Meeting, 2022-05-04

Minutes of Technical Board Meeting, 2022-May-04 Members Attending --- -Aaron -Bruce -Hemant -Honnappa -Jerin -Konstantin -Kevin (chair) -Maxime -Olivier -Stephen -Thomas NOTE: The technical board meetings are on every second Wednesday at https://meet.jit.si/DPDK at 3 pm U

RE: [PATCH v7 13/18] vdpa/ifc: read virtio max queues from hardware

Hi Chenbo, Thanks for your reply. This patch will be omitted in next version. > -Original Message- > From: Xia, Chenbo > Sent: Thursday, May 12, 2022 9:55 PM > To: Pei, Andy ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Cao, Gang ; Liu, > Changpeng > Subject: RE: [PATCH v7 13/18] vdp

[Bug 1009] [dpdk-22.07*] drivers/crypto/qat meson build failed with gcc 11.2.0 on Ub22.04/64

https://bugs.dpdk.org/show_bug.cgi?id=1009 Bug ID: 1009 Summary: [dpdk-22.07*] drivers/crypto/qat meson build failed with gcc 11.2.0 on Ub22.04/64 Product: DPDK Version: unspecified Hardware: All OS: All

[PATCH v2 2/2] example/vhost: support to clear in-flight packets for async dequeue

This patch allows vring_state_changed() to clear in-flight dequeue packets. It also clears the in-flight packets in a thread-safe way in destroy_device(). Signed-off-by: Yuan Wang --- examples/vhost/main.c | 26 +- 1 file changed, 21 insertions(+), 5 deletions(-) diff --

[PATCH v2 1/2] vhost: support clear in-flight packets for async dequeue

rte_vhost_clear_queue_thread_unsafe() supports to clear in-flight packets for async enqueue only. But after supporting async dequeue, this API should support async dequeue too. This patch also adds the thread-safe version of this API, the difference between the two API is that thread safety uses l

[PATCH v2 0/2] support to clear in-flight packets for async

These patches support to clear in-flight packets for async dequeue and introduce thread-safe version of this function. note: The patches depend on the following patches (http://patches.dpdk.org/project/dpdk/patch/20220513025058.12898-5-xuan.d...@intel.com/) (http://patches.dpdk.org/project/dpdk/pa

Re: [PATCH v3 1/8] eal: add initial support for RISC-V architecture

On Fri, May 13, 2022 at 8:50 AM Heinrich Schuchardt wrote: > > +Linux kernel > > + > > + > > +It is recommended to use Linux kernel built from > > +`SiFive Freedom Unleashed SDK `_. > > How would the Unleashed SDK help on a later board or a boa

RE: [PATCH v7 12/18] vdpa/ifc: add some log at vDPA launch before qemu connect

> -Original Message- > From: Pei, Andy > Sent: Friday, May 13, 2022 4:35 PM > To: Xia, Chenbo ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Cao, Gang ; Liu, > Changpeng > Subject: RE: [PATCH v7 12/18] vdpa/ifc: add some log at vDPA launch before > qemu connect > > Hi Chenbo, > > Than

RE: [PATCH v7 12/18] vdpa/ifc: add some log at vDPA launch before qemu connect

Hi Chenbo, Thanks for your reply. My reply is inline. > -Original Message- > From: Xia, Chenbo > Sent: Thursday, May 12, 2022 9:53 PM > To: Pei, Andy ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Cao, Gang ; Liu, > Changpeng > Subject: RE: [PATCH v7 12/18] vdpa/ifc: add some log at v

RE: [PATCH v7 09/18] examples/vdpa: add vDPA blk support in example

HI Chenbo, Thanks for your reply. My reply is inline. > -Original Message- > From: Xia, Chenbo > Sent: Thursday, May 12, 2022 9:34 PM > To: Pei, Andy ; dev@dpdk.org > Cc: maxime.coque...@redhat.com; Cao, Gang ; Liu, > Changpeng > Subject: RE: [PATCH v7 09/18] examples/vdpa: add vDPA blk

[RFC PATCH 2/4] net/bonding: move testpmd commands

Move related specific testpmd commands into this driver directory. While at it, fix checkpatch warnings. Signed-off-by: David Marchand --- app/test-pmd/cmdline.c | 1035 --- app/test-pmd/meson.build |3 - drivers/net/bonding/meson.build

[RFC PATCH 4/4] net/ixgbe: move testpmd commands

Move related specific testpmd commands into this driver directory. While at it, fix checkpatch warnings. The bypass code required some special init code before starting a port. This is removed from testpmd itself and a new (*untested*) command is added. Note: bypass commands were not compiled sin

[RFC PATCH 3/4] net/i40e: move testpmd commands

Move related specific testpmd commands into this driver directory. Signed-off-by: David Marchand --- app/test-pmd/cmdline.c | 665 drivers/net/i40e/i40e_testpmd.c | 655 +++ drivers/net/i40e/meson.build| 2 + 3 files cha

[RFC PATCH 1/4] app/testpmd: register driver specific commands

Introduce a testpmd API so that drivers can register specific commands. A driver can list some files to compile with testpmd, by setting them in the testpmd_sources (driver local) meson variable. drivers/meson.build then takes care of appending this to a global meson variable, and adding the drive

[RFC PATCH 0/4] Split driver specific commands out of testpmd

Hello, Following TB decision and recent discussions on the driver specific commands in testpmd, here is a proposal on how the split could be done. For now, this series simply moves the testpmd code in the driver directory. The driver specific testpmd code is still compiled as part of testpmd comp

[PATCH v3] net/i40e: fix max frame size config at port level

From: Wenxuan Wu Previously, max frame size can only be set when link is up, and the wait time is 1 sec. Startup time of 10G_BASET longer than 1s would result in failure. Acctually, max frame size of media type I40E_MEDIA_TYPE_BASET can be set regardless of link status. This patch omitted the l

RE: [PATCH v7 08/18] vdpa/ifc: add get device type ops to ifc driver

HI Chenbo, Thanks for your reply. I will implement a function "ifcvf_get_device_type" for both ifc net and blk ops. "ifcvf_get_device_type" will return device type according to internal->device_type. > -Original Message- > From: Xia, Chenbo > Sent: Thursday, May 12, 2022 9:41 PM > To:

[PATCH v1 4/4] net/mlx5: add validation for yellow meter action

Yellow meter action support is added in meter hierarchy validation. If one color uses meter action, the other can only use NULL action or the same meter action. And only shared meter is supported. Signed-off-by: Shun Hao Acked-by: Matan Azard --- doc/guides/nics/mlx5.rst| 6 +++-- driv

[PATCH v1 3/4] net/mlx5: support yellow meter action for hierarchy tag rule

When a hierarchy meter is shared by other ports, it's needed to iterate all meter policies in hierarchy to create tag rules, to set packet with next meter ID, which will be used by related meter drop count. This patch adds the tag rule for yellow support in hierarchy, so both green/yellow policy fl

[PATCH v1 2/4] net/mlx5: support yellow meter action in hierarchy

This patch adds the support of meter action for yellow meter policy flow, so can use meter action for both green and yellow policy flows in meter hierarchy. Currently must use the same meter within one meter policy. Packets passing green/yellow policy flow will have previous meter color of green/ye

[PATCH v1 1/4] net/mlx5: support previous meter color aware

This patch adds the support for previous color aware for meter. Start_color setting is set to UNDEFINED when creating meter object that is color aware. Signed-off-by: Shun Hao Acked-by: Matan Azard --- drivers/net/mlx5/mlx5.h| 2 ++ drivers/net/mlx5/mlx5_flow_aso.c | 19 +

[PATCH v1 0/4] Enable yellow meter hierarchy

To support yellow meter hierarchy, need to support meter action in yellow policy flow, so both green and yellow packet can go to next meter. Currently there's the limitation that only the same next meter supported for green and yellow. Meanwhile, color aware mode is supported, so the next meter ca

[PATCH v6 7/7] test/security: add inline IPsec IPv6 flow label cases

From: Vamsi Attunuru Patch adds unit tests for IPv6 flow label set & copy operations. Signed-off-by: Vamsi Attunuru Acked-by: Fan Zhang --- app/test/test_cryptodev_security_ipsec.c | 35 ++- app/test/test_cryptodev_security_ipsec.h | 10 +++ app/test/test_security_inline_proto.c|

[PATCH v6 6/7] test/security: add ESN and anti-replay cases for inline

Added cases to test anti replay for inline IPsec processing with and without extended sequence number support. Signed-off-by: Akhil Goyal Acked-by: Fan Zhang --- app/test/test_security_inline_proto.c | 311 ++ 1 file changed, 311 insertions(+) diff --git a/app/test/test

[PATCH v6 5/7] test/security: add more inline IPsec functional cases

Added more inline IPsec functional verification cases. These cases do not have known vectors but are verified using encap + decap test for all the algo combinations. Signed-off-by: Akhil Goyal Acked-by: Fan Zhang --- app/test/test_security_inline_proto.c | 517 ++ 1 file

[PATCH v6 4/7] test/security: add inline IPsec reassembly cases

Added unit test cases for IP reassembly of inline IPsec inbound scenarios. In these cases, known test vectors of fragments are first processed for inline outbound processing and then received back on loopback interface for inbound processing along with IP reassembly of the corresponding decrypted p

[PATCH v6 3/7] test/security: add combined mode inline IPsec cases

Added combined encap and decap test cases for various algorithm combinations Signed-off-by: Akhil Goyal Acked-by: Fan Zhang --- app/test/test_security_inline_proto.c | 102 ++ 1 file changed, 102 insertions(+) diff --git a/app/test/test_security_inline_proto.c b/app/te

[PATCH v6 2/7] test/security: add inline inbound IPsec cases

Added test cases for inline Inbound protocol offload verification with known test vectors from Lookaside mode. Signed-off-by: Akhil Goyal Acked-by: Fan Zhang --- app/test/test_security_inline_proto.c | 65 +++ 1 file changed, 65 insertions(+) diff --git a/app/test/test_

[PATCH v6 1/7] app/test: add unit cases for inline IPsec offload

A new test suite is added in test app to test inline IPsec protocol offload. In this patch, predefined vectors from Lookaside IPsec test are used to verify the IPsec functionality without the need of external traffic generators. The sent packet is loopbacked onto the same interface which is receive

[PATCH v6 0/7] app/test: add inline IPsec and reassembly cases

IP reassembly offload was added in last release. The test app for unit testing IP reassembly of inline inbound IPsec flows is added in this patchset. For testing IP reassembly, base inline IPsec is also added. The app is enhanced in v4 to handle more functional unit test cases for inline IPsec simi