[PATCH] ethdev: convert string initialization

) 15.0.0 20241003 (experimental) [2] ../lib/ethdev/rte_flow.h:906:36: error: initializer-string for array of ‘unsigned char’ is too long [-Werror=unterminated-string-initialization] 906 | .hdr.dst_addr.addr_bytes = "\xff\xff\xff\xff\xf

Re: [PATCH v4 1/6] eventdev: introduce event pre-scheduling

On Tue, Oct 1, 2024 at 7:44 PM wrote: > > From: Pavan Nikhilesh > > Event pre-scheduling improves scheduling performance by assigning events > to event ports in advance when dequeues are issued. > The dequeue operation initiates the pre-schedule operation, which completes > in parallel without af

Re: [PATCH] net/gve: always attempt Rx refill on DQ

On 10/2/2024 12:45 AM, Joshua Washington wrote: > Before this patch, gve_rx_refill_dqo() is only called if the number of > packets received in a cycle is non-zero. However, in a > memory-constrained scenario, this doesn't behave well, as this could be > a potential source of lockup, if there is no

Re: [PATCH] app/testpmd: show output of commands read from file

On 8/22/2024 11:36 AM, Bruce Richardson wrote: > Testpmd supports the "--cmdline-file" parameter to read a set of initial > commands from a file. However, the only indication that this has been > done successfully on startup is a single-line message, no output from > the commands is seen. > > To i

Re: [PATCH] app/testpmd: show output of commands read from file

On 10/4/2024 5:55 AM, Ferruh Yigit wrote: > On 8/22/2024 11:36 AM, Bruce Richardson wrote: >> Testpmd supports the "--cmdline-file" parameter to read a set of initial >> commands from a file. However, the only indication that this has been >> done successfully on startup is a single-line message, n

Re: [PATCH v4 2/6] eventdev: add event port pre-schedule modify

On Tue, Oct 1, 2024 at 7:14 PM wrote: > > From: Pavan Nikhilesh > > Some event devices allow pre-schedule types to be modified at > runtime on an event port. > Add `RTE_EVENT_DEV_CAP_EVENT_PER_PORT_PRESCHEDULE` capability > to indicate that the event device supports this feature. > > Add `rte_eve

Re: [PATCH v2 1/3] app/testpmd: add register keyword

On 9/6/2024 2:02 PM, Varghese, Vipin wrote: > [AMD Official Use Only - AMD Internal Distribution Only] > > >   >> > > >> --- a/app/test-pmd/macswap_sse.h >> > > >> +++ b/app/test-pmd/macswap_sse.h >> > > >> @@ -16,13 +16,13 @@ do_macswap(struct rte_mbuf *pkts[], uint16_t >> nb, >> > > >>    u

Re: [PATCH v2 0/3] app/testpmd: improve sse based macswap

On 8/21/2024 3:38 PM, Vipin Varghese wrote: > Goal of the patch series is to improve SSE macswap on x86_64 by > reducing the stalls in backend engine. Original implementation of > the SSE-mac-swap makes loop call to multiple load, shuffle & store. > > Using SIMD ISA interleaving, register variable

Re: [PATCH 0/4] Support new card using NFP 3800 chip

On 9/3/2024 2:41 AM, Chaoyong He wrote: > This patch series add support of a new card which using the NFP 3800 chip. > Because it has different configure BAR size and flow steering rules > limit, we also do some refactor to the related logic. > > Chaoyong He (4): > net/nfp: add a new flag to ind

Re: [PATCH] doc: update TAP device features

On 10/4/2024 3:26 AM, Stephen Hemminger wrote: > On Fri, 4 Oct 2024 02:48:21 +0100 > Ferruh Yigit wrote: > >> On 9/4/2024 4:42 PM, Stephen Hemminger wrote: >>> The TAP device does have per-queue stats and handles multi-process. >>> >>> Signed-off-by: Stephen Hemminger >>> --- >>> doc/guides/nic

Re: [PATCH] net/gve: fix mbuf allocation memory leak for DQ Rx

On 10/2/2024 12:48 AM, Joshua Washington wrote: > Currently, gve_rxq_mbufs_alloc_dqo() allocates RING_SIZE buffers, but > only posts RING_SIZE - 1 of them, inevitably leaking a buffer every > time queues are stopped/started. This could eventually lead to running > out of mbufs if an application sto

Re: [PATCH v2] app/testpmd: show output of commands read from file

On 8/22/2024 11:41 AM, Bruce Richardson wrote: > Testpmd supports the "--cmdline-file" parameter to read a set of initial > commands from a file. However, the only indication that this has been > done successfully on startup is a single-line message, no output from > the commands is seen. > > To i

Re: [PATCH v4 3/6] eventdev: add SW event preschedule hint

On Wed, Oct 2, 2024 at 2:19 AM wrote: > > From: Pavan Nikhilesh > > Add a new eventdev API to provide a hint to the eventdev PMD to > pre-schedule the next event into the event port, without releasing > the current flow context. > Event device that support this feature advertises the capability >

Re: [RFC PATCH] app/testpmd: display TM parameters when adding nodes

On 8/12/2024 2:26 PM, Bruce Richardson wrote: > The commands to add TM nodes and shapers take many parameters without > any descriptive words in between to identify what parameter is what. To > help make it clear what a command is actually doing, and to help catch > any issues with parameters put i

[PATCH v5 3/6] crypto/cnxk: support EDDSA

Support EDDSA crypto algorithm in CNXK PMD. Signed-off-by: Gowrishankar Muthukrishnan --- v5: - long line fixed. --- doc/guides/cryptodevs/features/cn10k.ini | 1 + drivers/common/cnxk/hw/cpt.h | 3 +- drivers/common/cnxk/roc_ae.c | 52 +- drivers/com

[PATCH v5 1/6] cryptodev: add EDDSA asymmetric crypto algorithm

Add support for asymmetric EDDSA in cryptodev, as referenced in RFC: https://datatracker.ietf.org/doc/html/rfc8032 Signed-off-by: Gowrishankar Muthukrishnan --- doc/guides/cryptodevs/features/default.ini | 1 + doc/guides/prog_guide/cryptodev_lib.rst| 2 +- lib/cryptodev/rte_crypto_asym.h

Re: [PATCH] net/nfp: reserve BAR for expansion ROM

On 9/3/2024 3:34 AM, Chaoyong He wrote: > For some platform, the warm restart of host doesn't trigger > the reset of NIC, which causes the initialize process of NIC > not executed with the right expansion ROM mapping. Consequently, > the PXE boot won't work in this case. > > Now reserve BAR 2.0 wh

[PATCH v5 4/6] test/crypto: add asymmetric EDDSA test cases

Add test cases to validate EDDSA sign and verify ops, as per RFC 8032. Signed-off-by: Gowrishankar Muthukrishnan --- app/test/test_cryptodev_asym.c | 345 +++- app/test/test_cryptodev_ecdh_test_vectors.h | 94 +++- app/test/test_cryptodev_ecdsa_test_vectors.h | 4 + app

[PATCH v5 5/6] examples/fips_validation: support EDDSA

Add EDDSA support in fips_validation app. Signed-off-by: Gowrishankar Muthukrishnan --- examples/fips_validation/fips_validation.c| 2 + examples/fips_validation/fips_validation.h| 23 ++ .../fips_validation/fips_validation_eddsa.c | 307 + examples/fips_validation/m

[PATCH v5 2/6] crypto/openssl: support EDDSA

Support EDDSA crypto algorithm in OpenSSL PMD. Signed-off-by: Gowrishankar Muthukrishnan --- v5: - fixed compilation error due to RTE_LOG_CHECK_NO_NEWLINE. --- doc/guides/cryptodevs/features/openssl.ini | 1 + drivers/crypto/openssl/openssl_pmd_private.h | 13 ++ drivers/crypto/openssl/rte

[PATCH v5 6/6] app/crypto-perf: support EDDSA

Added support for EDDSA 25519 curve SIGN and VERIFY operations. Signed-off-by: Gowrishankar Muthukrishnan --- app/test-crypto-perf/cperf_ops.c | 52 app/test-crypto-perf/cperf_options.h | 2 + app/test-crypto-perf/cperf_options_parsing.c | 9 +++- app/t

[PATCH v2 2/2] cryptodev: move RSA padding information into xform

RSA padding information could be a xform entity rather than part of crypto op, as it seems associated with hashing algorithm used for the entire crypto session, where this algorithm is used in message digest itself. Even in virtIO standard spec, this info is associated in the asymmetric session cre

[PATCH v2 1/2] cryptodev: fix RSA xform for ASN.1 syntax

As per ASN.1 syntax (RFC 3447 Appendix A.1.2), RSA private key would need specification of quintuple along with private exponent. It is up to the implementation to internally handle, but not at RTE itself to make them exclusive each other. Removing union on them allows asymmetric implementation in

[PATCH v2 0/2] cryptodev: fix RSA xform to support VirtIO standard

In this series of patches, RSA crypto xform is fixed to support VirtIO standard. Changes: v2: - Decoupled spec related patches into this series from v1. Gowrishankar Muthukrishnan (2): cryptodev: fix RSA xform for ASN.1 syntax cryptodev: move RSA padding information into xform app/test/t

Re: [PATCH 0/3] support load firmware from flash

On 9/3/2024 6:52 AM, Chaoyong He wrote: > This patch series add the needed logic to support load firmware from the > flash in card. > > Chaoyong He (3): > net/nfp: fix potential problem on certain version BSP > net/nfp: add two APIs of the NSP module > net/nfp: support load firmware from fla

[PATCH v4 1/2] ipsec: allow stateless IPsec processing

Introduce stateless packet preparation API for IPsec processing. The new API would allow preparation of IPsec packets without altering the internal state of an IPsec session. For outbound IPsec processing, the change enables user to provide sequence number to be used for the IPsec operation. Sign

[PATCH v4 2/2] test/ipsec: add unit test for stateless processing

Add unit test for IPsec stateless processing. Signed-off-by: Aakash Sasidharan --- app/test/test_ipsec.c | 113 -- 1 file changed, 99 insertions(+), 14 deletions(-) diff --git a/app/test/test_ipsec.c b/app/test/test_ipsec.c index 6cb1bac1e7..ac63c3b6d3 10

Re: [PATCH] drivers: fix error CQE handling

On Tue, 2 May 2023 21:49:22 +0300 Alexander Kozyrev wrote: > The completion queue element size can be independently configured > to report either 64 or 128 bytes CQEs by programming cqe_sz parameter > at CQ creation. This parameter depends on the cache line size and > affects both regular CQEs an

[PATCH v13 2/3] event/dlb2: add support for independent enqueue

DLB devices need events to be enqueued in the same order they are dequeued. Applications are not suppose to change event order between dequeue and to enqueue. Since Eventdev standard does not add such restrictions independent enqueue support is needed for DLB PMD so that it restores dequeue order o

[PATCH v13 1/3] eventdev: add support for independent enqueue

This commit adds support for independent enqueue feature and updates Event Device and PMD feature list. A new capability RTE_EVENT_DEV_CAP_INDEPENDENT_ENQ is introduced. It allows out-of-order enqueuing of RTE_EVENT_OP_FORWARD or RELEASE type events on an event port where this capability is enable

[PATCH v13 0/3] Independent Enqueue Support

v13: Address comments. v12: Address comments. v11: Address comments. v10: Add acked-by reviewer name. v9: Address comments. v8: Address build issues. v7: Address documentation reviews. v6: Update patch with more documentation. v5: Address build issues. v4: Address comments. v3: Fix CI/build issues.

[PATCH v13 3/3] event/dsw: add capability for independent enqueue

To use independent enqueue capability applications need to set flag RTE_EVENT_PORT_CFG_INDEPENDENT_ENQ during port setup only if the capability RTE_EVENT_DEV_CAP_INDEPENDENT_ENQ exists. Hence, this commit adds the capability of independent enqueue to the DSW driver. Signed-off-by: Abdullah Sevince

[PATCH v14 2/3] event/dlb2: add support for independent enqueue

DLB devices need events to be enqueued in the same order they are dequeued. Applications are not suppose to change event order between dequeue and to enqueue. Since Eventdev standard does not add such restrictions independent enqueue support is needed for DLB PMD so that it restores dequeue order o

[PATCH v14 1/3] eventdev: add support for independent enqueue

This commit adds support for independent enqueue feature and updates Event Device and PMD feature list. A new capability RTE_EVENT_DEV_CAP_INDEPENDENT_ENQ is introduced. It allows out-of-order enqueuing of RTE_EVENT_OP_FORWARD or RELEASE type events on an event port where this capability is enable

[PATCH v14 0/3] Independent Enqueue Support

v14: Address comments. v13: Address comments. v12: Address comments. v11: Address comments. v10: Add acked-by reviewer name. v9: Address comments. v8: Address build issues. v7: Address documentation reviews. v6: Update patch with more documentation. v5: Address build issues. v4: Address comments. v

[PATCH v14 3/3] event/dsw: add capability for independent enqueue

To use independent enqueue capability applications need to set flag RTE_EVENT_PORT_CFG_INDEPENDENT_ENQ during port setup only if the capability RTE_EVENT_DEV_CAP_INDEPENDENT_ENQ exists. Hence, this commit adds the capability of independent enqueue to the DSW driver. Signed-off-by: Abdullah Sevince

[PATCH v2 02/10] baseband/acc: queue allocation refactor

Refactor to manage queue memory per operation more flexibly for VRB devices. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/acc_common.h | 5 + drivers/baseband/acc/rte_vrb_pmd.c | 214 - 2 files changed, 157 insertions(+), 62 deletions(-) diff --git a/driv

[PATCH v2 01/10] baseband/acc: fix access to deallocated mem

Prevent op_addr access during queue_stop operation, as this memory may have been deallocated. Fixes: e640f6cdfa84 ("baseband/acc200: add LDPC processing") Cc: sta...@dpdk.org Signed-off-by: Hernan Vargas Reviewed-by: Maxime Coquelin --- drivers/baseband/acc/rte_acc100_pmd.c | 36 --

[PATCH v2 00/10] acc baseband PMD fix and updates for 24.11

This series targets 24.11. v2: Rebased to the latest next-baseband-for-main which includes needed rte_bbdev lib updates. v1: It includes a memory access fix, refactoring of queue allocation and general improvements. Hernan Vargas (10): baseband/acc: fix access to deallocated mem baseband/acc

[PATCH v2 07/10] baseband/acc: algorithm tuning for LDPC decoder

Reverting to MS1 version of the algorithm to improve MU1 fading conditions. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/rte_vrb_pmd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/baseband/acc/rte_vrb_pmd.c b/drivers/baseband/acc/rte_vrb_pmd.c index

[PATCH v2 10/10] baseband/acc: cosmetic changes

Cosmetic code changes. No functional impact. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/rte_acc100_pmd.c | 2 +- drivers/baseband/acc/rte_vrb_pmd.c| 62 +++ 2 files changed, 44 insertions(+), 20 deletions(-) diff --git a/drivers/baseband/acc/rte_acc100_pm

[PATCH v2 06/10] baseband/acc: remove soft output bypass

Removing soft output bypass capability due to device limitations. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/rte_vrb_pmd.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/baseband/acc/rte_vrb_pmd.c b/drivers/baseband/acc/rte_vrb_pmd.c index 26335d55

[PATCH v2 05/10] baseband/acc: enhance SW ring alignment

Calculate the aligned total size required for queue rings, ensuring that the size is a power of two for proper memory allocation. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/acc_common.h | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/baseband/acc/acc

[PATCH v2 08/10] baseband/acc: remove check on HARQ memory

Automatically reset HARQ memory to prevent errors and simplify usage. In a way we can assume that the HARQ output operation will always overwrite the buffer, so we can reset this from the driver to prevent an error being reported when application fails to do this explicitly. Signed-off-by: Hernan

[PATCH v2 09/10] baseband/acc: reset ring data valid bit

Reset only the valid bit to keep info ring data notably for dumping. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/rte_vrb_pmd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/baseband/acc/rte_vrb_pmd.c b/drivers/baseband/acc/rte_vrb_pmd.c index 27c8bdca3d08

[PATCH v2 03/10] baseband/acc: configure max queues per device

Configure max_queues based on the number of queue groups and numbers of AQS per device variant. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/rte_vrb_pmd.c | 9 +++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/baseband/acc/rte_vrb_pmd.c b/drivers/baseband/

[PATCH v2 04/10] baseband/acc: future proof structure comparison

Some implementation in the PMD is based on some size assumption from the bbdev structure, which should use sizeof instead to be more future proof in case these structures change. Signed-off-by: Hernan Vargas --- drivers/baseband/acc/acc_common.h | 4 ++-- 1 file changed, 2 insertions(+), 2 delet

Re: [dpdk-dev v1] doc/multi-process: fixed grammar and rephrasing

On Wed, 1 Jun 2022 17:57:19 +0800 Kai Ji wrote: > Update and rephrasing some sentences, small improvements > made to the multi-process sample application user guide > > Fixes: d0dff9ba445e ("doc: sample application user guide") > Cc: bernard.iremon...@intel.com > > Signed-off-by: Kai Ji It's

Re: [PATCH] doc: update TAP device features

On 9/4/2024 4:42 PM, Stephen Hemminger wrote: > The TAP device does have per-queue stats and handles multi-process. > > Signed-off-by: Stephen Hemminger > --- > doc/guides/nics/features/tap.ini | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/doc/guides/nics/features/tap.ini > b/doc/

Re: [PATCH v4] vhost: support CPU copy for small packets

On Mon, 29 Aug 2022 08:56:58 +0800 Wenwu Ma wrote: > Offloading small packets to DMA degrades throughput 10%~20%, > and this is because DMA offloading is not free and DMA is not > good at processing small packets. In addition, control plane > packets are usually small, and assign those packets to

Re: [PATCH] doc: update TAP device features

On Fri, 4 Oct 2024 02:48:21 +0100 Ferruh Yigit wrote: > On 9/4/2024 4:42 PM, Stephen Hemminger wrote: > > The TAP device does have per-queue stats and handles multi-process. > > > > Signed-off-by: Stephen Hemminger > > --- > > doc/guides/nics/features/tap.ini | 2 ++ > > 1 file changed, 2 inse

Re: [PATCH v2 2/2] usertools/telemetry: add new telemetry client

On Wed, 31 Aug 2022 12:52:50 +0100 Conor Walsh wrote: > A lot of DPDK apps do not provide feedback to their users while > running, but many interesting metrics are available through the > app's telemetry socket. Currently, the main way to view these > metrics is to query them using the dpdk-telem

[PATCH v3] app/proc-info: add rte_eal_cleanup() to avoid memory leak

From: Fidaullah Noonari when app is launched with -m proc-info exit without rte_eal_cleanup() causing memory leakage. This commit resolves the memory leakage issue and closes app properly. Bugzilla id: 898 Signed-off-by: Fidaullah Noonari Acked-by: Stephen Hemminger --- v3 - handle eventdev_xs

Re: [PATCH v5] bitmap: add scan from offset function

On Mon, 3 Jul 2023 14:39:08 +0200 Volodymyr Fialko wrote: > +/** > + * Bitmap initialize internal scan pointers at the given position for the > scan function. > + * > + * Note: for private/internal use, for public: > + * @see rte_bitmap_scan_from_offset() > + * > + * @param bmp > + * Handle to

Re: [v2 2/2] examples: move vendor specific apps to drivers sub directory

On Wed, 5 Jul 2023 15:26:26 +0530 Hemant Agrawal wrote: > As approved by DPDK technical board on 2021-03-24 NTB > raw driver example application will be moved to > example/rawdev/ to avoid PMD specific example application > to show up in examples directory. > > Signed-off-by: Hemant Agrawal A

Re: [v2 1/2] doc: add policy for adding vendor PMD specific examples

On Wed, 5 Jul 2023 15:26:25 +0530 Hemant Agrawal wrote: > This patch update the dpdk sample app policy to support > vendor PMD specific test examples in the respective drivers > sub-directory in examples. > > Signed-off-by: Hemant Agrawal > Acked-by: Jerin Jacob Acked-by: Stephen Hemminger

Re: [PATCH] [RFC] cryptodev: replace LIST_END enumerators with APIs

On 9/5/2024 11:14 AM, Akhil Goyal wrote: > Replace *_LIST_END enumerators from asymmetric crypto > lib to avoid ABI breakage for every new addition in > enums with inline APIs. > > Signed-off-by: Akhil Goyal > --- > This patch was discussed in ML long time back. > https://patches.dpdk.org/project

Re: [EXTERNAL] Re: [PATCH] [RFC] cryptodev: replace LIST_END enumerators with APIs

On 9/6/2024 8:45 AM, Akhil Goyal wrote: >>> >>> Here's an idea... >>> >>> We can introduce a generic design pattern where we keep the _LIST_END enum >> value at the end, somehow marking it private (and not part of the API/ABI), >> and >> move the _list_end() function inside the C file, so it uses

Re: [PATCH] [RFC] cryptodev: replace LIST_END enumerators with APIs

On 9/23/2024 9:41 PM, Akhil Goyal wrote: > Hi Morten, > > Apologies for delayed response. >> Maybe a combination, returning the lowest end of the two versions of the >> list, >> would work... >> >> -- >> Common header file (rte_common.h): >> ---

Re: [PATCH] drivers: remove compile-time option for IEEE 1588

On Wed, 17 Apr 2024 14:24:00 +0100 Ferruh Yigit wrote: > > :) remove compile flag in 24.11 LTS. > > > > But we may end up in same situation in 24.11, some drivers not being > > ready, so we should merge this patch very early in the 24.11 to give > > time to drivers to fix if they were not ready

Re: [PATCH] drivers: remove compile-time option for IEEE 1588

On 10/3/2024 8:12 PM, Stephen Hemminger wrote: > On Wed, 17 Apr 2024 14:24:00 +0100 > Ferruh Yigit wrote: > >>> :) remove compile flag in 24.11 LTS. >>> >>> But we may end up in same situation in 24.11, some drivers not being >>> ready, so we should merge this patch very early in the 24.11 to giv

[PATCH] app/dumpcap: fix handling of jumbo frames

If dumpcap (in legacy pcap mode) tried to handle a large segmented frame it would core dump because rte_pktmbuf_read() would return NULL. Fix by using same logic as in pcap PMD. Fixes: cbb44143be74 ("app/dumpcap: add new packet capture application") Reported-by: Tianli Lai Signed-off-by: Stephen

Re: [PATCH] Add bus master enable/disable APIs for CDX devices

On 10/3/2024 11:16 PM, Stephen Hemminger wrote: > On Fri, 27 Oct 2023 17:22:11 +0100 > Ferruh Yigit wrote: > >> From: Shubham Rohila >> >> Define rte_cdx_vfio_bm_enable and rte_cdx_vfio_bm_disable to >> enable or disable bus master functionality for cdx devices. >> >> Signed-off-by: Shubham Rohi

Re: [PATCH dpdk v2 05/16] fib6,rib6,lpm6: use ipv6 addr struct

On Tue, 1 Oct 2024 10:17:17 +0200 Robin Jarry wrote: > Replace ad-hoc uint8_t[16] array types in the API of rte_fib6, rte_rib6 > and rte_lpm6. Update all code accordingly. > > Unfortunately, these three libraries are strongly intertwined, it is not > possible to split this change in separate co

Re: [PATCH dpdk v2 06/16] net: add ipv6 address utilities

On Tue, 1 Oct 2024 10:17:18 +0200 Robin Jarry wrote: > +/** > + * Copy an IPv6 address into another one. > + * > + * @param dst > + * The address into which to copy data. > + * @param src > + * The address from which to copy. > + */ > +static inline void > +rte_ipv6_addr_cpy(struct rte_ipv6_

Re: [PATCH dpdk v2 09/16] pipeline: use ipv6 addr struct

On Tue, 1 Oct 2024 10:17:21 +0200 Robin Jarry wrote: > diff --git a/examples/ip_pipeline/cli.c b/examples/ip_pipeline/cli.c > index e8269ea90c11..66fdeac8f501 100644 > --- a/examples/ip_pipeline/cli.c > +++ b/examples/ip_pipeline/cli.c > @@ -3540,8 +3540,8 @@ parse_table_action_encap(char **toke

Re: [PATCH dpdk v2 03/16] net: add structure for ipv6 addresses

On Tue, 1 Oct 2024 10:17:15 +0200 Robin Jarry wrote: > There is currently no structure defined for IPv6 addresses. Introduce > one that is simply a uint8_t array of 16 elements without any union. The > idea is to ensure this structure alignment is 1 so that it can be mapped > directly on unalign

Re: [PATCH dpdk v2 04/16] net: use ipv6 structure for header addresses

On Tue, 1 Oct 2024 10:17:16 +0200 Robin Jarry wrote: > diff --git a/app/test/packet_burst_generator.c > b/app/test/packet_burst_generator.c > index 2cd34abc1a65..76a409a56452 100644 > --- a/app/test/packet_burst_generator.c > +++ b/app/test/packet_burst_generator.c > @@ -149,8 +149,8 @@ initial

Re: [PATCH dpdk v2 01/16] net: split raw checksum functions in separate header

On Tue, 1 Oct 2024 10:17:13 +0200 Robin Jarry wrote: > The checksum functions are used by both ipv4 and ipv6 functions. In > preparation of moving ipv6 symbols to a new header, move the checksum > related symbols to another dedicated header. > > Signed-off-by: Robin Jarry > --- Acked-by: Step

[PATCH] net/gve: fix refill logic causing memory corruption

There is a seemingly mundane error in the RX refill path which can lead to major issues and ultimately program crashing. This error occurs as part of an edge case where the exact number of buffers the refill causes the ring to wrap around to 0. The current refill logic is split into two conditions

[PATCH] net/gve: add IO memory barriers before reading descriptors

Without memory barriers, there is no guarantee that the CPU will actually wait until after the descriptor has been fully written before loading descriptor data. In this case, it is possible that stale data is read and acted on by the driver when processing TX or RX completions. This change adds re

[PATCH v2] drivers: fix error CQE handling

The completion queue element size can be independently configured to report either 64 or 128 bytes CQEs by programming cqe_sz parameter at CQ creation. This parameter depends on the cache line size and affects both regular CQEs and error CQEs. But the error handling assumes that an error CQE is 64

[PATCH v2] drivers: ignore non-critical syndromes for Tx queues

Only 3 syndromes are considered critical and warrant a queue restart. All other syndromes can be safely ignored. We ignore them for Rx queues. Skip non-critical error CQEs for Tx queues as well. Fixes: 957e45fb7b ("net/mlx5: handle Tx completion with error") Cc: sta...@dpdk.org Signed-off-by: Ale

RE: [RFC v2 0/2] Add high-performance timer facility

> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Thursday, 3 October 2024 20.37 > > On Wed, 15 Mar 2023 18:03:40 +0100 > Mattias Rönnblom wrote: > > > This patchset is an attempt to introduce a high-performance, highly > > scalable timer facility into DPDK. > > > > More spec

Re: [PATCH 2/2] ethdev: fix race on ports for telemetry commands

On Wed, Oct 02, 2024 at 09:26:10PM +0200, Robin Jarry wrote: > David Marchand, Oct 02, 2024 at 21:18: > > On Wed, Oct 2, 2024 at 9:09 PM Robin Jarry wrote: > > > I was going to suggest adding a rte_spinlock_t* parameter to a new > > > telemetry register function that would need to be held while th

Re: [PATCH v2] service: extend service function call statistics

> From: Mattias Rönnblom > Sent: Wednesday, October 2, 2024 8:43 PM > To: Marchand, David > Cc: Mattias Rönnblom ; dev@dpdk.org > ; Van Haaren, Harry ; Stefan > Sundkvist > Subject: Re: [PATCH v2] service: extend service function call statistics > > On 2024-10-02 21:08, David Marchand wrote: >

Re: [PATCH 2/2] ethdev: fix race on ports for telemetry commands

On Thu, Oct 3, 2024 at 11:46 AM Bruce Richardson wrote: > > On Wed, Oct 02, 2024 at 09:26:10PM +0200, Robin Jarry wrote: > > David Marchand, Oct 02, 2024 at 21:18: > > > On Wed, Oct 2, 2024 at 9:09 PM Robin Jarry wrote: > > > > I was going to suggest adding a rte_spinlock_t* parameter to a new >

Re: [PATCH v2 1/1] common/cnxk: fix updated loglevel from NOTICE to INFO

On Tue, Oct 1, 2024 at 2:24 PM Rakesh Kudurumalla wrote: > > In latest dpdk PMD log type is removed and driver > specific log type is added for CNXK. This patch > changes loglevel of CNXK from NOTICE to INFO > to display logs while running applications > > Fixes: 455a771fd6f1 ("common/cnxk: fix se

[PATCH] test/security: skip IPsec post process for negative tests

Skips calling test_ipsec_post_process for negative inline IPsec tests as received packet might not be valid for a negative case. Signed-off-by: Srujana Challa --- app/test/test_cryptodev_security_ipsec.c | 1 + app/test/test_security_inline_proto.c| 25 +++- 2 files chan

DPDK Release Status Meeting 2024-10-03

Release status meeting minutes 2024-10-03 = Agenda: * Release Dates * Subtrees * Roadmaps * LTS * Defects * Opens Participants: * AMD * ARM * Intel * Marvell * Nvidia * Red Hat Release Dates - The following are the current/updated working dat

[PATCH dpdk v2 1/2] telemetry: add api to register command with private argument

Add a new rte_telemetry_register_cmd_arg public function to register a telemetry endpoint with a callback that takes an additional private argument. This will be used in the next commit to protect ethdev endpoints with a lock. Update perform_command() to take a struct callback object copied from

[PATCH dpdk v2 0/2] Fix race in ethdev telemetry

Following a discussion we had during the summit, here is one series to fix a race between an application thread and the telemetry thread handling requests on ethdev ports. The problem may be generic to other device classes providing telemetry callbacks, but for now, this series goes with a simple

Re: [PATCH v4] common/cnxk: fix IRQ reconfiguration

On Tue, Oct 1, 2024 at 6:41 PM wrote: > > From: Pavan Nikhilesh > > Unregister SSO device and NPA IRQs before resizing > IRQs to cleanup stale IRQ handles. > > Fixes: 993107f0f440 ("common/cnxk: limit SSO interrupt allocation count") > Cc: sta...@dpdk.org > > Signed-off-by: Pavan Nikhilesh Appl

[PATCH dpdk v2 2/2] ethdev: fix potential race in telemetry endpoints

While invoking telemetry commands (which may happen at any time, out of control of the application), an application thread may concurrently add/remove ports. The telemetry callbacks may then access partially initialized/uninitialised ethdev data. Reuse the ethdev lock that protects port allocation

Re: [PATCH dpdk v2 1/2] telemetry: add api to register command with private argument

On Thu, Oct 03, 2024 at 01:24:41PM +0200, Robin Jarry wrote: > Add a new rte_telemetry_register_cmd_arg public function to register > a telemetry endpoint with a callback that takes an additional private > argument. > > This will be used in the next commit to protect ethdev endpoints with > a lock

Re: [PATCH dpdk v2 2/2] ethdev: fix potential race in telemetry endpoints

On Thu, Oct 03, 2024 at 01:24:42PM +0200, Robin Jarry wrote: > While invoking telemetry commands (which may happen at any time, out of > control of the application), an application thread may concurrently > add/remove ports. The telemetry callbacks may then access partially > initialized/uninitiali

[PATCH v3 1/1] dmadev: support priority configuration

From: Vamsi Attunuru Some DMA controllers offer the ability to configure priority level for the hardware command queues, allowing for the prioritization of DMA command execution based on queue importance. This patch introduces the necessary fields in the dmadev structures to retrieve information

Re: [PATCH v6 7/7] vhost: optimize memcpy routines when cc memcpy is used

On 9/20/24 12:27, Mattias Rönnblom wrote: In build where use_cc_memcpy is set to true, the vhost user PMD suffers a large performance drop on Intel P-cores for small packets, at least when built by GCC and (to a much lesser extent) clang. This patch addresses that issue by using a custom virt

[PATCH v4 1/1] dmadev: support priority configuration

From: Vamsi Attunuru Some DMA controllers offer the ability to configure priority level for the hardware command queues, allowing for the prioritization of DMA command execution based on queue importance. This patch introduces the necessary fields in the dmadev structures to retrieve information

Re: [PATCH] config/riscv: name the cross file properly

Staszek, can you update your email? (same with up...@semihalf.com?) On Wed, Oct 2, 2024 at 6:51 PM 'Stephen Hemminger' via upstream wrote: > > On Tue, 21 Jun 2022 14:29:23 +0200 > Stanislaw Kardach wrote: > > > Since the riscv64_linux_gcc was in fact a Ubuntu-specific cross-file, > > rename it.

Re: [PATCH v4 2/2] timer: allow platform to override cpu TSC frequency

On Thu, Oct 3, 2024 at 12:31 PM Bruce Richardson wrote: > > On Wed, Oct 02, 2024 at 10:14:57PM +0300, Isaac Boukris wrote: > > On Wed, Oct 2, 2024 at 8:11 PM Bruce Richardson > > wrote: > > > > > > On Wed, Oct 02, 2024 at 07:56:36PM +0300, Isaac Boukris wrote: > > > > The CPU value is often not a

[PATCH v5 0/2] Improve TSC frequency accuracy

Changes if V5: - fix absolute delta calculation per Bruce's comment. Isaac Boukris (2): timer: lower rounding of TSC estimation to 100KHz timer: allow platform to override cpu TSC frequency lib/eal/common/eal_common_timer.c | 3 +- lib/eal/common/eal_private.h | 2 +- lib/eal/freebsd

[PATCH v5 1/2] timer: lower rounding of TSC estimation to 100KHz

In practice, the frequency is often not a nice round number, while the estimation results are rather accurate, just a couple of KHz away from the kernel's tsc_khz value, so it should suffice. Rounding to 10MHz can cause a significant drift from real time, up to a second per 10 minutes. See also b

[PATCH v5 2/2] timer: allow platform to override cpu TSC frequency

The CPU provided value is often not accurate, allow overriding it based on info from the host OS. On Linux X86, if the tsc_known_freq cpu flag is missing, it means the kernel doesn't trust it and calculates its own. We should do the same to avoid drift. On freebsd we have access to the kernel tsc

Re: [PATCH dpdk v2 1/2] telemetry: add api to register command with private argument

Bruce Richardson, Oct 03, 2024 at 13:39: On Thu, Oct 03, 2024 at 01:24:41PM +0200, Robin Jarry wrote: Add a new rte_telemetry_register_cmd_arg public function to register a telemetry endpoint with a callback that takes an additional private argument. This will be used in the next commit to prot

Re: [PATCH dpdk v2 1/2] telemetry: add api to register command with private argument

Robin Jarry, Oct 03, 2024 at 14:36: +typedef int (*telemetry_arg_cb)(const char *cmd, const char *params, + struct rte_tel_data *info, void *arg); + Not sure about this, but I'd tend to have the arg parameter as second parameter, to keep the "info" as the final parameter. My sugge

RE: [EXTERNAL] [PATCH v4 1/1] dmadev: support priority configuration

Hi Vamsi, Looks good overall. Minor nit inline. With the change, Acked-by: Anoob Joseph Thanks, Anoob > From: Vamsi Attunuru > > Some DMA controllers offer the ability to configure priority level > for the hardware command queues, allowing for the prioritization

RE: [EXTERNAL] [PATCH v4 1/1] dmadev: support priority configuration

>-Original Message- >From: Anoob Joseph >Sent: Thursday, October 3, 2024 6:37 PM >To: Vamsi Krishna Attunuru ; >tho...@monjalon.net; fengcheng...@huawei.com; >bruce.richard...@intel.com; m...@smartsharesystems.com >Cc: dev@dpdk.org; kevin.la...@intel.com; Jerin Jacob ; >conor.wa...@intel

[PATCH 01/20] common/cnxk: implement SSO HW info

From: Pavan Nikhilesh Add SSO HW info mbox to get hardware capabilities, and reuse them instead of depending on hardcoded values. Remove redundant includes. Signed-off-by: Pavan Nikhilesh --- Depends-on: series-33204 ("add Marvell cn20k SOC support for mempool and net") drivers/common/cnxk/ro

[PATCH 02/20] event/cnxk: add CN20K specific device probe

From: Pavan Nikhilesh Add platform specific event device probe and remove, also add event device info get function. Signed-off-by: Pavan Nikhilesh --- doc/guides/eventdevs/cnxk.rst | 30 + doc/guides/rel_notes/release_24_11.rst | 4 ++ drivers/common/cnxk/roc_sso.c |

  1   2   >