Re: [PATCH v3 4/5] mempool: avoid floating point expression in static assertion

On 1/16/24 21:41, Stephen Hemminger wrote: Clang does not handle casts in static_assert() expressions. It doesn't like use of floating point to calculate threshold. Use a different expression with same effect; yes this will cause checkpatch nag. Signed-off-by: Stephen Hemminger --- lib/mempoo

Re: static_assert, sfc, and clang issues

On 1/17/24 01:49, Stephen Hemminger wrote: On Tue, 16 Jan 2024 23:14:36 +0100 Morten Brørup wrote: +1 for #2 just make it a block. I prefer that you implement the workaround in the RTE_BUILD_BUG_ON() macro, by surrounding it by "do { } while (0)", like this: #define RTE_BUILD_BUG_ON(condit

Re: [PATCH v3 1/1] ethdev: parsing multiple representor devargs string

On 1/16/24 12:55, Harman Kalra wrote: Adding support for parsing multiple representor devargs strings passed to a PCI BDF. There may be scenario where port representors for various PFs or VFs under PFs are required and all these are representor ports shall be backed by single pci device. In such

Re: [PATCH v4] dts: add Dockerfile

Reviewed-by: Juraj Linkeš On Tue, Jan 16, 2024 at 8:18 PM wrote: > > From: Juraj Linkeš > > The Dockerfile defines development and CI runner images. > > Signed-off-by: Juraj Linkeš > Signed-off-by: Jeremy Spewock

Re: [PATCH v3 1/5] event/opdl: fix non-constant compile time assertion

On Wed, Jan 17, 2024 at 10:58:12AM +0300, Andrew Rybchenko wrote: > On 1/16/24 21:41, Stephen Hemminger wrote: > > RTE_BUILD_BUG_ON() was being used with a non-constant value. > > The inline function rte_is_power_of_2() is not constant since > > inline expansion happens later in the compile process

RE: static_assert, sfc, and clang issues

> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Tuesday, 16 January 2024 23.50 > > On Tue, 16 Jan 2024 23:14:36 +0100 > Morten Brørup wrote: > > > > +1 for #2 just make it a block. > > > > I prefer that you implement the workaround in the RTE_BUILD_BUG_ON() > macro, by surr

Re: [PATCH] net/gve: Enable stats reporting for GQ format

On 1/16/2024 6:18 AM, Rushil Gupta wrote: > > > On Fri, Jan 12, 2024 at 8:36 PM Ferruh Yigit > wrote: > > On 12/22/2023 3:39 PM, Rushil Gupta wrote: > > Read from shared region to retrieve imissed statistics for GQ from > device. > > Tested using `sh

RE: [PATCH v3 1/5] event/opdl: fix non-constant compile time assertion

> From: Bruce Richardson [mailto:bruce.richard...@intel.com] > Sent: Wednesday, 17 January 2024 10.27 > > On Wed, Jan 17, 2024 at 10:58:12AM +0300, Andrew Rybchenko wrote: > > On 1/16/24 21:41, Stephen Hemminger wrote: > > > RTE_BUILD_BUG_ON() was being used with a non-constant value. > > > The in

[PATCH v3 00/24] Fixes and improvements in crypto cnxk

Add following features - TLS record processing offload (TLS 1.2-1.3, DTLS 1.2) - Rx inject to allow lookaside packets to be injected to ethdev Rx - Use PDCP_CHAIN opcode instead of PDCP opcode for cipher-only and auth only cases - PMD API to submit instructions directly to hardware Changes in v3

[PATCH v3 01/24] common/cnxk: fix memory leak

From: Akhil Goyal dev_init() acquires some resources which need to be cleaned in case a failure is observed afterwards. Fixes: c045d2e5cbbc ("common/cnxk: add CPT configuration") Signed-off-by: Akhil Goyal --- drivers/common/cnxk/roc_cpt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(

[PATCH v3 02/24] crypto/cnxk: use common macro

Having different macros for same purpose may cause issues if one is updated without updating the other. Use same macro by including the header. Signed-off-by: Anoob Joseph --- drivers/crypto/cnxk/cnxk_cryptodev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/c

[PATCH v3 03/24] crypto/cnxk: fallback to SG if headroom is not available

From: Tejasree Kondoj Falling back to SG mode for cn9k lookaside IPsec if headroom is not available. Signed-off-by: Tejasree Kondoj --- drivers/crypto/cnxk/cn9k_ipsec_la_ops.h | 8 +--- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/crypto/cnxk/cn9k_ipsec_la_ops.h b/

[PATCH v3 04/24] crypto/cnxk: return microcode completion code

Return microcode completion code in case of errors. This allows applications to check the failure reasons in more granularity. Signed-off-by: Anoob Joseph --- drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/crypto/cnxk/cn10k_cryptodev_ops.c

[PATCH v3 05/24] crypto/cnxk: fix ECDH pubkey verify in cn9k

From: Gowrishankar Muthukrishnan Fix ECDH pubkey verify in cn9k. Fixes: baae0994fa96 ("crypto/cnxk: support ECDH") Signed-off-by: Gowrishankar Muthukrishnan --- drivers/crypto/cnxk/cn9k_cryptodev_ops.c | 12 +++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/cr

[PATCH v3 06/24] crypto/cnxk: enable digest gen for zero len input

From: Aakash Sasidharan With zero length input, digest generation fails with incorrect value. Fix this by completely avoiding the gather component when the input packet has zero data length. Signed-off-by: Aakash Sasidharan --- drivers/crypto/cnxk/cnxk_se.h | 2 +- 1 file changed, 1 insertion(

[PATCH v3 08/24] common/cnxk: add Rx inject configs

From: Rahul Bhansali Add Rx inject config for feature enable/disable, and store Rx chan value per port. Signed-off-by: Rahul Bhansali --- drivers/common/cnxk/roc_idev.c | 44 + drivers/common/cnxk/roc_idev.h | 5 drivers/common/cnxk/roc_idev_priv.h |

[PATCH v3 10/24] crypto/cnxk: enable Rx inject for 103

From: Vidya Sagar Velumuri Enable Rx inject feature for 103XX Signed-off-by: Vidya Sagar Velumuri --- drivers/crypto/cnxk/cnxk_cryptodev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/cnxk/cnxk_cryptodev.c b/drivers/crypto/cnxk/cnxk_cryptodev.c index b168

[PATCH v3 07/24] crypto/cnxk: enable Rx inject in security lookaside

From: Vidya Sagar Velumuri Add Rx inject fastpath API. Add devargs "rx_inject_qp" to specify the QP to be used for Rx inject. When the RX inject feature flag is enabled: 1. Reserve a queue pair to use for RX Inject mode. 2. Enable RXC and disable full packet mode for that queue pair. Signed-off-

[PATCH v3 09/24] crypto/cnxk: Rx inject config update

From: Rahul Bhansali - Update chan in CPT inst from port's Rx chan - Set Rx inject config in Idev struct Signed-off-by: Rahul Bhansali --- drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 4 +++- drivers/crypto/cnxk/cn10k_ipsec.c | 3 +++ drivers/crypto/cnxk/cnxk_cryptodev.h | 1 + dri

[PATCH v3 12/24] common/cnxk: update opad-ipad gen to handle TLS

For TLS opcodes, ipad is at the offset 64 as compared to the packed implementation for IPsec. Extend the function to handle TLS contexts as well. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- drivers/common/cnxk/cnxk_security.c | 15 --- drivers/common/cnxk/cnx

[PATCH v3 13/24] common/cnxk: add TLS record contexts

Add TLS record read and write contexts. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- drivers/common/cnxk/roc_cpt.h | 4 +- drivers/common/cnxk/roc_ie_ot_tls.h | 199 drivers/common/cnxk/roc_se.h| 11 ++ 3 files changed, 211 in

[PATCH v3 15/24] crypto/cnxk: add TLS record session ops

From: Vidya Sagar Velumuri Add TLS record session ops for creating and destroying security sessions. Add support for both read and write sessions. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- drivers/crypto/cnxk/cn10k_cryptodev_sec.h | 8 + drivers/crypto/cnxk/cn10k_t

[PATCH v3 11/24] crypto/cnxk: rename security caps as IPsec security caps

From: Vidya Sagar Velumuri Security capabilities would vary between IPsec and other new offloads. Rename existing security caps to indicate that they are IPsec specific ones. Rename and change the scope of common functions, inorder to avoid code duplication. These functions can be used by both I

[PATCH v3 17/24] crypto/cnxk: add TLS capability

From: Vidya Sagar Velumuri Add TLS 1.2 record read and write capability. Add DTLS 1.2 record read and write capability. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- doc/guides/rel_notes/release_24_03.rst| 2 + drivers/common/cnxk/hw/cpt.h |

[PATCH v3 14/24] crypto/cnxk: separate IPsec from security common code

The current structs and functions assume only IPsec offload. Separate it out to allow for addition of TLS. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- drivers/crypto/cnxk/cn10k_cryptodev.c | 2 +- drivers/crypto/cnxk/cn10k_cryptodev_sec.c | 127

[PATCH v3 16/24] crypto/cnxk: add TLS record datapath handling

From: Vidya Sagar Velumuri Add support for TLS record handling in datapath. Signed-off-by: Anoob Joseph Signed-off-by: Vidya Sagar Velumuri --- drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 57 +++- drivers/crypto/cnxk/cn10k_cryptodev_sec.c | 7 + drivers/crypto/cnxk/cn10k_tls_ops.h |

[PATCH v3 18/24] crypto/cnxk: add PMD APIs for raw submission to CPT

Add PMD APIs to allow applications to directly submit CPT instructions to hardware. Signed-off-by: Anoob Joseph --- doc/api/doxy-api-index.md | 1 + doc/api/doxy-api.conf.in | 1 + doc/guides/rel_notes/release_24_03.rst| 1 + drivers/crypto/cnxk/cn10k_cryp

[PATCH v3 19/24] crypto/cnxk: replace PDCP with PDCP chain opcode

From: Tejasree Kondoj Replacing PDCP opcode with PDCP chain opcode. Signed-off-by: Tejasree Kondoj --- drivers/common/cnxk/roc_se.c | 331 +- drivers/common/cnxk/roc_se.h | 18 +- drivers/crypto/cnxk/cnxk_se.h | 96 +- 3 files changed, 135 insertions

[PATCH v3 20/24] crypto/cnxk: validate the combinations supported in TLS

From: Vidya Sagar Velumuri Validate the cipher and auth combination to allow only the ones supported by hardware. Signed-off-by: Vidya Sagar Velumuri --- drivers/crypto/cnxk/cn10k_tls.c | 35 - 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/driver

[PATCH v3 21/24] crypto/cnxk: use a single function for opad ipad

From: Vidya Sagar Velumuri Use a single function for opad and ipad generation for IPsec, TLS and flexi crypto. Signed-off-by: Vidya Sagar Velumuri --- drivers/common/cnxk/cnxk_security.c | 65 ++--- drivers/common/cnxk/cnxk_security.h | 5 --- drivers/common/cnxk/roc_s

[PATCH v3 22/24] crypto/cnxk: add support for TLS 1.3

From: Vidya Sagar Velumuri Add support for TLS-1.3. Signed-off-by: Vidya Sagar Velumuri --- drivers/common/cnxk/roc_ie_ot_tls.h | 50 +-- drivers/crypto/cnxk/cn10k_cryptodev_sec.h | 3 +- drivers/crypto/cnxk/cn10k_tls.c | 159 +- 3 files changed, 136

[PATCH v3 23/24] crypto/cnxk: add TLS 1.3 capability

From: Vidya Sagar Velumuri Add TLS 1.3 record read and write capability Signed-off-by: Vidya Sagar Velumuri --- doc/guides/rel_notes/release_24_03.rst| 4 +- .../crypto/cnxk/cnxk_cryptodev_capabilities.c | 92 +++ 2 files changed, 94 insertions(+), 2 deletions(-) diff

[PATCH v3 24/24] crypto/cnxk: add CPT SG mode debug

From: Tejasree Kondoj Adding CPT SG mode debug dump. Signed-off-by: Tejasree Kondoj --- drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 135 +- drivers/crypto/cnxk/cnxk_cryptodev_ops.h | 7 ++ 2 files changed, 141 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/cnx

RE: [PATCH] doc: update command scope information

Acked-by: Rakesh Kudurumalla > -Original Message- > From: sk...@marvell.com > Sent: Monday, January 8, 2024 1:04 PM > To: Sunil Kumar Kori ; Rakesh Kudurumalla > > Cc: dev@dpdk.org > Subject: [PATCH] doc: update command scope information > > From: Sunil Kumar Kori > > Set of CLI comm

[PATCH] net/iavf: fix application reset callback calls

Don't trigger an application reset callback if the port is not started. Bugzilla ID: 1337 Fixes: 675a104e2e94 ("net/iavf: fix abnormal disable HW interrupt") Cc: sta...@dpdk.org Signed-off-by: David Marchand --- drivers/net/iavf/iavf_vchnl.c | 5 - 1 file changed, 4 insertions(+), 1 deletio

RE: [V1 0/2] use traffic class PRM field for IPv6 modification

Hi, > -Original Message- > From: Gavin Li > Sent: Friday, January 12, 2024 9:51 AM > To: dev@dpdk.org; Dariusz Sosnowski ; Slava > Ovsiienko ; Ori Kam ; > Suanming Mou ; Matan Azrad > > Cc: Jiawei(Jonny) Wang ; Raslan Darawsheh > > Subject: [V1 0/2] use traffic class PRM field for IPv6 m

[PATCH v2 2/2] event/cnxk: use WFE LDP loop for getwork routine

From: Pavan Nikhilesh Use WFE LDP loop while polling for GETWORK completion for better power savings. Disabled by default and can be enabled by configuring meson with -Dc_args='-DRTE_ARM_USE_WFE'. Signed-off-by: Pavan Nikhilesh --- doc/guides/eventdevs/cnxk.rst | 9 ++ drivers/event/c

[PATCH v2 1/2] config/arm: allow WFE to be enabled config time

From: Pavan Nikhilesh Allow RTE_ARM_USE_WFE to be enabled at meson configuration time by passing it via c_args instead of modifying `config/arm/meson.build`. Example usage: meson build -Dc_args='-DRTE_ARM_USE_WFE' \ --cross-file config/arm/arm64_cn10k_linux_gcc Signed-off-by: Pavan Nik

[PATCH] doc: update LTS maintenance to 3 years

The existing official policy was to maintain LTS releases for 2 years. 19.11 and 20.11 LTS releases were maintained for 3 years and there was not significant issues caused by code divergence from main etc. Update the policy to indicate 3 years maintenance for LTS releases, but note that it depend

RE: [External] : Re: [PATCH] net/tap: Modified TAP BPF program as per the Kernel-version upgrade requirements.

No, I did not run with Cilium. Thanks, Madhuker. -Original Message- From: Stephen Hemminger Sent: 17 January 2024 08:56 To: Madhuker Mythri Cc: dev@dpdk.org; ferruh.yi...@amd.com Subject: Re: [External] : Re: [PATCH] net/tap: Modified TAP BPF program as per the Kernel-version upgrade

[PATCH v2] doc: update LTS maintenance to 3 years

The existing official policy was to maintain LTS releases for 2 years. 19.11 and 20.11 LTS releases were maintained for 3 years and there was not significant issues caused by code divergence from main etc. Update the policy to indicate 3 years maintenance for LTS releases, but note that it depend

Re: [PATCH v3 5/5] eal: replace out of bounds VLA with static_assert

On Wed, 17 Jan 2024 08:53:44 +0100 Mattias Rönnblom wrote: > >* Triggers an error at compilation time if the condition is true. > >*/ > > -#define RTE_BUILD_BUG_ON(condition) ((void)sizeof(char[1 - > > 2*!!(condition)])) > > +#define RTE_BUILD_BUG_ON(condition) { static_assert(!(conditio

RE: [PATCH] net/mlx5/hws: fix ESP matching validation

Hi, > -Original Message- > From: Michael Baum > Sent: Monday, January 15, 2024 2:10 PM > To: dev@dpdk.org > Cc: Matan Azrad ; Dariusz Sosnowski > ; Raslan Darawsheh ; Slava > Ovsiienko ; Ori Kam ; > Suanming Mou ; Hamdan Igbaria > ; sta...@dpdk.org > Subject: [PATCH] net/mlx5/hws: fix ESP

RE: [PATCH] net/mlx5: fix GENEVE TLV option management

Hi, > -Original Message- > From: Michael Baum > Sent: Monday, January 15, 2024 2:13 PM > To: dev@dpdk.org > Cc: Matan Azrad ; Dariusz Sosnowski > ; Raslan Darawsheh ; Slava > Ovsiienko ; Ori Kam ; > Suanming Mou ; Shiri Kuzin ; > sta...@dpdk.org > Subject: [PATCH] net/mlx5: fix GENEVE TLV

Re: [PATCH v3 5/5] eal: replace out of bounds VLA with static_assert

On Wed, 17 Jan 2024 10:52:40 +0300 Andrew Rybchenko wrote: > On 1/16/24 21:41, Stephen Hemminger wrote: > > Both Gcc, clang and MSVC have better way to do compile time > > assertions rather than using out of bounds array access. > > The old method would fail if -Wvla is enabled because compiler >

[PATCH v4 0/6] use static assert to cathc build errors

This series fixes a couple places where expressions that could not be evaluated as constant early in compiler passes were used. Then converts RTE_BUILD_BUG_ON() with static_assert. static_assert() is more picky about the expression has to be a constant, which also catches some existing undefined b

[PATCH v4 1/6] eal: introduce RTE_MIN_T() and RTE_MAX_T() macros

These macros work like RTE_MIN and RTE_MAX but take an explicit type. Necessary when being used in static assertions since RTE_MIN and RTE_MAX use temporary variables which confuses compilers constant expression checks. These macros could also be useful in other scenarios when bounded range is usef

[PATCH v4 2/6] event/opdl: fix non-constant compile time assertion

RTE_BUILD_BUG_ON() was being used with a non-constant value. The inline function rte_is_power_of_2() is not constant since inline expansion happens later in the compile process. Replace it with the macro which will be constant. Fixes: 4236ce9bf5bf ("event/opdl: add OPDL ring infrastructure library

[PATCH v4 3/6] net/sfc: fix non-constant expression in RTE_BUILD_BUG_ON()

The macro RTE_MIN has some hidden assignments to provide type safety which means the statement can not be fully evaluated in first pass of compiler. Replace RTE_MIN() with equivalent macro. Fixes: 4f93d790 ("net/sfc: support TSO for EF100 native datapath") Cc: ivan.ma...@oktetlabs.ru Signed-of

[PATCH v4 4/6] net/i40e: avoid using const variable in assertion

Clang does not allow const variable in a static_assert expression. Signed-off-by: Stephen Hemminger --- drivers/net/i40e/i40e_ethdev.h | 1 + drivers/net/i40e/i40e_rxtx_vec_sse.c | 10 -- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/i40e/i40e_ethdev.h

[PATCH v4 5/6] mempool: avoid floating point expression in static assertion

Clang does not handle casts in static_assert() expressions. It doesn't like use of floating point to calculate threshold. Use a different expression with same effect. Modify comment in mlx5 so that developers don't go searching for old value. Signed-off-by: Stephen Hemminger --- drivers/net/mlx

[PATCH v4 6/6] eal: replace out of bounds VLA with static_assert

Both Gcc, clang and MSVC have better way to do compile time assertions rather than using out of bounds array access. The old method would fail if -Wvla is enabled because compiler can't determine size in that code. Also, the use of new _Static_assert will catch broken code that is passing non-cons

RE: [PATCH v4 5/6] mempool: avoid floating point expression in static assertion

> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Wednesday, 17 January 2024 19.20 > > Clang does not handle casts in static_assert() expressions. > It doesn't like use of floating point to calculate threshold. > Use a different expression with same effect. > > Modify comment

[dpdk-dev] [PATCH v2] eal: refactor rte_eal_init into sub-functions

From: Rahul Gupta In continuation to the following email, I am sending this patch. (https://inbox.dpdk.org/dev/20231110172523.ga17...@microsoft.com/) Initialization requires rte_eal_init + rte_pktmbuf_pool_create which can consume a total time of 500-600 ms: a) For many devices FLR may take a si

[PATCH v1] gro : packets not getting flushed in heavy-weight mode API

In heavy-weight mode GRO which is based on timer, the GRO packets will not be flushed inspite of timer expiry if there is no packet in the current poll. If timer mode GRO is enabled the rte_gro_timeout_flush API should be invoked. Signed-off-by: Kumara Parameshwaran --- v1: Changes to make su

Re: [PATCH v1] gro : packets not getting flushed in heavy-weight mode API

On Thu, Jan 18, 2024 at 1:22 AM Kumara Parameshwaran < kumaraparames...@gmail.com> wrote: > In heavy-weight mode GRO which is based on timer, the GRO packets will not > be > flushed inspite of timer expiry if there is no packet in the current poll. > If timer mode GRO is enabled the rte_gro_timeou

[PATCH v9] gro: fix reordering of packets in GRO layer

In the current implementation when a packet is received with special TCP flag(s) set, only that packet is delivered out of order. There could be already coalesced packets in the GRO table belonging to the same flow but not delivered. This fix makes sure that the entire segment is delivered with the

Re: [PATCH v9] gro: fix reordering of packets in GRO layer

On Thu, Jan 18, 2024 at 1:40 AM Kumara Parameshwaran < kumaraparames...@gmail.com> wrote: > In the current implementation when a packet is received with > special TCP flag(s) set, only that packet is delivered out of order. > There could be already coalesced packets in the GRO table > belonging to

[PATCH v2] gro : packets not getting flushed in heavy-weight mode API

In heavy-weight mode GRO which is based on timer, the GRO packets will not be flushed inspite of timer expiry if there is no packet in the current poll. If timer mode GRO is enabled the rte_gro_timeout_flush API should be invoked. Signed-off-by: Kumara Parameshwaran --- v1: Changes to make su

[PATCH v3] gro : packets not getting flushed in heavy-weight mode API

In heavy-weight mode GRO which is based on timer, the GRO packets will not be flushed inspite of timer expiry if there is no packet in the current poll. If timer mode GRO is enabled the rte_gro_timeout_flush API should be invoked. Signed-off-by: Kumara Parameshwaran --- v1: Changes to make su

[PATCH v4] gro : packets not getting flushed in heavy-weight mode API

In heavy-weight mode GRO which is based on timer, the GRO packets will not be flushed in spite of timer expiry if there is no packet in the current poll. If timer mode GRO is enabled the rte_gro_timeout_flush API should be invoked. Signed-off-by: Kumara Parameshwaran --- v1: Changes to make s

Re: [dpdk-dev] [PATCH v2] eal: refactor rte_eal_init into sub-functions

On Wed, 17 Jan 2024 11:25:02 -0800 Rahul Gupta wrote: > + lcore_id = rte_lcore_id(); > + lcore_id = rte_get_next_lcore(lcore_id, 0, 1); > + /* Gives status of rte_eal_init_async() */ > + while (rte_eal_init_async_done(lcore_id) == 0) > + ; Will this all work if applic

Re: [PATCH v2 1/2] config/arm: allow WFE to be enabled config time

On 2024/1/17 10:25 PM, pbhagavat...@marvell.com wrote: From: Pavan Nikhilesh Allow RTE_ARM_USE_WFE to be enabled at meson configuration time by passing it via c_args instead of modifying `config/arm/meson.build`. Example usage: meson build -Dc_args='-DRTE_ARM_USE_WFE' \ --cross-fil

Re: [PATCH 1/2] config/arm: fix CN10K minimum march requirement

On 2024/1/4 5:18 PM, pbhagavat...@marvell.com wrote: From: Pavan Nikhilesh Meson selects march and mcpu based on compiler support and partnumber, only the minimum required march should be defined in cross compile configuration file. Fixes: 1b4c86a721c9 ("config/arm: add Marvell CN10K") Cc: s

Re: [PATCH 2/2] config/arm: add armv9-a march

On 2024/1/4 5:18 PM, pbhagavat...@marvell.com wrote: From: Pavan Nikhilesh Now that major versions of GCC recognize armv9-a march option, add it to the list of supported march. Update neoverse-n2 part number to include march as armv9-a. Signed-off-by: Pavan Nikhilesh --- config/arm/meson.

FreeBSD 14.0 build failure

DPDK will not build on FreeBSD 14.0 [2/2] Generating kernel/freebsd/nic_uio with a custom command FAILED: kernel/freebsd/nic_uio.ko /usr/bin/make -f ../kernel/freebsd/BSDmakefile.meson KMOD_OBJDIR=kernel/freebsd KMOD_SRC=../kernel/freebsd/nic_uio/nic_uio.c KMOD=nic_uio 'KMOD_CFLAGS=-I/home/shem

[RFC 1/2] config/arm: add Neoverse V2 part number

Add Arm Neoverse V2 part number Signed-off-by: Honnappa Nagarahalli --- config/arm/meson.build | 10 ++ 1 file changed, 10 insertions(+) diff --git a/config/arm/meson.build b/config/arm/meson.build index 36f21d2259..18b595ead1 100644 --- a/config/arm/meson.build +++ b/config/arm/meson.b

[RFC 2/2] config/arm: add NVIDIA Grace CPU

Add meson build configuration for NVIDIA Grace platform with 64-bit Arm Neoverse V2 cores. Signed-off-by: Honnappa Nagarahalli --- config/arm/arm64_grace_linux_gcc | 16 config/arm/meson.build | 10 ++ 2 files changed, 26 insertions(+) create mode 100644 confi

Re: [RFC 1/2] config/arm: add Neoverse V2 part number

On 2024/1/18 10:32 AM, Honnappa Nagarahalli wrote: Add Arm Neoverse V2 part number Signed-off-by: Honnappa Nagarahalli --- config/arm/meson.build | 10 ++ 1 file changed, 10 insertions(+) diff --git a/config/arm/meson.build b/config/arm/meson.build index 36f21d2259..18b595ead1 100

Re: [RFC 2/2] config/arm: add NVIDIA Grace CPU

On 2024/1/18 10:32 AM, Honnappa Nagarahalli wrote: Add meson build configuration for NVIDIA Grace platform with 64-bit Arm Neoverse V2 cores. Signed-off-by: Honnappa Nagarahalli --- config/arm/arm64_grace_linux_gcc | 16 config/arm/meson.build | 10 ++ 2

Ubuntu Upgrade 20.04.6 to 22.04 Jammy 23.06 HomeGateway example

Dear DPDK Folks, I am following the latest build of home gateway https://s3-docs.fd.io/vpp/23.06/usecases/home_gateway.html for testing and development. Running Linux PXC-SM-002 5.15.0-91-generic #101-Ubuntu vpp/jammy,now 23.10-release amd64 [installed] PRETTY_NAME="Ubuntu 22.04.3 LTS" NAME="Ub

Re: [PATCH v3] event/dsw: optimize serving port logic

On Wed, Jan 17, 2024 at 3:14 PM Mattias Rönnblom wrote: > > To reduce flow migration overhead, replace the array-based > representation of which set of ports are bound to a particular queue > by a bitmask-based one. > > The maximum number of DSW event ports remains 64, but after this > change can

[Bug 1367] net/mlx5 Tx stuck if mbuf has too many segments

https://bugs.dpdk.org/show_bug.cgi?id=1367 Bug ID: 1367 Summary: net/mlx5 Tx stuck if mbuf has too many segments Product: DPDK Version: 23.11 Hardware: All OS: All Status: UNCONFIRMED Severity: normal