Allows application to query maximum number of mbuf segments that can
be chained together.
Signed-off-by: Gerry Gribbon
Acked-by: Ori Kam
---
v2:
* Moved max_num_mbuf_segs field in the sparse rte_regexdev_info
struct to reuse an existing hole.
* Renamed max_num_mbuf_segs to max_segs.
drivers/
> Subject: [v2 0/7] FIPS asymmetric validation
>
> This patch series adds support in fips_validation app to perform
> asymmetric validation. To start with, RSA algorithm is used in
> the evaluation. For the key value pairs which is multiprecision
> in arithmetic, openssl library is used.
>
> Chan
> > Subject: [v1] examples/fips_validation: fix SHA MCT test from segfault
> >
> > In case of FIPS 140-2 format of test vectors in MCT test, msg is not given
> > in
> > the test vector, hence pt will be NULL which test function has to handle
> > correctly.
> >
> > Fixes: d5c247145c2c ("examples/fi
> > Subject: [PATCH v2 2/2] examples/fips_validation: add parsing for TDES
> >
> > Added function to parse algorithm for TDES CBC and ECB tests in json.
> >
> > Signed-off-by: Gowrishankar Muthukrishnan
> > ---
>
> Acked-by: Brian Dooley
Series applied to dpdk-next-crypto
Thanks.
> > Subject: [PATCH v2] examples/fips_validation: fix memory allocation in AES
> > MCT test
> >
> > Instead of allocating memory in every external iteration, do once in the
> > beginning of AES MCT tests and free at the end.
> >
> > Fixes: 8b8546aaedf ("examples/fips_validation: add parsing for AES
On 10/7/22 09:09, Sunil Kumar Kori wrote:
-Original Message-
From: Andrew Rybchenko
Sent: Tuesday, October 4, 2022 2:33 PM
To: Ferruh Yigit ; Thomas Monjalon
; Ray Kinsella
Cc: dev@dpdk.org; Jerin Jacob Kollanukkaran ; Sunil
Kumar Kori
Subject: [EXT] [PATCH v4] ethdev: support congesti
This patch provides a function for memory copy using non-temporal store,
load or both, controlled by flags passed to the function.
Applications sometimes copy data to another memory location, which is only
used much later.
In this case, it is inefficient to pollute the data cache with the copied
d
The title of this patch needs an update - I would suggest something
like:
"build: make version file optional for drivers"
More comments inline below.
On Thu, Oct 06, 2022 at 10:19:22AM +0300, Abdullah Ömer Yamaç wrote:
> Most of the drivers don't have a special version.map file. They just
> incl
On 06/10/2022 18:32, Stephen Hemminger wrote:
On Thu, 6 Oct 2022 09:38:01 +
Tadhg Kearney wrote:
Add API to allow uncore frequency adjustment. Uncore is a
term used by Intel to describe function of a microprocessor
that are closely connected to the core to achieve high
performance. This
On Wed, Oct 05, 2022 at 10:10:10PM +0200, David Marchand wrote:
> On Wed, Oct 5, 2022 at 4:35 PM Bruce Richardson
> wrote:
> >
> > To ensure all users are aware of KNI's deprecated status at build time
> > we can take the following actions:
> >
> > 1. disable the library by default. It can be re-e
> > Subject: [PATCH v1] examples/fips_validation: fix parsing SHA test type from
> > JSON vector
> >
> > Store SHA test type in its own interim info struct instead of AES.
> >
> > Fixes: d5c247145c2 ("examples/fips_validation: add parsing for SHA")
> >
> > Signed-off-by: Gowrishankar Muthukrishnan
From: Morten Brørup
A flush threshold for the mempool cache was introduced in DPDK version
1.3, but rte_mempool_do_generic_get() was not completely updated back
then, and some inefficiencies were introduced.
Fix the following in rte_mempool_do_generic_get():
1. The code that initially screens t
Hi Brian,
> Added functionality to parse algorithm for AES CTR test
>
> Signed-off-by: Brian Dooley
> Acked-by: Kai Ji
> Acked-by: Gowrishankar Muthukrishnan
> ---
> v2: fix clang warning for int-in-bool-context
> ---
> v3: in reply to fix and patchwork CI
> ---
> v4: missing acks
> ---
> exam
Hi Brian,
> Subject: [v1 2/2] examples/fips_validation: add ECDSA validation
>
> This patch adds support in fips_validation app to validate ECDSA.
>
> Signed-off-by: Gowrishankar Muthukrishnan
> ---
Can you review this and ack?
> This patch reallocates the openssl version check from
> qat_session_configure() to a proper qat_security_session_create()
> routine
>
> Fixes: 3227bc7138f5 ("crypto/qat: use intel-ipsec-mb for partial hash and
> AES")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Brian Dooley
> ---
Please rebase.
> Fixed not set output length in asym pmd
> when doing RSA.
>
> Fixes: 002486db239e ("crypto/qat: refactor asymmetric session")
>
> Signed-off-by: Arek Kusztal
Please fix compilation
Hello Bruce,
On Wed, Oct 5, 2022 at 4:35 PM Bruce Richardson
wrote:
> diff --git a/drivers/net/kni/meson.build b/drivers/net/kni/meson.build
> index 2acc989694..2deb2c4166 100644
> --- a/drivers/net/kni/meson.build
> +++ b/drivers/net/kni/meson.build
> @@ -6,6 +6,11 @@ if is_windows
> reason
On 10/6/2022 6:13 PM, Stephen Hemminger wrote:
On Thu, 6 Oct 2022 16:26:24 +0800
Dongdong Liu wrote:
Do you think does it worth to list this as one of the PMD future in
future list, in 'doc/guides/nics/features.rst' ?
As Andrew said
It does not deserve entry in features.
It is a deep debuggin
>
> Add fixed point multiplication for EC curve in CNXK.
>
> Signed-off-by: Kiran Kumar K
> Signed-off-by: Gowrishankar Muthukrishnan
Acked-by: Anoob Joseph
On 9/12/22 12:09, Thomas Monjalon wrote:
> 16/03/2022 13:01, Ilya Maximets:
>> 'has_vlan' attribute is only supported by sfc, mlx5 and cnxk.
>> Other drivers doesn't support it. Most of them (like i40e) just
>> ignore it silently. Some drivers (like mlx4) never had a full
>> support of the eth it
On 10/7/22 13:50, Ilya Maximets wrote:
> On 9/12/22 12:09, Thomas Monjalon wrote:
>> 16/03/2022 13:01, Ilya Maximets:
>>> 'has_vlan' attribute is only supported by sfc, mlx5 and cnxk.
>>> Other drivers doesn't support it. Most of them (like i40e) just
>>> ignore it silently. Some drivers (like ml
> Subject: RE: [v1] crypto/cnxk: add support for fixed point multiplication
Add support for -> support
>
> >
> > Add fixed point multiplication for EC curve in CNXK.
> >
> > Signed-off-by: Kiran Kumar K
> > Signed-off-by: Gowrishankar Muthukrishnan
>
> Acked-by: Anoob Joseph
>
Applied to dpd
> Subject: [v1] crypto/cnxk: support exponent type private key
>
> This patch adds support for RTE_RSA_KEY_TYPE_EXP in cnxk crypto
> driver.
>
> Signed-off-by: Gowrishankar Muthukrishnan
> ---
> drivers/crypto/cnxk/cnxk_ae.h| 60 ++--
> drivers/crypto/cnxk/cnxk_c
On Fri, Oct 07, 2022 at 01:08:38PM +0200, David Marchand wrote:
> Hello Bruce,
>
> On Wed, Oct 5, 2022 at 4:35 PM Bruce Richardson
> wrote:
> > diff --git a/drivers/net/kni/meson.build b/drivers/net/kni/meson.build
> > index 2acc989694..2deb2c4166 100644
> > --- a/drivers/net/kni/meson.build
> >
On Mon, Sep 12, 2022 at 7:08 PM Bruce Richardson
wrote:
>
> This patchset bumps the minimum meson version from 0.49.2 to 0.53.
> Rather than specifying a specific point-release of 0.53, as was done
> with 0.49, the version specifier is kept to the major release number
> only for simplicity, as new
> Add support for 8-byte and 16-byte tags for ZUC-EIA3-256.
>
> Signed-off-by: Pablo de Lara
Applied to dpdk-next-crypto
Thanks.
> Subject: [PATCH v3] examples/ipsec-secgw: free event vector mbufs
>
> Free mbufs from event vector list when enqueue operation fails
> and during event port flush for cleanup.
>
> Signed-off-by: Rahul Bhansali
Acked-by: Akhil Goyal
Applied to dpdk-next-crypto
Thanks.
Add removal note for experimental empty poll API.
CC: David Hunt
Signed-off-by: Reshma Pattan
Acked-by: David Hunt
---
doc/guides/prog_guide/power_man.rst | 8
1 file changed, 8 insertions(+)
diff --git a/doc/guides/prog_guide/power_man.rst
b/doc/guides/prog_guide/power_man.rst
ind
Currently, the intel-ipsec-mb library only supports SGL for
GCM and ChaCha20-Poly1305 algorithms through the JOB API.
To add SGL support for other algorithms, a workaround approach is
added in the AESNI_MB PMD. SGL feature flags can now be added to
the PMD.
Some additional Snow3G SGL and AES test
The segment size for some tests was too small to hold the auth digest.
This caused issues when using op->sym->auth.digest.data for comparisons
in AESNI_MB PMD after a subsequent patch enables SGL.
For example, if segment size is 2, and digest size is 4, then 4 bytes
are read from op->sym->auth.dig
The intel-ipsec-mb library supports SGL for GCM and ChaChaPoly
algorithms using the JOB API.
This support was added to AESNI_MB PMD previously, but the SGL feature
flags could not be added due to no SGL support for other algorithms.
This patch adds a workaround SGL approach for other algorithms
us
More tests are added to test variations of OOP SGL for snow3g.
This includes LB_IN_SGL_OUT and SGL_IN_LB_OUT.
Signed-off-by: Ciara Power
Acked-by: Fan Zhang
Acked-by: Pablo de Lara
---
app/test/test_cryptodev.c | 48 +++
1 file changed, 39 insertions(+), 9 d
The current blockcipher test function only has support for two types of
SGL test, INPLACE or OOP_SGL_IN_LB_OUT. These types are hardcoded into
the function, with the number of segments always set to 3.
To ensure all SGL types are tested, blockcipher test vectors now have
fields to specify SGL type
21/09/2022 15:56, Shijith Thotton:
> This is a continuation of the discussions[1] to add mbuf physical address
> field to dynamic field.
> Previous version was to add PA field to dynamic field area based on the EAL
> IOVA mode option. It was
> deemed unsafe as some components could still use the
> -Original Message-
> From: Thomas Monjalon
-- snip --
> > +Removal Note
> > +
> > +The experimental empty poll APIs will be removed from the library in
> > +a future DPDK release.
>
> It looks common in this file to forget the empty line after a title, but
> please
> don
Please rebase
Acked-by: Kai Ji
> -Original Message-
> From: Dooley, Brian
> Sent: Monday, October 3, 2022 4:27 PM
> To: Ji, Kai
> Cc: dev@dpdk.org; sta...@dpdk.org; Dooley, Brian
>
> Subject: [PATCH v1] crypto/qat: reallocate on openssl version check
>
> This patch reallocates the op
On Fri, Oct 07, 2022 at 03:17:57PM +0200, David Marchand wrote:
> On Mon, Sep 12, 2022 at 7:08 PM Bruce Richardson
> wrote:
> >
> > This patchset bumps the minimum meson version from 0.49.2 to 0.53.
> > Rather than specifying a specific point-release of 0.53, as was done
> > with 0.49, the version
On 10/6/22 20:29, Stephen Hemminger wrote:
On Thu, 6 Oct 2022 22:31:24 +0530
Hanumanth Pothula wrote:
+ /**
+* Points to an array of mempools.
+*
+* Valid only when RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL flag is set in
+* Rx offloads.
+*
+* This pr
Hi Kai,
> -Original Message-
> From: Kai Ji
> Sent: Tuesday 4 October 2022 17:09
> To: dev@dpdk.org
> Cc: gak...@marvell.com; Ji, Kai ; sta...@dpdk.org
> Subject: [dpdk-dev v1] crypto/qat: fix of qat build request session in mp
>
> This patch fix the session pointer passed in set_session
I'm not sure in testpmd patch. Review would be useful and may be we
should postpone it to rc2.
v7:
- Drop RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL offload which seems to be
unnecessary. Positive max_rx_mempools in dev_info is sufficient to
indicate that the capability is support and positive number o
Avoid Rx mempool checks duplication logic.
Signed-off-by: Andrew Rybchenko
---
lib/ethdev/rte_ethdev.c | 82 +
1 file changed, 42 insertions(+), 40 deletions(-)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 01fac713a2..b3dba291e7 10
From: Hanumanth Pothula
Presently, HW is programmed only to receive packets from LPB pool.
Making all packets received from LPB pool.
But, CNXK HW supports two pools,
- SPB -> packets with smaller size (less than 4K)
- LPB -> packets with bigger size (greater than 4K)
Patch enables multiple m
From: Hanumanth Pothula
This patch adds support for the mulitiple mempool.
Some of the HW has support for choosing memory pools based on the
packet's size. The pool sort capability allows PMD to choose a
memory pool based on the packet's length.
On multiple mempool support enabled, populate memp
From: Hanumanth Pothula
Some of the HW has support for choosing memory pools based on the
packet's size. The capability allows to choose a memory pool based
on the packet's length.
This is often useful for saving the memory where the application
can create a different pool to steer the specific
> -Original Message-
> +/* Enable dump Rx/Tx descriptor. */
> +#define DESC_PARAM_NUM 3
> +
> +struct desc_param {
> + uint16_t queue_id; /* A queue identifier on this port. */
> + uint16_t offset;/* The offset of the descriptor starting from tail.
> */
> + uint16_t num
To ensure all users are aware of KNI's deprecated status at build time
we can take the following actions:
1. disable the library by default. It can be re-enabled by setting
disabled_libs to the empty string (or other string not including
'kni')
2. add support for a list of deprecated libs t
When KNI is being used at runtime, output a warning message about its
deprecated status. This is part of the deprecation process for KNI
agreed by the DPDK technical board.[1]
[1] http://mails.dpdk.org/archives/dev/2022-June/243596.html
Signed-off-by: Bruce Richardson
---
doc/guides/rel_notes/d
While KNI (or any other deprecated library) may be disabled by default,
for build testing we need it enabled. Therefore explicitly set
"disable_libs" build parameter to empty for any DPDK build where the
value is not being explicitly set by the script.
Signed-off-by: Bruce Richardson
---
devtool
On 10/7/2022 4:27 AM, Gagandeep Singh wrote:
This series have list of patch for bug fixes and
some enhancements to DPAA1 and DPAA2 net drivers.
v2-change-log:
* update commit messages
* update DPAA NIC doc for kernel version matching
* update DPAA supported packet type info
* Freeing the interna
On Fri, Oct 7, 2022 at 4:11 PM Bruce Richardson
wrote:
> > - We have an issue with mingw cross compilation.
> > https://github.com/ovsrobot/dpdk/actions/runs/3039251235/jobs/4893964186
> >
> > + meson build --werror --cross-file config/x86/cross-mingw
> > -Dexamples=helloworld -Dplatform=generic -
On Fri, Oct 07, 2022 at 05:26:05PM +0200, David Marchand wrote:
> On Fri, Oct 7, 2022 at 4:11 PM Bruce Richardson
> wrote:
> > > - We have an issue with mingw cross compilation.
> > > https://github.com/ovsrobot/dpdk/actions/runs/3039251235/jobs/4893964186
> > >
> > > + meson build --werror --cros
This patch reallocates the openssl version check from
qat_session_configure() to a proper qat_security_session_create()
routine
Fixes: 3227bc7138f5 ("crypto/qat: use intel-ipsec-mb for partial hash and AES")
Cc: sta...@dpdk.org
Signed-off-by: Brian Dooley
---
v2: rebase on main
---
drivers/cryp
On Fri, Oct 7, 2022 at 5:34 PM Bruce Richardson
wrote:
>
> On Fri, Oct 07, 2022 at 05:26:05PM +0200, David Marchand wrote:
> > On Fri, Oct 7, 2022 at 4:11 PM Bruce Richardson
> > wrote:
> > > > - We have an issue with mingw cross compilation.
> > > > https://github.com/ovsrobot/dpdk/actions/runs/
07/10/2022 16:37, Andrew Rybchenko:
> From: Hanumanth Pothula
>
> Some of the HW has support for choosing memory pools based on the
> packet's size. The capability allows to choose a memory pool based
> on the packet's length.
The second sentence is redundant.
> This is often useful for saving
On Fri, 07 Oct 2022 18:08:57 +0200
Thomas Monjalon wrote:
> > + /* Ensure that we have one and only one source of Rx buffers */
> > + if ((mp != NULL) +
>
> + operator?
> Are we sure a boolean is always translated as 1?
Yes, it is likely part of C standard.
On Fri, 7 Oct 2022 09:18:14 -0700
Stephen Hemminger wrote:
> On Fri, 07 Oct 2022 18:08:57 +0200
> Thomas Monjalon wrote:
>
> > > + /* Ensure that we have one and only one source of Rx buffers */
> > > + if ((mp != NULL) +
> >
> > + operator?
> > Are we sure a boolean is always translated a
This patchset bumps the minimum meson version from 0.49.2 to 0.53.2.
Ideally, the minimum version should be 0.53 without a point release, but
some DPDK builds (mingw) are broken with 0.53.0 due to issue[1], fixed
by commit[2] in 0.53.1. Therefore we use the latest point release from
0.53 branch i.e
Hi Morten,
>-Original Message-
>From: Ankur Dwivedi
>Sent: Thursday, October 6, 2022 8:49 PM
>To: dev@dpdk.org
>Cc: tho...@monjalon.net; m...@ashroe.eu; or...@nvidia.com;
>ferruh.yi...@xilinx.com; ch...@att.com; humi...@huawei.com;
>linvi...@tuxdriver.com; ciara.lof...@intel.com; qi.z.zh.
On 10/7/22 19:20, Stephen Hemminger wrote:
On Fri, 7 Oct 2022 09:18:14 -0700
Stephen Hemminger wrote:
On Fri, 07 Oct 2022 18:08:57 +0200
Thomas Monjalon wrote:
+ /* Ensure that we have one and only one source of Rx buffers */
+ if ((mp != NULL) +
+ operator?
Are we sure a bool
Anyone from Red Hat care to suggest a fix for the problem below, related to the
ancient GCC (version 4.8.5) on RHEL 7?
I get this warning:
error: unknown option after '#pragma GCC diagnostic' kind [-Werror=pragmas]
for source code containing:
#pragma GCC diagnostic ignored "-Wdiscarded-qualifier
Added functionality to parse algorithm for AES CTR test
Signed-off-by: Brian Dooley
Acked-by: Kai Ji
Acked-by: Gowrishankar Muthukrishnan
---
v2: fix clang warning for int-in-bool-context
---
v3: in reply to fix and patchwork CI
---
v4: missing acks
---
v5: add documentation
---
doc/guides/sam
On 10/6/2022 7:26 AM, Andrew Rybchenko wrote:
From: Ciara Loftus
libbpf v0.8.0 deprecates the bpf_get_link_xdp_id() and
bpf_set_link_xdp_fd() functions. Use meson to detect if
bpf_xdp_attach() is available and if so, use the recommended
replacement functions bpf_xdp_query_id(), bpf_xdp_attach()
On 10/7/2022 6:19 PM, Ferruh Yigit wrote:
On 10/6/2022 7:26 AM, Andrew Rybchenko wrote:
From: Ciara Loftus
libbpf v0.8.0 deprecates the bpf_get_link_xdp_id() and
bpf_set_link_xdp_fd() functions. Use meson to detect if
bpf_xdp_attach() is available and if so, use the recommended
replacement fun
Avoid Rx mempool checks duplication logic.
Signed-off-by: Andrew Rybchenko
---
lib/ethdev/rte_ethdev.c | 82 +
1 file changed, 42 insertions(+), 40 deletions(-)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 01fac713a2..b3dba291e7 10
I'm not sure in testpmd patch. Review would be useful and may be we
should postpone it to rc2.
v8:
- Process review notes
v7:
- Drop RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL offload which seems to be
unnecessary. Positive max_rx_mempools in dev_info is sufficient to
indicate that the capability is s
From: Hanumanth Pothula
Some of the HW has support for choosing memory pools based on the
packet's size.
This is often useful for saving the memory where the application
can create a different pool to steer the specific size of the
packet, thus enabling more efficient usage of memory.
For examp
From: Hanumanth Pothula
Some of the HW has support for choosing memory pools based on the
packet's size. The pool sort capability allows PMD/NIC to choose
a memory pool based on the packet's length.
On multiple mempool support enabled, populate mempool array and
also print pool name on which pac
From: Hanumanth Pothula
Presently, HW is programmed only to receive packets from LPB pool.
Making all packets received from LPB pool.
But, CNXK HW supports two pools,
- SPB -> packets with smaller size (less than 4K)
- LPB -> packets with bigger size (greater than 4K)
Patch enables multiple m
On 10/7/22 19:08, Thomas Monjalon wrote:
07/10/2022 16:37, Andrew Rybchenko:
@@ -1067,6 +1067,24 @@ struct rte_eth_rxconf {
*/
union rte_eth_rxseg *rx_seg;
+ /**
+* Array of mempools to allocate Rx buffers from.
+*
+* This provides support for multipl
On 10/6/2022 7:26 AM, Andrew Rybchenko wrote:
Update net/af_xdp build to support libbfp v0.8.0.
Avoid library version based checks, check for function presense
instead.
v4:
- just rebase
- do not mention libbpf v0.8.0 as a strict limitation
v3:
- avoid version-based checks
Andre
This patch series provides features and performance improvements
relevant for the upstream release of DPDK 22.11.
There are some bits (like struct ionic_dev_intf) only useful
for drivers and device types which have not yet been upstreamed.
All of the changes are confined to the ionic PMD.
Links t
These fields all need to be LE when talking to the FW.
Fixes: a27d901331da ("net/ionic: add Rx and Tx handling")
Cc: cardigli...@ntop.org
Cc: sta...@dpdk.org
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 27 +++
1 file changed, 15 insertions(+), 12 del
This field needs to be LE when talking to the FW.
Fixes: 22e7171bc63b ("net/ionic: support RSS")
Cc: cardigli...@ntop.org
Cc: sta...@dpdk.org
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ionic/ioni
Otherwise the log messages will be garbled.
Fixes: 4ae96cb88fa0 ("net/ionic: do minor logging fixups")
Cc: sta...@dpdk.org
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ionic/ionic_dev.c b/driver
Check the match variable after copying cmd info, or else there can
be unexpected results.
Fixes: a27e0e96ab77 ("net/ionic: observe endianness in Rx filter")
Cc: andrew.bo...@amd.com
Cc: sta...@dpdk.org
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rx_filter.c | 2 +-
1 file changed, 1
Report descriptor errors in ierrors instead of imissed.
Don't report rx_queue_empty or rx_queue_disabled in imissed,
since those packet errors are already included in the
rx_*_drop_packets counters.
This makes the reported stats correct.
Fixes: 3cdfd90579e7 ("net/ionic: add stats")
Cc: cardigli...
Pensando Systems has been acquired by AMD.
Update all copyright strings and email addresses.
Signed-off-by: Andrew Boyer
---
MAINTAINERS| 4 ++--
doc/guides/nics/ionic.rst | 16
doc/guides/rel_notes/release_22_11.rst | 5 +
drivers/
Remove GPL2 and leave only BSD-3-Clause. This is more in line with
the norms of the DPDK community.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic.h | 2 +-
drivers/net/ionic/ionic_dev.c | 2 +-
drivers/net/ionic/ionic_dev.h | 2 +-
drivers/net/ionic/ionic_ethdev.c
Test min and max MTU against values read from firmware, for correctness.
Update the firmware field name, for clarity.
The device must be stopped before changing MTU, for correctness.
Store the calculated frame size in the queue, for performance.
Signed-off-by: Andrew Boyer
Signed-off-by: R Mohame
There is only one doorbell page in DPDK configurations, so
no helper function is needed.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 13 +
1 file changed, 1 insertion(+), 12 deletions(-)
diff --git a/drivers/net/ionic/ionic_lif.c b/drivers/net/ionic/ionic_lif.c
i
These bits are not used. Remove them to simplify the code.
Fix the spacing on the IONIC_ALIGN #define.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic.h| 1 -
drivers/net/ionic/ionic_dev.h| 4 +---
drivers/net/ionic/ionic_ethdev.h | 2 --
3 files changed, 1 insertion(+), 6 de
There is no need to allocate the interrupt vector list if
datapath packet interrupts are not enabled.
This conserves resources.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_ethdev.c | 12 +++-
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ionic/ioni
Enable the interrupt if the platform & device support it.
This prevents spurious interrupts on virtual platforms.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ionic/ionic_lif.c b/drivers
For future support of virtual devices, move the PCI code to its own
file. Create a new device interface, struct ionic_dev_intf, to plug
in to common code.
Signed-off-by: Andrew Boyer
Signed-off-by: Neel Patel
Signed-off-by: R Mohamed Shah
---
drivers/net/ionic/ionic.h | 13 +-
drivers
Free all of the mbufs in the receive queue when the queue is
stopped. This will allow them to be resized when the MTU is
changed.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c | 16 +
drivers/net/ionic/ionic_dev.h | 2 +
drivers/net/ionic/ionic_lif.c | 32 -
dr
The first (header) segment includes the standard headroom.
Subsequent segments do not.
Store the fragment counts in the queue structure.
Precalculating improves performance by reducing
how much work must be done in the hot path.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.h |
This makes the code safer by helping the compiler catch errors.
Rename the variables, too; they're not callbacks anymore.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 28 +---
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/drivers/net/
This improves readability.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/net/ionic/ionic_rxtx.c
index 0f251eca13..0c1cc842cf 100644
--- a/drivers/net/ionic/io
Linearize Tx mbuf chains in the info array.
This avoids walking the mbuf chain during flush.
Move a few branches out of the hot path.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.c | 2 +-
drivers/net/ionic/ionic_rxtx.c | 143 -
2 files changed,
These fields don't need to be set in the hot path.
This improves performance.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 38 ++
1 file changed, 34 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/net/ionic/
Linearize RX mbuf chains in the expanded info array.
Clean one and fill one per CQE (completions are not coalesced).
Touch the mbufs as little as possible in the fill stage.
When touching the mbuf in the clean stage, use the rearm_data unions.
Ring the doorbell once at the end of the bulk clean/fil
Use a put() rather than a free() in the optimized case.
Signed-off-by: Andrew Boyer
---
doc/guides/nics/features/ionic.ini | 1 +
doc/guides/rel_notes/release_22_11.rst | 1 +
drivers/net/ionic/ionic_ethdev.c | 2 +-
drivers/net/ionic/ionic_lif.h | 1 +
drivers/net/ionic/ionic
Do bulk allocations to improve performance.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_lif.h | 6 ++
drivers/net/ionic/ionic_rxtx.c | 35 ++
2 files changed, 33 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ionic/ionic_lif.h b/drivers/
This improves performance by reducing branching.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 63 --
1 file changed, 29 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/net/ionic/ionic_rxtx.c
index 5ee6573a5
This improves performance by reducing branching.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_rxtx.c | 47 --
1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ionic/ionic_rxtx.c b/drivers/net/ionic/ionic_rxtx.c
index bb09c4eb1
This improves performance, since clients may be able to skip SW
packet classification.
Signed-off-by: Andrew Boyer
---
doc/guides/rel_notes/release_22_11.rst | 1 +
drivers/net/ionic/ionic_ethdev.c | 1 +
drivers/net/ionic/ionic_rxtx.c | 19 +++
drivers/net/ionic/
These may be useful for clients.
Signed-off-by: Andrew Boyer
Signed-off-by: Allen Hubbe
---
doc/guides/nics/features/ionic.ini | 1 +
doc/guides/rel_notes/release_22_11.rst | 1 +
drivers/net/ionic/ionic_ethdev.c | 2 ++
drivers/net/ionic/ionic_rxtx.c | 39 +
This may be useful for clients.
Signed-off-by: Andrew Boyer
Signed-off-by: Allen Hubbe
---
doc/guides/nics/features/ionic.ini | 1 +
drivers/net/ionic/ionic_ethdev.c | 1 +
drivers/net/ionic/ionic_rxtx.c | 51 ++
drivers/net/ionic/ionic_rxtx.h | 1 +
4 f
When 'ionic_cmb' is set to '1', queue memory will be allocated from
the device's onboard memory (Controller Memory Buffer). In some
configurations, this will dramatically reduce packet latency and
increase PPS.
Add the WC_ACTIVATE flag to the PCI driver flags.
Write combining must be enabled to ac
Some clients have opinions about how often to flush the
transmit ring.
The default value is the number of Tx descriptors minus the
default Tx burst size.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.h| 1 +
drivers/net/ionic/ionic_ethdev.c | 4 ++--
drivers/net/ionic/ionic_
1 - 100 of 189 matches
Mail list logo