On Fri, Apr 5, 2024 at 2:55 AM Tyler Retzlaff
wrote:
> On Thu, Apr 04, 2024 at 09:09:40AM +0200, David Marchand wrote:
> > On Wed, Apr 3, 2024 at 6:49 PM Tyler Retzlaff
> > > this breaks the abi. David does libabigail pick this up i wonder?
> >
> > Yes, the CI flagged it.
> >
> > Looking at the UN
On Thu, Apr 04, 2024 at 11:47:49AM -0700, Tyler Retzlaff wrote:
> On Fri, Mar 15, 2024 at 08:28:55AM +, Bruce Richardson wrote:
> > On Thu, Mar 14, 2024 at 11:30:22PM -0700, Tyler Retzlaff wrote:
> > > Use static deps when default_library=static and use shared deps when
> > > using default_libr
From: Krishna Kanth Reddy
Modified the Configuration file to use the latest ARM Cross-Compiler.
Fixed the linker errors for the undefined references to the APIs
isal_deflate_init, isal_deflate, isal_inflate_init, isal_inflate,
isal_inflate_stateless, isal_deflate_stateless,
isal_deflate_set_huff
From: Tomasz Zawadzki
Starting with Clang 17 the list of pmds could
contain empty string. Please see:
https://bugs.dpdk.org/show_bug.cgi?id=1313
This is a fix proposed by alia...@nvidia.com in the
issue above.
Signed-off-by: Tomasz Zawadzki
Signed-off-by: Sebastian Brzezinka
---
buildtools/p
From: Alexey Marchuk
mlx5 common library checks if several symbols/definitions
are presented in system header files. If some are not
presented, they will be enabled by mlx5_glue library.
The problem appears with clang and '-Werror' - code
generated by meson is not compiled due to unused variable:
Hello Sebastian,
On Fri, Apr 5, 2024 at 1:07 PM Sebastian Brzezinka
wrote:
> -
> Intel Technology Poland sp. z o.o.
> ul. Slowackiego 173 | 80-298 Gdansk | Sad Rejonowy Gdansk Polnoc | VII
> Wydzial Gospodarczy Krajowego Rejestr
On Fri, Apr 5, 2024 at 1:09 PM Sebastian Brzezinka
wrote:
>
> From: Tomasz Zawadzki
>
> Starting with Clang 17 the list of pmds could
> contain empty string. Please see:
> https://bugs.dpdk.org/show_bug.cgi?id=1313
>
> This is a fix proposed by alia...@nvidia.com in the
> issue above.
>
> Signed-
Hi Nicolas,
On 4/5/24 03:24, Chautru, Nicolas wrote:
Maxime,
I am unsure I get the meaning. Is there anything to be done for this patch?
I think it is just a mistake on my side when applying the series, I
don't explain how it happened.
I will pick it for the next release, nothing to do on you
When the rte_memcpy() size is 16, the same 16 bytes are copied twice.
In the case where the size is known to be 16 at build tine, omit the
duplicate copy.
Reduced the amount of effectively copy-pasted code by using #ifdef
inside functions instead of outside functions.
Suggested-by: Stephen Hemmin
This series aims at fixing outer UDP checksum for Intel nics (i40e and
ice). While reviewing the API, I found out some discrepancies in the
mbuf documentation that I tried to fix.
I also noticed that the net/hns3 is really similar in its internals and
aligned its implementation.
As I touched testp
ICE_TX_CTX_EIPT_NONE == 0.
There is a good chance that !(anything & 0) is always true :-).
While removing this part of the check is doable, let's keep a check that
the descriptor does contain a outer ip type.
Fixes: 2ed011776334 ("net/ice: fix outer UDP Tx checksum offload")
Signed-off-by: David
At the moment, if the driver sets an incorrect Tx descriptor, the HW
will raise a MDD event reported as:
ice_interrupt_handler(): OICR: MDD event
Add some debug info for this case and the VF index in all logs.
Signed-off-by: David Marchand
---
drivers/net/ice/ice_ethdev.c | 29 +
Mandate use of rte_eth_tx_prepare() in the mbuf Tx checksum offload
examples.
Remove unneeded resetting of checksums to align with the mbuf
API doxygen.
Clarify the case when requesting "inner" checksum offload with
lack of outer L4 checksum offload.
Fixes: f00dcb7b0a74 ("mbuf: fix Tx checksum o
Resetting the outer IP checksum to 0 is not something mandated by the
mbuf API and is done by rte_eth_tx_prepare(), or per driver if needed.
Fixes: 4fb7e803eb1a ("ethdev: add Tx preparation")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
app/test-pmd/csumonly.c | 10 ++
1 file c
Setting a pseudo header checksum in the outer UDP checksum is a Intel
(and some other vendors) requirement.
Applications (like OVS) requesting outer UDP checksum without doing this
extra setup have broken outer UDP checksums.
Move this specific setup from testpmd to the "common" helper
rte_net_int
According to the X710 datasheet (and confirmed on the field..), X710
devices do not support outer checksum offload.
"""
8.4.4.2 Transmit L3 and L4 Integrity Offload
Tunneling UDP headers and GRE header are not offloaded while the
X710/XXV710/XL710 leaves their checksum field as is.
If a checksum
According to the X710 datasheet, X710 devices do not support outer
checksum offload.
"""
8.4.4.2 Transmit L3 and L4 Integrity Offload
Tunneling UDP headers and GRE header are not offloaded while the
X710/XXV710/XL710 leaves their checksum field as is.
If a checksum is required, software should pr
If requesting an inner (L3/L4 checksum or L4 segmentation) offload,
when the hardware does not support recomputing outer UDP checksum,
automatically disable it in the common helper.
Signed-off-by: David Marchand
---
app/test-pmd/csumonly.c| 10 ++-
doc/guides/prog_guide/mbuf_lib.
Hello,
> On Fri, Apr 5, 2024 at 2:55 AM Tyler Retzlaff
[...]
>> i'm jealous we don't have libabigail on windows, so helpful.
Heh, thank you for the kind words.
David Marchand writes:
[...]
> libabigail is written in C++ and relies on the elfutils and libxml2
> libraries.
That is correct.
On Fri, Apr 05, 2024 at 02:46:28PM +0200, Morten Brørup wrote:
> When the rte_memcpy() size is 16, the same 16 bytes are copied twice.
> In the case where the size is known to be 16 at build tine, omit the
> duplicate copy.
>
> Reduced the amount of effectively copy-pasted code by using #ifdef
> i
When the rte_memcpy() size is 16, the same 16 bytes are copied twice.
In the case where the size is known to be 16 at build tine, omit the
duplicate copy.
Reduced the amount of effectively copy-pasted code by using #ifdef
inside functions instead of outside functions.
Suggested-by: Stephen Hemmin
On Fri, Apr 5, 2024 at 2:51 PM David Marchand wrote:
>
> ICE_TX_CTX_EIPT_NONE == 0.
> There is a good chance that !(anything & 0) is always true :-).
Note to self... rather than joking on a Friday afternoon, re test the
*whole* series.
> @@ -2751,7 +2751,7 @@ ice_parse_tunneling_params(uint64_t
Recheck-request: iol-intel-Functional
checking for lab infra failure
On Thu, Apr 4, 2024 at 11:31 AM Nicholas Pratte wrote:
>
> The previous implementation configures and allocates hugepage sizes
> based on a system default. This can lead to two problems: overallocation of
> hugepages (which may
Recheck-request: iol-intel-Functional
checking for lab infra failure
On Wed, Apr 3, 2024 at 5:51 PM Stephen Hemminger
wrote:
>
> On Wed, 3 Apr 2024 11:23:19 -0700
> Tyler Retzlaff wrote:
>
> > Some libraries that could be built with MSVC were not being built.
> >
> > Switch from explicit inclu
Recheck-request: iol-intel-Functional
I see it's applied but I just want to clean up the record - checking
for lab infra failure
On Thu, Apr 4, 2024 at 6:39 AM Bruce Richardson
wrote:
>
> On Thu, Apr 04, 2024 at 11:18:16AM +0100, Bruce Richardson wrote:
> > On Wed, Apr 03, 2024 at 01:55:41PM +02
Recheck-request: iol-intel-Functional, iol-intel-Performance
On Wed, Apr 3, 2024 at 6:21 AM Jie Hai wrote:
>
> From: Dengdui Huang
>
> Currently, the RTE_MBUF_F_RX_IEEE1588_TMST offload flag will
> not be set when the scatter algorithm is used.
> This patch fixes it.
>
> Fixes: 4801f0403b58 ("ne
This series aims at fixing outer UDP checksum for Intel nics (i40e and
ice). While reviewing the API, I found out some discrepancies in the
mbuf documentation that I tried to fix.
I also noticed that the net/hns3 is really similar in its internals and
aligned its implementation.
As I touched testp
ICE_TX_CTX_EIPT_NONE == 0.
There is a good chance that !(anything & 0) is true :-).
While removing this noop check is doable, let's check that the
descriptor does contain a outer ip type.
Fixes: 2ed011776334 ("net/ice: fix outer UDP Tx checksum offload")
Signed-off-by: David Marchand
---
Change
At the moment, if the driver sets an incorrect Tx descriptor, the HW
will raise a MDD event reported as:
ice_interrupt_handler(): OICR: MDD event
Add some debug info for this case and the VF index in all logs.
Signed-off-by: David Marchand
---
drivers/net/ice/ice_ethdev.c | 29 +
Mandate use of rte_eth_tx_prepare() in the mbuf Tx checksum offload
examples.
Remove unneeded resetting of checksums to align with the mbuf
API doxygen.
Clarify the case when requesting "inner" checksum offload with
lack of outer L4 checksum offload.
Fixes: f00dcb7b0a74 ("mbuf: fix Tx checksum o
Resetting the outer IP checksum to 0 is not something mandated by the
mbuf API and is done by rte_eth_tx_prepare(), or per driver if needed.
Fixes: 4fb7e803eb1a ("ethdev: add Tx preparation")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
app/test-pmd/csumonly.c | 10 ++
1 file c
Setting a pseudo header checksum in the outer UDP checksum is a Intel
(and some other vendors) requirement.
Applications (like OVS) requesting outer UDP checksum without doing this
extra setup have broken outer UDP checksums.
Move this specific setup from testpmd to the "common" helper
rte_net_int
According to the X710 datasheet (and confirmed on the field..), X710
devices do not support outer checksum offload.
"""
8.4.4.2 Transmit L3 and L4 Integrity Offload
Tunneling UDP headers and GRE header are not offloaded while the
X710/XXV710/XL710 leaves their checksum field as is.
If a checksum
According to the X710 datasheet, X710 devices do not support outer
checksum offload.
"""
8.4.4.2 Transmit L3 and L4 Integrity Offload
Tunneling UDP headers and GRE header are not offloaded while the
X710/XXV710/XL710 leaves their checksum field as is.
If a checksum is required, software should pr
If requesting an inner (L3/L4 checksum or L4 segmentation) offload,
when the hardware does not support recomputing outer UDP checksum,
automatically disable it in the common helper.
Signed-off-by: David Marchand
---
app/test-pmd/csumonly.c| 10 ++-
doc/guides/prog_guide/mbuf_lib.
On Fri, 5 Apr 2024 01:22:59 +
"Chautru, Nicolas" wrote:
> Hi Stephen,
>
> Your script is causing some odd line split which are not required I believe.
> Also doing mix of space and tabs.
>
> - rte_memcpy(&desc->req.fcw_ld, &desc_first->req.fcw_ld,
> ACC_FCW_LD_BLEN);
> +
On Thu, 4 Apr 2024 14:04:45 -0700
Nicolas Chautru wrote:
> Capturing additional queue stats counter for the
> depth of enqueue batch still available on the given
> queue. This can help application to monitor that depth
> at run time.
>
> Signed-off-by: Nicolas Chautru
> ---
> lib/bbdev/rte_bb
On 3/30/2024 1:14 PM, Dengdui Huang wrote:
When the port's timestamping function failed to initialize
(for example, the device does not support PTP), the packets
received by the hardware do not contain the timestamp.
In this case, IEEE1588 packet forwarding should not start.
This patch fix it.
> From: David Marchand [mailto:david.march...@redhat.com]
> Sent: Friday, 5 April 2024 16.46
>
> Mandate use of rte_eth_tx_prepare() in the mbuf Tx checksum offload
> examples.
I strongly disagree with this change!
It will cause a huge performance degradation for shaping applications:
A packet
On Sat, 30 Mar 2024 15:44:09 +0800
Dengdui Huang wrote:
> When the port's timestamping function failed to initialize
> (for example, the device does not support PTP), the packets
> received by the hardware do not contain the timestamp.
> In this case, IEEE1588 packet forwarding should not start.
The DPDK has a lot of unnecessary usage of rte_memcpy.
This patch set replaces cases where rte_memcpy is used with a fixed
size constant size.
Typical example is:
rte_memcpy(mac_addrs, mac.addr_bytes, RTE_ETHER_ADDR_LEN);
which can be replaced with:
memcpy(mac_addrs, mac.addr_bytes
Rte_memcpy should not be used for the simple case of copying
a fix size structure because it is slower and will hide problems
from code analysis tools. Coverity, fortify and other analyzers
special case memcpy().
Gcc (and Clang) are smart enough to inline copies which
will be faster.
Signed-off-b
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/eal/common/eal_common_options.c | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/lib/eal/common/eal_common_options.c
b/lib/eal/common/eal_common_options.c
index e541f079
Replace use of rte_memcpy in ethdev. Most of these were
fixed size, and the others were not in the fast path.
Where possible replace memcpy() with structure assignment
which has same effect is type safe.
Signed-off-by: Stephen Hemminger
ethdev: struct assign
---
lib/ethdev/rte_ethdev.c | 12 ++
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/eventdev/rte_event_crypto_adapter.c | 2 +-
lib/eventdev/rte_event_dma_adapter.c| 4 ++--
lib/eventdev/rte_event_timer_adapter.c | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/cryptodev/rte_cryptodev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/cryptodev/rte_cryptodev.c b/lib/cryptodev/rte_cryptodev.c
index 886eb7adc4..137525 100644
---
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/ip_frag/rte_ipv6_fragmentation.c | 4 +---
lib/ip_frag/rte_ipv6_reassembly.c| 6 ++
2 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/lib/ip_frag/rte_ipv6_fragmentation.c
b/l
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/net/rte_ether.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/net/rte_ether.c b/lib/net/rte_ether.c
index f59c20289d..761b38f805 100644
--- a/lib/net/rte_ether.c
+++ b/li
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/lpm/rte_lpm6.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/lib/lpm/rte_lpm6.c b/lib/lpm/rte_lpm6.c
index 46d8f71a2d..242695dd4d 100644
--- a/lib/lpm/rte_lpm6.c
+++ b/lib/
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/node/ip6_lookup.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/lib/node/ip6_lookup.c b/lib/node/ip6_lookup.c
index 309964f60f..b8e567ccd9 100644
--- a/lib/node/ip6_l
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/pdcp/pdcp_process.c | 36 ++--
1 file changed, 18 insertions(+), 18 deletions(-)
diff --git a/lib/pdcp/pdcp_process.c b/lib/pdcp/pdcp_process.c
index 9b9b881124..6
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/pipeline/rte_table_action.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/lib/pipeline/rte_table_action.c b/lib/pipeline/rte_table_action.c
index 87c3e0e2c9..aec84dee
Mostly automatically generated by devtools/cocci/rte_memcpy.cocci
The fib/trie.c was relying on headers
rte_rib6 -> rte_memcpy -> rte_vect
since rib6 is no longer using rte_memcpy need to get rte_vect.h
Signed-off-by: Stephen Hemminger
---
lib/fib/trie.c | 2 +-
lib/rib/rte_rib6.h | 5 +++-
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
lib/security/rte_security.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/security/rte_security.c b/lib/security/rte_security.c
index e5c862f5f5..28d59ef388 100644
--- a/
Included here but never used.
Signed-off-by: Stephen Hemminger
---
drivers/bus/auxiliary/linux/auxiliary.c | 1 -
drivers/bus/fslmc/fslmc_bus.c| 1 -
drivers/bus/fslmc/fslmc_vfio.c | 1 -
drivers/bus/fslmc/portal/dpaa2_hw_dpbp.c | 1 -
drivers/bus/fslmc/portal/dpaa2_hw_dpc
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
drivers/raw/ifpga/afu_pmd_he_hssi.c | 3 +--
drivers/raw/ifpga/afu_pmd_he_lpbk.c | 3 +--
drivers/raw/ifpga/afu_pmd_he_mem.c | 3 +--
drivers/raw/ifpga/afu_pmd_n3000.c
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
drivers/baseband/acc/rte_acc100_pmd.c | 16 +++-
drivers/baseband/acc/rte_vrb_pmd.c | 21 ++---
drivers/baseband/la12xx/bbdev_la12xx.c | 4 ++--
3 files changed, 19 i
Automatically generated by devtools/cocci/rte_memcpy.cocci
Also, remove unnecessary includes of rte_memcpy.h
Signed-off-by: Stephen Hemminger
---
drivers/common/idpf/idpf_common_device.c | 4 ++--
drivers/common/idpf/idpf_common_virtchnl.c | 10 ++
drivers/common/qat/qat_qp.c
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
drivers/crypto/ccp/ccp_crypto.c | 14 +-
drivers/crypto/cnxk/cnxk_cryptodev_ops.c | 2 +-
drivers/crypto/cnxk/cnxk_se.h| 2 +-
3 files changed, 7 insertions(+), 11 d
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
Acked-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c| 2 +-
drivers/crypto/ipsec_mb/pmd_snow3g.c | 4 +-
drivers/crypto/qat/qat_sym_session.c | 52 +
Automatically generated by devtools/cocci/rte_memcpy.cocci
Also, remove unnecessary includes of rte_memcpy.h
Signed-off-by: Stephen Hemminger
---
drivers/event/cnxk/cnxk_eventdev_selftest.c | 1 -
drivers/event/cnxk/cnxk_tim_evdev.c | 4 ++--
drivers/event/dlb2/dlb2.c
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
Acked-by: Hemant Agrawal
---
drivers/mempool/dpaa/dpaa_mempool.c | 4 ++--
drivers/mempool/dpaa2/dpaa2_hw_mempool.c | 5 ++---
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
drivers/ml/cnxk/cn10k_ml_model.c | 8 +---
drivers/ml/cnxk/cn10k_ml_ops.c | 11 +++
drivers/ml/cnxk/cnxk_ml_ops.c| 2 +-
drivers/ml/cnxk/mvtvm_ml_model.c | 8 +---
drivers/ml/
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
app/test-pmd/cmdline.c | 48 ++---
app/test-pmd/cmdline_flow.c | 24 +--
app/test-pmd/config.c | 8 +++
app/test-pmd/csumonly.c | 1
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
app/graph/neigh.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/app/graph/neigh.c b/app/graph/neigh.c
index 79fd542c89..77f0766133 100644
--- a/app/graph/neigh.c
+++ b/ap
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
app/test-eventdev/test_pipeline_common.c | 19 +++
1 file changed, 7 insertions(+), 12 deletions(-)
diff --git a/app/test-eventdev/test_pipeline_common.c
b/app/test-eventdev/test_pip
Automatically generated by devtools/cocci/rte_memcpy.cocci
Signed-off-by: Stephen Hemminger
---
app/test/commands.c | 1 -
app/test/packet_burst_generator.c | 4 +--
app/test/test_crc.c | 5 ++--
app/test/test_cryptodev.c | 18 ++
This included but never used here.
Signed-off-by: Stephen Hemminger
---
app/test-pipeline/config.c | 1 -
app/test-pipeline/init.c| 1 -
app/test-pipeline/main.c| 1 -
app/test-pipeline/runtime.c | 1 -
4 files changed, 4 deletions(-)
diff --git a/app/test-pipeline/config.c b/app/test-
Includes rte_memcpy.h but no rte_memcpy used.
Signed-off-by: Stephen Hemminger
---
app/test-bbdev/test_bbdev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/app/test-bbdev/test_bbdev.c b/app/test-bbdev/test_bbdev.c
index cf224dca5d..7309d85bc5 100644
--- a/app/test-bbdev/test_bbdev.c
+++ b/
Automatically generated by devtools/cocci/rte_memcpy.cocci
Use structure assignment where possible.
Signed-off-by: Stephen Hemminger
---
examples/bbdev_app/main.c | 2 +-
examples/bond/main.c | 1 -
examples/ip_fragmentation/main.c
Recent patch set for rte_memcpy, discovered that the
mail addresses for yuying.zh...@intel.com and zhouguoy...@huawei.com
could not be found.
Signed-off-by: Stephen Hemminger
---
MAINTAINERS | 2 --
1 file changed, 2 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 7abb3aee49..e29e0cdb
Hi Stephen,
It is not strictly ABI compatible since the size of the structure increases,
hence only updating for 24.11.
> -Original Message-
> From: Stephen Hemminger
> Sent: Friday, April 5, 2024 8:15 AM
> To: Chautru, Nicolas
> Cc: dev@dpdk.org; maxime.coque...@redhat.com; hemant.
Hi all,
We are using 2 Mellanox VFs with DPDK v22.11 but seeing an issue when
dpdk rte_proc_secondary process is trying to xmit packets out. Please
note DPDK rte_proc_primary process is able to successfully xmit
packets out. Issue seems to be in check_cqe as it always returns
MLX5_CQE_STATUS_HW_OW
Recheck-request: iol-intel-Functional
Sorry about the spam!
On Tue, Apr 2, 2024 at 12:55 PM Tyler Retzlaff
wrote:
>
> Some libraries that could be built with MSVC were not being built.
>
> Switch from explicit include to exclude of libs to get immediate CI
> coverage of libraries that already wo
The support of doing RSS for rte_flow_action was a cool idea
but it has been broken for several releases of DPDK as the
kernel and BPF infrastructure changed.
This series cleans up the BPF program, implements several
features that were never completed in the original code
and changes to use the cu
The TAP device can use same file descriptopr for both rx and tx queues.
This allows up to 8 queues (versus 4).
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/meson.build | 2 +-
drivers/net/tap/rte_eth_tap.c | 197 +++---
drivers/net/tap/rte_eth_tap.h | 3
The build process for TAP eBPF RSS is now changed, so documentation
needs to be updated.
Since kernel 4.19 is the oldest current LTS supported kernel,
the TAP documentation can be simplified. Any complaints about
flow not working means the kernel is out of scope of current DPDK.
Signed-off-by: St
The driver doesn't support these other hash types, and there
is no reason to implement these in future. The rss_flows list
was set but never used.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/rte_eth_tap.h | 4 +---
drivers/net/tap/tap_flow.c| 1 -
drivers/net/tap/tap_rss.h | 6 -
The flow RSS support via BPF was not using the key, or
hash type parameters. Which is good because they were never
properly setup.
Fix the setup and validate the flow parameters, the BPF
side gets fixed later.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_flow.c | 65
The proper place for finding bpf structures and functions is
in linux/bpf.h. The original version was trying to workaround the
case where the build environment was running on old pre BPF
version of Glibc, but the target environment had BPF.
Having own private (and divergent) version headers leads
Rewrite the BPF program used to do queue based RSS.
Important changes:
- uses newer BPF map format BTF
- accepts key as parameter rather than constant default
- can do L3 or L4 hashing
- supports IPv4 options
- supports IPv6 extension headers
- restru
There were multiple issues in the RSS queue support in the TAP
driver. This required extensive rework of the BPF support.
Change the BPF loading to use bpftool to
create a skeleton header file, and load with libbpf.
The BPF is always compiled from source so less chance that
source and instructions
The BPF api was replaced by use of libbpf.
And the BPF instruction header was replaced by the skeleton.
Signed-off-by: Stephen Hemminger
---
drivers/net/tap/tap_bpf_api.c | 196
drivers/net/tap/tap_bpf_insns.h | 1741 ---
2 files changed, 1937 deletions(-)
de
Change my address as VMware was acquired by Broadcom.
Signed-off-by: Jochen Behrens
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 7abb3aee49..7b13e2b036 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -981,7 +981,7 @@ F: doc/gui
On Mon, Mar 25, 2024 at 7:56 PM Robin Jarry wrote:
>
> Hi Jerin, all,
>
> I apologize in advance for the long email :)
> I am working on a project [1] that uses rte_graph extensively. In the
Great.
You may consider improving and/or adding inbuilt nodes for generic
protocol processing.
Furthermor
Recheck-request: iol-intel-Functional
Replied to the wrong version before
On Wed, Apr 3, 2024 at 2:23 PM Tyler Retzlaff
wrote:
>
> Some libraries that could be built with MSVC were not being built.
>
> Switch from explicit include to exclude of libs to get immediate CI
> coverage of libraries th
86 matches
Mail list logo
