binding with vfio driver, when IOMMU is disabled, causes program to crash.
this patch adds a flag for noiommmu-mode. when this is set, if IOMMU is
disabled, it changes vfio into unsafe noiommu mode and prints warning
message.
Signed-off-by: Fidaullah Noonari
---
usertools/dpdk-devbind.py | 39 ++
Hi Wenwu,
> -Original Message-
> From: Ma, WenwuX
> Sent: Thursday, February 17, 2022 11:16 PM
> To: maxime.coque...@redhat.com; Xia, Chenbo
> Cc: dev@dpdk.org; Hu, Jiayu ; Wang, Yinan
> ; He, Xingguang ; Ma,
> WenwuX
> Subject: [PATCH] net/vhost: get csum offload capabilities of vhost
vDPA driver first uses kernel driver to allocate doorbell(VAR) area for
each device. Then uses var->mmap_off and var->length to mmap uverbs device
file as doorbell userspace virtual address.
Current kernel driver provides var->mmap_off equal to page start of VAR.
It's fine with x86 4K page server,
Virtual devices created on ifpga raw device are not removed when
ifpga is closed. To avoid such problem, ifpga virtual device remove
function is implemented, virtual device is removed in raw device
close function.
Signed-off-by: Wei Huang
Acked-by: Tianfei Zhang
Acked-by: Rosen Xu
---
v2: clean
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v22.03-rc4
There are 31 new patches in this snapshot.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_22_03.html
This is the last release candidate.
Only documentation should be upda
11/03/2022 21:05, Bruce Richardson:
> This set contains a number of fixes, most of which are for
> build issues discovered when compiling on FreeBSD with clang.
>
> Bruce Richardson (5):
> eal/freebsd: add missing C++ include guards
> compressdev: separate out driver-only headers
> compressd
09/03/2022 12:25, Ferruh Yigit:
> Won't able to allocate time on these components, resigning from
> maintaining them.
>
> Signed-off-by: Ferruh Yigit
Applied
Thanks for all the good work
> > This patch fixes the stack buffer overflow error reported
> > from AddressSanitizer.
> > Function send_packetsx4() tries to access out of bound data
> > from rte_mbuf and fill it into TX buffer even in the case
> > where no pending packets (len = 0).
> > Performance impact:- No
> >
> > ASAN er
https://bugs.dpdk.org/show_bug.cgi?id=957
Bug ID: 957
Summary: IXGBE LSC IRQ configured state is lost on certain link
down events
Product: DPDK
Version: 20.11
Hardware: All
OS: All
Status: UNCONF
From: Shuanglin Wang
Fix ulp parser to ignore segment_offset of IPV4 header.
Currently the IPV4 handler is assuming default setting,
which causes the flow table to be updated incorrectly.
Fixes: 741172be52de ("net/bnxt: refactor flow parser in ULP")
Cc: sta...@dpdk.org
Signed-off-by: Shuanglin
> > Testpmd reads flex item configuration from a JSON file.
> > Flex item input link description is stored in testpmd flow item format. For
> > example, `eth type is 0x0800`.
> > The item description is placed into a general testpmd CLI flow rule command
> > template and parsed to convert string in
13/03/2022 10:01, Gregory Etelson:
> GTP header can be followed by an optional 32 bits extension.
> GTP notifies about the extension presence through the E, S or PN
> header bits.
>
> Csum GTP header parser did not check the extension bits value.
>
> The patch updates GTP header length if at-leas
09/03/2022 12:50, Dariusz Sosnowski:
> From: Ferruh Yigit
> > On 3/1/2022 11:51 AM, Dariusz Sosnowski wrote:
> > > This patch adds implicit registration of metadata dynamic field and
> > > flag
> >
> > Hi Dariusz,
> >
> > metaday dynamic field is explicitly registered when testpmd command used
>
13/03/2022 14:21, Tal Shnaiderman:
> > Subject: [PATCH v3] app/testpmd: fix show RSS RETA on Windows
> >
> > Replaced using strtoul with strtoull when converting to 64-bit mask field.
> > In Windows strtoul returns 32-bit values which cause an issue with show RSS
> > RETA.
> >
> > Fixes: 66c59490
> > Replaced using strtoul with strtoull when converting to
> > 64-bit mask field.
> > In Windows strtoul returns 32-bit values which cause an
> > issue with show RSS reta.
> >
> > Fixes: 66c594904ac ("ethdev: support multiple sizes of redirection table")
> > Cc:sta...@dpdk.org
> >
> > Signed-off-b
14/03/2022 03:33, Zhang, Qi Z:
> From: Yigit, Ferruh
> > On 3/11/2022 7:04 AM, Liu, KevinX wrote:
> > > From: Zhang, Yuying
> > >>> From: Liu, KevinX
> > Testpmd forwards packets in checksum mode that it needs to
> > calculate the checksum of each layer's protocol.
> >
> > In
This reverts commit d91c4b1bb5a938734fe8e66da8f965304919f38e.
When enabling TC OV unconditionally, it is observed the performance
drops by ~20% hence reverting this commit.
Fixes: d91c4b1bb5a9 ("sched: enable traffic class oversubscription
unconditionally")
Signed-off-by: Megha Ajmera
---
conf
> -Original Message-
> From: Jiang, YuX
> Sent: Thursday, March 10, 2022 4:58 PM
> To: Thomas Monjalon ; dev (dev@dpdk.org)
> ; Yigit, Ferruh ; Maxime Coquelin
> ; Jerin Jacob Kollanukkaran
>
> Cc: Devlin, Michelle ; Mcnamara, John
> ; Yigit, Ferruh
> Subject: RE: release candidate 22.03-
10/03/2022 00:41, Gerry Gribbon:
> Depending on number of jobs specified on command line, part of the
> data buffer may not get searched, resulting in incorrect number of
> matches being reported.
>
> Additional change to ensure the "All Matches" summary outputs the
> correct match start locations
10/03/2022 19:54, Stephen Hemminger:
> On Thu, 10 Mar 2022 19:30:40 +0100
> David Marchand wrote:
>
> > This is something caught in UNH FreeBSD env.
> >
> > For some reason [1], the pcap/bpf.h header started to define _BPF_H_.
> >
> > It happens that the bpf_impl.h internal DPDK header uses thi
From: David Marchand
> On Thu, Mar 10, 2022 at 6:04 PM Michael Baum
> wrote:
> > > > # strace -r -f ./dpdk-dir/v21.11/examples/dpdk-l3fwd-power
> > > > --lcores
> > > > 0@3,1@5 -a :82:00.0 --in-memory -- -p 0x1 -P --config '(0,0,1)'
> > > > ...
> > > > [pid 534983] 0.000348 epoll_wait(2
> -Original Message-
> From: Ajmera, Megha
> Sent: Monday, March 14, 2022 9:59 AM
> To: dev@dpdk.org; Mcnamara, John ; Singh,
> Jasvinder ; Dumitrescu, Cristian
> ; Thakur, Sham Singh
>
> Subject: [PATCH] Revert "sched: enable traffic class oversubscription
> unconditionally"
>
> This
On 14/03/2022 09:59, Megha Ajmera wrote:
This reverts commit d91c4b1bb5a938734fe8e66da8f965304919f38e.
When enabling TC OV unconditionally, it is observed the performance
drops by ~20% hence reverting this commit.
Fixes: d91c4b1bb5a9 ("sched: enable traffic class oversubscription
uncondition
> >This patch removes coverity defect CID 375828:
> >Untrusted value as argument (TAINTED_SCALAR)
It lacks an explanation of the cause.
> >Coverity issue: CID 375828
You should not write CID above.
> >
> >Fixes: ceb863938708 ("crypto/aesni_gcm: support all truncated digest sizes")
> >
> >Signed-
> > > AES-GMAC requires plaintext length to be 0 when using AES-GCM, so only
> > > AAD data is used.
> > >
> > > Fixes: a501609ea646 ("crypto/ipsec_mb: fix length and offset
> > > settings")
> > > Cc: pablo.de.lara.gua...@intel.com
> > > Cc: sta...@dpdk.org
> > >
> > > Signed-off-by: Pablo de Lara
This reverts commit d91c4b1bb5a938734fe8e66da8f965304919f38e.
When enabling TC OV unconditionally, it is observed the performance
drops by ~20% hence reverting this commit.
Signed-off-by: Megha Ajmera
---
config/rte_config.h | 1 +
drivers/net/softnic/rte_eth_softnic_tm.c
11/03/2022 14:45, Ciara Loftus:
> Commit 81fe6720f84f ("net/af_xdp: reserve fill queue before socket create")
> moves the fill queue reserve logic to before the creation of the socket in
> order to suppress kernel logs like:
>
> XSK buffer pool does not provide enough addresses to fill 2047 buffer
On Thu, Mar 10, 2022 at 6:04 PM Michael Baum wrote:
> > > # strace -r -f ./dpdk-dir/v21.11/examples/dpdk-l3fwd-power --lcores
> > > 0@3,1@5 -a :82:00.0 --in-memory -- -p 0x1 -P --config '(0,0,1)'
> > > ...
> > > [pid 534983] 0.000348 epoll_wait(26, [], 1, 10) = 0
> > > [pid 534983] 0
When setup RX queue, the rxdid would be changed if it's
"IAVF_RXDID_LEGACY_0/1", that caused the scan hw ring used the wrong
function 'iavf_rx_scan_hw_ring_flex_rxd()'.
Ignore the rxdid changed when equals "IAVF_RXDID_LEGACY_0/1".
Fixes: 0ed16e01313e ("net/iavf: fix function pointer in multi-proc
On Mon, Mar 14, 2022 at 6:59 AM Ke Zhang wrote:
>
> when dpdk is compiled in ASan, there is a memory leaks after
> quit testpmd if set mcast_addr, this patch fix this issue.
The memory leak is present regardless of ASan being compiled in.
Plus, afaiu, the issue happens too when closing a port.
I
On Fri, Mar 11, 2022 at 05:11:02PM -0800, Stephen Hemminger wrote:
> On Fri, 11 Mar 2022 20:05:23 +
> Bruce Richardson wrote:
>
> > When compiling on FreeBSD with clang and include checking enabled,
> > errors are emitted due to differences in how empty structs/unions are
> > handled in C and
> -Original Message-
> From: Alexander Kozyrev
> Sent: Saturday, March 12, 2022 1:08
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Slava Ovsiienko
> ; Matan Azrad
> Subject: [PATCH v3] net/mlx5: handle MPRQ incompatibility with external
> buffers
>
> Multi-Packet Rx queue uses PMD-managed
Acked-by: Viacheslav Ovsiienko
> -Original Message-
> From: Gregory Etelson
> Sent: Thursday, March 10, 2022 8:00
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh ;
> sta...@dpdk.org; Xiaoyun Li ; Aman Singh
> ; Yuying Zhang ;
> Slava Ovsiienko
> Subject: [PAT
11/03/2022 12:12, Loftus, Ciara:
> >
> > 10/03/2022 09:49, Loftus, Ciara:
> > > > When the PMD is configured to load a custom XDP program, it sets
> > > > XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD flag to prevent libbpf from
> > > > loading its default XDP program. However, when queue_count is set to
>
> -Original Message-
> From: Wang, YuanX
> Sent: Saturday, March 12, 2022 12:35 AM
> To: maxime.coque...@redhat.com; Xia, Chenbo
> Cc: dev@dpdk.org; Hu, Jiayu ; Ling, WeiX
> ; Wang, YuanX
> Subject: [PATCH] net/vhost: fix access to freed memory
>
> This patch fixes heap-use-after-free r
35 matches
Mail list logo
