Added -v option to switch between different lookup implementations
to measure their performance and correctness.
Signed-off-by: Vladimir Medvedkin
---
app/test-fib/main.c | 65 ++---
1 file changed, 62 insertions(+), 3 deletions(-)
diff --git a/ap
On Fri, Oct 16, 2020 at 06:46:12PM +0200, David Marchand wrote:
> On Fri, Oct 16, 2020 at 5:56 PM Bruce Richardson
> wrote:
> > > librte_eal.so is indeed built with the 64 value:
> > > $ pahole -C rte_mem_config build/install/lib64/librte_eal.so |grep memsegs
> > > die__process_function: tag not s
14/09/2020 18:40, Stephen Hemminger:
> On Mon, 14 Sep 2020 16:35:58 +0100
> "Burakov, Anatoly" wrote:
>
> > >* Replacement function for calloc(), using huge-page memory. Memory
> > > area is
> > > @@ -239,9 +243,9 @@ rte_zmalloc_socket(const char *type, size_t size,
> > > unsigned align, in
> Subject: [PATCH] crypto/caam_jr: fix caam sec era invalid issue
>
> of_init() should be called before using any of_* APIs to retrieve
> information from the device tree and if reading integer value
> that must be converted to cpu endianness before using.
>
> Fixes: 1d678de329ab ("crypto/caam_jr
Hi Zhihong,
On 10/14/20 9:44 AM, Zhihong Wang wrote:
> I'm resigning from DPDK virtio and vhost maintainer as I'm leaving Intel.
>
> Sincerely thank Maxime, Chenbo and the community for all the support.
Thanks for all your contributions to Vhost and Virtio, you will be
missed!
I hope we can see
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, October 15, 2020 2:44 PM
> To: Matan Azrad ; Shahaf Shuler
> ; Slava Ovsiienko
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix use of atomic cmpset for age state
>
> According
> > -Original Message-
> > From: Ferruh Yigit
> > Sent: Wednesday, October 14, 2020 11:38 PM
> > To: Zhang, Qi Z ; Yang, SteveX
> > ; Ananyev, Konstantin
> > ; dev@dpdk.org
> > Cc: Zhao1, Wei ; Guo, Jia ; Yang,
> > Qiming ; Wu, Jingjing ;
> > Xing, Beilei ; Stokes, Ian
> > Subject: Re:
This patch fixes out of bound access of an array.
Coverity issue: 363466, 363459
Fixes: b5dfa6703d49 ("net/softnic: update subport rate dynamically")
Signed-off-by: Savinay Dharmappa
---
drivers/net/softnic/rte_eth_softnic_tm.c | 15 +--
1 file changed, 13 insertions(+), 2 deletions
> -Original Message-
> From: Dharmappa, Savinay
> Sent: Monday, October 19, 2020 11:50 AM
> To: Dumitrescu, Cristian ; Singh, Jasvinder
> ; dev@dpdk.org
> Cc: Dharmappa, Savinay
> Subject: [PATCH v1] net/softnic: fix out of bound access
>
> This patch fixes out of bound access of an a
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, October 15, 2020 4:37 PM
> To: Slava Ovsiienko ; Shahaf Shuler
> ; Matan Azrad
> Cc: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH v2] net/mlx5: add debug print of LRO minimal
> size
>
> Add debug printout showi
15/10/2020 11:47, Gagandeep Singh:
> dpaa2_qdma was partially using direct pmd APIs.
> This patch changes that and adapt the driver to use
> more of the rawdev APIs
>
> Signed-off-by: Gagandeep Singh
> ---
> drivers/raw/dpaa2_qdma/dpaa2_qdma.c | 339 ++--
> drivers/raw/dp
Hi Bruce,
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, October 16, 2020 12:59 PM
> To: Ali Alnubani
> Cc: dev@dpdk.org; NBU-Contact-Thomas Monjalon
> ; Asaf Penso
> Subject: Re: [dpdk-dev] performance degradation with fpic
>
> On Thu, Oct 15, 2020 at 06:08:04PM +0100,
This patch fixes out of bound access of an array.
Coverity issue: 363466, 363459
Fixes: b5dfa6703d49 ("net/softnic: update subport rate dynamically")
Signed-off-by: Savinay Dharmappa
---
v2: addressed review comments of v1
---
drivers/net/softnic/rte_eth_softnic_tm.c | 13 -
1 file
This patchset resolves a coverity issue where the return value of
rte_eth_switch_domain_alloc() was not being checked and also removes
a use of rte_panic within ixgbe_pf_host_init().
Conor Walsh (2):
net/ixgbe: fix unchecked return value
net/ixgbe: remove rte_panic
drivers/net/ixgbe/ixgbe_et
Remove the usage of rte_panic() within ixgbe_pf_host_init()
Signed-off-by: Conor Walsh
---
drivers/net/ixgbe/ixgbe_pf.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_pf.c b/drivers/net/ixgbe/ixgbe_pf.c
index 4e25b1e72e..833863af5a 100644
--- a
The return value of rte_eth_switch_domain_alloc() was not being checked
within ixgbe_pf_host_init() which caused a coverity issue. If the call
fails a warning is logged using PMD_INIT_LOG() and *vfinfo is free'd.
ixgbe_pf_host_init() now has a return value which is checked in
eth_ixgbe_dev_init()
19/10/2020 12:33, Akhil Goyal:
> > Subject: [PATCH] crypto/caam_jr: fix caam sec era invalid issue
> >
> > of_init() should be called before using any of_* APIs to retrieve
> > information from the device tree and if reading integer value
> > that must be converted to cpu endianness before using.
>
> 19/10/2020 12:33, Akhil Goyal:
> > > Subject: [PATCH] crypto/caam_jr: fix caam sec era invalid issue
> > >
> > > of_init() should be called before using any of_* APIs to retrieve
> > > information from the device tree and if reading integer value
> > > that must be converted to cpu endianness
On Mon, Oct 19, 2020 at 11:47:48AM +, Ali Alnubani wrote:
> Hi Bruce,
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Friday, October 16, 2020 12:59 PM
> > To: Ali Alnubani
> > Cc: dev@dpdk.org; NBU-Contact-Thomas Monjalon
> > ; Asaf Penso
> > Subject: Re: [dpdk-dev] p
On 10/19/2020 11:49 AM, Ananyev, Konstantin wrote:
-Original Message-
From: Ferruh Yigit
Sent: Wednesday, October 14, 2020 11:38 PM
To: Zhang, Qi Z ; Yang, SteveX
; Ananyev, Konstantin
; dev@dpdk.org
Cc: Zhao1, Wei ; Guo, Jia ; Yang,
Qiming ; Wu, Jingjing ;
Xing, Beilei ; Stokes, Ian
> -Original Message-
> From: Dharmappa, Savinay
> Sent: Monday, October 19, 2020 12:52 PM
> To: Dumitrescu, Cristian ; Singh, Jasvinder
> ; dev@dpdk.org
> Cc: Dharmappa, Savinay
> Subject: [PATCH v2] net/softnic: fix out of bound access
>
> This patch fixes out of bound access of an a
Hi there.
I tried the following:
export CPPFLAGS=' -stdlib=libc++ ' CXXFLAGS=' -stdlib=libc++ '
> meson build-clang
> cd build-clang
> ninja -j 4
>
and got such issues:
> [213/2379] Compiling C object 'lib/76b5a35@@rte_bitratestats@sta
> /librte_bitratestats_rte_bitrate.c.o'.
> clang-11: warnin
On Mon, Oct 19, 2020 at 04:17:36PM +0300, Ivan Serdyuk wrote:
> Hi there.
> I tried the following:
>
> export CPPFLAGS=' -stdlib=libc++ ' CXXFLAGS=' -stdlib=libc++ '
> > meson build-clang
> > cd build-clang
> > ninja -j 4
> >
>
Hi Ivan
Why are you exporting these CPP and CXX flags? The CXX flags
On 15/09/2020 15:41, David Marchand wrote:
> On Mon, Sep 7, 2020 at 10:15 AM Ruifeng Wang wrote:
>>
>> The rte_lpm structure is exported because lookup API is inlined.
>> But most of the structure can be hidden.
>> Discussion at: http://patches.dpdk.org/patch/72403/
>> This patch set aimed to hide
> -Original Message-
> From: dev On Behalf Of Shiri Kuzin
> Sent: Monday, October 19, 2020 9:37 AM
> To: dev@dpdk.org
> Cc: ma...@mellanox.com; rasl...@mellanox.com;
> viachesl...@mellanox.com; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix xstats reset reinitialization
>
From: Ciara Power
A number of components in DPDK have optional AVX-512 or other vector
code paths which can be selected at runtime. Rather than having each
component provide its own mechanism to select a code path, this patchset
adds support for a single setting to control what code paths are use
From: Ciara Power
This patch adds a max SIMD bitwidth EAL configuration. The API allows
for an app to set this value. It can also be set using EAL argument
--force-max-simd-bitwidth, which will lock the value and override any
modifications made by the app.
Each arch has a define for the default
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Konstantin Ananyev
---
v4: Updated enum names.
---
drivers/net/i40e/i40e_rxtx.c | 19 +-
From: Ciara Power
This patch adds documentation on the usage of the max SIMD bitwidth EAL
setting to enable AVX-512 at runtime.
Signed-off-by: Ciara Power
Acked-by: Kevin Laatz
---
v6: Updated enum value.
v4: Updated docs to reflect renamed enum.
v3:
- Added enum value for disabling use of m
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Somnath Kotur
---
v4: Updated enum name.
---
drivers/net/bnxt/bnxt_ethdev.c | 7 +--
1 file cha
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Amaranath Somalapuram
---
v4: Updated enum name.
---
drivers/net/axgbe/axgbe_rxtx.c | 4 +++-
1 fil
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Hyong Youb Kim
---
v4: Updated enum name.
---
drivers/net/enic/enic_rxtx_vec_avx2.c | 4 +++-
1 fil
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Qi Zhang
---
v4: Updated enum name.
---
drivers/net/fm10k/fm10k_ethdev.c | 10 +++---
1 file ch
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Reviewed-by: Bruce Richardson
---
v4: Updated enum name.
---
drivers/net/iavf/iavf_rxtx.c | 17 +++---
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Qi Zhang
---
v4: Updated enum name.
---
drivers/net/ice/ice_rxtx.c | 17 +++--
1 file c
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Viacheslav Ovsiienko
---
v4: Updated enum name.
v2: Moved check for max bitwidth into existing check
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Konstantin Ananyev
Reviewed-by: Haiyue Wang
---
v4:
- Updated enum name.
- Moved placement of c
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU
enabled path.
Signed-off-by: Ciara Power
Acked-by: Yipeng Wang
---
v4: Updated enum name.
---
lib/librte_member/rte_member_ht.c | 4 +++-
1 file chang
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Reviewed-by: Chenbo Xia
Acked-by: Maxime Coquelin
---
v4: Updated enum name.
v3: Moved max SIMD bitwidth chec
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: David Hunt
---
v4: Updated enum name.
v3: Moved max SIMD bitwidth check to configure function with o
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Signed-off-by: Ciara Power
Acked-by: Yipeng Wang
---
v4: Updated enum name.
---
lib/librte_efd/rte_efd.c | 8 ++--
1 file changed, 6
From: Ciara Power
When choosing the vector path, max SIMD bitwidth is now checked to
ensure the vector path is suitable. To do this, the scalar function is
chosen by default in the struct, but at node initialisation time, this
function pointer is updated to the vector version if supported, and
if
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
The vector path was initially chosen in RTE_INIT, however this is no
longer suitable as we cannot check the max SIMD bitwidth at that time.
From: Ciara Power
When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path. These checks are added in the check alg helper functions.
Signed-off-by: Ciara Power
Acked-by: Konstantin Ananyev
Tested-by: Konstantin A
Recent patch [1] adds to ethdev the API for query of age action.
This patch implements in MLX5 PMD the query of age action using
this API.
[1] https://mails.dpdk.org/archives/dev/2020-October/184864.html
---
v2: Update age resolution to seconds,
v3: Replace rte_atomic ops with c11 atomics.
v4: Rem
19/10/2020 14:49, Akhil Goyal:
> >
> > 19/10/2020 12:33, Akhil Goyal:
> > > > Subject: [PATCH] crypto/caam_jr: fix caam sec era invalid issue
> > > >
> > > > of_init() should be called before using any of_* APIs to retrieve
> > > > information from the device tree and if reading integer value
> >
> >
> > testpmd will initialize default max packet length to 1518 which
> > doesn't include vlan tag size in ether overheader. Once, send the
> > max mtu length packet with vlan tag, the max packet length will
> > exceed 1518 that will cause packets dropped d
11/07/2020 10:28, Hemant Agrawal:
> This patch adds support for free funnction.
>
> Signed-off-by: Hemant Agrawal
Squashed patches 1 & 2 and applied, thanks
There was no ack or conclusion for this patch.
17/08/2020 17:11, Stephen Hemminger:
> On Mon, 17 Aug 2020 11:37:40 +0100
> Bruce Richardson wrote:
>
> > On Fri, Aug 14, 2020 at 12:20:28PM -0700, Stephen Hemminger wrote:
> > > On Fri, 14 Aug 2020 22:09:11 +0300
> > > Dmitry Kozlyuk wrote:
> > >
15/10/2020 02:55, Stephen Hemminger:
> By using the alloc_size() attribute the compiler can optimize
> better and detect errors at compile time.
>
> For example, Gcc will fail one of the invalid allocation examples
> in app/test/test_malloc.c because the allocation is outside the
> limits of memor
19/10/2020 16:13, Thomas Monjalon:
> 15/10/2020 02:55, Stephen Hemminger:
> > By using the alloc_size() attribute the compiler can optimize
> > better and detect errors at compile time.
> >
> > For example, Gcc will fail one of the invalid allocation examples
> > in app/test/test_malloc.c because
I am a new hns3 pmd developer and reviewer for upstreaming hns3
pmd driver. So I want to help out here as well.
Signed-off-by: Lijun Ou
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f7ecb53..2bd2d63 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
>
> > >
> > > testpmd will initialize default max packet length to 1518 which
> > > doesn't include vlan tag size in ether overheader. Once, send the
> > > max mtu length packet with vlan tag, the max packet length will
> > > exceed 1518 that will cause pac
Hi,
19/10/2020 16:27, Lijun Ou:
> I am a new hns3 pmd developer and reviewer for upstreaming hns3
> pmd driver. So I want to help out here as well.
>
> Signed-off-by: Lijun Ou
>
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -637,6 +637,7 @@ Hisilicon hns3
> M: Wei Hu (Xavier)
> M: Min Hu (Con
On Mon, Oct 19, 2020 at 3:49 PM David Marchand
wrote:
>
> From: Ciara Power
>
> A number of components in DPDK have optional AVX-512 or other vector
> code paths which can be selected at runtime. Rather than having each
> component provide its own mechanism to select a code path, this patchset
>
On Fri, Oct 16, 2020 at 7:39 PM Dharmik Thakkar wrote:
>
> Integrate RCU QSBR to make it easier for the applications to use lock
> free algorithm.
>
> Resource reclamation implementation was split from the original
> series, and has already been part of RCU library. Rework the series
> to base has
13/10/2020 18:45, Bruce Richardson:
> On Tue, Oct 13, 2020 at 05:28:20PM +0100, Ciara Power wrote:
> > When the socket connection failed, an error was printed to screen but
> > the function did not return an error, and continued to try read from the
> > socket. This is now corrected to close the so
On Fri, Oct 16, 2020 at 12:54 AM Honnappa Nagarahalli
wrote:
> > > IMO, this is not a performance critical path and it is not a difficult
> > > solution to
> > store these values in the application. My suggestion is to skip adding the
> > API
> > and store the values in the application.
> > > Vl
15/10/2020 19:02, Kevin Laatz:
> On 13/10/2020 16:56, Ciara Power wrote:
> > If an error occurred when reading from the socket, the function
> > returned without closing the socket. This is now fixed to avoid the
> > resource leak of the sock variable going out of scope.
> >
> > Fixes: bd78cf693ebd
Hi Guy,
> -Original Message-
> From: g...@marvell.com
> Sent: Monday, October 19, 2020 12:27 PM
> Subject: [PATCH v1] app/regex: change default qp configuration flags
>
> From: Guy Kaneti
>
> By default qp configuration flags was set with
> RTE_REGEX_QUEUE_PAIR_CFG_OOS_F.
> Changed fla
Add type argument to dir24_8_get_lookup_fn()
Now it supports 3 different lookup implementations:
RTE_FIB_DIR24_8_SCALAR_MACRO
RTE_FIB_DIR24_8_SCALAR_INLINE
RTE_FIB_DIR24_8_SCALAR_UNI
Add new rte_fib_set_lookup_fn() - user can change lookup
function type runtime.
Signed-off-by: Vladimir Medvedk
Add new lookup implementation for DIR24_8 algorithm using
AVX512 instruction set
Signed-off-by: Vladimir Medvedkin
Acked-by: Konstantin Ananyev
---
doc/guides/rel_notes/release_20_11.rst | 3 +
lib/librte_fib/dir24_8.c | 39
lib/librte_fib/dir24_8_avx512.c| 165
Move dir24_8 table layout and lookup definition into the
private header file. This is necessary for implementing a
vectorized lookup function in a separate .с file.
Signed-off-by: Vladimir Medvedkin
Acked-by: Konstantin Ananyev
---
lib/librte_fib/dir24_8.c | 225 +---
Move trie table layout and lookup definition into the
private header file. This is necessary for implementing a
vectorized lookup function in a separate .с file.
Signed-off-by: Vladimir Medvedkin
Acked-by: Konstantin Ananyev
---
lib/librte_fib/trie.c | 121 --
Add new lookup implementation for FIB6 trie algorithm using
AVX512 instruction set
Signed-off-by: Vladimir Medvedkin
Acked-by: Konstantin Ananyev
---
doc/guides/rel_notes/release_20_11.rst | 2 +-
lib/librte_fib/meson.build | 17 +++
lib/librte_fib/rte_fib6.c | 2 +
Add type argument to trie_get_lookup_fn()
Now it only supports RTE_FIB6_TRIE_SCALAR
Add new rte_fib6_set_lookup_fn() - user can change lookup
function type runtime.
Signed-off-by: Vladimir Medvedkin
Acked-by: Konstantin Ananyev
---
lib/librte_fib/rte_fib6.c | 20 +++-
lib/
Added -v option to switch between different lookup implementations
to measure their performance and correctness.
Signed-off-by: Vladimir Medvedkin
---
app/test-fib/main.c | 65 ++---
1 file changed, 62 insertions(+), 3 deletions(-)
diff --git a/ap
Hi Guy,
> -Original Message-
> From: g...@marvell.com
> Sent: Sunday, October 18, 2020 3:04 PM
> To: NBU-Contact-Thomas Monjalon ;
> or...@mellanox.com; john.mcnam...@intel.com; marko.kovace...@intel.com
> Cc: dev@dpdk.org; g...@marvell.com; jer...@marvell.com;
> smad...@marvell.com; dov
This patch series implements vectorized lookup using AVX512 for
ipv4 dir24_8 and ipv6 trie algorithms.
Also introduced rte_fib_set_lookup_fn() to change lookup function type.
Added option to select lookup function type in testfib application.
v13:
- reflect the latest changes in "eal: add max SIM
Hi Guy,
> -Original Message-
> From: g...@marvell.com
> Sent: Sunday, October 18, 2020 3:04 PM
> Subject: [PATCH v3 2/2] doc: add l3fwd-regex application user guide
>
> From: Guy Kaneti
>
> Adding the user guide for l3fwd regex application.
>
> Signed-off-by: Guy Kaneti
> ---
Acked-
On Mon, 19 Oct 2020 16:11:19 +0200
Thomas Monjalon wrote:
> There was no ack or conclusion for this patch.
>
> 17/08/2020 17:11, Stephen Hemminger:
> > On Mon, 17 Aug 2020 11:37:40 +0100
> > Bruce Richardson wrote:
> >
> > > On Fri, Aug 14, 2020 at 12:20:28PM -0700, Stephen Hemminger wrote:
The memory subsystem is leaving open a file descriptor for each
rtemap file. This can lead to hundreds of extra open file descriptors
which has negative side effects. For example, the application may go
over its maximum file descriptor limit, or the application may be using
limited API's like selec
19/10/2020 12:42, Maxime Coquelin:
> Hi Zhihong,
>
> On 10/14/20 9:44 AM, Zhihong Wang wrote:
> > I'm resigning from DPDK virtio and vhost maintainer as I'm leaving Intel.
> >
> > Sincerely thank Maxime, Chenbo and the community for all the support.
>
> Thanks for all your contributions to Vhost
On Mon, 19 Oct 2020 08:42:35 -0700
Stephen Hemminger wrote:
> The memory subsystem is leaving open a file descriptor for each
> rtemap file. This can lead to hundreds of extra open file descriptors
> which has negative side effects. For example, the application may go
> over its maximum file desc
Currently, users have to use external RCU mechanisms to free resources
when using lock free hash algorithm.
Integrate RCU QSBR process to make it easier for the applications to use
lock free algorithm.
Refer to RCU documentation to understand various aspects of
integrating RCU library into other
Replace rte_atomic APIs with C11 atomic APIs in
test_hash_readwrite_lf_perf.c
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_hash_readwrite_lf_perf.c | 89 +++---
1 file changed, 36 insertions(+), 53 deletions(-)
diff --git a/app/test/test_hash_r
Add functional and performance tests for the integrated RCU QSBR.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_hash.c | 390 -
app/test/test_hash_readwrite_lf_perf.c | 171 ++-
2
Integrate RCU QSBR to make it easier for the applications to use lock
free algorithm.
Resource reclamation implementation was split from the original
series, and has already been part of RCU library. Rework the series
to base hash integration on RCU reclamation APIs.
Refer 'Resource reclamation f
10/09/2020 14:23, Bruce Richardson:
> On Thu, Sep 10, 2020 at 01:19:55PM +0100, Ferruh Yigit wrote:
> > On 9/10/2020 12:32 PM, Bruce Richardson wrote:
> > > The build-sdk-meson.rst file originates from the short plain-text meson
> > > instructions added in 2018. Add SPDX tag and copyright notice ba
15/10/2020 17:05, Bruce Richardson:
> Rather than specifying specific drivers in the driver directory to load, we
> can just pass in the whole driver directory to the "-d" EAL flag, causing
> all drivers to load. This makes the load of driver independent of any
> specific driver names.
>
> Signed-
https://bugs.dpdk.org/show_bug.cgi?id=560
Bug ID: 560
Summary: excessive numbers of open file handles kept open
Product: DPDK
Version: 20.11
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Hi Ori,
> -Original Message-
> From: Ori Kam
> Sent: Monday, October 19, 2020 6:03 PM
> To: Guy Kaneti ; or...@mellanox.com
> Cc: NBU-Contact-Thomas Monjalon ; Smadar Fuks
> ; dev@dpdk.org
> Subject: [EXT] RE: [PATCH v1] app/regex: change default qp configuration
> flags
>
> External Em
This patch validates the queue index parameter, in order
to ensure neither out-of-bound accesses nor NULL pointer
dereferencing happen.
Fixes: a67f286a6596 ("vhost: export queue free entries")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 5 +
1 file chan
The series aims at improving virtqueue metadata pointers
dereferencing robust.
First patch fixes a real issue reported by our QE.
Five next patches validates queue index passed as input
of the Vhost API. They are split in 5 patches to ease
backporting to LTSes.
Last patch is not mandatory now th
This patch validates the queue index parameter, in order
to ensure neither out-of-bound accesses nor NULL pointer
dereferencing happen.
Fixes: 9eed6bfd2efb ("vhost: allow to enable or disable features")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 5 +
1
The Vhost-user backend implementation assumes there will be
no holes in the device's array of virtqueues metadata
pointers.
It can happen though, and would cause segmentation faults,
memory leaks or undefined behaviour.
This patch keep the assumption that there is no holes in this
array, and allo
This patch validates the queue index parameter, in order
to ensure no out-of-bound accesses happen.
Fixes: 9eed6bfd2efb ("vhost: allow to enable or disable features")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 6 ++
1 file changed, 6 insertions(+)
dif
This patch validates the queue index parameter, in order
to ensure no out-of-bound accesses happen.
Fixes: bd2e0c3fe5ac ("vhost: add APIs for live migration")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 6 ++
1 file changed, 6 insertions(+)
diff --git
This patch validates the queue index parameter, in order
to ensure neither out-of-bound accesses nor NULL pointer
dereferencing happen.
Fixes: 4d891f77ddfa ("vhost: add APIs to get inflight ring")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 10 +-
1
This patch checks whether the virtqueue metadata pointer
is valid before dereferencing it. It is not considered
a fix as earlier patch ensures there are no holes in the
array of virtqueue metadata pointers.
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 11 +++
lib/li
> > >>
> > >> Hi Ruifeng,
> > >>
> > >> On 15/09/2020 17:02, Bruce Richardson wrote:
> > >>> On Mon, Sep 07, 2020 at 04:15:17PM +0800, Ruifeng Wang wrote:
> > Fields except tbl24 and tbl8 in rte_lpm structure have no need to
> > be exposed to the user.
> > Hide the unneeded exposur
On 10/19/2020 3:28 PM, Ananyev, Konstantin wrote:
testpmd will initialize default max packet length to 1518 which
doesn't include vlan tag size in ether overheader. Once, send the
max mtu length packet with vlan tag, the max packet length will
exceed 1518 that will cause packets dropped dire
On 10/19/2020 4:07 AM, Yang, SteveX wrote:
-Original Message-
From: Ferruh Yigit
Sent: Wednesday, October 14, 2020 11:38 PM
To: Zhang, Qi Z ; Yang, SteveX
; Ananyev, Konstantin
; dev@dpdk.org
Cc: Zhao1, Wei ; Guo, Jia ; Yang,
Qiming ; Wu, Jingjing ;
Xing, Beilei ; Stokes, Ian
Subject
15/10/2020 17:05, Bruce Richardson:
> Use the newer macros defined by meson in all DPDK source code, to ensure
> there are no errors when the old non-standard macros are removed.
>
> Signed-off-by: Bruce Richardson
> Acked-by: Luca Boccassi
> ---
> 85 files changed, 389 insertions(+), 389 delet
15/10/2020 17:28, Andrew Rybchenko:
> On 10/15/20 6:05 PM, Bruce Richardson wrote:
> > Since each version map file is contained in the subdirectory of the library
> > it refers to, there is no need to include the library name in the filename.
> > This makes things simpler in case of library renamin
15/10/2020 17:05, Bruce Richardson:
> Following on from discussion in RFC v1 and v2 of this set, this version
> reworks the automated macros defined by meson to indicate if a
> particular library or driver is enabled in the build. However, while it
> does so, it also maintains compatibility with pr
19/10/2020 12:21, Bruce Richardson:
> On Fri, Oct 16, 2020 at 06:46:12PM +0200, David Marchand wrote:
> > On Fri, Oct 16, 2020 at 5:56 PM Bruce Richardson
> > wrote:
> > > > librte_eal.so is indeed built with the 64 value:
> > > > $ pahole -C rte_mem_config build/install/lib64/librte_eal.so |grep
On Mon, Oct 19, 2020 at 6:37 PM Dharmik Thakkar wrote:
>
> Integrate RCU QSBR to make it easier for the applications to use lock
> free algorithm.
>
> Resource reclamation implementation was split from the original
> series, and has already been part of RCU library. Rework the series
> to base has
15/10/2020 14:04, Anatoly Burakov:
> +/**
> + * This function is not supported on ARM.
> + */
> +static inline void
> +rte_power_monitor(const volatile void *p, const uint64_t expected_value,
> + const uint64_t value_mask, const uint64_t tsc_timestamp,
> + const uint8_t
Coverity reported dead code for a few error
checks which are indeed not reachable.
Coverity issue: 363451, 363454, 363455
Signed-off-by: Nicolas Chautru
---
drivers/baseband/acc100/rte_acc100_pmd.c | 9 -
1 file changed, 9 deletions(-)
diff --git a/drivers/baseband/acc100/rte_acc100_pm
101 - 200 of 234 matches
Mail list logo
