From: Ophir Munk:
> This patch series is part of preparing mlx5 PMD to compile and run under
> multiple OSs. Part #2
>
> v1:
> Initial release
>
> Ophir Munk (8):
> net/mlx5: remove dv dependency in mlx5_dev_ctx_shared struct
> net/mlx5: rename ib in names
> net/mlx5: move socket files u
Implemented the needed Windows eal timer functions.
Signed-off-by: Fady Bader
---
lib/librte_eal/common/meson.build | 1 +
lib/librte_eal/windows/eal.c| 6 +++
lib/librte_eal/windows/eal_timer.c | 90 +
lib/librte_eal/windows/include/rte_o
Eal common timer doesn't compile under Windows.
Compilation log:
error LNK2019:
unresolved external symbol nanosleep referenced in function
rte_delay_us_sleep
error LNK2019:
unresolved external symbol get_tsc_freq referenced in function set_tsc_freq
error LNK2019:
unresolved external symbol sleep
This patchset splits OS dependent EAL timer functions and implements them for
windows.
v2:
* fixing styles and correctness errors.
v3:
* fixing correctness, get_tsc_freq was reimplemented.
v4:
* rebasing to the new version of "Windows basic memory management" series.
* fixing styl
Implementation of rte_proc_type_t for Windows as it is needed for Windows
eal timer.
Signed-off-by: Fady Bader
---
lib/librte_eal/windows/eal.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index d084606a6..feee91244 100644
> Subject: [PATCH v8 0/3] eal timer split and implementation for Windows
>
> This patchset splits OS dependent EAL timer functions and implements them
> for windows.
>
> v2:
> * fixing styles and correctness errors.
> v3:
> * fixing correctness, get_tsc_freq was reimplemented.
> v4:
>
Hi,
> -Original Message-
> From: Gregory Etelson
> Sent: Monday, June 8, 2020 7:02 PM
> To: dev@dpdk.org
> Cc: Gregory Etelson ; Matan Azrad
> ; Raslan Darawsheh
> Subject: [PATCH 1/1] net/mlx5: fix flow memory allocation size
>
> In DV enabled MLX5 PMD build
> mlx5_ipool_cfg[MLX5_IPOOL
Hi,
> -Original Message-
> From: Dekel Peled
> Sent: Wednesday, June 10, 2020 4:25 PM
> To: Matan Azrad ; Slava Ovsiienko
> ; Raslan Darawsheh
> Cc: dev@dpdk.org
> Subject: [PATCH] net/mlx5: move GTP mask define to correct location
>
> Recent patch [1] added definition of mask MLX5_GTP_
Hi Matan,
> -Original Message-
> From: Matan Azrad
> Sent: Friday, June 12, 2020 7:06 PM
> To: Xia, Chenbo ; Maxime Coquelin
>
> Cc: dev@dpdk.org; Wang, Xiao W ; Tiwei Bie
> ; sta...@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH] vhost: fix host notifier configuration error
> flow
>
>
> H
The 'vfio_res' is not freed when unmapping resource by primary process.
This leads to memory leak.
Fixes: ab53203e194b ("vfio: enable unmapping resource for secondary")
Cc: sta...@dpdk.org
Signed-off-by: Yunjian Wang
---
drivers/bus/pci/linux/pci_vfio.c | 1 +
1 file changed, 1 insertion(+)
di
PF could add or delete a RSS rule base on the PF's hash capability.
Some new rss input set will be supported, the protocols as below:
eth/vlan/l2tpv3/esp/ah/pfcp/gtpu.
Signed-off-by: Jeff Guo
---
v2->v1:
separate hdrs and fields parsing
---
drivers/net/ice/ice_hash.c | 597 ++
Previous iavf only support inner ipv4 hash for GTPU, this patch aims to
enable inner 5 tuple hash for GTPU, that involves inner ipv4 src/dst,
tcp sport/dport, udp sport/dport and protocol id.
Signed-off-by: Jeff Guo
---
drivers/net/iavf/iavf_hash.c | 1670 --
1 fi
Each cross-compilation case needs to define the target compiler
and the meson cross file.
Given the compiler is already defined in the cross file,
the latter is enough.
The function "build" is changed to accept a cross file alternatively
to the compiler name. In the case of a file (detected if rea
In order to better support PPC and Windows,
their compilation is tested on Linux with Meson
with the script test-meson-builds.sh,
supposed to be called in every CI labs.
Thomas Monjalon (4):
devtools: shrink cross-compilation test definition
devtools: allow non-standard toolchain in meson test
If a compiler is not found in $PATH, the compilation test is skipped.
In some cases, the compiler could be found after extending $PATH
in an environment configuration script (called by load-devel-config).
The decision to skip is deferred to a later stage, after loading the
configuration script.
I
The CPU is defined as Power8, running as little endian.
Signed-off-by: Thomas Monjalon
---
config/ppc/ppc64le-power8-linux-gcc | 11 +++
devtools/test-meson-builds.sh | 5 +
2 files changed, 16 insertions(+)
create mode 100644 config/ppc/ppc64le-power8-linux-gcc
diff --git a
The Meson cross file is renamed from meson_mingw.txt to cross-mingw,
and is added to test-meson-builds.sh.
The only example supported on Windows so far is "helloworld",
that's why the default list of examples is overriden.
Signed-off-by: Thomas Monjalon
---
config/x86/{meson_mingw.txt => cross-
15/06/2020 00:57, Thomas Monjalon:
> The Meson cross file is renamed from meson_mingw.txt to cross-mingw,
> and is added to test-meson-builds.sh.
>
> The only example supported on Windows so far is "helloworld",
> that's why the default list of examples is overriden.
>
> Signed-off-by: Thomas Mon
Note for v9:
rte_eal_memory.h renamed, dependent patchsets have to be updated.
This patchset implements basic MM with the following features:
* Hugepages are dynamically allocated in user-mode.
* Only 2MB hugepages are supported.
* IOVA is always PA, obtained through kernel-mode driver.
* No 32-b
Introduce OS-independent wrappers in order to support common EAL code
on Unix and Windows:
* eal_file_open: open or create a file.
* eal_file_lock: lock or unlock an open file.
* eal_file_truncate: enforce a given size for an open file.
Implementation for Linux and FreeBSD is placed in "unix" sub
All supported OS create memory segment lists (MSL) and reserve VA space
for them in a nearly identical way. Move common code into EAL private
functions to reduce duplication.
Signed-off-by: Dmitry Kozlyuk
---
lib/librte_eal/common/eal_common_memory.c | 96 ++
lib/librte_eal/comm
Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
Enum rte_page_sizes has members valued above this limit, which get
wrapped to zero, resulting in compilation error (duplicate values in
enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
Remove rte_page_size
Introduce OS-independent wrappers for memory management operations used
across DPDK and specifically in common code of EAL:
* rte_mem_map()
* rte_mem_unmap()
* rte_mem_page_size()
* rte_mem_lock()
Windows uses different APIs for memory mapping and reservation, while
Unices reserve memory by mappi
It is not guaranteed that sizeof(long) == sizeof(size_t). On Windows,
sizeof(long) == 4 and sizeof(size_t) == 8 for 64-bit programs.
Tracepoints using "long" field emitter are therefore invalid there.
Add dedicated field emitter for size_t and use it to store size_t values
in all existing tracepoin
With memory management implemented for Windows, the guide for running
sample applications is going to be extended with hugepages and driver
setup. Move run instructions to a separate file to give space for
planned expansion.
Signed-off-by: Dmitry Kozlyuk
---
doc/guides/windows_gsg/build_dpdk.rs
Code in Linux EAL that supports dynamic memory allocation (as opposed to
static allocation used by FreeBSD) is not OS-dependent and can be reused
by Windows EAL. Move such code to a file compiled only for the OS that
require it. Keep Anatoly Burakov maintainer of extracted code.
Signed-off-by: Dmi
Limited version imported previously lacks at least SLIST macros.
Import a complete file from FreeBSD, since its license exception is
already approved by Technical Board.
Signed-off-by: Dmitry Kozlyuk
---
lib/librte_eal/windows/include/sys/queue.h | 663 +++--
1 file changed, 601
1. Map CPU cores to their respective NUMA nodes as reported by system.
2. Support systems with more than 64 cores (multiple processor groups).
3. Fix magic constants, styling issues, and compiler warnings.
4. Add EAL private function to map DPDK socket ID to NUMA node number.
Signed-off-by: Dmitry
EAL common code depends on tracepoint calls, but generic implementation
cannot be enabled on Windows due to missing standard library facilities.
Add stub functions to support tracepoint compilation, so that common
code does not have to conditionally include tracepoints until proper
support is added
Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode. Multi-process mode is not
implemented and is forcefully disabled at startup. Assign myself as a
maintainer for Windo
Add hugepages discovery ("large pages" in Windows terminology)
and update documentation for required privilege setup. Only 2MB
hugepages are supported and their number is estimated roughly
due to the lack or unstable status of suitable OS APIs.
Assign myself as maintainer for the implementation fil
On Sat, 13 Jun 2020 10:55:14 +0200
Thomas Monjalon wrote:
> The Windows user guide is referencing a general link to download MinGW:
> http://mingw-w64.org/doku.php/download
> For those who want to install MinGW on Windows, I thing it is simpler
> to give this more direct link:
> http:
> It looks to be a false positive, but we need to find a way to remove
> the warning with a code change.
>
> This workaround in lib/librte_eal/common/eal_common_options.c
> makes 200% sure the default_set is initialized:
>
> - if (pthread_getaffinity_np(pthread_self(), sizeof(rte_cpuset_t),
> -Original Message-
> From: Yigit, Ferruh
> Sent: Friday, June 12, 2020 2:38 AM
> To: Zhang, Qi Z ; Yang, Qiming
> Cc: Ye, Xiaolong ; dev@dpdk.org; Nowlin, Dan
> ; Stillwell Jr, Paul M
> Subject: Re: [dpdk-dev] [PATCH v2 22/52] net/ice/base: increase timeout after
> PFR
>
> On 6/9/20
Add descriptor field offset and mask definition. It is used to parse
FDIR rx descriptor field value.
Signed-off-by: Yahui Cao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_lan_tx_rx.h | 44
1 file changed, 44 inser
FDIR can forward Ethernet packets with non-IP ethertype.
Signed-off-by: Yahui Cao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_fdir.c | 15 +++
drivers/net/ice/base/ice_fdir.h | 2 ++
drivers/net/ice/base/ice_flow.c | 29
Upgrade base with below main changes
1. add more protocol support - L2TPv3/ESP/AH/PFCP.
2. Add IPv6 prefix RSS support.
3. support GENEVE and VXLAN rules with VLAN.
4. Add E823L device IDs
5. couple bug fixes and code clean.
v3:
- fix commit log base on Ferruh's comment.
[PATCH v2 10/52] remove
For Flow Director, we don't want to re-use an existed profile with the
same field vector and mask. Merging two different flow_type’s field
vector will also make them sharing trained rule and cause rule
interference.
For example:
issue rule A: IPV4_TCP matching tcp src&dst port 80 to queue 8
issue
Consolidate implementation of ice_aq_set_mac_cfg for switch mode
and NIC mode. As per the specification, the driver needs to call
set_mac_cfg (opcode 0x0603) to be able to exercise jumbo frames.
Signed-off-by: Anirudh Venkataramanan
Signed-off-by: Jeb Cramer
Signed-off-by: Paul M. Stillwell Jr
Currently, the FW link override feature is only permitted for E810
devices. However, the ice_fw_supports_link_override() guards against FW
versions irrespective of the device. This assumes FW versions between
the families are aligned, which is not the case.
Signed-off-by: Jeb Cramer
Signed-off-b
When writing the driver's struct ice_tlan_ctx structure, do not write the
8-bit element int_q_state with the associated internal-to-hardware field
which is 122-bits, otherwise the helper function ice_write_byte() will use
undefined behavior when setting the mask used for that write. This should
no
This change improve VSI filter configuration rebuild for
multiport configuration, ie. where 1 PF includes more than
one logical port. For some functions, association between
port and corresponding switch_info or port_info structure
has been lost because by default the pointer to the first
element o
A u8 idx in ice_acl_add_entry causes the code to truncate the values
greater than 255 to 255 or less when calling ice_aq_program_acl_entry()
resulting in the wrong TCAM index being programmed for the specified
rule. The result is that the rule action doesn't work correctly
(packets don't get route
Add and report AUI PHY types as an AUI media type
Signed-off-by: Doug Dziggel
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 5 +++--
drivers/net/ice/base/ice_type.h | 1 +
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/dri
Report AOC types as fiber instead of unknown
Signed-off-by: Doug Dziggel
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 12
1 file changed, 12 insertions(+)
diff --git a/drivers/net/ice/base/ice_common.c
b/drivers/net/ice/base
Consolidate the Promiscuous rule for SMBM on the chosen logical port.
Signed-off-by: Shibin Koikkara Reeny
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 145 ++
1 file changed, 115 insertions(+), 30 delet
As currently, we are supporting only 5 PHY_SPEEDs for phy_type_high.
Thus, we should adjust the value of ICE_PHY_TYPE_HIGH_MAX_INDEX to 5.
Signed-off-by: Chinh T Cao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 2 +-
1 file changed, 1
Move the swap of flow director addresses and ports into training packet
generation. This reduces the code written for ACL.
Signed-off-by: Henry Tieman
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_fdir.c | 59 ---
Add missing space between end of comment text and comment terminator,
and remove unnecessary punctuation.
Signed-off-by: Bruce Allan
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl.c| 25 +-
drivers/net/ice/base/ice_acl_ctrl.
There are some function prototypes at the beginning of the file and
some at the end, group them all together so that they are in one
consistent location.
Signed-off-by: Tony Nguyen
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_fdir.h | 83
Add additional UDP payload to allow for additional headers such as ESP.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ice/base/ic
FDIR can forward:
- L2TPV3 packets with session id.
- IPSEC ESP packets with security parameter index.
- IPSEC AH packets with security parameter index.
- NAT_T ESP packets with security parameter index.
- PFCP packets with s field value.
Signed-off-by: Yahui Cao
Signed-off-by: Paul M. Stillwell
Currently the caller needs to initialize the ice_cfg_phy_fec() parameter
ice_aqc_set_phy_cfg_data FEC fields before calling. However, this is not
necessary since ice_cfg_phy_fec() calls Get PHY Capabilities.
Initialize ice_aqc_set_phy_cfg_data FEC capabilities and FEC option fields
from Get PHY Ca
Add couple functions that DPDK would like to use for accessing the
NVM.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.h | 1 -
drivers/net/ice/base/ice_nvm.c| 67 +--
drivers/net/ice/base/ice_nvm.h| 10
This patch introduces comp_report variable so that the called can
determine whether to report completion on error or on all cases.
Signed-off-by: Yahui Cao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_fdir.c | 2 +-
drivers/net/ice/base/ice_fdir.h
To allow for resets during package download, increase the timeout period
after performing a PF Reset. The time waited is the global config lock
timeout plus the normal PFSWR timeout.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/
When programming GENEVE and VXLAN switch rules, there are some instances
where both VLAN tagged packets plus non-VLAN tagged packets are needed
to match the rule.
In order to perform this action in one rule, the switch code needs
to setup the packet flag mask to ignore the VLAN packet flag. This
w
Where possible, cuddle multiple lines of function signatures to be
consistent throughout the code.
Signed-off-by: Bruce Allan
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 3 +--
drivers/net/ice/base/ice_controlq.c | 9 +++--
driver
This patch mainly does cleanups related to unnecessary braces.
There might be different opnion to keep braces if more than
single line, but the purpose here is trying to sync DPDK's base
code with kernel's copy and its more convenient for future update.
Signed-off-by: Tony Nguyen
Signed-off-by: P
Some IPv6 prefix related fields are defined in this patch, so that we
can use prefixes instead of full IPv6 address for RSS. These prefixes
include the first 32, 48, 64 bits of both SRC and DST IPV6 address.
Signed-off-by: Junfeng Guo
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
Return ICE_ERR_DOES_NOT_EXIST return code if admin command error code is
ICE_AQ_RC_ENOENT (not exist). ice_aq_sw_rules is used when switch
rule is getting added/deleted/updated. In case of delete/update
switch rule, admin command can return ICE_AQ_RC_ENOENT error code
if such rule does not exist, h
The definition of ICE_SW_RULE_RX_TX_ETH_HDR_SIZE open codes the size of
a structure field. Replace this with the use of FIELD_SIZEOF.
Signed-off-by: Jacob Keller
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.h | 17 -
1 file cha
Remove unnecessary case branch, since since the the switch and pe pipeline
stage is not designed to be handled by the flow module.
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/ice/base/ice_flow.c b/drivers/net/ice/b
To avoid having stale information about "adv_rule" per recipe, when all
rules associated to a given recipe are deleted, reset the "adv_rule"
flag otherwise it causes problem later on when decisions about filter
rules being present or not are made based on "adv_rule" flag.
Removed setting "adv_rule
This patch add more dummy packet type for pppoe packet,
it enable tcp/udp layer of ipv4/ipv6 for pppoe payload,
so we can use L4 dst/src port as input set for switch
filter.
Signed-off-by: Wei Zhao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_protoco
Add debug logs for ice_aq_get_phy_caps(), and format
ice_aq_set_phy_cfg() and ice_aq_get_link_info() debug logs to make them
more readable.
Signed-off-by: Paul Greenwalt
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 69 +
The capability flags used to report whether an NVM component has
a pending update are stored as simple booleans. If ice_parse_caps finds
the relevant capability then the boolean is set to true.
If the capability is not provided by firmware, then the boolean value
will be left alone. This works dur
Mask bits before accessing the rate limiting profile type field.
Signed-off-by: Tarun Singh
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_sched.c | 11 ++-
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ice/base/ice_
Function ice_rem_adv_rule_id return incorrect error code (ICE_ERR_PARAM)
whereas it should have returned ICE_ERR_DOES_NOT_EXIST return code
if filter list is empty or unable to find "rule" in list
Fixes: f89aa3affa9e ("net/ice/base: support removing advanced rule")
Cc: sta...@dpdk.org
Signed-off-
When removing VSI from VSI list, if only one VSI left, we need
to downgrade a switch rule's action from "to VSI LIST" to "to VSI",
So, needs to update the VSI handle to the last remaining VSI for the
new action but not the first VSI be added to the list.
Signed-off-by: Haiyue Wang
Signed-off-by:
The variable 'adj' is initialized to 0 and later used in an addition, but
the value is never changed from 0. Remove the variable since it's doing
nothing.
Signed-off-by: Tony Nguyen
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 3 +--
1 file
There are no implementations for these two functions so remove the
prototypes.
Signed-off-by: Tony Nguyen
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_fdir.h | 5 -
1 file changed, 5 deletions(-)
diff --git a/drivers/net/ice/base/ice_fdir.h b/dr
The profile TCAM tables are implemented such that entries with a smaller
index in the table have a higher priority. When records to be added to the
table have flags to differentiate between standard PTG and VSIG records,
then these entries need to have higher priority in order to be found and
proce
Handles memory leaks during control queue initialization and
buffer allocation failures. The MACRO - ICE_FREE_CQ_BUFS is modified to
re-use for this fix.
Fixes: 6c1f26be50a2 ("net/ice/base: add control queue information")
Cc: sta...@dpdk.org
Signed-off-by: Surabhi Boob
Signed-off-by: Paul M. Sti
struct ice_aqc_get_phy_caps_data has multiple autoneg enable bits.
ice_is_phy_caps_an_enabled checks all bits and returns true if any
autoneg enable bits are set.
Signed-off-by: Paul Greenwalt
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 1
When PPPOE header is not selected, pppoe should not be included in
ipv4 ptype bitmaps.
Signed-off-by: Yahui Cao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 8 ++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/ne
By default the queues are configured in legacy mode. The default
bandwidth settings for legacy/advanced modes are different. The existing
code was using the advanced mode default value of 1 which was
incorrect. This caused the unbalanced BW sharing among siblings.
The recommended default value is a
Add support for LLDP forwarding to SW programming in FW
LLDP Filter Control is 0x0A0A.
Signed-off-by: Sharon Haroni
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/
When free vsi list resource after vsi list update to empty, some
useless code in function ice_remove_vsi_list_rule() should be deleted.
Signed-off-by: Wei Zhao
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 17 +
1 file chang
Distribute the tx queues evenly across all queue groups. This will
help the queues to get more equal sharing among the queues when all
are in use.
In the previous algorithm, the next queue group node will be picked up
only after the previous one filled with max children.
For example: if VSI is con
ice_set_fc takes a u8 pointer 'aq_failures' as an input parameter. If
this function encounters an error, in addition to returning an appropriate
ice_status enum code, it also populates aq_failures with a link specific
error value.
If the caller does not initialize this variable to 0 before calling
The parameter ref_cnt is used for tracking how many
rules are reusing this VSI list, so it can only be
updated when a rule which using this list be deleted.
Fixes: f89aa3affa9e ("net/ice/base: support removing advanced rule")
Cc: sta...@dpdk.org
Signed-off-by: Wei Zhao
Signed-off-by: Paul M. Sti
There isn't a case for 1G SGMII in ice_get_media_type() so add
the handling for it.
Also handle the special case where some direct attach
cables may report that they support 1G SGMII, but
that is erroneous since SGMII is supposed to be a
backplane media type (between a MAC and a PHY). If
the drive
This patch add initialization for prof_res_bm_init flag
to zero in order that the possible resource for field vector
in the package file can be initialized.(in ice_init_prof_result_bm)
Fixes: 453d087ccaff ("net/ice/base: add common functions")
Cc: sta...@dpdk.org
Signed-off-by: Wei Zhao
Signed-o
In the flow API, add ability to add IPV4/IPV6 rules that match on
packets with or without inner L4 protocols.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 168 ++
drivers/net/ic
Add support for E823L devices.
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 5 +
drivers/net/ice/base/ice_devids.h | 10 ++
drivers/net/ice/base/ice_nvm.c| 5 +
drivers/net/ice/ice_ethdev.c | 5 +
4 files changed, 25 insertions(+)
diff --git a/
This patch add more tunnel type definition ipv4/ipv6 packet,
it enable tcp/udp layer of ipv4/ipv6 as L4 payload but without
L4 dst/src port number as input set for switch filter rule.
For example:
we can download a switch rule to direct ipv4 packet with specific
source and destination ip address t
Hi Luca,
Testing with dpdk v19.11.3-rc1 from Red Hat looks good.
We cover below 14 scenarios and and all get PASS on RHEL8 testing:
(1)Guest with device assignment(PF) throughput testing(1G hugepage size): PASS
(2)Guest with device assignment(PF) throughput testing(2M hugepage size) : PASS
(3)Gu
Remove PPPoD's packet type from PPPoE's ptype bitmap.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M. Stillwell Jr
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ice/base/ice_flow.c b/drivers/net/ice/
The legacy filter API will be superseded. This patch use
private api to change the implementation of commands
global_config gre-key-len and
show port fdir
Signed-off-by: Chenxu Di
---
app/test-pmd/cmdline.c | 23 -
app/test-pmd/config.c | 74 +++---
The legacy filter API will be superseded by rte_flow.
There are also several small features which can not be
implemented in rte_flow.
This patch re-implemented features get_fdir_info, get_fdir_stat and
set_gre_key_len as private API.
This patch also enable RSS action in flow query.
v2:
-fixed the
The legacy filter API will be superseded by rte_flow.
There are also several small features which can not be
implemented in rte_flow. This patch re-implemented these
features as private API.
Three APIs are added:
rte_pmd_i40e_get_fdir_info.
rte_pmd_i40e_get_fdir_stats.
rte_pmd_i40e_set_gre_key_len.
The legacy filter API will be superseded by rte_flow.
There are also several small features which can not be
implemented in rte_flow. This patch re-implemented these
features as private API.
Two APIs are added:
rte_pmd_ixgbe_get_fdir_info.
rte_pmd_ixgbe_get_fdir_stats.
Signed-off-by: Chenxu Di
--
This patch support RSS action in flow query.
It can display the RSS configuration of the specified rule.
Signed-off-by: Chenxu Di
---
app/test-pmd/config.c | 55 +++
1 file changed, 55 insertions(+)
diff --git a/app/test-pmd/config.c b/app/test-pmd/config
This patch enables flow query function to get the
configuration ofthe specified rule.
Signed-off-by: Chenxu Di
---
drivers/net/i40e/i40e_flow.c | 51
1 file changed, 51 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e/i40e_flow.c
in
Hi, Guinan
> -Original Message-
> From: dev On Behalf Of Guinan Sun
> Sent: Friday, June 12, 2020 11:24 AM
> To: dev@dpdk.org
> Cc: Sun, GuinanX
> Subject: [dpdk-dev] [PATCH 00/21] update ixgbe base code
>
> update ixgbe base code.
>
> Guinan Sun (21):
> net/ixgbe/base: clear VFMBMEM
Hi zhaowei
> -Original Message-
> From: Zhao1, Wei
> Sent: Monday, June 15, 2020 1:47 PM
> To: Sun, GuinanX ; dev@dpdk.org
> Cc: Sun, GuinanX
> Subject: RE: [dpdk-dev] [PATCH 00/21] update ixgbe base code
>
> Hi, Guinan
>
> > -Original Message-
> > From: dev On Behalf Of Guinan
On 15/06/2020 01:43, Dmitry Kozlyuk wrote:
> Introduce OS-independent wrappers for memory management operations used
> across DPDK and specifically in common code of EAL:
>
> * rte_mem_map()
> * rte_mem_unmap()
> * rte_mem_page_size()
> * rte_mem_lock()
>
> Windows uses different APIs for memory
Hi, Guinan
> -Original Message-
> From: dev On Behalf Of Guinan Sun
> Sent: Thursday, June 11, 2020 1:24 PM
> To: dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Sun,
> GuinanX
> Subject: [dpdk-dev] [PATCH] net/i40e: enable port filter by switch filter
>
> This patch enables the filter tha
Hi zhaowei
> -Original Message-
> From: Zhao1, Wei
> Sent: Monday, June 15, 2020 2:13 PM
> To: Sun, GuinanX ; dev@dpdk.org
> Cc: Xing, Beilei ; Guo, Jia ; Sun,
> GuinanX
> Subject: RE: [dpdk-dev] [PATCH] net/i40e: enable port filter by switch filter
>
> Hi, Guinan
>
> > -Original Me
1 - 100 of 106 matches
Mail list logo
