t;net/mlx5/hws: support default miss table")
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/hws/mlx5dr_table.c | 18 --
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mlx5/hws/mlx5dr_table.c
b/drivers/net/mlx5/hws/mlx5dr_table.c
index b371f42..c1c6
|
| 1 | 0 | FDB_RX |
++-+--+
There can be no two groups which only differ in their fdb sub domain.
A table must be created in a group which has the same fdb sub domain.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/linux/mlx5_os.c
From: Bing Zhao
The "send_to_kernel" action is shared and created during the HWS
configuration stage. By default, the NIC Rx and Tx flags are needed.
There is only one case that the FDB* flags are needed when creating
the action, the same as other shared actions. Only the transfer proxy
port nee
V1: initial version
V2: rebase + determine unified fdb based on FW capability
Bing Zhao (1):
net/mlx5: remove unneeded FDB flag on representor action
Ophir Munk (3):
common/mlx5: support FDB unified capability query
net/mlx5: support FDB unified domain
net/mlx5/hws: allow different types
This commit queries the FW for the new unified FDB mode and saves it in
mlx5 shared device as fdb_unified_en bit.
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/mlx5_devx_cmds.c | 3 +++
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
2 files changed, 4 insertions(+)
diff --git a/drivers/common
t;net/mlx5/hws: support default miss table")
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/hws/mlx5dr_table.c | 18 --
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mlx5/hws/mlx5dr_table.c
b/drivers/net/mlx5/hws/mlx5dr_table.c
index b371f42..c1c6
From: Bing Zhao
The "send_to_kernel" action is shared and created during the HWS
configuration stage. By default, the NIC Rx and Tx flags are needed.
There is only one case that the FDB* flags are needed when creating
the action, the same as other shared actions. Only the transfer proxy
port nee
|
| 1 | 0 | FDB_RX |
++-+--+
There can be no two groups which only differ in their fdb sub domain.
A table must be created in a group which has the same fdb sub domain.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/linux/mlx5_os.c
This commit queries the FW for the new unified FDB mode and saves it in
mlx5 shared device as fdb_unified_en bit.
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/mlx5_devx_cmds.c | 3 +++
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
2 files changed, 4 insertions(+)
diff --git a/drivers/common
-by: Ophir Munk
Acked-by: Morten Brørup
Acked-by: Alok Prasad
---
V1-V5 updates based on review comments
V6 Style erorr fix
V7: rebased
V8: positioning changelog in the right place
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c
-by: Ophir Munk
Reviewed-by: Thomas Monjalon
Reviewed-by: David Marchand
Reviewed-by: Anatoly Burakov
Acked-by: Morten Brørup
Acked-by: Alok Prasad
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 42
-by: Ophir Munk
Reviewed-by: Thomas Monjalon
Reviewed-by: David Marchand
Reviewed-by: Anatoly Burakov
Acked-by: Morten Brørup
Acked-by: Alok Prasad
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 42
> > --- a/lib/eal/common/eal_common_memzone.c
> > +++ b/lib/eal/common/eal_common_memzone.c
> > +#define DEFAULT_MAX_MEMZONE 2560
>
> Maybe add "_COUNT" at the end to make clear it is not about the size of a
> memzone.
> We should add a comment here to explain the meaning of this default:
> used u
-by: Ophir Munk
Reviewed-by: Thomas Monjalon
Reviewed-by: David Marchand
Reviewed-by: Anatoly Burakov
Acked-by: Morten Brørup
Acked-by: Alok Prasad
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 42
> -Original Message-
> Subject: Re: [PATCH v4] lib: set/get max memzone segments
>
> On 5/24/2023 11:25 PM, Ophir Munk wrote:
> > Currently, the max memzones count constat (RTE_MAX_MEMZONE) is used
> to
> > decide how many memzones a DPDK application
Hi Morten,
>
> I retracted my objection to the RFC, but should also have added:
>
> Acked-by: Morten Brørup
Ack.
Hi Anatoly,
Thank you for your review. I noticed a review by David Marchand that addresses
similar points to yours. In V4 I supply a reply to you both.
>
> Commit message could use a little rewording and shortening. Suggested:
>
> ---
>
> Currently, RTE_MAX_MEMZONE constant is used to decide h
Hello David,
Thank you for your review. I noticed a review by Anatoly Burakov that addresses
similar points to yours. In V4 I supply a reply to you both.
> -Original Message-
> From: David Marchand
> Sent: Thursday, 4 May 2023 10:27
> To: Ophir Munk
> Cc: dev@dpdk.org; B
-by: Ophir Munk
Acked-by: Morten Brørup
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 42 -
config/rte_config.h | 1 -
drivers/net/qede/base/bcm_osal.c
memzone: rte_memzone_max_get().
Signed-off-by: Ophir Munk
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 43 -
config/rte_config.h | 1 -
drivers/net/qede/base
memzone: rte_memzone_max_get().
Signed-off-by: Ophir Munk
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 43 -
config/rte_config.h | 1 -
drivers/net/qede/base
Thank you Morten Brorup and Thomas Monjalon for the fruitful discussion.
I am sending a V2 version that meets the understandings in the RFC so far.
If confirmed I will send PATCH V1.
Thank you, Tyler Retzlaff, for your comments.
> > --- a/app/test/test_memzone.c
> > +++ b/app/test/test_memzone.c
> > @@ -871,7 +871,7 @@ test_memzone_bounded(void) static int
> > test_memzone_free(void)
> > {
> > - const struct rte_memzone *mz[RTE_MAX_MEMZONE + 1];
> > + const struct rte_m
Thank you Stephen Memminger for you comment.
> Subject: Re: [RFC] lib: set/get max memzone segments
>
> On Wed, 19 Apr 2023 11:36:34 +0300
> Ophir Munk wrote:
>
> > +int ecore_mz_mapping_alloc(void)
> > +{
> > + ecore_mz_mappi
Thank you Devendra Singh Rawat for your valuable comments.
> >+int ecore_mz_mapping_alloc(void)
> >+{
> >+ecore_mz_mapping = rte_malloc("ecore_mz_map", 0,
> >+rte_memzone_max_get() * sizeof(struct rte_memzone *));
>
> Second parameter of rte_malloc() should be size and Third param
zed.
> This commit adds an API which must be called before rte_eal_init():
> rte_memzone_max_set(int max). If not called, the default memzone
> (RTE_MAX_MEMZONE) is used. There is also an API to query the effective
> max memzone: rte_memzone_max_get().
>
> Signed-off-by: Ophir M
memzone: rte_memzone_max_get().
Signed-off-by: Ophir Munk
---
app/test/test_func_reentrancy.c | 2 +-
app/test/test_malloc_perf.c | 2 +-
app/test/test_memzone.c | 2 +-
config/rte_config.h | 1 -
drivers/net/qede/base/bcm_osal.c| 26
ion option.
> -Original Message-
> From: Bruce Richardson
> Sent: Monday, 13 February 2023 16:53
> To: NBU-Contact-Thomas Monjalon (EXTERNAL)
> Cc: Ophir Munk ; dev@dpdk.org; Matan Azrad
> ; Lior Margalit ; Asaf Penso
> ; david.march...@redhat.com;
> honnappa.nagaraha.
- it is set by default to 2560. The hard coded definition of
RTE_MAX_MEMZONE is removed. During meson build time the RTE_MAX_MEMZONE
can be optionally defined as the value of max_memzones parameter.
Signed-off-by: Ophir Munk
---
RFC:
https://patchwork.dpdk.org/project/dpdk/patch
Thanks Dmitry and Bruce for your inputs. Option 1 is my favorite.
We all agree on Option 1. I will send a patch based on it.
Thank you.
> -Original Message-
> From: Dmitry Kozlyuk
> Sent: Monday, 30 January 2023 12:01
> To: Ophir Munk
> Cc: dev@dpdk.org; Ophir Mun
3
Add a function which must be called before rte_eal_init():
void rte_memzone_set_max(int max) {memzone_max = max;}
If not called, the default memzone (RTE_MAX_MEMZONE) is used.
With this option there is no need to recompile DPDK and it allows
using an in-box packaged DPDK.
Signed-off-by: Ophir Mu
gsz > max_size
rather than the suggested one:
tso_segsz > *txq->mtu + mbuf_in->l2_len)
Regards,
Ophir
> -Original Message-
> From: Ferruh Yigit
> Sent: Saturday, May 21, 2022 1:08 AM
> To: Harold Huang ; dev@dpdk.org;
> jiayu...@intel.com;
Acked-by: Ophir Munk
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, January 15, 2021 1:11 PM
> To: dev@dpdk.org
> Cc: david.march...@redhat.com; Bruce Richardson
> ; sta...@dpdk.org; Olivier Matz
> ; Ophir Munk ; Ferruh
> Yigit
> Subject
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, January 8, 2021 11:09 AM
> To: Ophir Munk
> Cc: dev@dpdk.org; Ori Kam
> Subject: Re: [dpdk-dev] [PATCH v2 5/6] app/regex: support performance
> measurements per QP
>
> 20/12/2020 11:41, Ophir
Performance measurement (elapsed time and Gbps) are based on Linux
clock() API. The resolution is improved by replacing the clock() API
with rte_rdtsc_precise() API.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
---
app/test-regex/main.c | 31 +--
1 file changed, 13
. Then for each core the
application calls rte_eal_remote_launch() with the worker routine
(run_regex) as its parameter.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
---
app/test-regex/main.c | 155 -
doc/guides/tools/testregex.rst | 30 ++-
Up to this commit measuring the parsing elapsed time and Giga bits per
second performance was done on the aggregation of all QPs (per core).
This commit separates the time measurements per individual QP.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
---
app/test-regex/main.c | 34
Up to this commit the input data file was read from scratch for each QP,
which is redundant. Starting from this commit the data file is read only
once at startup. Each QP will clone the data.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
---
app/test-regex/main.c | 63
Function rte_pktmbuf_pool_create() is moved from init_port() routine to
run_regex() routine. Looking forward on multi core support - init_port()
will be called only once as part of application startup while mem pool
creation should be called multiple times (per core).
Signed-off-by: Ophir Munk
error: qp may be used uninitialized in this function
[-Werror=maybe-uninitialized]
time = ((double)qp->end - qp->start) / CLOCKS_PER_SEC;
Adding Acked-By
Ophir Munk (6):
app/regex: move mem pool creation to worker routine
app/regex: support multi QPs
app/regex: read d
follows:
enqueue(QP #1)
enqueue(QP #2)
...
enqueue(QP #n)
dequeue(QP #1)
dequeue(QP #2)
...
dequeue(QP #n)
A new parameter 'nb_qps' was added to configure the number of QPs:
--nb_qps .
If not configured, nb_qps is set to 1 by default.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
.
[1]
("net/mlx5/linux: wrap rte alarm API with mlx5")
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, January 8, 2021 4:55 PM
> To: Ferruh Yigit
> Cc: Tal Shnaiderman ; dev@dpdk.org; Matan Azrad
> ; Raslan Darawsheh ; Ophir
> Munk ; Dekel
> -Original Message-
> From: Ferruh Yigit
> Sent: Friday, January 8, 2021 2:08 PM
> To: Tal Shnaiderman ; dev@dpdk.org
> Cc: NBU-Contact-Thomas Monjalon ; Matan Azrad
> ; Raslan Darawsheh ; Ophir
> Munk
> Subject: Re: [dpdk-dev] [PATCH v2 04/35] common/mlx5
v1: First release
Ophir Munk (2):
net/mlx5/linux: wrap sampling actions with OS calls
net/mlx5/windows: implement sampling actions wrappers
drivers/common/mlx5/windows/mlx5_glue.h | 34 +
drivers/net/mlx5/linux/mlx5_flow_os.h | 47 +
drivers
missing sampling DV structs
are added as stubs to windows/mlx5_glue.h file.
Signed-off-by: Ophir Munk
Acked-by: Matan Azrad
---
drivers/common/mlx5/windows/mlx5_glue.h | 34 +
drivers/net/mlx5/windows/mlx5_flow_os.h | 52 +
2 files changed, 86
Wrap glue calls dr_create_flow_action_sampler() and
dr_create_flow_action_dest_array() with OS APIs. This commit is a follow
up on [1].
[1]
commit b293fbf9672b ("net/mlx5: add OS specific flow actions operations")
Signed-off-by: Ophir Munk
Acked-by: Matan Azrad
---
drivers/net/
Performance measurement (elapsed time and Gbps) are based on Linux
clock() API. The resolution is improved by replacing the clock() API
with rte_rdtsc_precise() API.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 32 ++--
1 file changed, 14 insertions(+), 18
Up to this commit measuring the parsing elapsed time and Giga bits per
second performance was done on the aggregation of all QPs (per core).
This commit separates the time measurements per individual QP.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 33
follows:
enqueue(QP #1)
enqueue(QP #2)
...
enqueue(QP #n)
dequeue(QP #1)
dequeue(QP #2)
...
dequeue(QP #n)
A new parameter 'nb_qps' was added to configure the number of QPs:
--nb_qps .
If not configured, nb_qps is set to 1 by default.
Signed-off-by: Ophir Munk
---
app/test-re
. Then for each core the
application calls rte_eal_remote_launch() with the worker routine
(run_regex) as its parameter.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 155 -
doc/guides/tools/testregex.rst | 30 ++--
2 files changed, 164
Up to this commit the input data file was read from scratch for each QP,
which is redundant. Starting from this commit the data file is read only
once at startup. Each QP will clone the data.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 63
Function rte_pktmbuf_pool_create() is moved from init_port() routine to
run_regex() routine. Looking forward on multi core support - init_port()
will be called only once as part of application startup while mem pool
creation should be called multiple times (per core).
Signed-off-by: Ophir Munk
This patchset enhances the regex application to support multi Q with multi
cores.
v1: Initial release.
v2: Update documentation (testregex.rst).
Fix checkpath mispelling errors.
Ophir Munk (6):
app/regex: move mem pool creation to worker routine
app/regex: support multi QPs
app/regex
This patchset enhances the regex application to support multi Q with multi
cores.
v1: initial release
Ophir Munk (6):
app/regex: move mem pool creation to worker routine
app/regex: support multi QPs
app/regex: read data file once at startup
app/regex: support multi cores
app/regex
Up to this commit measuring the parsing elapsed time and Giga bits per
second performance was done on the aggregation of all QPs (per core).
This commit seperates the time measurements per individual QP.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 33
Performance measurement (elapsed time and Gbps) are based on Linux
clock() API. The resolution is improved by replacing the clock() API
with rte_rdtsc_precise() API.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 32 ++--
1 file changed, 14 insertions(+), 18
. Then for each core the
application calls rte_eal_remote_launch() with the worker routine
(run_regex) as its parameter.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 155 --
1 file changed, 139 insertions(+), 16 deletions(-)
diff --git a/app/
Function rte_pktmbuf_pool_create() is moved from init_port() routine to
run_regex() routine. Looking forward on multi core support - init_port()
will be called only once as part of application startup while mem pool
creation should be called multiple times (per core).
Signed-off-by: Ophir Munk
:
enque(QP #1)
enque(QP #2)
...
enque(QP #n)
deque(QP #1)
deque(QP #2)
...
deque(QP #n)
A new parameter 'nb_qps' was added to configure the number of QPs:
--nb_qps .
If not configured, nb_qps is set to 1 by defalut.
Signed-off-by: Ophir Munk
---
app/test-regex/ma
Up to this commit the input data file was read from scratch for each QP,
which is redundant. Starting from this commit the data file is read only
once at startup. Each QP will clone the data.
Signed-off-by: Ophir Munk
---
app/test-regex/main.c | 63
;)
Signed-off-by: Ophir Munk
Acked-by: Viacheslav Ovsiienko
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5_rxq.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index a733eda..0510186 100644
--- a/driver
Add missing out of order scan capability
RTE_REGEXDEV_CAPA_QUEUE_PAIR_OOS_F to mlx5 regex PMD.
Signed-off-by: Ophir Munk
Acked-by: Ori Kam
---
Depends-on: patch-81673 ("regexdev: add OOS capability definition") `
Depends-on: patch-81509 ("app/regex: configure qp acco
Wrap glue call dv_create_flow_action_dest_devx_tir() with an OS API.
Fixes: b293fbf9672b ("net/mlx5: add OS specific flow actions operations")
Cc: sta...@dpdk.org
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/linux/mlx5_flow_os.h | 26 ++
drivers/net/mlx5/m
From: Tal Shnaiderman
Implement OS function call to get pdn.
Signed-off-by: Tal Shnaiderman
---
drivers/net/mlx5/windows/mlx5_os.c | 21 +
1 file changed, 21 insertions(+)
diff --git a/drivers/net/mlx5/windows/mlx5_os.c
b/drivers/net/mlx5/windows/mlx5_os.c
index e334110..
Exclude call to rte_intr_callback_register under Windows using
definition RTE_EXEC_ENV_WINDOWS.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/mlx5_txpp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_txpp.c b/drivers/net/mlx5/mlx5_txpp.c
index c22ddc9..4405054
From: Tal Shnaiderman
Support VF BDF scanning by checking both the BDF and raw BDF provided by
DevX. In Linux a PCI address is formatted as: domain, bus, device,
function (DBDF). This is right for both a PF and a VF. In Windows a PF
also has a DBDF format, but the domain is always 0, while a VF
-off-by: Ophir Munk
---
drivers/common/mlx5/windows/mlx5_win_defs.h | 6 +
drivers/net/mlx5/windows/mlx5_os.c | 481 +++-
2 files changed, 482 insertions(+), 5 deletions(-)
diff --git a/drivers/common/mlx5/windows/mlx5_win_defs.h
b/drivers/common/mlx5/windows
From: Tal Shnaiderman
Currently the mlx5 PMD is supported on Windows for clang
compiler only, adding restriction in meson.build files
until mingw support will be added as well.
Signed-off-by: Tal Shnaiderman
---
drivers/common/mlx5/meson.build | 4 ++--
drivers/net/mlx5/meson.build| 4 ++--
each PCI device call mlx5_dev_spawn() to create an eth device (struct
rte_ethdev). The implementation of device spawn is in the follow up
commit. Finally, the device list is free.
Signed-off-by: Tal Shnaiderman
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.c | 278
mlx5_flow_adjust_priority() is used to adjust priorities according to
priorities levels. It is Verbs based and it is called from shared code
(mlx5_flow_dv.c). Therefore, wrap it in an OS API.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/linux/mlx5_flow_os.h | 20
drivers
From: Tal Shnaiderman
This commit copies the interface name as saved in the device context
since its creation.
Signed-off-by: Tal Shnaiderman
---
drivers/net/mlx5/windows/mlx5_ethdev_os.c | 28
1 file changed, 28 insertions(+)
diff --git a/drivers/net/mlx5/windows
From: Tal Shnaiderman
This commit replaces included file mlx5_glue.h with file mlx5_prm.h
in file mlx5_common_mp.h. The new inclusion defines 'enum ibv_wq_state'
which is used in file mlx5_common_mp.h and causes Windows compilation
warnings if not declared in advance.
Fixes: 9d60f54569fd ("commo
This commit implements mlx5_os_open_device() API. It calls glue API
open_device() then glue API query_device() to fill in 'struct
mlx5_context' with data for later usage.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.c | 43 ++
1 fi
added to array of actions and will be used later
by the flow creation API.
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/windows/mlx5_win_defs.h | 16
drivers/net/mlx5/windows/mlx5_flow_os.c | 21 ++---
2 files changed, 30 insertions(+), 7 deletions(-)
diff
From: Tal Shnaiderman
This commit implements mlx5_is_removed() API. A new glue call
'init_shutdown_event' is added to support the new API.
Signed-off-by: Tal Shnaiderman
---
drivers/common/mlx5/windows/mlx5_glue.c| 21 +
drivers/common/mlx5/windows/mlx5_glue.h| 1 +
format and copy the DV translated PRM bits into the
matcher struct. This matcher struct will be used later by the flow
creation API.
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/windows/mlx5_win_defs.h | 55 +
drivers/net/mlx5/windows/mlx5_flow_os.c | 30
case an OS does not support an API - it can return in
its implementation an error ENOTSUP.
Fixes: 042f5c94fd3a ("net/mlx5: refactor device operations for Linux")
Fixes: b541ecb63618 ("net/mlx5: refactor eth dev ops for Windows")
Signed-off-by: Ophir Munk
---
drivers/net/
From: Tal Shnaiderman
Windows warns on missing function prototype get_if_name. To fix it -
move the prototype to shared file mlx5.h and add missing definition
IF_NAMESIZE to Windows mlx5_os.h file.
Fixes: e9c0b96e3526 ("net/mlx5: move Linux ifname function")
Cc: sta...@dpdk.org
Signed-off-by: T
From: Tal Shnaiderman
This commits implements API mlx5_get_mac(). It returns the MAC address
saved in the device context since its creation.
Signed-off-by: Tal Shnaiderman
---
drivers/net/mlx5/windows/meson.build | 1 +
drivers/net/mlx5/windows/mlx5_ethdev_os.c | 43
Add mlx5 as the first driver to be compiled under Windows (file
drivers/net/meson.build).
Signed-off-by: Ophir Munk
---
drivers/net/meson.build | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/meson.build b/drivers/net/meson.build
index 4e4c2c9..a341962
From: Tal Shnaiderman
This commit adds a new glue function query_rt_values to support the new
API mlx5_read_clock().
Signed-off-by: Tal Shnaiderman
---
drivers/common/mlx5/mlx5_prm.h | 1 +
drivers/common/mlx5/windows/mlx5_glue.c| 26 ++
drivers/common/
This commit adds stubs to VLAN VM operations. It is the Windows
equivalent implementation of (1). The Linux implementation was based on
Netlink APIs which are not supported in Windows.
(1)
commit 7af10d29a4a0 ("net/mlx5/linux: refactor VLAN")
Signed-off-by: Ophir Munk
---
driver
:
-#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+#if defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_INFINIBAND_VERBS_H)
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/mlx5.c| 2 +-
drivers/net/mlx5/mlx5.h| 4 ++--
drivers/net/mlx5/mlx5_devx.c | 8
drivers/net/mlx5
-by: Ophir Munk
---
drivers/common/mlx5/mlx5_prm.h | 6 +
drivers/net/mlx5/windows/mlx5_flow_os.c | 46 ++---
2 files changed, 42 insertions(+), 10 deletions(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 1dfd6bd
From: Tal Shnaiderman
This commit implements API mlx5_get_mtu(). It returns the MTU size as
saved in the device context since its creation.
Signed-off-by: Tal Shnaiderman
---
drivers/net/mlx5/windows/mlx5_ethdev_os.c | 27 +++
1 file changed, 27 insertions(+)
diff --gi
Wrap glue call dr_create_flow_action_default_miss() with an OS API. This
commit is a follow up on (1).
(1)
commit d4d85aa6f13a ("common/mlx5: add default miss action")
commit b293fbf9672b ("net/mlx5: add OS specific flow actions operations")
Signed-off-by: Ophir Munk
---
dr
From: Tal Shnaiderman
Add support for mlx5_link_update() to get link speed and link state.
Other parameters are currently hard-coded.
Signed-off-by: Tal Shnaiderman
---
drivers/net/mlx5/windows/mlx5_ethdev_os.c | 39 +++
1 file changed, 39 insertions(+)
diff --git
supports flow priority 0.
Signed-off-by: Ophir Munk
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/windows/mlx5_win_defs.h | 7 +
drivers/net/mlx5/windows/meson.build| 1 +
drivers/net/mlx5/windows/mlx5_flow_os.c | 188 ++
drivers/net/mlx5/windows/mlx5_flow_os.h
From: Tal Shnaiderman
This commit is the Windows equivalent of the Linux implementation.
Windows returns an error ENOTSUP for the APIs to create/destroy event
channel or to subscribe an event.
Signed-off-by: Tal Shnaiderman
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/windows
Add #include to file mlx5_devx_cmds.h. It is required for
Windows to identify the __rte_internal definition.
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/mlx5_devx_cmds.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h
b/drivers
mlx5_dev_get_flow_ctrl
mlx5_dev_set_flow_ctrl
mlx5_get_module_info
mlx5_get_module_eeprom
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_ethdev_os.c | 199 ++
1 file changed, 199 insertions(+)
diff --git a/drivers/net/mlx5/windows/mlx5_ethdev_os.c
b/drivers/net
This commit is the Windows part implementation of (1).
(1)
commit d5ed8aa9449d ("net/mlx5: add memory region callbacks
in per-device cache")'
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.c | 17 +
1 file changed, 17 inse
Windows supports the primary process with no secondary process control.
This commit adds stubs for requests to start/stop the data-path to the
secondary process and for requests to start/stop a queue of the primary
process.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/meson.build
PTHREAD_MUTEX_INITIALIZER is a Linux macro defined in
/usr/include/pthread.h. It is used by mlx5 PMD but it is not included
in DPDK Windows pthread implementation. Therefore define it privately
in windows/mlx5_os.h file.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.h | 1 +
1
This is a hack commit. Linux epoll mechanism is not implemented in
Windows. Therefore define rte_intr_free_epoll_fd API to do nothing.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/mlx5/windows/mlx5_os.h
b
Errno ETOOMANYREFS may not be supported under Windows. In such cases
add its definition.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/mlx5/windows/mlx5_os.h
b/drivers/net/mlx5/windows/mlx5_os.h
index dd3515c
Prior to this commit meson did not progress beyond directory
drivers/common for Windows compilations. This commit enables drivers
compilation under this directory.
Signed-off-by: Ophir Munk
Acked-by: Matan Azrad
---
drivers/common/meson.build | 8 +++-
1 file changed, 3 insertions(+), 5
re DV dependencies")
Signed-off-by: Ophir Munk
---
drivers/common/mlx5/windows/mlx5_common_os.h | 74
1 file changed, 74 insertions(+)
diff --git a/drivers/common/mlx5/windows/mlx5_common_os.h
b/drivers/common/mlx5/windows/mlx5_common_os.h
index ba16641..9ff6bef 100644
---
File drivers/net/mlx5/windows/mlx5_os.h is added. It includes specific
Windows definitions such as PCI driver flags link state changes
interrupts, link removal interrupts.
Signed-off-by: Ophir Munk
---
drivers/net/mlx5/windows/mlx5_os.h | 19 +++
1 file changed, 19 insertions
Currently MR operations are Verbs based. This commit updates MR
operations prototypes such that DevX MR operations callbacks can be used
as well. Rename 'struct mlx5_verbs_ops' as 'struct mlx5_mr_ops' and
move it to shared file mlx5.h.
Signed-off-by: Ophir Munk
A
1 - 100 of 567 matches
Mail list logo
