The rte_flow feature breaks the current monolithic approach for ethdev and
introduces the new generic flow API to ethdev using a plugin-like approach.
Basically, the rte_flow API is still logically part of ethdev:
- It extends the ethdev functionality: rte_flow is a new feature/capability
of eth
This patch introduces the generic ethdev API for the traffic manager
capability, which includes: hierarchical scheduling, traffic shaping,
congestion management, packet marking.
Main features:
- Exposed as ethdev plugin capability (similar to rte_flow approach)
- Capability query API per port, per
This patch set introduces an ethdev-based abstraction layer for Quality of
Service (QoS) Traffic Manager, which includes: hierarchical scheduling, traffic
shaping, congestion management, packet marking. The goal is to provide a simple
generic API that is agnostic of the underlying HW, SW or mixed H
On 2/28/2017 9:20 AM, Nelio Laranjeiro wrote:
> Mark value is always reported even when not requested or invalid.
>
> Fixes: ea3bc3b1df94 ("net/mlx5: support mark flow action")
> CC: sta...@dpdk.org
> Reported-by: Mark Bloch
> Signed-off-by: Nelio Laranjeiro
> Acked-by: Adrien Mazarguil
Appli
On 2/28/2017 8:33 AM, Nelio Laranjeiro wrote:
> The returned error code was wrongly handled causing the PMD to refuse to
> start.
>
> Fixes: 91572d2a0b1a ("net/mlx5: fix startup when flow cannot be applied")
>
> CC: sta...@dpdk.org
> Signed-off-by: Nelio Laranjeiro
Squashed into original commit
On 3/1/2017 12:49 PM, Nelio Laranjeiro wrote:
> Changes in v2:
>
> - Send series to dev@dpdk.org
>
> This series brings:
>
> - fixes:
>- handle error on Queue Pair creation.
>- Move a free to the right function.
>- Uses a single RSS drop queue for dropping flows.
> - Enhance IPv6
On 3/1/2017 6:04 AM, Wenzhuo Lu wrote:
> Some minor changes and fixes, including,
> link block check for KR,
> complete HW initialization even if SFP is not present,
> add VF xcast promiscuous mode.
>
> Wenzhuo Lu (9):
> net/ixgbe/base: make a debug message simple
> net/ixgbe/base: remove X550
On 3/1/2017 6:04 AM, Wenzhuo Lu wrote:
net/ixgbe/base: update shared code version to 2017.02.27
* Add link block check for KR.
* Complete HW initialization even if SFP is not present.
* Add VF xcast promiscuous mode.
> Signed-off-by: Wenzhuo Lu
<...>
On 3/1/2017 6:04 AM, Wenzhuo Lu wrote:
> Fix ICC build error by removing the EWARN third parameter.
Build error:
.../drivers/net/ixgbe/base/ixgbe_phy.c(1543):
error #268: the format string ends before this argument
EWARN(hw, "WARNING: Intel (R) Netwo
Hi Olivier,
> -Original Message-
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> Sent: Friday, March 3, 2017 8:45 AM
> To: Venkatesan, Venky
> Cc: Richardson, Bruce ; dev@dpdk.org;
> thomas.monja...@6wind.com; Ananyev, Konstantin
> ; Lu, Wenzhuo ;
> Zhang, Helin ; Wu, Jingjing
> ;
So far, virtio-user with vhost-user as the backend can only support
client mode. So when vhost user backend is down, i.e., unix socket
connection is broken and cannot be re-connected. We will force the
link state to be down.
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_ethdev.c
To check the link status, we use inotify to check if the file
/sys/class/net/tapX/flags is modified.
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_ethdev.c | 27
drivers/net/virtio/virtio_user/virtio_user_dev.c | 24 +
driver
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_ethdev.c | 17 ++--
drivers/net/virtio/virtio_user/virtio_user_dev.c | 25 +++-
drivers/net/virtio/virtio_user/virtio_user_dev.h | 2 +-
drivers/net/virtio/virtio_user_ethdev.c | 12 +
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_user/virtio_user_dev.c | 1 +
drivers/net/virtio/virtio_user_ethdev.c | 13 +++--
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c
b/drivers/net/virtio/virti
Signed-off-by: Jianfeng Tan
---
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 32 --
lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 2 ++
.../linuxapp/eal/include/exec-env/rte_interrupts.h | 5 ++--
3 files changed, 34 insertions(+), 5 deletions(-)
diff --git a
This is an attempt to add LSC and Rxq interrupt for a virtual device,
virtio-user (with the backend of both vhost-user and vhost-kernel).
HOW TO TEST:
Step 1: start testpmd with a virtual vhost device:
$ testpmd -c 0x3 -n 4 --socket-mem 1024 --no-pci \
--vdev 'eth_vhost0,iface=/tmp/so
Add queue based pipeline test with maximum number of stages available
in the device.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 39 +++
1 file changed, 39 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_ev
Add flow based pipeline test with maximum number of stages available
in the device.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 70 +++
1 file changed, 70 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eve
Add queue based two stage pipeline test with all combination
of schedule types.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 169 ++
1 file changed, 169 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventd
Add helper functions to launch and wait for n cores to complete the
operation with deadlock detection.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 88 +++
1 file changed, 88 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
Added unit test case to verify simple event enqueue and dequeue
operation with different schedule types
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 54 +++
1 file changed, 54 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 44
1 file changed, 44 insertions(+)
diff --git a/drivers/event/octeontx/ssovf_evdev.c
b/drivers/event/octeontx/ssovf_evdev.c
index 26c84c8..94a0eb8 100644
-
Added unit test case to verify enqueue and dequeue operations
with multiple queues and a single port.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_event
add test setup and teardown routines.
Signed-off-by: Jerin Jacob
---
app/test/Makefile | 5 +-
app/test/test_eventdev_octeontx.c | 98 +++
2 files changed, 102 insertions(+), 1 deletion(-)
create mode 100644 app/test/test_eventdev_octeontx.c
Each test case expected to run as standalone.
On setup, configure the device in requested mode and start the device.
On tear down, close the device and free the allocated resources
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 122 ++
1 fi
On Fri, 3 Mar 2017 16:40:28 +0100
Gaetan Rivet wrote:
> +
> +static struct rte_eth_dev *
> +pci_addr_to_eth_dev(struct rte_pci_addr *addr)
> +{
> + uint8_t pid;
> +
> + if (addr == NULL)
> + return NULL;
> + for (pid = 0; pid < RTE_MAX_ETHPORTS; pid++) {
> + s
On Fri, 3 Mar 2017 16:40:25 +0100
Gaetan Rivet wrote:
> This device state means that the device is managed externally, by
> whichever party has set this state (PMD or application).
>
> Note: this new device state is only an information. The related device
> structure and operators are still val
On Fri, 3 Mar 2017 16:40:23 +0100
Gaetan Rivet wrote:
> Other configuration items (i.e. MAC addresses) are stored within
> rte_eth_dev_data, but not this one.
>
> Signed-off-by: Gaetan Rivet
Maybe time to introduce a generic set of bit array operations like
kernel set/clear/test bit functions
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
MAINTAINERS | 9 +++
doc/guides/eventdevs/index.rst| 38 +++
doc/guides/eventdevs/octeontx.rst | 131 ++
doc/guides/index.rst | 1 +
4 files change
Add the following tests based existing helper functions
- Queue based producer-consumer ingress order test
- Run existing queue and flow based ordering test in dequeue timeout
mode
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 15 +++
1 file changed, 15 inserti
Add flow based producer-consumer based ingress order test
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 60 +++
1 file changed, 60 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventdev_octeontx.c
index 1af
Add queue and flow based pipeline test with maximum number of
stages available in the device.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 41 +++
1 file changed, 41 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/tes
Add unit test case to verify queue to port multi link
establishment operation.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 77 +++
1 file changed, 77 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventdev
Add flow based two stage pipeline test with all combination
of schedule types.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 170 ++
1 file changed, 170 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventde
Add unit test case to verify multi queue enqueue and multi core/port
dequeue operation.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 53 +++
1 file changed, 53 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test
Add test case to verify queue to port single link establishment operation.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 62 +++
1 file changed, 62 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventdev_oct
Added unit test case to verify the priority associated with
each event queue available in the device.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 59 +++
1 file changed, 59 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b
Add helper functions to generate, inject, consume and validate the events.
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev_octeontx.c | 202 ++
1 file changed, 202 insertions(+)
diff --git a/app/test/test_eventdev_octeontx.c
b/app/test/test_eventdev_oc
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 49 +-
drivers/event/octeontx/ssovf_evdev.h | 2 ++
drivers/event/octeontx/ssovf_worker.c | 50 +++
3 files changed, 100 insertio
If device is configured with RTE_EVENT_DEV_CFG_PER_DEQUEUE_TIMEOUT
configuration then use different fast path dequeue handler to wait till
requested amount of nanosecond if the event is not available.
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evde
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.h | 4 ++
drivers/event/octeontx/ssovf_worker.c | 116 ++
2 files changed, 120 insertions(+)
diff --git a/drivers/event/octeontx/ssovf_evdev.h
b/drivers/event/octe
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/Makefile | 5 ++
drivers/event/octeontx/ssovf_evdev.h | 30
drivers/event/octeontx/ssovf_worker.c | 140 ++
3 files changed, 175 insertions(+)
create mode 10064
SSO co-processor runs at a different frequency than core clock.
Request PF to convert the ns to SSO get_work timeout period.
On dequeue, If device is configured with
RTE_EVENT_DEV_CFG_PER_DEQUEUE_TIMEOUT configuration then
use different fast path dequeue handler to wait till requested
amount of nan
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 46
1 file changed, 46 insertions(+)
diff --git a/drivers/event/octeontx/ssovf_evdev.c
b/drivers/event/octeontx/ssovf_evdev.c
index d1be360..babd59f 100644
-
queues to port link and unlink establishment is through
setting/resetting the queue/group membership in
SSOW_VHWS_GRPMSK_CHGX
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 42
drivers/event/octeontx/ssovf
Add in the data-structures for the ports used by workers
to sent events to/from the HW scheduler. Also add a
function to release the resource allocated in setup
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 74 +++
Add the info_get function to return details on the queues, flow,
prioritization capabilities, etc. which this device has.
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 27 ++-
1 file changed, 26 insertions(+), 1 delet
Pretty much everything done in HW. Need to configure
the priority associated with event queue aka sso group
through a mailbox request to PF
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 63
drivers/event/
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drivers/event/octeontx/ssovf_evdev.c | 40
drivers/event/octeontx/ssovf_evdev.h | 4
2 files changed, 44 insertions(+)
diff --git a/drivers/event/octeontx/ssovf_evdev.c
b/drivers/event/octeo
This adds the minimal changes to allow a octeontx eventdev
implementation to be compiled, linked and created at run time.
The eventdev does nothing, but can be created via vdev
on command line, e.g.
sudo ./build/app/test -c 0xff00 --vdev=event_octeontx
...
Initializing event_octeontx domain=4 max_
ssovf VF device has mailbox mechanism to communicate
with PF device. This patch adds support for a mbox API to
send the mailbox request to PF device.
The ssovf VF device will be used as the communication channel
to talk to PF devices of all the network accelerated
co-processors in Octeontx. Exposin
An event device consists of event queues and event ports.
On Octeontx HW, each event queues(sso group/ssovf) and
event ports(sso hws/ssowvf) are enumerated as separate
SRIOV VF PCIe device.In order to expose as an event device,
On PCIe probe, the driver stores the information associated
with the PC
ssovf and ssowvf PCIe VF devices are shared
between eventdev PMD and ethdev PMD.This patch
expose a set of interface API to get info
about probed ssovf and ssowvf VF resources to use
with eventdev and ethdev vdev devices latter.
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
drive
An event device consists of event queues and event ports.
On Octeontx HW, each event queues(sso group/ssovf) and
event ports(sso hws/ssowvf) are enumerated as separate
SRIOV VF PCIe device.In order to expose as an event device,
On PCIe probe, the driver stores the information associated
with the PC
Signed-off-by: Jerin Jacob
Signed-off-by: Santosh Shukla
---
config/common_base | 6 +++
config/defconfig_arm64-thunderx-linuxapp-gcc | 6 +++
drivers/event/Makefile | 1 +
drivers/event/octeontx/Makefile| 5
From: Shreyansh Jain
Suggested-by: Ferruh Yigit
Signed-off-by: Shreyansh Jain
---
mk/rte.lib.mk | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mk/rte.lib.mk b/mk/rte.lib.mk
index 33a5f5a..ac4df9a 100644
--- a/mk/rte.lib.mk
+++ b/mk/rte.lib.mk
@@ -79,7 +79,7 @@ endif
# T
eventdev driver may return error on dequeue timeout tick conversion.
Change the pmd callback interface to address the same.
Signed-off-by: Jerin Jacob
---
drivers/event/skeleton/skeleton_eventdev.c | 4 +++-
lib/librte_eventdev/rte_eventdev.c | 3 +--
lib/librte_eventdev/rte_eventdev_pmd
The following patch set adds Cavium OCTEONTX HW based eventdev
implementation to the next-eventdev tree.
Introduction to OCTEON-TX ARM processors can be found
here: http://www.cavium.com/OCTEON-TX_ARM_Processors.html
The first two patches in the series make changes to the eventdev
API and common
Minimum value of nb_event_ports and/or nb_event_queues
should be one before reconfiguring the event device.
Fixes: 4c9a26e419a7 ("app/test: unit test case for eventdev APIs")
Signed-off-by: Jerin Jacob
---
app/test/test_eventdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff
On Fri, 3 Mar 2017 16:40:22 +0100
Gaetan Rivet wrote:
> This PMD intercepts and manages Ethernet device removal events issued by
> slave PMDs and re-initializes them transparently when brought back so that
> existing applications do not need to be modified to benefit from true
> hot-plugging sup
The following patch set adds Cavium OCTEONTX HW based eventdev
implementation to the next-eventdev tree.
Introduction to OCTEON-TX ARM processors can be found
here: http://www.cavium.com/OCTEON-TX_ARM_Processors.html
The first two patches in the series make changes to the eventdev
API and common
Hi Venky,
On Fri, 3 Mar 2017 16:18:52 +, "Venkatesan, Venky"
wrote:
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> > Sent: Thursday, March 2, 2017 8:15 AM
> > To: Richardson, Bruce
> > Cc: dev@dpdk.org; thomas.monja...@6wind.com; Anany
Le 02/03/2017 à 01:20, Allain Legacy a écrit :
+Since the initial implementation of AVP devices, vhost-user has become
+part of the qemu offering with a significant performance increase over
+the original virtio implementation. However, vhost-user still does
+not achieve the level of performance
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
> Sent: Thursday, March 2, 2017 8:15 AM
> To: Richardson, Bruce
> Cc: dev@dpdk.org; thomas.monja...@6wind.com; Ananyev, Konstantin
> ; Lu, Wenzhuo ;
> Zhang, Helin ; Wu, Jingjing
> ; adrien.mazarg...
So far, the crypto performance application was only able to
test one buffer size and one burst size.
With this commit, multiple sizes can be passed, either as a range
of values or as a list of values.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf_ops.c | 20 +-
ap
On Fri, Mar 03, 2017 at 04:40:22PM +0100, Gaetan Rivet wrote:
> This PMD intercepts and manages Ethernet device removal events issued by
> slave PMDs and re-initializes them transparently when brought back so that
> existing applications do not need to be modified to benefit from true
> hot-pluggin
When testing cipher only operations, there is no need to append digest
at the end of the buffer.
Signed-off-by: Pablo de Lara
---
app/test-crypto-perf/cperf_test_latency.c| 8 +---
app/test-crypto-perf/cperf_test_throughput.c | 10 ++
app/test-crypto-perf/cperf_test_verify.c
With this patchset, user will be able to run performance tests
on different buffer and burst sizes, in a single run, instead
of having to run the application several times.
Also, the verify option has been removed and, instead,
a new verify test has been created, to simplify the throughput
and lat
From: Sergio Gonzalez Monroy
In order to simplify throughput and latency tests,
verify option has been removed from these and moved
as a separate test.
Signed-off-by: Sergio Gonzalez Monroy
---
app/test-crypto-perf/Makefile| 1 +
app/test-crypto-perf/cperf_ops.h |
With this patchset, user will be able to run performance tests
on different buffer and burst sizes, in a single run, instead
of having to run the application several times.
Also, the verify option has been removed and, instead,
a new verify test has been created, to simplify the throughput
and lat
Remove DPDK QAT sample app, in favour of the newer applications
that use the cryptodev library: ipsec-gw and l2fwd-crypto,
which has support for Intel QuickAssist devices.
Signed-off-by: Pablo de Lara
---
MAINTAINERS| 5 -
doc/guides/prog_guide/source_or
> On Mar 3, 2017, at 6:27 AM, Pascal Mazon wrote:
>
> This patchset adds the special "remote" feature to the tap PMD, that
> actually enables capturing traffic from another netdevice. This is
> especially useful to get packets into the DPDK app, when the remote
> netdevice has no DPDK support.
>
> On Mar 3, 2017, at 4:45 AM, Pascal Mazon wrote:
>
> This series add support for the flow API in tap PMD.
>
> It enables filtering specific packets incoming on the tap netdevice, to
> process only desired ones. Under the hood, it uses kernel TC (traffic
> control), which takes place very early
> On Mar 3, 2017, at 4:45 AM, Pascal Mazon wrote:
>
> Supported flow rules are now mapped to TC rules on the tap netdevice.
> The netlink message used for creating the TC rule is stored in struct
> rte_flow. That way, by simply changing a metadata in it, we can require
> for the rule deletion wi
Signed-off-by: Gaetan Rivet
Acked-by: Olga Shern
---
drivers/net/failsafe/failsafe_args.c| 22
drivers/net/failsafe/failsafe_eal.c | 2 ++
drivers/net/failsafe/failsafe_ether.c | 62 +++--
drivers/net/failsafe/failsafe_ops.c | 17 +
Signed-off-by: Gaetan Rivet
Acked-by: Olga Shern
---
drivers/net/failsafe/failsafe_private.h | 8 +++
drivers/net/failsafe/failsafe_rxtx.c| 117 ++--
2 files changed, 105 insertions(+), 20 deletions(-)
diff --git a/drivers/net/failsafe/failsafe_private.h
b/dri
Signed-off-by: Gaetan Rivet
Acked-by: Olga Shern
---
drivers/net/failsafe/failsafe_ops.c | 125 +++-
1 file changed, 123 insertions(+), 2 deletions(-)
diff --git a/drivers/net/failsafe/failsafe_ops.c
b/drivers/net/failsafe/failsafe_ops.c
index 57de33f..0ed49b2 1
Add the "exec" device type.
The parameters given to this type of device will be executed in a shell.
The output of this command is then used as a definition for a device.
That command can be re-interpreted if the related device is not
plugged-in. It allows for a device definition to react to syste
Signed-off-by: Gaetan Rivet
Acked-by: Olga Shern
---
drivers/net/failsafe/Makefile | 1 +
drivers/net/failsafe/failsafe.c | 1 +
drivers/net/failsafe/failsafe_eal.c | 2 +
drivers/net/failsafe/failsafe_ether.c | 76 +++
drivers/net/failsafe/failsafe_flow.c
Introduce the fail-safe poll mode driver initialization and enable its
build infrastructure.
This PMD allows for applications to benefits from true hot-plugging
support without having to implement it.
It intercepts and manages Ethernet device removal events issued by
slave PMDs and re-initializes
Periodically check for the existence of a device.
If a device has not been initialized and exists on the system, then it
is probed and configured.
The configuration process strives to synchronize the states between the
plugged-in sub-device and the fail-safe device.
Signed-off-by: Gaetan Rivet
A
Make pci_probe_all_drivers public, no further changes to it.
Introduce a public function for pci_scan_one. This functions scan one
device, but does not allocate that device or insert it within the device
list.
---
lib/librte_eal/bsdapp/eal/rte_eal_version.map | 1 +
lib/librte_eal/common/eal_co
Other configuration items (i.e. MAC addresses) are stored within
rte_eth_dev_data, but not this one.
Signed-off-by: Gaetan Rivet
---
lib/librte_ether/rte_ethdev.c | 19 ++-
lib/librte_ether/rte_ethdev.h | 10 ++
2 files changed, 28 insertions(+), 1 deletion(-)
diff --git
Make the pci_detach_all_drivers public. No further changes.
Signed-off-by: Gaetan Rivet
---
lib/librte_eal/bsdapp/eal/rte_eal_version.map | 5 +
lib/librte_eal/common/eal_common_pci.c | 6 +++---
lib/librte_eal/common/include/rte_pci.h | 15 +++
lib/librte_ea
Take this helper from the testpmd app to offer it alongside the flow
API.
This allows PMDs and applications to save flow rules in their generic
format for later processing. This is useful when rules cannot be applied
immediately, such as when the device is not properly initialized.
Signed-off-by:
This device state means that the device is managed externally, by
whichever party has set this state (PMD or application).
Note: this new device state is only an information. The related device
structure and operators are still valid and can be used normally.
It is however made private by device
This PMD intercepts and manages Ethernet device removal events issued by
slave PMDs and re-initializes them transparently when brought back so that
existing applications do not need to be modified to benefit from true
hot-plugging support.
The stacked PMD approach shares many similarities with the
For drivers supporting the LSC event, enable it.
This allows to test LSC event support.
Add the --no-lsc-interrupt parameter to explicitly disable the link status
change interrupt.
Signed-off-by: Gaetan Rivet
---
app/test-pmd/parameters.c | 4
app/test-pmd/testpmd.c| 13 +
This is a rather simple handler that prints a message with the name of
the current event. It can be used to check PMD callback registration and
triggers.
Signed-off-by: Gaetan Rivet
---
app/test-pmd/testpmd.c | 47 +++
1 file changed, 47 insertions(+)
Enable device removal event for PMD supporting it.
Add the --no-rmv-interrupt parameter to explicitly disable it.
Signed-off-by: Gaetan Rivet
Signed-off-by: Elad Persiko
---
app/test-pmd/parameters.c | 4
app/test-pmd/testpmd.c| 43 +++
app/test
Extend the LSC event handling to support the device removal as well. The
Verbs library will send several related events, that can conflict
with the LSC event itself.
The event handling has thus been made capable of receiving and signaling
several event types at once.
Signed-off-by: Gaetan Rivet
This new API allows reacting to a device removal.
A device removal is the sudden disappearance of a device from its
bus.
PMDs implementing support for this notification guarantee that the removal
of the underlying device does not incur a risk to the application.
In particular, Rx/Tx bursts and al
This new event represents the sudden removal of a device from its bus.
The underlying resources exposed by the bus are expected not to be available
anymore. The application should thus be able to react and possibly clean up
related resources that it reserved for the removed device.
This event is d
This commit replaces redundant code with public ethdev layer calls.
Signed-off-by: Gaetan Rivet
---
app/test-pmd/cmdline.c | 31 +++
app/test-pmd/cmdline_flow.c | 2 +-
app/test-pmd/config.c | 12 ++--
app/test-pmd/parameters.c | 4 ++--
app/tes
Make the rte_eth_dev_count() return the correct number of devices even
after some are detached by the hotplug API.
This change does not affect existing applications that do not use
hotplug API calls. Those that do are already aware that port IDs are not
necessarily contiguous.
Signed-off-by: Gaet
This iterator helps applications iterate over the device list and skip
holes caused by invalid or detached devices.
Signed-off-by: Gaetan Rivet
---
lib/librte_ether/rte_ethdev.c | 13 +
lib/librte_ether/rte_ethdev.h | 19 +++
2 files changed, 32 insertions(+)
diff --
1. The hotplug API currently available in DPDK introduces the notion of
device states (DEV_DETACHED, DEV_ATTACHED). These states are implicit
and internal to the ethdev layer.
2. Device enumeration and access is done directly, without regard to the
underlying state of a device. Applicatio
The hotplug API introduced multiple states for a device with possible
values defined internally, while the related field in struct rte_eth_dev
was made public.
Exposing those states improves consistency because applications have to
deal with the device list directly.
"DEV_DETACHED" is renamed "RT
If LSC interrupts are enabled, the application expects the link_update
ops to be executed by the PMD itself.
No link status change event is received upon probing, therefore the link
status update must be forced.
Fixes: c4da6caa426d ("mlx4: handle link status interrupts")
Cc: sta...@dpdk.org
Sign
Most ConnectX-3 adapters expose two physical ports on a single PCI bus
address.
Add a new port parameter allowing the user to choose
either or both physical ports to be used by the application.
This parameter is used as follows:
Selecting only the second port:
-w 00:00.0,port=1
Selecting bot
1 - 100 of 239 matches
Mail list logo
